1. A multi-objective planning method for a new energy convergence network is characterized by comprising the following steps:

acquiring basic data of a sending end network; the basic data comprise position coordinates of the new energy station, position coordinates of the main network transformer substation and connection relations among the main network transformer substations;

obtaining historical operating data, and determining the value range of an optimized variable according to the historical operating data and the basic data; wherein the historical operating data comprises load historical data and power source historical data;

and inputting the value range of the optimized variable into a preset multi-target double-layer planning model for solving to obtain a planning scheme set.

2. The method of claim 1, wherein the multi-objective two-layer planning model comprises a first planning model and a second planning model;

inputting the value range of the optimized variable into a preset multi-target double-layer planning model for solving to obtain a planning scheme set, wherein the planning scheme set comprises the following steps:

solving the first planning model by using a differential evolution algorithm in the value range of the optimized variable to obtain a target optimized variable;

and determining the boundary condition of a second planning model according to the target optimization variables, and solving the second planning model by using a mixed integer linear programming method to obtain the planning scheme set.

3. The method of claim 2, wherein the multi-objective two-layer optimization model building process comprises:

constructing an objective function of the first planning model according to the optimization objective of the first planning model; wherein the optimization objectives of the first planning model include: the construction cost is minimum, the limited electric quantity of new energy is minimum, the output power of a connection point of a direct current conversion station and a local alternating current power grid is maximized, the load balance of each line in a sending end network is highest, and the symmetry of each node direct-connected power supply and each direct-connected load in the sending end network is highest;

determining constraint conditions of the first planning model according to the connection relation between the new energy station and the collection substation;

determining an objective function of the second planning model according to the optimization objective of the second planning model;

and determining constraint conditions of the second planning model according to the optimization variables of the first planning model and the physical operation constraint of the new energy collection network.

4. The method of claim 2, wherein the objective optimization variables include an initial planning solution and a cross planning solution;

solving the first planning model by using a differential evolution algorithm in the value range of the optimized variable to obtain a target optimized variable, comprising the following steps of:

dividing the optimized variables in the first planning model according to variable types to obtain a continuous variable population and a discrete variable population;

initializing the continuous variable population within the value range of the optimized variable to obtain q generations of continuous population individuals; the q generation continuous population individuals comprise collected substation coordinates, collected substation transformation capacity and line transmission capacity;

randomly initializing the discrete variable population to obtain a q-generation discrete population, wherein the q-generation discrete population is a construction decision variable of a line to be selected, 0 represents that the line to be selected is not constructed, and 1 represents that the line to be selected is constructed;

carrying out topological constraint verification on the q-generation discrete population according to constraint conditions of the first planning model, and enabling the q-generation discrete population and the q-generation continuous population which meet the topological constraint to form an initial planning scheme;

carrying out variation and cross operation on the q-generation continuous population individuals to form q + 1-generation cross continuous population individuals corresponding to the q-generation continuous population individuals; forming a cross planning scheme by the q generation of discrete population which accords with the topological constraint and the q +1 generation of cross continuous population;

determining a boundary condition of a second planning model according to the target optimization variable, and solving the second planning model by using a mixed integer linear programming method to obtain the planning scheme set, wherein the method comprises the following steps:

inputting the initial planning scheme and the cross planning scheme into the second planning model for solving to obtain a node injection power mismatch amount of a q-generation initial planning scheme and a node injection power mismatch amount of a q + 1-generation cross planning scheme;

when the node injection power mismatch amount of the q-generation initial planning scheme does not exceed a preset mismatch amount threshold, solving an objective function value corresponding to the initial planning scheme according to the first planning model to obtain an objective function value of the initial planning scheme;

when the node injection power mismatch amount of the q +1 generation cross planning scheme does not exceed the preset mismatch amount threshold, solving an objective function value corresponding to the cross planning scheme according to the first planning model to obtain a cross planning scheme objective function value;

selecting operation is carried out according to the objective function value of the initial planning scheme and the objective function value of the cross planning scheme to obtain q +1 generation of continuous population individuals;

generating a minimum non-dominated set of the q +1 generation of continuous population individuals, and adding the minimum non-dominated set to the planning scheme set;

and when the quantity of the planning scheme sets is larger than the preset quantity or the population algebra is larger than the algebra threshold value, outputting the planning scheme sets.

5. The method of claim 4, further comprising:

when the number of the planning scheme sets is smaller than or equal to the preset number and the population algebra is smaller than or equal to the algebra threshold, adding one to the population algebra q, and performing updating operation on the discrete variable population to obtain a q +1 generation discrete population;

and forming a new initial planning scheme by the q +1 generation of discrete population and the q +1 generation of continuous population, wherein the objective function value corresponding to the new initial planning scheme is selected as the objective function value corresponding to the q +1 generation of continuous population in the previous round, and returning to execute the steps of carrying out variation and cross operation on the q +1 generation of continuous population.

6. The method of claim 4, wherein said performing a selection operation according to the initial planning scheme objective function values and the cross-planning scheme objective function values to obtain q +1 generation of consecutive population individuals comprises:

when the target function value of the initial planning scheme is superior to the target function value of the cross planning scheme, taking the q generation continuous population individuals as the q +1 generation continuous population individuals;

and when the target function value of the cross planning scheme is superior to the target function value of the initial planning scheme, taking the q +1 generation cross continuous population individuals corresponding to the q generation continuous population individuals as the q +1 generation continuous population individuals.

7. The method of claim 4, further comprising:

when the node injection power mismatching amount of the q-generation initial planning scheme exceeds a preset mismatching amount threshold, regenerating q-generation continuous population individuals and q-generation discrete populations, and forming the q-generation discrete populations which accord with topological constraint and the regenerated q-generation continuous population individuals into the initial planning scheme;

when the node injection power mismatching amount of the q +1 generation cross planning scheme exceeds the preset mismatching amount threshold, regenerating q +1 generation cross continuous population individuals, and forming a cross planning scheme by the q generation discrete population which accords with the topological constraint and the regenerated q +1 generation cross continuous population individuals;

and returning to the step of inputting the initial planning scheme and the cross planning scheme into the second planning model for solving.

8. A multi-objective planning apparatus for a new energy convergence network, the apparatus comprising:

the first acquisition module is used for acquiring basic data of a sending end network; the basic data comprise position coordinates of the new energy station, position coordinates of the main network transformer substation and connection relations among the main network transformer substations;

the second acquisition module is used for acquiring historical operating data and determining the value range of the optimization variable according to the historical operating data and the basic data; wherein the historical operating data comprises load historical data and power source historical data;

and the planning module is used for inputting the value range of the optimized variable into a preset multi-target double-layer planning model for solving to obtain a planning scheme set.

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.

Background

Most of the power grid planning work under new energy access is concentrated on power transmission network optimization planning, optimization targets considered by most of the existing new energy convergence network planning methods are mostly optimal in static economy, balance of various system performances in the operation process is difficult to guarantee, and planning requirements of the existing new energy station convergence network cannot be met.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a multi-objective planning method, apparatus, computer device and storage medium for a new energy convergence network, which can improve the optimized performance.

In a first aspect, a multi-objective planning method for a new energy collection network is provided, and the method includes:

acquiring basic data of a sending end network; the basic data comprise position coordinates of the new energy station, position coordinates of the main network transformer substation and connection relations among the main network transformer substations;

obtaining historical operating data, and determining the value range of an optimized variable according to the historical operating data and basic data; the historical operation data comprises load historical data and power supply historical data;

and inputting the value range of the optimized variable into a preset multi-target double-layer planning model for solving to obtain a planning scheme set.

In one embodiment, the multi-objective two-layer planning model includes a first planning model and a second planning model;

inputting the value range of the optimized variable into a preset multi-target double-layer planning model for solving to obtain a planning scheme set, wherein the planning scheme set comprises the following steps:

solving the first planning model by using a differential evolution algorithm in the value range of the optimized variable to obtain a target optimized variable;

and determining the boundary condition of the second planning model according to the target optimization variable, and solving the second planning model by using a mixed integer linear planning method to obtain a planning scheme set.

In one embodiment, the process of establishing the multi-objective double-layer optimization model includes:

constructing an objective function of the first planning model according to the optimization objective of the first planning model; wherein the optimization objectives of the first planning model include: the construction cost is minimum, the limited electric quantity of new energy is minimum, the output power of a connection point of a direct current conversion station and a local alternating current power grid is maximized, the load balance of each line in a sending end network is highest, and the symmetry of each node direct-connected power supply and each direct-connected load in the sending end network is highest;

determining constraint conditions of the first planning model according to the connection relation between the new energy station and the collection substation;

determining an objective function of the second planning model according to the optimization objective of the second planning model;

and determining constraint conditions of a second planning model according to the optimization variables of the first planning model and the physical operation constraints of the new energy collection network.

In one embodiment, the objective optimization variables include an initial planning solution and a cross planning solution;

solving the first planning model by using a differential evolution algorithm in the value range of the optimization variables to obtain target optimization variables, wherein the method comprises the following steps:

dividing the optimized variables in the first planning model according to variable types to obtain a continuous variable population and a discrete variable population;

initializing a continuous variable population within the value range of the optimized variable to obtain q generations of continuous population individuals; the q generation continuous population individuals comprise collected substation coordinates, collected substation transformation capacity and line transmission capacity;

randomly initializing a discrete variable population to obtain a q-generation discrete population, wherein the q-generation discrete population is a construction decision variable of a line to be selected, 0 represents that the line to be selected is not constructed, and 1 represents that the line to be selected is constructed;

carrying out topological constraint verification on the q-generation discrete population according to constraint conditions of the first planning model, and enabling the q-generation discrete population and the q-generation continuous population which meet the topological constraint to form an initial planning scheme;

carrying out variation and cross operation on the q-generation continuous population individuals to form q + 1-generation cross continuous population individuals corresponding to the q-generation continuous population individuals; forming a cross planning scheme by q-generation discrete populations and q + 1-generation cross continuous population individuals which accord with topological constraints;

determining the boundary condition of a second planning model according to the target optimization variables, and solving the second planning model by using a mixed integer linear planning method to obtain a planning scheme set, wherein the planning scheme set comprises the following steps:

inputting the initial planning scheme and the cross planning scheme into a second planning model for solving to obtain a node injection power mismatch amount of a q-generation initial planning scheme and a node injection power mismatch amount of a q + 1-generation cross planning scheme;

when the node injection power mismatch amount of the q-generation initial planning scheme does not exceed a preset mismatch amount threshold, solving an objective function value corresponding to the initial planning scheme according to the first planning model to obtain an objective function value of the initial planning scheme;

when the node injection power mismatch amount of the q +1 generation cross planning scheme does not exceed a preset mismatch amount threshold, solving an objective function value corresponding to the cross planning scheme according to the first planning model to obtain an objective function value of the cross planning scheme;

selecting according to the objective function value of the initial planning scheme and the objective function value of the cross planning scheme to obtain q +1 generation continuous population individuals;

generating a minimum non-dominated set of q +1 generation continuous population individuals, and adding the minimum non-dominated set into a planning scheme set;

and when the quantity of the planning scheme sets is larger than the preset number or the population algebra is larger than the algebra threshold value, outputting the planning scheme sets.

In one embodiment, the method further comprises:

when the number of the planning scheme sets is smaller than or equal to the preset number and the population algebra is smaller than or equal to the algebra threshold, adding one to the population algebra q, and performing updating operation on the discrete variable population to obtain a q +1 generation discrete population;

and forming a new initial planning scheme by the q +1 generation of discrete population and the q +1 generation of continuous population, wherein the objective function value corresponding to the new initial planning scheme is selected as the objective function value corresponding to the q +1 generation of continuous population in the previous round, and returning to execute the steps of carrying out variation and cross operation on the q +1 generation of continuous population.

In one embodiment, performing a selection operation according to an initial planning scheme objective function value and a cross-planning scheme objective function value to obtain q +1 generation of consecutive population individuals includes:

when the objective function value of the initial planning scheme is superior to the objective function value of the cross planning scheme, taking the continuous population individuals of the q generation as continuous population individuals of the q +1 generation;

and when the objective function value of the cross planning scheme is superior to the objective function value of the initial planning scheme, taking q +1 generation cross continuous population individuals corresponding to the q generation continuous population individuals as q +1 generation continuous population individuals.

In one embodiment, the method further comprises:

when the node injection power mismatching amount of the q-generation initial planning scheme exceeds a preset mismatching amount threshold, regenerating q-generation continuous population individuals and q-generation discrete populations, and forming the q-generation discrete populations which accord with topological constraint and the regenerated q-generation continuous population individuals into the initial planning scheme;

when the node injection power mismatching amount of the q +1 generation cross planning scheme exceeds a preset mismatching amount threshold, regenerating q +1 generation cross continuous population individuals, and forming a cross planning scheme by the q generation discrete population which accords with the topological constraint and the regenerated q +1 generation cross continuous population individuals;

and returning to execute the step of inputting the initial planning scheme and the cross planning scheme into the second planning model for solving.

In a second aspect, a multi-objective planning apparatus for a new energy convergence network is provided, the apparatus including:

the first acquisition module is used for acquiring basic data of a sending end network; the basic data comprise position coordinates of the new energy station, position coordinates of the main network transformer substation and connection relations among the main network transformer substations;

the second acquisition module is used for acquiring historical operating data and determining the value range of the optimized variable according to the historical operating data and the basic data; the historical operation data comprises load historical data and power supply historical data;

and the planning module is used for inputting the value range of the optimized variable into a preset multi-target double-layer planning model for solving to obtain a planning scheme set.

In a third aspect, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

acquiring basic data of a sending end network; the basic data comprise position coordinates of the new energy station, position coordinates of the main network transformer substation and connection relations among the main network transformer substations;

obtaining historical operating data, and determining the value range of an optimized variable according to the historical operating data and basic data; the historical operation data comprises load historical data and power supply historical data;

and inputting the value range of the optimized variable into a preset multi-target double-layer planning model for solving to obtain a planning scheme set.

In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

acquiring basic data of a sending end network; the basic data comprise position coordinates of the new energy station, position coordinates of the main network transformer substation and connection relations among the main network transformer substations;

obtaining historical operating data, and determining the value range of an optimized variable according to the historical operating data and basic data; the historical operation data comprises load historical data and power supply historical data;

and inputting the value range of the optimized variable into a preset multi-target double-layer planning model for solving to obtain a planning scheme set.

The multi-target planning method, the multi-target planning device, the computer equipment and the storage medium of the new energy convergence network acquire basic data of a sending end network; the basic data comprise position coordinates of the new energy station, position coordinates of the main network transformer substation and connection relations among the main network transformer substations; obtaining historical operating data, and determining the value range of an optimized variable according to the historical operating data and basic data; the historical operation data comprises load historical data and power supply historical data; and inputting the value range of the optimized variable into a preset multi-target double-layer planning model for solving to obtain a planning scheme set. The method comprehensively considers the multi-target optimization problem in the new energy convergence network and solves the problem through a preset multi-target double-layer planning model to obtain a planning scheme set, so that the synchronous optimization of the multi-target performance in the sending-end network is realized.

Drawings

FIG. 1 is a diagram of an embodiment of an application environment of a multi-objective planning method for a new energy collection network;

FIG. 2 is a schematic flow chart diagram illustrating a multi-objective planning method for a new energy aggregation network in one embodiment;

FIG. 3 is a schematic diagram of a multi-objective planning method for a new energy aggregation network in one embodiment;

FIG. 4 is a flowchart illustrating a multi-objective planning method for a new energy collection network in accordance with an embodiment;

FIG. 5 is a diagram illustrating the results of a conventional planning method in one embodiment;

FIG. 6 is a diagram illustrating results of a multi-objective planning method for a new energy aggregation network in one embodiment;

FIG. 7 is a block diagram of a multi-objective planning apparatus for a new energy collection network in one embodiment;

FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

Most of the power grid planning work under new energy access is concentrated on power transmission network optimization planning, and most of the methods consider that the form of a new energy collection network is relatively fixed, and the optimization space is relatively small. In the research of the convergence network planning of a few new energy stations, most of the inventions take economy as a main optimization target or even a unique optimization target, only consider the line construction cost, the system operation cost and the new energy abandonment cost, and have insufficient modeling on the factors such as the new energy sending capacity, the local load supply capacity and the like which need to be considered in the construction of a new energy sending end base; in addition, the current scheme mostly uses a single planning scheme as an output result, in actual engineering, the planning scheme needs to be subjected to operation simulation calculation and comprehensive evaluation, a certain number of alternative schemes are needed as reference, and the current scheme is difficult to meet the requirement.

The optimization planning of the new energy station convergence network in the sending-end network is realized under the multiple targets of considering economy and optimal network operation performance.

The multi-target planning method for the new energy collection network can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal inputs the basic data, the historical operation data and other parameters required during planning of the sending terminal network into a preset multi-target double-layer planning model for solving to obtain a planning scheme set. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.

In one embodiment, as shown in fig. 2, a multi-objective planning method for a new energy collection network is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:

step 202, acquiring basic data of a sending end network; the basic data comprise position coordinates of the new energy station, position coordinates of the main network transformer substation and connection relations among the main network transformer substations.

As shown in fig. 3, the sending-end network includes a network formed by a new energy collection network and a local ac power grid. The new energy collection network comprises a new energy station, a collection substation to be built, a collection line between the new energy station and the collection substation to be built, and a collection line between the collection substation to be built and a main network substation. The local alternating-current power grid comprises a main network transformer substation and a main network line between the main network transformer substations, and the direct-current line starting point is a transformer substation connected with the direct-current line in the main network transformer substation. The basic data of the sending end network comprises the position coordinates of the built power stations of the sending end network, the connection relation among the existing lines and the transmission capacity of the main line. The transmission capacity of the main line is specified by the national grid planning department.

Specifically, the terminal acquires the position coordinates of the new energy station, the position coordinates of the main network transformer substation, the connection relationship between the main network transformer substations and the transmission capacity of the main network line.

Step 204, acquiring historical operating data, and determining the value range of the optimized variable according to the historical operating data and the basic data; wherein the historical operating data comprises load historical data and power source historical data.

The load historical data refers to load power data of the local communication main network at each moment in a planning calculation time period. The power source historical data comprises the maximum power generation capacity of the new energy station and the upper and lower limits of the active output power of the main network transformer substation.

Specifically, the terminal acquires a time period needing to be considered in planning calculation, then acquires the upper limit and the lower limit of active output power of an original conventional unit in a local communication main network in the time period, acquires the maximum power generation capacity of a new energy station in the time period at each moment, and acquires load power data of the local communication main network in the planning calculation time period at each moment.

And determining the value range of the corresponding optimization variable in the planning model according to the basic data and the historical operation data of the sending terminal network.

Meanwhile, the terminal also needs to acquire other parameters required in planning calculation. Other parameters include conventional unit generation cost parameters, line construction cost parameters, crossover probability factors, mutation factors, replication probability factors, mating probability factors, population generations, number of individuals per generation, and the like. The power generation cost parameter and the line construction cost parameter of the conventional unit can be determined according to actual cost, the cross probability factor, the mutation factor, the replication probability factor, the mating probability factor and the population algebra can be determined according to empirical values, and the number of individuals of each generation is determined according to the number of optimized variables.

And step 206, inputting the value range of the optimized variable into a preset multi-target double-layer planning model for solving to obtain a planning scheme set.

The multi-target double-layer planning model is a planning model considering economy and optimal network operation performance. The economy is that the construction cost is minimum, the network operation performance is optimal, and the performance of optimization targets such as minimum limited electric quantity of new energy, maximum power output of a connection point of a direct current conversion station and a local alternating current power grid, highest load balance of each line in a sending end network, highest symmetry of a direct connection power supply and a direct connection load of each node in the sending end network and the like is best.

Specifically, the optimized variables are initialized within the value range of the optimized variables, and the optimized variables are optimized through each layer of model in the multi-objective double-layer planning model to obtain a planning scheme set meeting the planning requirements.

In the multi-target planning method of the new energy convergence network, basic data of a sending end network is obtained; the basic data comprise position coordinates of the new energy station, position coordinates of the main network transformer substation and connection relations among the main network transformer substations; obtaining historical operating data, and determining the value range of an optimized variable according to the historical operating data and basic data; the historical operation data comprises load historical data and power supply historical data; and inputting the value range of the optimized variable into a preset multi-target double-layer planning model for solving to obtain a planning scheme set. The method comprehensively considers the multi-target optimization problem in the new energy convergence network and solves the problem through a preset multi-target double-layer planning model to obtain a planning scheme set, so that the synchronous optimization of the multi-target performance in the sending-end network is realized.

In an alternative embodiment, the multi-objective two-layer planning model includes a first planning model and a second planning model;

inputting the value range of the optimized variable into a preset multi-target double-layer planning model for solving to obtain a planning scheme set, wherein the planning scheme set comprises the following steps:

solving the first planning model by using a differential evolution algorithm in the value range of the optimized variable to obtain a target optimized variable;

and determining the boundary condition of the second planning model according to the target optimization variable, and solving the second planning model by using a mixed integer linear planning method to obtain a planning scheme set.

Specifically, the multi-objective two-layer planning model includes a first planning model and a second planning model. The optimization variables include optimization variables of the first planning model and optimization variables of the second planning model. Initializing the optimized variables of the first planning model in the value range of the optimized variables, and solving the optimized variables in the first planning model by using a differential evolution algorithm to obtain target optimized variables.

And determining boundary conditions of the optimized variables of the second planning model according to the target optimized variables, solving the optimized variables of the second planning model by using a mixed integer linear programming method, adding the optimal planning scheme into a planning scheme set, and obtaining a final planning scheme set when the planning scheme set meets preset planning requirements.

In this embodiment, optimization variables are optimized and solved through a multi-objective double-layer planning model, optimization conditions such as economic performance and network operation performance can be comprehensively considered, and the obtained planning target set can simultaneously meet optimization targets such as minimum construction cost, minimum limited electric quantity of new energy, maximum output power of a connection point of a direct current conversion station and a local alternating current power grid, highest load balance of each line in a sending-end network, and highest symmetry of a direct connection power supply and a direct connection load of each node in the sending-end network. The construction cost is reduced, the active loss of the main network in real-time operation is reduced, and the optimization performance of the transmission end network in all aspects of planning and operation is improved.

In an alternative embodiment, the process of establishing the multi-objective two-layer optimization model includes:

constructing an objective function of the first planning model according to the optimization objective of the first planning model; wherein the optimization objectives of the first planning model include: the construction cost is minimum, the limited electric quantity of new energy is minimum, the output power of a connection point of a direct current conversion station and a local alternating current power grid is maximized, the load balance of each line in a sending end network is highest, and the symmetry of each node direct-connected power supply and each direct-connected load in the sending end network is highest;

determining constraint conditions of the first planning model according to the connection relation between the new energy station and the collection substation;

determining an objective function of the second planning model according to the optimization objective of the second planning model;

and determining constraint conditions of a second planning model according to the optimization variables of the first planning model and the physical operation constraints of the new energy collection network.

Specifically, the multi-target double-layer planning model cooperatively considers the performances of line construction economy, new energy access capacity, direct current sending capacity, tide distribution balance and the like. The optimization objectives of the first planning model include minimum construction cost, minimum limited electric quantity of new energy, maximum output power of a connection point of the direct current conversion station and the local alternating current power grid, highest load balance of each line in the sending-end network, and highest symmetry of each node direct-connected power supply and direct-connected load in the sending-end network.

The objective function of the first planning model includes: the method comprises the following steps of constructing a cost function, a new energy limited electric quantity function, a direct current sending channel utilization function, a power flow distribution entropy function of each line in a sending end network, and a symmetry function of each node direct connection power supply and a direct connection load in the sending end network.

The constraint condition of the first planning model is a topological constraint, namely a connection condition constraint, between the new energy station and the collection substation in the collection network. The optimization variables of the first planning model are collected substation coordinates, collected substation capacity, line transmission capacity and line construction decision variables.

The optimization objective of the second planning model is to minimize the system operating cost. And the objective function of the second planning model is a conventional unit power generation cost function and an active tide loss proportioning penalty cost function of each node. The constraint conditions of the second planning model are that under different planning schemes, the line power flow, the node voltage phase angle and the power supply power of each node are all within an allowable range. The optimization variables of the second planning model are the new energy electricity limiting power, the direct current output power, the generating power of the conventional thermal power generating unit, the line transmission power and the node voltage phase angle.

Suppose that the sending end network has N nodes, the node number is i, and the node i is a set of a new energy station node, a to-be-built collection station node, and a local main alternating current power grid node. Wherein the node set of the newly-built new energy station is I_RNumber N_RThe nodes of the sink station to be built are integrated into I_SNumber N_SLocal backbone alternating current grid node set is I_MNumber N_MThe local backbone alternating current power grid node set comprises a local alternating current power grid node set connected with a direct current channel starting point, and the local alternating current power grid node set connected with the direct current channel starting point is I_DNumber N_DAnd (4) respectively. In planning, a candidate set of lines to be built is determined in advance, the number of the lines is k, and the number of candidates of the lines to be built is N_K. In the planning calculation, the optimal direct current load flow corresponding to each time T in a certain typical time period is calculated, and the T typical times are included in total.

Establishing a corresponding objective function for the optimization objective of the first optimization model, wherein the formula is as follows:

in the formula, an optimization target F1 is the total construction cost of a convergence network, K1 is a set of lines to be constructed, K2 is a set of substations to be constructed, each substation is equivalent to a line according to the traditional load flow calculation, each substation comprises two nodes, and the capacity of each substation is the transmission capacity of the line; a is_kTaking the decision variable of 0-1 of the kth line, wherein the line is not constructed when the value is 0, and the line is constructed when the value is 1; c_lTen thousand yuan/(MW x km) is the construction cost of the transmission line; c_sThe construction cost of the unit capacity of the transformer substation is ten thousand yuan/MW;the transmission/transformation capacity of the kth line or the transformer substation; d_kFor the length of the kth transmission line, the calculation method is

In the formula, L_iSet of lines connected for node i, L_jSet of lines connected for node j, (x)_i,y_i) Is the coordinate of node i, (x)_j,y_j) Is the coordinate of node j.

Optimization goal F₂The limited electric quantity of each new energy station is the minimum, in the formula,and the power limit power of the new energy power station on the node i at the moment t.

Optimization goal F₃In order to increase the utilization rate of the direct current output channel,for node i power delivered via the DC line, P_i ^D.maxIs a direct current at node iMaximum transmission capacity of the transmission channel.

Optimization goal F₄Entropy is distributed for each line flow. In the formula (I), the compound is shown in the specification,for the active power flow of line k at time t,in order to be the transmission capacity of the line k,is the KL-th load rate interval range, KL is the number of load rate intervals, and is the experimental set value in the planning calculation, the general suggested value is 10,representing the probability that the line k load rate is within the kl-th load rate interval.

Optimization goal F₅Rank correlation coefficient of connecting load and power supply to each node, wherein d_iIs calculated by

In the formula (I), the compound is shown in the specification,respectively the maximum power generation capacity of the new energy station at the point i at the time t and the power generation power of the conventional unit,for the active load power at node i and the power delivered by the DC channel at time t, Rank (x)_i) Represents the variable x_iRank in the set.

The constraint conditions of the first planning model stipulate the connection relationship between the new energy station and the collection substation in the collection network, and the specific formula is as follows:

Z_ij>0(i∈I_R,j∈I_D) (5)

formula (2) provides that each new energy station node has at least one line to connect with other nodes.

Equation (3) specifies that each collection substation is to be connected to at least two other nodes.

Equation (4) provides that each collection substation is connected to at least one new energy site node.

The formula (5) specifies that the mutual impedance between each new energy station node and the dc-link node is positive.

And determining an objective function of the second planning model according to the optimization objective of the second planning model, wherein the specific formula is as follows:

the constraint conditions of the second planning model are that under the planning scheme determined by the first optimization model, the line load flow, the node voltage phase angle and the power supply power of each node are all in an allowable range, and the specific formula is as follows:

a_k＝0,1(k∈{k∈L_i|i∈I_R∪I_S}) (14)

the formula (6) is an optimization target of a lower-layer optimization model, and the minimum power generation cost of a conventional unit and the minimum penalty cost of power source and load power mismatch of each node are taken as targets; the optimization variables in the underlying optimization model are Is the unit generation cost, theta, of the conventional unit at time node i_i,tFor the phase angle of the voltage at node ij at time t, epsilon_i,tThe amount of injected power mismatch at node i at time t is obtained from equations (7) and (8), K_ubA penalty factor for the amount of power mismatch.

And the formula (7) is an injection power equation of the new energy station and the collection substation node. L is_iLine sets connected for node i, B_ijThe value is the admittance value of the line between nodes i and j, which can be selected according to the practical engineering parameters.

Equation (8) is the injection power equation for the master network node.

Equation (9) is line load flow calculation and constraint, P_i ^sub.maxThe transformation capacity formula (10) for the collection substation is the voltage phase angle range constraint of each node,is the maximum voltage phase angle value of node i.

And the formula (11) is the constraint of the limited electric quantity range of the new energy.

And the formula (12) is the upper limit constraint of the generating power of the conventional unit of the node i, wherein,is the active power of the unit m at time t, C_iIs a conventional unit set at a node i;respectively the upper and lower limits of the active output of the unit m.

Equation (13) is a constraint on the DC line output power at node i, where P_i ^D.min、P_i ^D.maxThe upper and lower limits of active power are sent out for the direct current line respectively.

And the formula (14) is used for limiting the values of the decision variables of the line construction.

In an alternative embodiment, the objective optimization variables include an initial planning solution and a cross-planning solution;

solving the first planning model by using a differential evolution algorithm in the value range of the optimization variables to obtain target optimization variables, wherein the method comprises the following steps:

dividing the optimized variables in the first planning model according to variable types to obtain a continuous variable population and a discrete variable population;

initializing a continuous variable population within the value range of the optimized variable to obtain q generations of continuous population individuals; the q generation continuous population individuals comprise collected substation coordinates, collected substation transformation capacity and line transmission capacity;

randomly initializing a discrete variable population to obtain a q-generation discrete population, wherein the q-generation discrete population is a construction decision variable of a line to be selected, 0 represents that the line to be selected is not constructed, and 1 represents that the line to be selected is constructed;

carrying out topological constraint verification on the q-generation discrete population according to constraint conditions of the first planning model, and enabling the q-generation discrete population and the q-generation continuous population which meet the topological constraint to form an initial planning scheme;

carrying out variation and cross operation on the q-generation continuous population individuals to form q + 1-generation cross continuous population individuals corresponding to the q-generation continuous population individuals; forming a cross planning scheme by q-generation discrete populations and q + 1-generation cross continuous population individuals which accord with topological constraints;

determining the boundary condition of a second planning model according to the target optimization variables, and solving the second planning model by using a mixed integer linear planning method to obtain a planning scheme set, wherein the planning scheme set comprises the following steps:

inputting the initial planning scheme and the cross planning scheme into a second planning model for solving to obtain a node injection power mismatch amount of a q-generation initial planning scheme and a node injection power mismatch amount of a q + 1-generation cross planning scheme;

when the node injection power mismatch amount of the q-generation initial planning scheme does not exceed a preset mismatch amount threshold, solving an objective function value corresponding to the initial planning scheme according to the first planning model to obtain an objective function value of the initial planning scheme;

when the node injection power mismatch amount of the q +1 generation cross planning scheme does not exceed a preset mismatch amount threshold, solving an objective function value corresponding to the cross planning scheme according to the first planning model to obtain an objective function value of the cross planning scheme;

selecting according to the objective function value of the initial planning scheme and the objective function value of the cross planning scheme to obtain q +1 generation continuous population individuals;

generating a minimum non-dominated set of q +1 generation continuous population individuals, and adding the minimum non-dominated set into a planning scheme set;

and when the quantity of the planning scheme sets is larger than the preset number or the population algebra is larger than the algebra threshold value, outputting the planning scheme sets.

Wherein the variable type includes a continuous variable and a discrete variable.

Specifically, the collected substation coordinates, the collected substation capacity, the line transmission capacity and the line construction decision variables are divided into continuous variable populations and discrete variable populations according to variable types. As shown in table 1, the collected substation coordinates, the collected substation capacity, and the line transmission capacity are continuous variable populations, and the line construction decision variables are discrete variable populations.

Table 1 variable grouping table

The above optimized variables form the boundary conditions of the optimized variables in the second planning model, and the optimized variables of the lower layer optimization problem are shown in table 2:

TABLE 2 optimization variables for the second planning model

As shown in fig. 4, the specific solving steps are:

step a 1: setting a population algebra q to be 1, initializing optimized variables in the first population to the third population according to a formula (15), and obtaining q continuous population individuals:

X_v(q)＝X_v ^min+rand()□(X_v ^max-X_v ^min),(v＝1,2…Q) (15)

in the formula, X_v(q) denotes the v-th individual in the q-th generation, which is a vector consisting of the pooled substation coordinates, the pooled substation transformation capacity, and the line transmission capacity, rand () is a random number between 0 and 1, X_v ^max,X_v ^minRespectively the upper and lower limit values of the individual. The value range of the collected substation coordinates can be determined by a polygon formed by the new energy station and the main network substation, and the collection substation transformation capacity and the line transmission capacityThe value range of the capacity is determined by the value range of the optimization variable.

Step a 2: and for the fourth population, randomly initializing to form q-generation discrete populations according to the formula (16):

POP_vk(q)＝randi() (16)

in the formula, POP_vk(q) is the kth component of the qth generation of the v individual, corresponding to the construction decision variable of the kth line, and randi () randomly generates 0 and 1 values.

Step a 3: POP according to formulas (2) - (5)_v(q) carrying out topology constraint check, if the individual satisfies the topology constraint shown in the formulas (2) - (5), retaining, if the individual does not satisfy the topology constraint condition, returning to the step a2, and regenerating the individual POP_v(q)。

Step a 4: q-generation discrete population POP_v(q) and q generations of consecutive population individuals X_v(q) forming a complete initial planning scheme for converged networks<POP_v(q),X_v(q)>。

Step a 5: after the values of the line construction decision variables and the values of the line capacity and the transformation capacity are known, the boundary conditions of the second planning model are completely determined. Will initially plan the plan<POP_v(q),X_v(q)>And carrying out optimal power flow solution in the second planning model to obtain the node injection power mismatching amount of the q-generation initial planning scheme.

Step a 6: judging the node injection power mismatching amount of the q-generation initial planning scheme according to a formula (17), when the node injection power mismatching amount of the q-generation initial planning scheme does not exceed a preset mismatching amount threshold value, reserving the initial planning scheme, and solving an objective function value F corresponding to the initial planning scheme according to a first planning model_i(X), (i ═ 1,2 … 5), the initial planning scheme objective function values are obtained.

Step a 7: calculating difference vectors for q successive population individuals in the first to third populations according to formula (18):

D_v1,2(q)＝X_v1(q)-X_v2(q) (18)

D_v1,2(q) is optional two individuals X in the q generation population_v1And X_v2And (5) obtaining a difference vector. Weighting the difference vector and another individual in the generation population to obtain a q +1 generation variant individual

Y_v(q+1)＝X_v3(q)+F□(X_v1(q)-X_v2(q)) (19)

Wherein F is a variation factor, and is taken as a value in the whole planning calculation, and F belongs to [0,2 ].

Step a 8: defining q generation continuous population individuals in the first to third populations, and defining corresponding q +1 generation crossed continuous population individuals U_v(q +1) is as follows:

in the formula, Y_vj(q +1) is the j component of the v individual corresponding to the variant individual in the q +1 generation, CR is a cross probability factor, which is given in advance in the planning calculation and belongs to (0, 1).

And (3) forming a cross planning scheme by the q-generation discrete population and the q + 1-generation cross continuous population which accord with the topological constraint.

Step a 9: after the values of the line construction decision variables and the values of the line capacity and the transformation capacity are known, the boundary conditions of the second planning model are completely determined. Plan the cross<POP_v(q),U_v(q+1)>And performing optimal power flow solution in the second planning model to obtain the q +1 generation cross node injection power mismatch amount.

Step a 10: judging the injection power mismatch amount of the q +1 generation cross planning scheme, and solving an objective function value F corresponding to the cross planning scheme according to the first planning model when the node injection power mismatch amount of the q +1 generation cross planning scheme does not exceed a preset mismatch amount threshold value_2i(X), (i ═ 1,2 … 5), the cross-planning scheme objective function values are obtained.

Step a 11: the initial planning schemeSelecting the objective function value of the standard function value and the cross planning scheme according to a formula (21) to obtain q +1 generation continuous population individuals X_v(q +1), wherein the v-th individual is:

wherein F (·) represents the objective function vector, > represents absolute dominance, i.e., F (X) > F (Y):F_i(X)≥F_i(Y)。

step a 12: for q +1 generation continuous population individual X_v(q +1), identifying and extracting the minimum non-dominated set P according to Pareto discrimination standard_qThe number of the collection elements is N_Pareto。

Step a 13: and judging whether the quantity of the planning scheme sets is greater than a preset quantity or not and whether the population algebra is greater than an algebra threshold value or not, and outputting the planning scheme sets when the quantity of the planning scheme sets is greater than the preset quantity or the population algebra is greater than the algebra threshold value.

Further, the planning scheme set obtained according to the differential evolution algorithm is an alternative scheme in new energy convergence network planning, more reasonable options can be provided for engineering personnel, and further N is needed_ParetoThe best embodiment is selected from the schemes. In the embodiment of the present application, the TOPSIS method may be further combined to select the optimal scheme, or the engineering cost may be combined, different targets are summed according to the economic weight, the lowest value of the comprehensive cost is taken as the optimal scheme, and the process of determining the optimal implementation scheme is not limited herein.

In this embodiment, the sequence of the initialization process of each generation of population individuals and decision variables is not limited, that is, the sequence of step a1 and steps a2-a3 is not limited, as long as each generation of population individuals and decision variables can be obtained to form an initial planning scheme. The process of solving the corresponding objective function values by the initial planning scheme and the cross planning scheme can be carried out together, or the objective function values corresponding to the initial planning scheme can be solved first, then q +1 generation cross continuous population individuals corresponding to the q generation continuous population individuals are solved to form a cross planning scheme, and then the objective function values corresponding to the cross planning scheme are solved.

In the embodiment, the optimization space is improved and the optimization performance of the planning model is improved by considering the solution of the planning model of the plurality of optimization targets. Finally, a planning scheme set meeting the conditions can be obtained through multi-objective optimization solution, a plurality of reasonable options can be provided for actual engineering solution, and then the optimal planning scheme can be selected according to subsequent requirements.

In an optional embodiment, the method further comprises:

when the number of the planning scheme sets is smaller than or equal to the preset number and the population algebra is smaller than or equal to the algebra threshold, adding one to the population algebra q, and performing updating operation on the discrete variable population to obtain a q +1 generation discrete population;

and forming a new initial planning scheme by the q +1 generation of discrete population and the q +1 generation of continuous population, selecting an objective function value corresponding to the new initial planning scheme as an objective function value corresponding to the q +1 generation of continuous population in the previous round, and returning to execute the steps of carrying out variation and cross operation on the q +1 generation of continuous population.

Specifically, step a 14: when the number of the planning scheme sets is smaller than or equal to the preset number and the population algebra is smaller than or equal to the algebra threshold, adding one to the population algebra q, updating the individuals of the population four according to a formula (22), and generating a q +1 generation discrete population POP_vk(q+1)：

In the formula, POP_v1k1(q) is optional individuals and elements in the q generation population, "[ lambda ] is a Boolean and operator,for negation operation, CR1 is the copy probability factor, and CR2 is the intersectionMatching probability factors, and 0 < CR1 < CR2 < 1.

And forming a new initial planning scheme by the q +1 generation of discrete population and the q +1 generation of continuous population, wherein the objective function value corresponding to the new initial planning scheme is selected as the objective function value corresponding to the q +1 generation of continuous population in the previous round. Returning to the step a7, performing mutation and crossover operation on the q +1 generation continuous population individuals to obtain crossover individuals corresponding to the q +1 generation continuous population individuals.

In an optional embodiment, performing a selection operation according to the objective function value of the initial planning scheme and the objective function value of the cross-planning scheme to obtain q +1 generation of consecutive population individuals, includes:

when the objective function value of the initial planning scheme is superior to the objective function value of the cross planning scheme, taking the continuous population individuals of the q generation as continuous population individuals of the q +1 generation;

and when the objective function value of the cross planning scheme is superior to the objective function value of the initial planning scheme, taking cross individuals corresponding to the q generation continuous population individuals as q +1 generation continuous population individuals.

Specifically, in step a11, the initial planning scheme objective function values and the cross planning scheme objective function values are selected according to a formula (21), and the magnitude relationship between each objective function value in the initial planning scheme objective function values and the corresponding objective function value in the cross planning scheme objective function values is determined, and the result includes step a 11-1: when each objective function value in the objective function values of the initial planning scheme is superior to the corresponding objective function value in the objective function values of the cross planning scheme, the objective function value of the initial planning scheme is superior to the objective function value of the cross planning scheme absolutely, and the objective function value of the initial planning scheme is used as a q +1 generation continuous population individual; otherwise, the result is step a 11-2: and when each objective function value in the cross planning scheme is superior to the corresponding objective function value in the initial planning scheme objective function value, the cross planning scheme objective function value is absolutely superior to the initial planning scheme objective function value, and the cross planning scheme objective function value is used as a q +1 generation continuous population individual.

In an optional embodiment, the method further comprises:

when the mismatch amount of the injection power of the q generation of primary nodes exceeds a preset mismatch amount threshold value, regenerating q generation of continuous population individuals and q generation of discrete populations, and forming an initial planning scheme by the q generation of discrete populations which accord with topological constraints and the regenerated q generation of continuous population individuals;

when the injection power mismatch amount of the q +1 generation cross node exceeds a preset mismatch amount threshold value, regenerating q +1 generation cross continuous population individuals, and forming a cross planning scheme by the q generation discrete population which accords with the topological constraint and the regenerated q +1 generation cross continuous population individuals;

and returning to execute the step of inputting the initial planning scheme and the cross planning scheme into the second planning model for solving.

Specifically, the q-generation initial node injection power mismatch amount is judged according to the formula (17), when the q-generation initial node injection power mismatch amount exceeds a preset mismatch amount threshold value, namely the result of the step a6 is yes, the initial planning scheme is deleted, the step a1 is returned, q-generation continuous population individuals and q-generation discrete populations are regenerated, and the q-generation discrete populations which meet the topological constraint and the regenerated q-generation continuous population individuals form the initial planning scheme.

And c, judging the injection power mismatching amount of the q +1 generation cross nodes, deleting the cross planning scheme when the injection power mismatching amount of the q +1 generation cross nodes exceeds a preset mismatching amount threshold value, namely the result of the step a10 is yes, returning to the step a7, regenerating q +1 generation cross continuous population individuals, and forming a cross planning scheme by the q generation discrete population which meets the topological constraint and the regenerated q +1 generation cross continuous population individuals.

The effect analysis of the present invention was performed in the case shown in fig. 5 and 6. In this case, the backbone network substation A, B, C and the lines a-C, B-C, A-C are already established, the positions of the new energy stations a and b are determined, and the line connection point needs to be selected when the collection line of the two stations is to be established. In the conventional planning method, if only the shortest construction route is considered, both stations are connected to the main network substation a, as shown in fig. 5. The line construction cost under the scheme is minimized, but after the line construction, the local load directly connected with the main network transformer substation B needs to be supplied with power by the new energy station, the tide on the main network line A-B is obviously increased, the network active loss in actual operation is increased, and meanwhile, the line A-B possibly needs to be expanded, so that the main network transformation cost is increased. If the minimization of the power flow crossing is considered in the convergent network planning construction, and the power supply path of the new energy station for supplying power to the local load is reduced, the formed planning scheme is as shown in fig. 6. And the station B is connected with the main network substation B so as to directly supply power to the local load, and under the scheme, the line construction cost is increased to some extent, but the active loss of the main network in real-time operation is effectively reduced, the transmission flux of the lines A-B is reduced, and the expansion cost of the main network is reduced.

The case analysis shows that after the coordination of line construction economy and power flow crossing conditions is considered together in the convergent network planning, the synchronous optimization of the performance of each aspect of the source end network can be realized in the whole planning and operation stages.

It should be understood that, although the steps in the flowcharts of fig. 2 and 4 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 2 and 4 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the steps or stages in other steps.

In one embodiment, as shown in fig. 7, a multi-objective planning apparatus for a new energy convergence network is provided, including: a first acquisition module 702, a second acquisition module 704, and a third acquisition module 706, wherein:

a first obtaining module 702, configured to obtain basic data of a sending-end network; the basic data comprise position coordinates of the new energy station, position coordinates of the main network transformer substation and connection relations among the main network transformer substations.

A second obtaining module 704, configured to obtain historical operating data, and determine a value range of the optimized variable according to the historical operating data and the basic data; wherein the historical operating data comprises load historical data and power source historical data.

And the planning module 706 is configured to input the value range of the optimized variable into a preset multi-objective double-layer planning model for solving, so as to obtain a planning scheme set.

In an alternative embodiment, the multi-objective two-layer planning model includes a first planning model and a second planning model;

the planning module 706 further includes a first planning unit and a second planning unit, where the first planning unit is configured to solve the first planning model by using a differential evolution algorithm within a value range of the optimized variable to obtain a target optimized variable;

and the second planning unit is used for determining the boundary condition of the second planning model according to the target optimization variable and solving the second planning model by using a mixed integer linear planning method to obtain a planning scheme set.

In an optional embodiment, the multi-objective planning apparatus for a new energy collection network further includes a planning model building module, configured to build an objective function of the first planning model according to an optimization objective of the first planning model; wherein the optimization objectives of the first planning model include: the construction cost is minimum, the limited electric quantity of new energy is minimum, the output power of a connection point of a direct current conversion station and a local alternating current power grid is maximized, the load balance of each line in a sending end network is highest, and the symmetry of each node direct-connected power supply and each direct-connected load in the sending end network is highest;

determining constraint conditions of the first planning model according to the connection relation between the new energy station and the collection substation;

determining an objective function of the second planning model according to the optimization objective of the second planning model;

and determining constraint conditions of a second planning model according to the optimization variables of the first planning model and the physical operation constraints of the new energy collection network.

In an alternative embodiment, the objective optimization variables include an initial planning solution and a cross-planning solution;

the first planning unit is also used for dividing the optimized variables in the first planning model according to variable types to obtain a continuous variable population and a discrete variable population;

initializing the continuous variable population within the value range of the optimized variable to obtain q generations of continuous population individuals; the q generation continuous population individuals comprise collected substation coordinates, collected substation transformation capacity and line transmission capacity;

randomly initializing the discrete variable population to obtain a q-generation discrete population, wherein the q-generation discrete population is a construction decision variable of the line to be selected, 0 represents that the line to be selected is not constructed, and 1 represents that the line to be selected is constructed;

carrying out topological constraint verification on the q-generation discrete population according to constraint conditions of the first planning model, and enabling the q-generation discrete population and the q-generation continuous population which meet the topological constraint to form an initial planning scheme;

carrying out variation and cross operation on the q-generation continuous population individuals to form q + 1-generation cross continuous population individuals corresponding to the q-generation continuous population individuals; forming a cross planning scheme by q-generation discrete populations and q + 1-generation cross continuous population individuals which accord with topological constraints;

the second planning unit is also used for inputting the initial planning scheme and the cross planning scheme into a second planning model for solving to obtain a node injection power mismatch amount of the q generation of initial planning scheme and a node injection power mismatch amount of the q +1 generation of cross planning scheme;

when the node injection power mismatch amount of the q-generation initial planning scheme does not exceed a preset mismatch amount threshold, solving an objective function value corresponding to the initial planning scheme according to the first planning model to obtain an objective function value of the initial planning scheme;

when the node injection power mismatch amount of the q +1 generation cross planning scheme does not exceed a preset mismatch amount threshold, solving an objective function value corresponding to the cross planning scheme according to the first planning model to obtain an objective function value of the cross planning scheme;

selecting operation is carried out according to the objective function value of the initial planning scheme and the objective function value of the cross planning scheme to obtain q +1 generation of continuous population individuals;

generating a minimum non-dominated set of q +1 generation continuous population individuals, and adding the minimum non-dominated set into a planning scheme set;

and outputting the planning scheme set when the quantity of the planning scheme set is greater than the preset number or the population algebra is greater than an algebra threshold value.

In an optional embodiment, the planning module 706 is further configured to, when the number of the planning scheme sets is less than or equal to the preset number and the population generation number is less than or equal to the generation threshold, add one to the population generation number q, and perform an update operation on the discrete variable population to obtain a q +1 generation discrete population;

and forming a new initial planning scheme by the q +1 generation of discrete population and the q +1 generation of continuous population, wherein the objective function value corresponding to the new initial planning scheme is selected as the objective function value corresponding to the q +1 generation of continuous population in the previous round, and returning to execute the steps of carrying out variation and cross operation on the q +1 generation of continuous population.

In an optional embodiment, the second planning unit is further configured to treat the q-generation consecutive population individuals as q + 1-generation consecutive population individuals when the initial planning scheme objective function values dominate the cross-planning scheme objective function values;

and when the objective function value of the cross planning scheme is superior to the objective function value of the initial planning scheme, taking cross individuals corresponding to the q generation of continuous population individuals as q +1 generation of continuous population individuals.

In one embodiment, the first planning unit is further configured to regenerate the q-generation continuous population individuals and the q-generation discrete population when a node injection power mismatch amount of the q-generation initial planning scheme exceeds a preset mismatch amount threshold, and combine the q-generation discrete population conforming to the topological constraint and the regenerated q-generation continuous population individuals into the initial planning scheme;

when the node injection power mismatching amount of the q +1 generation cross planning scheme exceeds a preset mismatching amount threshold, regenerating q +1 generation cross continuous population individuals, and forming a cross planning scheme by the q generation discrete population which accords with the topological constraint and the regenerated q +1 generation cross continuous population individuals;

and returning to execute the step of inputting the initial planning scheme and the cross planning scheme into the second planning model for solving.

For specific limitations of the multi-objective planning apparatus for the new energy collection network, reference may be made to the above limitations of the multi-objective planning method for the new energy collection network, and details thereof are not repeated herein. All or part of each module in the multi-target planning device of the new energy collection network can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a multi-objective planning method for a new energy collection network. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.

In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.