1. A power failure window period arranging method is characterized by comprising the following steps:

discretizing time-period type data of a historical power failure window period of preset type of power equipment in a preset regional power grid to obtain a model data set to be mined;

acquiring a frequent item set of the electric power equipment in the preset type of electric power equipment based on the model data set to be mined;

calculating and obtaining the annual co-stop confidence level of each electric power device in the preset type of electric power devices based on the frequent item set and by using a strong association rule mining method;

calculating and obtaining the average co-stop confidence level of each power device based on the annual co-stop confidence level of each power device;

and recommending the power equipment in the historical power failure window period based on the average same-stop confidence level of each power equipment, so as to realize the arrangement of the power failure window period.

2. The method for arranging the blackout window period according to claim 1, wherein the step of discretizing the time period type data of the historical blackout window period of the preset type of power equipment in the preset regional power grid to obtain the model data set to be mined comprises the following specific steps:

classifying the time period type number of the historical power failure window period of the preset type of power equipment in the preset regional power grid according to years to obtain the time period type number of the annual historical power failure window period;

dividing the time period number of the annual historical power failure window period by days, traversing the power failure window period of the preset type of power equipment, acquiring the power equipment which has power failure every day in the year, and forming a model data set to be mined.

3. The power outage window period arrangement method according to claim 2, wherein the specific step of obtaining the frequent item set of the preset kind of power equipment based on the model data set to be mined includes:

constructing the power equipment in the preset type of power equipment into a frequent 1 item set, and counting the occurrence frequency of each power equipment on each power failure date to obtain a counting frequency result;

taking the statistical frequency result as the support degree of each power device, removing the items with the support degree lower than a preset threshold value, and obtaining an item head table;

obtaining a power equipment set of each power failure date based on the item head table;

sequentially inserting the power equipment set of each power failure date into the FP tree according to the sequence of the support degree from high to low to obtain the FP tree after data insertion; in the power equipment set of each power failure date, the power equipment with the highest support degree is used as an ancestor power equipment node, and the rest power equipment is used as a descendant power equipment node; if the common ancestor power equipment exists, adding 1 to the node count of the corresponding common ancestor power equipment;

acquiring a simultaneous equipment stopping condition mode base of each electric equipment in the item head table based on the item head table and the FP tree after data insertion;

and performing recursive mining based on the simultaneous equipment stopping condition mode of each electric equipment to obtain a frequent item set of all the electric equipment in the item head table.

4. The power outage window scheduling method according to claim 3,

the specific step of obtaining the simultaneous outage device condition pattern base of each power device in the item header table based on the item header table and the FP tree after data insertion includes: finding the preselected electric equipment from the FP tree after data insertion, traversing and acquiring all ancestor electric equipment nodes of the preselected electric equipment and recording all acquisition paths; wherein the preselected power device is a power device selected from the entry header table; setting the count of the ancestor power equipment node in each acquisition path as the count of the preselected power equipment in the acquisition path to obtain a modified acquisition path; deleting the preselected power equipment in each modified acquisition path to obtain a simultaneous equipment-stopping condition mode base of the preselected power equipment;

the specific step of obtaining the frequent item sets of all the electric power equipment in the item header table based on the simultaneous outage equipment condition mode base recursion mining of each electric power equipment comprises: based on the co-stop equipment condition pattern base recursive mining of each power equipment, a frequent 2-item set of all power equipment in the item header table is obtained.

5. The power outage window period arrangement method according to claim 4, wherein the specific step of calculating and obtaining the annual co-outage confidence level of each power device in the preset type of power devices based on the frequent item set and by using a strong association rule mining method includes:

calculating and obtaining the annual co-stop confidence level between two pieces of electric equipment in the preset type of electric equipment by using a strong association rule mining method based on the obtained frequent 2 item set, wherein the calculation expression is as follows:

，

in the formula (I), the compound is shown in the specification,for the annual co-stop confidence of power device Y to power device X,for the number of power outages of the power equipment X and the power equipment Y at the same time,the number of times of power failure of the power equipment X.

6. The power outage window period arrangement method according to claim 1, wherein in the calculation of the average co-outage confidence level of each power equipment based on the year co-outage confidence level of each power equipment, the calculation expression of the average co-outage confidence level is,

，

in the formula, C _avg-XY For the average co-stop confidence of the m-th to n-th year of the power device X by the power device Y, _year the annual co-stop confidence level of the power equipment Y to the power equipment X in year is shown.

7. The method according to claim 1, wherein the step of recommending the power equipment with the historical blackout window period based on the average co-outage confidence level of each power equipment comprises the following specific steps:

in the power failure window period arrangement process, for each to-be-arranged power device, firstly, obtaining the average and stopping confidence level of the power device associated with the to-be-arranged power device;

if the average same-stopping confidence level of the associated power equipment is larger than a preset confidence threshold, checking whether the power failure window period of the associated power equipment is compiled or not; if the power failure window period of the associated power equipment is not compiled, stopping the compiling; and if the power failure window period of the associated power equipment is compiled, taking the power failure window period of the associated power equipment as the power failure window period of the power equipment to be compiled.

8. A blackout window period arrangement system, comprising:

the model data set to be mined acquiring module is used for discretizing time-period type data of a historical power failure window period of preset type electric equipment in a preset regional power grid to acquire a model data set to be mined;

a frequent item set acquisition module, configured to acquire a frequent item set of the electrical devices in the preset kind of electrical devices based on the model dataset to be mined;

the annual co-stop confidence coefficient acquisition module is used for calculating and acquiring annual co-stop confidence coefficients of all the electric power equipment in the preset type of electric power equipment based on the frequent item set and by using a strong association rule mining method;

the average co-stop confidence level acquisition module is used for calculating and acquiring the average co-stop confidence level of each power device based on the annual co-stop confidence level of each power device;

and the recommendation module is used for recommending the power equipment in the historical power failure window period based on the average co-stop confidence level of each power equipment, so as to realize the arrangement of the power failure window period.

9. An electronic device, comprising: a processor; a memory for storing computer program instructions; it is characterized in that the preparation method is characterized in that,

the computer program instructions, when loaded and executed by the processor, cause the processor to perform the method of blackout window scheduling according to any one of claims 1 to 7.

10. A computer readable storage medium storing computer program instructions, wherein the computer program instructions, when loaded and executed by a processor, cause the processor to perform the power outage window scheduling method according to any one of claims 1 to 7.

Background

The power failure plan is an important work of the power grid operation every year, and the power failure time of all equipment in the power grid can be compiled in advance to ensure the safe operation of the power grid. The power failure window period arrangement is a preparation work of power failure planning arrangement, and refers to a time period in which specified power equipment can be arranged to be overhauled in one year, and the influence of overhauling on power supply, power supply reliability, clean energy consumption and power grid operation safety is minimum in the time period.

The traditional power failure planning process is that the power failure window period of each device is determined through various condition criteria, and then the power failure time of each device is further refined on the basis of the power failure window period and by combining with the local actual situation. With the increasing scale of power grids, more and more power equipment are provided, and according to the traditional power failure window period compiling method at present, various condition criteria need to be manually edited and calculated for each equipment, so that the power failure window period of each equipment is obtained, time and labor are wasted, the working efficiency is low, and great pressure is caused to planning personnel.

At present, the research aiming at the power failure window period is less, most of the research is on the power failure planning, the goals of minimum power failure time, optimal economy and the like are achieved through various optimization algorithms, but the incidence relation of historical power failure window period data among analysis equipment is not mined in a data driving mode, the planning efficiency and the accuracy of planning personnel are improved, and support is provided for the planning personnel.

Disclosure of Invention

The present invention is directed to a method, system, device and medium for scheduling power outage window periods, so as to solve one or more of the above-mentioned problems. The invention can improve the programming efficiency and accuracy of the power failure window period arrangement and can reduce the labor cost.

In order to achieve the purpose, the invention adopts the following technical scheme:

the invention discloses a power failure window period arranging method, which comprises the following steps:

discretizing time-period type data of a historical power failure window period of preset type of power equipment in a preset regional power grid to obtain a model data set to be mined;

acquiring a frequent item set of the electric power equipment in the preset type of electric power equipment based on the model data set to be mined;

calculating and obtaining the annual co-stop confidence level of each electric power device in the preset type of electric power devices based on the frequent item set and by using a strong association rule mining method;

calculating and obtaining the average co-stop confidence level of each power device based on the annual co-stop confidence level of each power device;

in the power failure window period arrangement process, power equipment in the historical power failure window period is recommended based on the average co-stop confidence level of each power equipment, and power failure window period arrangement is achieved.

The further improvement of the invention is that the specific steps of discretizing the time-period data of the historical power failure window period of the preset type of power equipment in the preset regional power grid to obtain the model data set to be mined comprise:

classifying the time period type number of the historical power failure window period of the preset type of power equipment in the preset regional power grid according to years to obtain the time period type number of the annual historical power failure window period;

dividing the time period number of the annual historical power failure window period by days, traversing the power failure window period of the preset type of power equipment, acquiring the power equipment which has power failure every day in the year, and forming a model data set to be mined.

The further improvement of the present invention is that the specific step of obtaining the frequent item set of the preset kind of power equipment based on the model dataset to be mined includes:

constructing the power equipment in the preset type of power equipment into a frequent 1 item set, and counting the occurrence frequency of each power equipment on each power failure date to obtain a counting frequency result;

taking the statistical frequency result as the support degree of each power device, removing the items with the support degree lower than a preset threshold value, and obtaining an item head table;

obtaining a power equipment set of each power failure date based on the item head table;

sequentially inserting the power equipment set of each power failure date into the FP tree according to the sequence of the support degree from high to low to obtain the FP tree after data insertion; in the power equipment set of each power failure date, the power equipment with the highest support degree is used as an ancestor power equipment node, and the rest power equipment is used as a descendant power equipment node; if the common ancestor power equipment exists, adding 1 to the node count of the corresponding common ancestor power equipment;

acquiring a simultaneous equipment stopping condition mode base of each electric equipment in the item head table based on the item head table and the FP tree after data insertion;

and performing recursive mining based on the simultaneous equipment stopping condition mode of each electric equipment to obtain a frequent item set of all the electric equipment in the item head table.

In a further improvement of the present invention, the specific step of obtaining a simultaneous outage device condition pattern base for each power device in the entry header table based on the entry header table and the FP-tree after data insertion includes: finding the preselected electric equipment from the FP tree after data insertion, traversing and acquiring all ancestor electric equipment nodes of the preselected electric equipment and recording all acquisition paths; wherein the preselected power device is a power device selected from the entry header table; setting the count of the ancestor power equipment node in each acquisition path as the count of the preselected power equipment in the acquisition path to obtain a modified acquisition path; deleting the preselected power equipment in each modified acquisition path to obtain a simultaneous equipment-stopping condition mode base of the preselected power equipment; the specific step of obtaining the frequent item sets of all the electric power equipment in the item header table based on the simultaneous outage equipment condition mode base recursion mining of each electric power equipment comprises: based on the co-stop equipment condition pattern base recursive mining of each power equipment, a frequent 2-item set of all power equipment in the item header table is obtained.

The further improvement of the present invention is that the specific step of calculating and obtaining the annual co-stop confidence level of each power equipment in the preset type of power equipment based on the frequent item set and by using the strong association rule mining method includes:

calculating and obtaining the annual co-stop confidence level between two pieces of electric equipment in the preset type of electric equipment by using a strong association rule mining method based on the obtained frequent 2 item set, wherein the calculation expression is as follows:

，

in the formula (I), the compound is shown in the specification,for the annual co-stop confidence of power device Y to power device X,for the number of power outages of the power equipment X and the power equipment Y at the same time,the number of times of power failure of the power equipment X.

In a further improvement of the present invention, in the step of calculating and obtaining the average co-stop confidence level of each electric power equipment based on the year co-stop confidence level of each electric power equipment, the calculation expression of the average co-stop confidence level is,

，

in the formula, C _avg-XY For the average co-stop confidence of the m-th to n-th year of the power device X by the power device Y, _year the annual co-stop confidence level of the power equipment Y to the power equipment X in year is shown.

The further improvement of the invention is that the specific steps for recommending the power equipment in the historical power failure window period based on the average co-stop confidence level of each power equipment include:

in the power failure window period arrangement process, for each to-be-arranged power device, firstly, obtaining the average and stopping confidence level of the power device associated with the to-be-arranged power device;

if the average same-stopping confidence level of the associated power equipment is larger than a preset confidence threshold, checking whether the power failure window period of the associated power equipment is compiled or not; if the power failure window period of the associated power equipment is not compiled, stopping the compiling; and if the power failure window period of the associated power equipment is compiled, taking the power failure window period of the associated power equipment as the power failure window period of the power equipment to be compiled.

The invention relates to a power failure window period arranging system, which comprises:

the model data set to be mined acquiring module is used for discretizing time-period type data of a historical power failure window period of preset type electric equipment in a preset regional power grid to acquire a model data set to be mined;

a frequent item set acquisition module, configured to acquire a frequent item set of the electrical devices in the preset kind of electrical devices based on the model dataset to be mined;

the annual co-stop confidence coefficient acquisition module is used for calculating and acquiring annual co-stop confidence coefficients of all the electric power equipment in the preset type of electric power equipment based on the frequent item set and by using a strong association rule mining method;

the average co-stop confidence level acquisition module is used for calculating and acquiring the average co-stop confidence level of each power device based on the annual co-stop confidence level of each power device;

and the recommending module is used for recommending the power equipment in the historical power failure window period based on the average co-stop confidence level of each power equipment in the power failure window period arranging process so as to realize the power failure window period arranging.

An electronic device of the present invention includes: a processor; a memory for storing computer program instructions; when the computer program instructions are loaded and run by the processor, the processor executes any one of the above power outage window period arrangement methods of the present invention.

The invention relates to a computer readable storage medium, which stores computer program instructions, and when the computer program instructions are loaded and run by a processor, the processor executes any one of the above power outage window period arrangement methods.

Compared with the prior art, the invention has the following beneficial effects:

according to the power failure window period arrangement method, after the frequent item sets are obtained, the intelligent recommendation method for the same power failure window period power equipment is mined by using the strong association rule, the arrangement efficiency and accuracy of the power failure window period arrangement can be improved, and the labor cost can be reduced.

The method of the invention forms a model data set to be mined based on historical power failure window period data (which can be historical power failure window period data of all power equipment of a power grid in the past year) (which can be historical power failure window period data of all equipment formed into a model data set to be mined in the year); calculating the association relationship support degree and confidence degree existing in each device in the characterization data set by an FP-tree algorithm and a strong association mining method; the annual support degree and the confidence degree are integrated, the average confidence degree of each device is calculated, the association relation of the devices is evaluated, auxiliary reference is provided for window period compiling personnel, the devices with high association degree are calculated once, multiple devices are shared, and the working efficiency and the accuracy of the compiling personnel are improved.

The system of the invention fills the blank of the existing power failure window period compiling method in convenience and intellectualization, and can intelligently recommend the power failure window period for users.

In the application technology, the data mining technology is adopted, the strong association rule mining method is utilized after the frequent item set is obtained, the data value of the historical power failure window period is deeply mined by combining the characteristics of the power failure window period data, a new thought and a new method are provided for the power failure window period compiling and analyzing, and the power failure window period compiling efficiency can be effectively improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art are briefly introduced below; it is obvious that the drawings in the following description are some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.

Fig. 1 is a flowchart illustrating a power outage window period arrangement method according to an embodiment of the present invention;

FIG. 2 is a diagram illustrating the FP-Tree structure inserted into the first data set according to the embodiment of the present invention;

FIG. 3 is a diagram illustrating the FP-Tree structure inserted into the second data set according to an embodiment of the present invention;

FIG. 4 is a diagram of an FP-Tree structure inserted into a third data set according to an embodiment of the present invention;

FIG. 5 is a diagram of the FP-Tree structure inserted into the fourth data set in the embodiment of the present invention;

FIG. 6 is a diagram of an FP-Tree structure inserted into a fifth data set according to an embodiment of the present invention;

FIG. 7 is a diagram of an FP-Tree structure inserted into a sixth data set according to an embodiment of the present invention;

FIG. 8 is a diagram of an FP-Tree structure inserted into a seventh data set in an embodiment of the present invention.

Detailed Description

In order to make the purpose, technical effect and technical solution of the embodiments of the present invention clearer, the following clearly and completely describes the technical solution of the embodiments of the present invention with reference to the drawings in the embodiments of the present invention; it is to be understood that the described embodiments are only some of the embodiments of the present invention. Other embodiments, which can be derived by one of ordinary skill in the art from the disclosed embodiments without inventive faculty, are intended to be within the scope of the invention.

Example 1

Referring to fig. 1, a power outage window period arrangement method according to an embodiment of the present invention is an intelligent recommendation method for power equipment in the same power outage window period mined based on an FP-tree algorithm (a frequent pattern tree algorithm, which is given as an example; an Apriori algorithm may also be used to replace the frequent pattern tree algorithm) and a strong association rule, and specifically includes the following steps:

step 1, data preprocessing: discretizing time-segment type data (for example, the structure of the time-segment type data of the historical power failure window period of certain equipment is that the name of the certain equipment and the power failure window period of the certain equipment) of preset types of electric equipment (for example, an AC line, a DC line, a transformer, a current converter and the like) in a preset regional power grid (for example, a regional power grid, a provincial power grid, a local power grid and the like) to obtain a model data set to be mined;

step 2, mining to obtain a frequent item set: acquiring a frequent item set of the preset type of power equipment by utilizing an FP-tree algorithm based on the model data set to be mined;

step 3, calculating the annual confidence: on the basis of the frequent item set, acquiring annual confidence coefficients representing the incidence relation of each electric device in the preset type of electric devices by year calculation by using a strong association rule mining method;

step 4, calculating the average confidence: and obtaining the average confidence coefficient of the association relation existing in each electric power device based on the annual confidence coefficient of the association relation existing in each electric power device.

And 5, realizing power failure window period arrangement based on the obtained average confidence coefficient of the association relation existing in each power device.

According to the method provided by the embodiment of the invention, the same or similar power equipment in the historical power failure window period can be intelligently recommended in the process of compiling the power failure window period, the problems of limited experience of current window period compiling personnel, single compiling means, large repeated workload and the like are effectively solved, historical data are fully utilized, a big data mining method is applied, the same or similar power failure window period equipment is quickly obtained, and the working efficiency is improved.

In the invention, the power failure window period of the time period type is converted into discrete data, so that the resolvability of the power failure window period can be improved; the method for analyzing the power failure window period data by fusing the frequent itemset algorithm FP-Tree and the strong association rule mining algorithm is provided, and the association relation between the power failure window periods among the devices can be rapidly mined; the method for analyzing the association rule of the multi-year power failure window period considering the operation and the withdrawal of the power equipment is provided, and the accuracy of the association analysis of the power failure window period of the equipment is improved.

Example 2

Based on the above embodiment, the further optimization of the embodiment of the present invention is that step 1 specifically includes: and preprocessing the historical power failure window period data, converting the time period data into discrete data, and forming a mining model data set.

For example, the initial data structure of the power outage window period according to the embodiment of the present invention is shown in table 1.

TABLE 1 initial data Structure for Power off Window period

The method comprises the steps of firstly converting time period data into a mining model data set, namely splitting the data into 365 days every year, and then checking equipment which has power failure every day to form the mining model data set.

Illustratively, the mining model dataset of an embodiment of the present invention is shown in Table 2.

TABLE 2 model data set to be mined

The conversion method is that for each day of the year, the power failure window periods of all the equipment are traversed, if the power failure window period of the equipment comprises a certain day, the equipment is added into the power failure equipment set corresponding to the day, and a mining model data set is formed.

In the embodiment of the invention, the power failure window period of the time period type is converted into discrete data, so that the resolvability of the power failure window period can be improved.

Example 3

Based on the above embodiment, the further optimization of the embodiment of the present invention is that, in step 2, based on the mining model data set formed in step 1 (365 days of data should exist according to the actual situation, and only 7 days of data are taken as an example for the convenience of exemplary description here), a frequent item set is obtained by improving the FP-tree algorithm mining; the method specifically comprises the following steps:

1) scanning data, taking each power device as a frequent 1 item set, counting the occurrence frequency of each power failure date of each device, wherein the counting is the support degree of each power device, and then deleting the items with the support degree lower than the threshold value.

Illustratively, the support threshold is set to 3 in the following example of the first 7 rows in the mining model dataset, as shown in table 3.

TABLE 3 frequent 1 item set and corresponding support

As can be seen from table 3, device 2, device 1, device 4, and device 3 are frequent 1 item sets, and the number of devices 5 is smaller than the support threshold, so that deletion is performed, and the generated item header table is shown in table 4.

TABLE 4 item head table

2) Scanning data, eliminating the non-frequent 1 item set from the read original data, and arranging each device set in descending order according to the support degree to obtain the ordered data set, as shown in table 5.

TABLE 5 data set sorted by support

3) The specific flow of establishing the FP-tree is as follows, reading in the blackout equipment data set sorted according to the support degree, sequentially inserting the blackout equipment data set into the FP tree, and inserting the blackout equipment data set into the FP tree according to the sorted sequence in the blackout equipment set during insertion, wherein the node in the front of the sequence is an ancestor blackout equipment node, and the node in the back of the sequence is a descendant blackout equipment node. If there is a common ancestor blackout device, then the corresponding common ancestor blackout device node count is incremented by 1. After insertion, if a new blackout equipment node appears, the blackout equipment node corresponding to the entry head table is linked with the new blackout equipment node through the blackout equipment node linked list. And completing the building of the FP tree until all data are inserted into the FP tree.

Illustratively, in the data set according to the embodiment of the present invention, the number of blackout devices is large (several tens of thousands), the types of devices are relatively fixed (about 10 types), and in an actual grid topological relationship, an association relationship between different devices in each blackout device set in the data set may exist in a physical node. The FP-tree method analyzes the relevance among different devices in a tree connection mode, reflects the relevance among the devices according to the occurrence frequency of power failure devices, objectively reflects the physical relevance among the devices through tree topology connection, can also count the probability of power failure of the devices at the same time from a mathematical perspective, and provides a more comprehensive view angle for searching the relation of the power grid simultaneous-stop devices.

For example, in the embodiment of the present invention, as shown in fig. 2 to fig. 8, starting from the first piece of data in the data set, a blackout device node chain table formed by device 2, device 1, and device 4 is first formed, where device 2 is an ancestor blackout device node, device 1 and device 4 are descendant nodes, according to the above method, the count of each blackout device node is increased once, or a new blackout device node is added, and the finally generated FP tree is shown in fig. 8.

4) And sequentially upward from the bottom blackout equipment items of the item head table generated in the step 1), searching corresponding blackout equipment nodes through the FP-tree generated in the step 3), traversing upward, searching corresponding ancestor blackout equipment nodes and descendant blackout equipment nodes, counting, and sequentially finding the same-stop equipment condition mode bases corresponding to the item head table items.

The following steps are performed for each entry of the entry header table, resulting in a co-stop device conditional mode base.

Illustratively, the device 4 is taken as an example.

Finding all 'equipment 4' nodes from the FP tree, and traversing all ancestor blackout equipment nodes upwards to obtain 4 paths.

The device 4: 2, the device 1: 4, the device 2: 6

The device 4: 1, device 2: 6

The device 4: 1, device 1: 1

And secondly, setting the count of all ancestor power failure equipment nodes in the path as the count of the current descendant power failure equipment nodes.

The device 4: 2, the device 1: 2, device 2: 2

The device 4: 1, device 2: 1

The device 4: 1, device 1: 1

And deleting the first row of equipment 4 to obtain a conditional mode base.

The device 1: 2, device 2: 2

The device 2: 1

The device 1: 1

5) And recursively mining a frequent item set of item head table items from the condition mode base of the synchronous stop equipment.

In the method of the embodiment of the present invention, only the association relationship between 2 blackout devices is considered, and therefore, only the frequent 2 item set needs to be obtained, and therefore, the frequent 2 item set of the device 4 obtained by the device 4 condition mode basis is { device 4: 3, the device 1: 3}, { device 4: 3, device 2: 3 };

all the devices are subjected to recursive iteration to obtain a frequent 2-item set of all the power-off devices, as shown in table 6.

TABLE 6 frequent 2 item set of blackout equipment

Example 3

Based on the above embodiment, the further optimization of the embodiment of the present invention is that, in step 3, the confidence between each two pieces of equipment is calculated by generating the strong association rule between the pieces of equipment through the frequent item set; the inter-device confidence level refers to the probability that one device appears after the other device appears.

For device X and device Y, the co-stop confidence of Y versus X is:

，

in the formula (I), the compound is shown in the specification,for the annual co-stop confidence of power device Y to power device X,for the number of power outages of the power equipment X and the power equipment Y at the same time,the number of times of power failure of the power equipment X.

According to the formula, a strong association rule among the devices in the frequent item set can be calculated, the co-stop confidence level among the devices every year is calculated, and the calculation result list 7 is shown by taking the device 4 as an example.

TABLE 7 annual co-outage confidence level between plants

In the embodiment of the invention, the frequent item set and the corresponding co-stop confidence level of each device can be obtained according to the step 2 and the step 3.

Example 4

Based on the above embodiment, the further optimization of the embodiment of the present invention is that, in step 4, the average confidence of each device and other devices is calculated according to each electrical device confidence data every year, and the relevant devices with each device relevance ranked from top 10 to bottom are obtained, so as to provide a reference for the user.

The method comprises the steps that due to the fact that a power system may have returned equipment or newly added equipment, whether target equipment exists in historical annual data or not is searched, and if yes, a corresponding frequent item set and corresponding co-stop credibility data of the year are searched; if the device does not exist in the historical data, the associated device cannot be calculated through the method.

In the embodiment of the present invention, the average confidence of the associated device is obtained by the following formula:

，

in the formula, C _avg-XY For the average co-stop confidence of the m-th to n-th year of the power device X by the power device Y, _year the annual co-stop confidence level of the power equipment Y to the power equipment X in year is shown.

In the embodiment of the invention, all devices associated with the X devices are traversed, the average confidence degrees of the corresponding associated devices are obtained and ranked, the top 10 is taken as the device with the largest association degree, the device with the same window period as the current device is intelligently recommended when the power failure window period is compiled for a user, one-time operation is carried out, the compiling of a plurality of device window periods is completed, and the working efficiency is improved.

Example 5

Based on the foregoing embodiment, a further optimization of the embodiment of the present invention is that, in step 5, based on the obtained average co-outage confidence level of the association relationship existing in each power device, the specific step of implementing the power outage window period arrangement includes:

for each power device needing to be scheduled with the power failure window period, in the scheduling process, firstly checking the average confidence coefficient of the associated device of the power device, and if the associated average confidence coefficient is larger than a set confidence coefficient threshold (the value can be set according to actual conditions and experience of scheduling personnel, and is usually 0.9), checking whether the power failure window period of the associated device is scheduled or not;

if the associated equipment power failure window period is not compiled, a traditional power failure window period compiling method is adopted for compiling;

if the associated equipment power failure window period is compiled, the associated equipment window period can be copied and used as the equipment power failure window period; meanwhile, the power failure window period can be used as the power failure window period with the same stop confidence level larger than 0.9 in the equipment associated with the equipment, and the compiling efficiency is improved.

The method is characterized in that a power failure window period is a new concept in a power failure planning process of power grid equipment proposed in recent years, is a wider blackout available time range determined by various rules and criteria before the power failure planning, and is an important process for the future power failure planning. At present, the related technologies are relatively few, only two inventions about power failure window period confirmation and correction methods are published, the blank of the conventional power failure window period compiling method in convenience and intellectualization is filled, and the power failure window period can be intelligently recommended for users. In the application technology, the data mining technology is adopted, the FP-tree and strong association rule mining method is applied, the characteristics of the power failure window period data are combined, the data value of the historical power failure window period is deeply mined, a new thought and a new method are provided for the compilation and analysis of the power failure window period, and the compilation efficiency of the power failure window period can be effectively improved. The method is implemented and popularized by depending on the power failure window period integrated compiling system based on the regulation cloud, the method can be applied to the system, the existing power failure window period compiling method can be supplemented, historical data of the regulation cloud sea volume is fully utilized, data mining and analysis are carried out on the historical power failure window period, simultaneous shutdown equipment is intelligently recommended for workers, the working efficiency is effectively improved, and the future application prospect is wide. The invention has good innovation and strong practicability, and the conversion product can be popularized to various provinces and provinces. The regulation and control cloud platform is used as one of unified construction projects for constructing energy Internet by national network companies and is popularized and constructed nationwide. And (4) computing according to a set of software or a set of module 50 ten thousand, popularizing to each provincial level regulation cloud platform, and predicting that 1300 ten thousand yuan can be gained.

For example, chinese patent application publication No. CN111917139A discloses a method and a system for determining blackable window period of a power grid master device, where the method includes: a method for determining a blackable window period of a main device of a power grid is characterized by comprising the following steps: step 1: determining classification types of the classification of the functions of the power transmission and transformation equipment in the power grid according to the functions of the power transmission and transformation equipment; step 2: acquiring basic data corresponding to the classification type according to the classification type; and step 3: determining the blackable window period of the power transmission and transformation equipment according to the basic data; and 4, step 4: and outputting and displaying the blackable window period. The method is scientific and reasonable, can reduce the accompanying and stopping of the equipment and reduce the potential safety hazard of the power grid caused by maintenance. The technical scheme is a traditional power failure window period compiling method, wherein various types of data such as equipment types, power generation, loads and the like are considered in the compiling process, and various constraint conditions such as balance, consumption, safety and the like are considered.

For example, the study of the grid power failure planning self-learning expert library mainly aims at the improvement of the power failure planning, self-learning of a synchronous stop rule and a window period rule in the power failure planning expert library is carried out by adopting an association rule mining algorithm and a discrete segment gap weighting method, and a learning result is used as a supplement rule of the expert library. Firstly, the paper is directed at the arrangement of power outage plans rather than the arrangement of power outage window periods, and an association mining method is also used in the arrangement process of the power outage plans, but the disadvantages are that: firstly, the thesis is not processed after a frequent item set is formed, a complete scheme calculation confidence coefficient is not formed for a user to select, and secondly, historical data for many years are not processed respectively, so that an analysis result is not accurate enough. The embodiment of the invention provides a power failure window period data analysis method which integrates a frequent itemset algorithm FP-Tree and a strong association rule mining algorithm, and can rapidly mine the association relationship of power failure window periods between devices; the method for analyzing the association rule of the power failure window period of the power equipment for many years is provided, the association rule of the power equipment is analyzed according to the year and comprehensively evaluated, and the accuracy of the association analysis of the power failure window period of the equipment is improved.

In conclusion, the method and the device can intelligently recommend the power equipment with the same or similar historical power failure window period in the process of compiling the power failure window period, effectively solve the problems of limited experience of current window period compiling personnel, single compiling method, large repeated workload and the like, fully utilize historical data, rapidly acquire the same or similar power failure window period equipment by using a big data mining method, and improve the working efficiency. The invention provides a method for converting the power failure window period of a time period type into discrete data, thereby improving the resolvability of the power failure window period; the method for analyzing the power failure window period data by fusing the frequent itemset algorithm FP-Tree and the strong association rule mining algorithm is provided, and the association relation between the power failure window periods among the devices can be rapidly mined; the method for analyzing the association rule of the multi-year power failure window period considering the operation and the withdrawal of the power equipment is provided, and the accuracy of the association analysis of the power failure window period of the equipment is improved.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art can make modifications and equivalents to the embodiments of the present invention without departing from the spirit and scope of the present invention, which is set forth in the claims of the present application.