CN116522643A - Automatic construction method and system for power grid operation simulation scheme library - Google Patents

Abstract

The invention belongs to the technical field of electric power dispatching automation, and provides a method and system for automatically constructing a power grid operation simulation scheme library, including acquiring and analyzing power grid operation simulation topics and power grid operation simulation scheme constraint conditions, combining power grid physical models and data to extract power grid characteristic models, And based on the section matching algorithm, the initial operation mode of the power grid operation simulation scheme is generated; for different power grid operation simulation themes of fault handling, different preset faults of the power grid operation simulation scheme are generated; based on the scheduling knowledge base and the disposal scheme library, the set of disposal schemes is obtained by knowledge reasoning , through the grid operation simulation program preparation result evaluation system to evaluate the set of disposal programs, and obtain the optimal disposal program; classify the preliminary grid operation simulation programs according to the grid operation simulation theme, and generate the grid operation simulation program library. The invention provides dispatchers with a large number of classified practical grid operation simulation schemes.

Description

A method and system for automatically constructing a power grid operation simulation scheme library

technical field

The invention belongs to the technical field of electric power dispatching automation, and in particular relates to a method and system for automatically constructing a grid operation simulation scheme library.

Background technique

The Dispatcher Training System (DTS for short) provides an efficient and convenient platform for dispatcher professional skills training and joint anti-accident drills, and plays a vital role in improving the business analysis and research capabilities of control personnel and comprehensive accident handling capabilities effect. With the continuous advancement of the construction of AC-DC hybrid power grids and the explosive growth of new energy grid-connected scales, the operating characteristics of power grids have become increasingly complex, and the difficulty of generating the initial operation mode and power flow debugging of power grid operation simulation schemes for power grid dispatching has increased. However, the current level of DTS intelligence is low, and the debugging process of the power grid operation simulation scheme is complicated. It still needs to rely on experienced teachers to manually compile the power grid operation simulation scheme, and they need to participate in the whole process of drill training and simulation guidance to train students to solve the pre-stored power grid faults. The workload is heavy. Time-consuming and labor-intensive; in addition, the current DTS drill training simulation power grid operation simulation program has a serious shortage of resources. The power grid operation simulation program is often aimed at specified fault types without systematic classification management, which cannot meet the needs of dispatchers for specific training drill content in online drill training simulation. Necessary, resulting in unsystematic and insufficient training exercises for dispatchers, and the drill training content is not targeted and practical, and it is difficult to meet the needs of multiple dispatchers participating in training and personalized training drills at the same time, resulting in DTS not being able to become a dispatcher A daily and autonomous simulation tool for "on-demand drill training" anytime, anywhere.

The existing training teaching plan generation methods only focus on whether the initial operating conditions of the power grid generated by the DTS system are consistent with the content of the training teaching plan. The method of standard solutions cannot realize the autonomous and personalized training of students. In addition, if the feasible solution cannot be obtained by changing the operating parameters of the power grid equipment according to the calculation results of the power flow, it is necessary to change the constraint conditions of the teaching plan. This method does not explain how to adjust the initial constraint conditions of the teaching plan in an automated way. Adjust the teaching plan and use this method to get a feasible solution.

Contents of the invention

In order to solve the problems in the prior art, the present invention provides a method and system for automatically constructing a grid operation simulation scheme library. The invention reduces the workload of teachers through the automated and intelligent grid operation simulation scheme generation process, and provides dispatchers with a large number of classified and practical grid operation simulation schemes.

In order to achieve the above object, the present invention adopts the following technical solutions to achieve:

In the first aspect, the present invention provides a method for automatically building a power grid operation simulation scheme library, including:

Obtain and analyze the power grid operation simulation theme and grid operation simulation scheme constraint conditions, combine the power grid physical model and data to extract the power grid characteristic model, and generate the initial operation mode of the power grid operation simulation scheme based on the section matching algorithm;

According to different power grid operation simulation themes for fault handling, different power grid operation simulation schemes are generated with preset faults;

Based on the dispatching knowledge base and the disposal plan library, the disposal plan set is obtained by knowledge reasoning, and the disposal plan set is evaluated through the grid operation simulation plan preparation result evaluation system to obtain the optimal disposal plan;

Combining the initial operation mode of the power grid operation simulation scheme, the preset faults of the power grid operation simulation scheme, and the optimal disposal scheme to form a preliminary power grid operation simulation scheme; classifying the preliminary power grid operation simulation scheme according to the power grid operation simulation theme, and generating Grid operation simulation program library.

As a further improvement of the present invention, the power grid operation simulation theme includes a power grid operation simulation scheme theme for normal operation and a power grid operation simulation scheme theme for fault handling;

The subjects of the normal operation power grid operation simulation scheme include bus voltage exceeding the limit, line power exceeding the limit, load power exceeding the limit, load loss and operation mode change;

The themes of the grid operation simulation scheme for fault handling include DC faults, AC faults and cascading faults;

The constraint conditions of the power grid operation simulation scheme include the total load of the entire network, the total power generation of the entire network, the power of key tie lines, the power of key sections, the output of key generators, the power of key DC systems, the power of key loads, and the state of operation of key equipment; The constraints of the power grid operation simulation scheme are set based on the topological structure of the grid equipment and the operating state of the grid equipment, and the effective grid operation simulation scheme constraint conditions are used as the grid characteristic model.

As a further improvement of the present invention, the initial operation mode of the power grid operation simulation scheme generated based on the section matching algorithm includes:

Use the section matching algorithm to perform similarity matching with the historical state estimation section. The similarity matching method is as follows:

SIM _t = α _i C _it

In the formula, SIM _t represents the matching degree between the grid section at the historical time t and the operation section required by the power grid operation simulation scheme, C _it is the matching degree between the i-th constraint condition required by the grid operation simulation scheme and the section at time t, α _i is the weight coefficient of the i-th constraint condition;

Select the state estimation section at time t of the minimum value of SIM _t as the original operation mode of the power grid operation simulation scheme, adjust the original operation mode according to the constraints of the power grid operation simulation program, and verify whether the original operation mode meets the power flow convergence through power flow calculation, if If the power flow does not converge, it is necessary to change the constraints of the power grid operation simulation scheme. According to the size of the C _it score as a reference, modify the constraints of the power grid operation simulation scheme corresponding to the one with the smaller C _it score; the adjusted state will satisfy the convergence of the power flow The estimated section is used as the initial operation mode of the power grid operation simulation scheme.

As a further improvement of the present invention, the generation of preset faults in different power grid operation simulation schemes for different power grid operation simulation themes of fault handling includes:

The power grid fault handling plan includes substation overview, fault phenomenon and emergency response measures data;

Knowledge extraction of fault handling plans by means of keyword extraction through regular expressions;

The extracted faults are divided into DC faults, AC faults and cascading faults of preset faults in the power grid operation simulation scheme to form a preset fault library;

According to the type of equipment, the preset fault library is expanded; for different grid operation simulation themes of fault handling, the faults that meet the requirements are randomly selected from the expanded preset fault library to generate different grid operation simulation scheme preset faults.

As a further improvement of the present invention, after generating different power grid operation simulation schemes to preset faults, the method further includes:

Improve the characteristic model of power grid operation simulation scheme, including:

Based on the extracted power grid characteristic model, combined with the preset faults of the power grid operation simulation scheme, topology calculation and power flow calculation are performed, and the power grid working condition data before and after the fault and the preset faults of the power grid operation simulation scheme are used as the characteristic model of the power grid operation simulation scheme.

As a further improvement of the present invention, the scheduling-based knowledge base and the disposal scheme base use knowledge reasoning to obtain a set of disposal schemes, including:

Analyze the power grid fault handling plan, which is divided into the expected failure of the plan, the initial operation mode of the power grid in the plan, the operation mode after the failure of the plan, and the fault handling measures affecting the plan;

Knowledge extraction is carried out on the analyzed power grid fault disposal plan, and knowledge reasoning is carried out by using the method of decision-making knowledge graph to establish a disposal plan library.

As a further improvement of the present invention, the knowledge extraction of the analyzed power grid fault disposal plan, and the establishment of a disposal plan library by knowledge reasoning using the decision-making knowledge map method include:

Use the deep learning method to identify the entities of the power grid dispatching control management procedures, improve the dispatching knowledge base, and establish a decision-making knowledge map;

Establish a decision-making knowledge map as:

DG=(E,C,R,A)

DG is the decision-making knowledge graph engine; E is the entity set of power grid operating conditions, including power grid topology and power flow result data, E={e1,e2,...,em}, including circuit breaker, knife switch opening status, load power , generator output, line power, transformer power, cross-section power, bus voltage, number of generators running and condensers running; C is a set of condition definitions and a set of grid operation modes, C={c1,c2,…,cl} ; R is a rule set, in order to meet the rules of condition C triggering operation, knowledge extraction, knowledge fusion and knowledge reasoning generation are carried out according to the power grid fault plan and dispatching control management regulations; A is the set of fault handling dispatching operations, A={a1,a2, …, an}, including the operation of switch switch, adjustment of unit output, adjustment of power plant output, adjustment of power station, regional load power, control section power and DC power modulation included in the power grid failure plan and dispatch control management regulations;

Carry out knowledge extraction on the power grid fault disposal plan, and use the established decision-making knowledge map method to perform knowledge reasoning on the extracted data to establish a disposal plan library.

As a further improvement of the present invention, the evaluation system for compiling the results of the power grid operation simulation plan evaluates the disposal plan set to obtain the optimal disposal plan, including:

Search and evaluate the solution set based on knowledge reasoning, and output the fault solution when the search and evaluation results match and meet the rules in the rule set;

Based on the evaluation system for the preparation results of the power grid operation simulation plan, the fault disposal plan with the highest score is selected as the optimal disposal plan; the evaluation system for the preparation results of the power grid operation simulation plan is as follows:

Score _i ＝w _e S _ei +w _o S _oi

In the formula, Score _i is the comprehensive score of the disposal scheme Ai, w _e and w _o are the weights of electrical indicators and non-electrical indicators, S _ei and S _oi are the scores of electrical indicators and non-electrical indicators of the disposal scheme Ai;

The electrical index score S _ei is the sum of the electrical index scores, including the number of off-limit equipment, the percentage of off-limit power, the number of heavy-duty equipment, the percentage of heavy-duty equipment, and the network loss of the entire network; the non-electrical index S _oi is the sum of the non-electrical index scores, including the operation The number of steps, the scope involved in dispatching; S _ei and S _oi are weighted and added to obtain the comprehensive score Score _i of the disposal scheme Ai, and all disposal schemes are selected according to the comprehensive score with the highest score as the optimal disposal scheme of the power grid operation simulation scheme.

As a further improvement of the present invention, the initial operation mode of the power grid operation simulation scheme, the preset fault of the power grid operation simulation scheme and the optimal disposal scheme are combined to form a preliminary power grid operation simulation scheme; Classify the preliminary power grid operation simulation schemes to generate a power grid operation simulation scheme library, including:

Convert the generated power grid operation simulation scheme preset faults and optimal disposal schemes into power grid operation simulation scheme events step by step; a device failure in the power grid operation simulation scheme preset faults is regarded as a power grid operation simulation scheme event, and one time in the optimal disposal scheme The scheduling operation is a power grid operation simulation plan event, which is sorted in chronological order to form a power grid operation simulation plan event sequence; the result triggered by the plan event is the change of the operating state of the power grid equipment, including switch opening and closing, generator output change, and load power change ;

On the basis of the initial operation mode of the generated power grid operation simulation scheme, the faults in the event sequence of the power grid operation simulation scheme are triggered sequentially, and topology calculation and power flow calculation are performed to simulate the change of power grid operation status before and after the fault;

Classify the generated power grid operation simulation scheme according to the power grid operation simulation theme to generate a power grid operation simulation scheme library.

In a second aspect, the present invention provides a system for automatically building a power grid operation simulation scheme library, including:

The initial operation mode generation module is used to obtain and analyze the power grid operation simulation theme and the constraints of the power grid operation simulation scheme, combine the power grid physical model and data to extract the power grid characteristic model, and generate the initial operation mode of the power grid operation simulation scheme based on the section matching algorithm;

The preset fault generation module is used to generate different grid operation simulation scheme preset faults according to different power grid operation simulation themes for fault handling;

The optimal disposal plan generation module is used to obtain the disposal plan set by using knowledge reasoning based on the scheduling knowledge base and the disposal plan library, and evaluate the disposal plan set through the grid operation simulation plan preparation result evaluation system to obtain the optimal disposal plan;

The simulation scheme library generation module is used to combine the initial operation mode of the power grid operation simulation scheme, the preset fault of the power grid operation simulation scheme and the optimal disposal scheme to form a preliminary power grid operation simulation scheme; The power grid operation simulation schemes are classified to generate a power grid operation simulation scheme library.

As a further improvement of the present invention, in the initial operation mode generation module, the power grid operation simulation theme includes a normal operation power grid operation simulation scheme theme and a fault handling power grid operation simulation scheme theme;

The subjects of the normal operation power grid operation simulation scheme include bus voltage exceeding the limit, line power exceeding the limit, load power exceeding the limit, load loss and operation mode change;

The themes of the grid operation simulation scheme for fault handling include DC faults, AC faults and cascading faults;

The constraint conditions of the power grid operation simulation scheme include the total load of the entire network, the total power generation of the entire network, the power of key tie lines, the power of key sections, the output of key generators, the power of key DC systems, the power of key loads, and the state of operation of key equipment; The constraints of the power grid operation simulation scheme are set based on the topological structure of the grid equipment and the operating state of the grid equipment, and the effective grid operation simulation scheme constraint conditions are used as the grid characteristic model.

As a further improvement of the present invention, in the initial operation mode generation module, the generation of the initial operation mode of the power grid operation simulation scheme based on the section matching algorithm includes:

Use the section matching algorithm to perform similarity matching with the historical state estimation section. The similarity matching method is as follows:

SIM _t = α _i C _it

In the formula, SIM _t represents the matching degree between the grid section at the historical time t and the operation section required by the power grid operation simulation scheme, C _it is the matching degree between the i-th constraint condition required by the grid operation simulation scheme and the section at time t, α _i is the weight coefficient of the i-th constraint condition;

Select the state estimation section at time t of the minimum value of SIM _t as the original operation mode of the power grid operation simulation scheme, adjust the original operation mode according to the constraints of the power grid operation simulation program, and verify whether the original operation mode meets the power flow convergence through power flow calculation, if If the power flow does not converge, it is necessary to change the constraint conditions of the power grid operation simulation scheme. According to the size of the C _it score as a reference, modify the corresponding grid operation simulation scheme constraint conditions of the smaller C _it score; the adjusted state of the power flow convergence will be satisfied The estimated section is used as the initial operation mode of the power grid operation simulation scheme.

As a further improvement of the present invention, in the preset fault generation module, the generation of preset faults of different power grid operation simulation schemes for different power grid operation simulation themes of fault handling includes:

The power grid fault handling plan includes substation overview, fault phenomenon and emergency response measures data;

Knowledge extraction of fault handling plans by means of keyword extraction through regular expressions;

The extracted faults are divided into DC faults, AC faults and cascading faults of preset faults in the power grid operation simulation scheme to form a preset fault library;

According to the type of equipment, the preset fault library is expanded; for different grid operation simulation themes of fault handling, the faults that meet the requirements are randomly selected from the expanded preset fault library to generate different grid operation simulation scheme preset faults.

As a further improvement of the present invention, in the preset fault generating module, after generating different power grid operation simulation scheme preset faults, the method further includes:

Based on the extracted power grid characteristic model, combined with the preset faults of the power grid operation simulation scheme, topology calculation and power flow calculation are performed, and the power grid working condition data before and after the fault and the preset faults of the power grid operation simulation scheme are used as the characteristic model of the power grid operation simulation scheme.

As a further improvement of the present invention, in the optimal treatment plan generation module, the set of treatment plans obtained by knowledge reasoning based on the scheduling knowledge base and the treatment plan library includes:

Analyze the power grid fault handling plan, which is divided into the expected failure of the plan, the initial operation mode of the power grid in the plan, the operation mode after the failure of the plan, and the fault handling measures affecting the plan;

Knowledge extraction is carried out on the analyzed power grid fault disposal plan, and knowledge reasoning is carried out by using the method of decision-making knowledge graph to establish a disposal plan library.

As a further improvement of the present invention, in the optimal disposal scheme generation module, the knowledge extraction is performed on the analyzed power grid fault disposal plan, and knowledge reasoning is performed using the method of decision-making knowledge graph to establish a disposal scheme library, including:

Use the deep learning method to identify the entities of the power grid dispatching control management procedures, improve the dispatching knowledge base, and establish a decision-making knowledge map;

Establish a decision-making knowledge graph as:

DG=(E,C,R,A)

DG is the decision-making knowledge graph engine; E is the entity set of power grid operating conditions, including power grid topology and power flow result data, E={e1,e2,...,em}, including circuit breaker, knife switch opening status, load power , generator output, line power, transformer power, cross-section power, bus voltage, number of generators running and condensers running; C is a set of condition definitions and a set of grid operation modes, C={c1,c2,…,cl} ; R is a rule set, in order to meet the rules of condition C triggering operation, knowledge extraction, knowledge fusion and knowledge reasoning generation are carried out according to the power grid fault plan and dispatching control management regulations; A is the set of fault handling dispatching operations, A={a1,a2, …, an}, including the operation of switch switch, adjustment of unit output, adjustment of power plant output, adjustment of power station, regional load power, control section power and DC power modulation included in the power grid failure plan and dispatch control management regulations;

Carry out knowledge extraction on the power grid fault disposal plan, and use the established decision-making knowledge map method to perform knowledge reasoning on the extracted data to establish a disposal plan library.

As a further improvement of the present invention, in the optimal disposal plan generation module, the evaluation system for the preparation result evaluation system of the power grid operation simulation plan evaluates the set of disposal plans to obtain the optimal disposal plan, including:

Search and evaluate the solution set based on knowledge reasoning, and output the fault solution when the search and evaluation results match and meet the rules in the rule set;

Based on the evaluation system for the preparation results of the power grid operation simulation plan, the fault disposal plan with the highest score is selected as the optimal disposal plan; the evaluation system for the preparation results of the power grid operation simulation plan is as follows:

Score _i ＝w _e S _ei +w _o S _oi

In the formula, Score _i is the comprehensive score of the disposal scheme Ai, w _e and w _o are the weights of electrical indicators and non-electrical indicators, S _ei and S _oi are the scores of electrical indicators and non-electrical indicators of the disposal scheme Ai;

The electrical index score S _ei is the sum of the electrical index scores, including the number of off-limit equipment, the percentage of off-limit power, the number of heavy-duty equipment, the percentage of heavy-duty equipment, and the network loss of the entire network; the non-electrical index S _oi is the sum of the non-electrical index scores, including the operation The number of steps, the scope involved in dispatching; S _ei and S _oi are weighted and added to obtain the comprehensive score Score _i of the disposal scheme Ai, and all disposal schemes are selected according to the comprehensive score with the highest score as the optimal disposal scheme of the power grid operation simulation scheme.

As a further improvement of the present invention, in the simulation scheme library generation module, the initial operation mode of the power grid operation simulation scheme, the preset fault of the power grid operation simulation scheme and the optimal disposal scheme are combined to form a preliminary power grid operation Simulation schemes: classify the preliminary power grid operation simulation schemes according to the power grid operation simulation theme, and generate a power grid operation simulation scheme library, specifically including:

Convert the generated power grid operation simulation scheme preset faults and optimal disposal schemes into power grid operation simulation scheme events step by step; a device failure in the power grid operation simulation scheme preset faults is regarded as a power grid operation simulation scheme event, and one time in the optimal disposal scheme The scheduling operation is a power grid operation simulation plan event, which is sorted in chronological order to form a power grid operation simulation plan event sequence; the result triggered by the plan event is the change of the operating state of the power grid equipment, including switch opening and closing, generator output change, and load power change ;

On the basis of the initial operation mode of the generated power grid operation simulation scheme, the faults in the event sequence of the power grid operation simulation scheme are triggered sequentially, and topology calculation and power flow calculation are performed to simulate the change of power grid operation status before and after the fault;

Classify the generated power grid operation simulation scheme according to the power grid operation simulation theme to generate a power grid operation simulation scheme library.

In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and operable on the processor, and the processor implements the computer program when executing the computer program. The steps of the method for automatically constructing the power grid operation simulation scheme library.

In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for automatically constructing the power grid operation simulation scheme library are implemented.

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

The invention proposes a method for automatically constructing a power grid operation simulation scheme library, which automatically generates a customized power grid operation simulation scheme according to the selected power grid operation simulation theme, including the initial operation mode of the power grid operation simulation scheme, preset faults and disposal schemes, and forms them by classification Customized power grid operation simulation program library. According to the theme of the selected power grid operation simulation scheme, the customized power grid operation simulation scheme is automatically generated, and a library of customized power grid operation simulation schemes is formed by classification. Use the cross-section matching algorithm to perform similarity matching with the historical state estimation cross-section to obtain the state estimation cross-section with the highest similarity. On this basis, adjust the operation mode to generate the initial operation mode of the customized power grid operation simulation scheme. After generating the preset fault, based on the decision-making knowledge Tupu uses the knowledge reasoning method to obtain the optimal disposal plan, and combines the initial operation mode of the power grid operation simulation plan, preset faults and disposal plans to generate a customized power grid operation simulation plan, which realizes the automatic generation of the power grid operation simulation plan and reduces the workload of teachers. Through the automatic and intelligent generation process of power grid operation simulation schemes, the workload of teachers is reduced, and a large number of classified and practical power grid operation simulation schemes are provided for dispatchers.

Further, the present invention also proposes a method for generating a fault disposal plan based on the scheduling knowledge base and the disposal scheme library, and constructs the dispatching knowledge base and the disposal scheme based on the grid fault handling plan and the grid dispatching control management regulations using knowledge extraction, knowledge fusion, and knowledge reasoning methods library, according to the preset faults, the optimal disposal plan can be obtained through the evaluation system of the grid operation simulation plan, which meets the needs of the dispatcher for the specific training drill content in the online training, and assists the dispatcher to conduct training without the guidance of the instructor.

Further, in the automatic construction system of the power grid operation simulation scheme library of the present invention, the dispatcher can use DTS to start the customized power grid operation simulation scheme, and can carry out power grid dispatching simulation simulation and drill training independently and on demand anytime, anywhere without a teacher , Improving the scheduling skills and business level of dispatchers.

Description of drawings

Fig. 1 is a flow chart of a method for automatically building a power grid operation simulation scheme library according to the present invention;

Fig. 2 is a flow chart of a method for automatically constructing a power grid operation simulation scheme library;

Figure 3 is a flow chart for the automatic generation of a customized power grid operation simulation scheme;

Figure 4 shows the composition of the customized power grid operation simulation program library;

Fig. 5 is a schematic diagram of the automatic construction system of the power grid operation simulation scheme library provided by the present invention;

Figure 6 is a structural diagram of the automatic generation system of the customized power grid operation simulation scheme library;

Fig. 7 is a schematic diagram of an electronic device provided by the present invention.

Detailed ways

In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only It is an embodiment of a part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

It should be noted that the terms "first" and "second" in the description and claims of the present invention and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or device comprising a sequence of steps or elements is not necessarily limited to the expressly listed instead, may include other steps or elements not explicitly listed or inherent to the process, method, product or apparatus.

Terminology Explanation

1) Dispatcher training simulation (DTS, Dispatcher Training Simulator).

Dispatcher training simulation is a set of digital simulation system, which uses computer technology to reproduce various dispatching operations and system conditions after faults by establishing a mathematical model of the actual power system, and sends this information to the model of the power system control center In order to provide a realistic training environment for the dispatcher, so as to achieve the purpose of not affecting the operation of the actual power system and allowing the dispatcher to get an immersive actual combat exercise. DTS is the best tool for power grid training and research analysis.

2) Instructor: The trainer who monitors, controls and evaluates the power grid operation simulation process is usually an experienced dispatcher.

3) Trainees: Dispatchers or other personnel who conduct power grid operation simulations and receive training to improve dispatching skills and business levels.

At present, the resources of the power grid operation simulation scheme are seriously insufficient. The power grid operation simulation scheme is often aimed at the specified fault type and has not been systematically classified and managed. It cannot meet the needs of the dispatcher for the specific power grid operation simulation content in the operation drill training simulation, resulting in insufficient learning and drill for the dispatcher. System, insufficient. In addition, inexperienced trainees are not familiar with grid structure and complex faults. In the absence of fault solutions, instructors need to participate in the dispatching drill training to complete the drill training.

In addition, the current DTS power grid operation simulation scheme relies on manual production. Instructors not only need to set the initial grid operation mode, but also need to simulate and verify the standard disposal scheme in DTS. The plan production process is time-consuming and labor-intensive, and it is impossible to make a power grid operation simulation plan in time to respond to the dispatcher's autonomous training training needs. Faculty workload.

As shown in Figure 1, the embodiment of the present invention proposes a method and system for automatically constructing a power grid operation simulation scheme library, including:

S1. Obtain and analyze the power grid operation simulation theme and grid operation simulation scheme constraint conditions, combine the power grid physical model and data to extract the power grid characteristic model, and generate the initial operation mode of the power grid operation simulation scheme based on the section matching algorithm;

S2, according to different power grid operation simulation themes of fault handling, generate different power grid operation simulation scheme preset faults;

S3, based on the dispatching knowledge base and the disposal scheme database, use knowledge reasoning to obtain the disposal scheme set, evaluate the disposal scheme set through the grid operation simulation scheme preparation result evaluation system, and obtain the optimal disposal scheme;

S4, combining the initial operation mode of the power grid operation simulation scheme, the preset fault of the power grid operation simulation scheme, and the optimal disposal scheme to form a preliminary power grid operation simulation scheme; classifying the preliminary power grid operation simulation scheme according to the theme of the power grid operation simulation , to generate a power grid operation simulation scheme library.

Automatically generate a customized power grid operation simulation scheme according to the selected fault type, including the operation mode of the power grid operation simulation scheme, preset faults and fault handling schemes, so that the dispatcher can use the customized power grid operation simulation scheme without a teacher. Drill training simulation can reduce the workload of teachers, improve training efficiency and effect, and apply customized power grid operation simulation program library to advanced power grid applications such as DTS, which can improve the practical and intelligent level of DTS system.

Example 1

Each step of the embodiment of the present invention will be described in detail below.

In the above embodiment, in step S1, the power grid operation simulation theme includes the theme of the power grid operation simulation scheme for normal operation and the power grid operation simulation scheme theme for fault handling;

The subjects of the normal operation power grid operation simulation scheme include bus voltage exceeding the limit, line power exceeding the limit, load power exceeding the limit, load loss and operation mode change;

The themes of the grid operation simulation scheme for fault handling include DC faults, AC faults and cascading faults;

The constraint conditions of the power grid operation simulation scheme include the total load of the entire network, the total power generation of the entire network, the power of key tie lines, the power of key sections, the output of key generators, the power of key DC systems, the power of key loads, and the state of operation of key equipment; The constraints of the power grid operation simulation scheme are set based on the topological structure of the grid equipment and the operating state of the grid equipment, and the effective grid operation simulation scheme constraint conditions are used as the grid characteristic model.

In the above embodiment, in step S1, the generation of the initial operation mode of the power grid operation simulation scheme based on the section matching algorithm includes:

Use the section matching algorithm to perform similarity matching with the historical state estimation section. The similarity matching method is as follows:

SIM _t = α _i C _it

In the formula, SIM _t represents the matching degree between the grid section at the historical time t and the operation section required by the power grid operation simulation scheme, C _it is the matching degree between the i-th constraint condition required by the grid operation simulation scheme and the section at time t, α _i is the weight coefficient of the i-th constraint condition;

Select the state estimation section at time t of the minimum value of SIM _t as the original operation mode of the power grid operation simulation scheme, adjust the original operation mode according to the constraints of the power grid operation simulation program, and verify whether the original operation mode meets the power flow convergence through power flow calculation, if If the power flow does not converge, it is necessary to change the constraints of the power grid operation simulation scheme. According to the size of the C _it score as a reference, modify the constraints of the power grid operation simulation scheme corresponding to the one with the smaller C _it score; the adjusted state will satisfy the convergence of the power flow The estimated section is used as the initial operation mode of the power grid operation simulation scheme.

In the above embodiment, in step S2, the generation of preset faults in different power grid operation simulation schemes for different power grid operation simulation themes of fault handling includes:

The power grid fault handling plan includes substation overview, fault phenomenon and emergency response measures data;

Knowledge extraction of fault handling plans by means of keyword extraction through regular expressions;

The extracted faults are divided into DC faults, AC faults and cascading faults of preset faults in the power grid operation simulation scheme to form a preset fault library;

According to the type of equipment, the preset fault library is expanded; for different grid operation simulation themes of fault handling, the faults that meet the requirements are randomly selected from the expanded preset fault library to generate different grid operation simulation scheme preset faults.

In the above embodiment, in step S2, after generating different power grid operation simulation schemes to preset faults, the method further includes:

Based on the extracted power grid characteristic model, combined with the preset faults of the power grid operation simulation scheme, topology calculation and power flow calculation are performed, and the power grid working condition data before and after the fault and the preset faults of the power grid operation simulation scheme are used as the characteristic model of the power grid operation simulation scheme.

In the above-mentioned embodiment, in step S3, the set of treatment plans is obtained by using knowledge reasoning based on the scheduling knowledge base and the treatment plan base, including:

Analyze the power grid fault handling plan, which is divided into the expected failure of the plan, the initial operation mode of the power grid in the plan, the operation mode after the failure of the plan, and the fault handling measures affecting the plan;

Knowledge extraction is carried out on the analyzed power grid fault disposal plan, and knowledge reasoning is carried out by using the method of decision-making knowledge graph to establish a disposal plan library.

In the above embodiment, in step S3, the knowledge extraction of the analyzed power grid fault handling plan is performed, and knowledge reasoning is performed using the method of decision-making knowledge graph to establish a handling plan library, including:

Use the deep learning method to identify the entities of the power grid dispatching control management procedures, improve the dispatching knowledge base, and establish a decision-making knowledge graph;

Establish a decision-making knowledge map as:

DG=(E,C,R,A)

DG is the decision-making knowledge graph engine; E is the entity set of power grid operating conditions, including power grid topology and power flow result data, E={e1,e2,...,em}, including circuit breaker, knife switch opening status, load power , generator output, line power, transformer power, cross-section power, bus voltage, number of generators running and condensers running; C is a set of condition definitions and a set of grid operation modes, C={c1,c2,…,cl} ; R is a rule set, in order to meet the rules of condition C triggering operation, knowledge extraction, knowledge fusion and knowledge reasoning generation are carried out according to the power grid fault plan and dispatching control management regulations; A is the set of fault handling dispatching operations, A={a1,a2, …, an}, including the operation of switch switch, adjustment of unit output, adjustment of power plant output, adjustment of power station, regional load power, control section power and DC power modulation included in the power grid failure plan and dispatch control management regulations;

Carry out knowledge extraction on the power grid fault disposal plan, and use the established decision-making knowledge map method to perform knowledge reasoning on the extracted data to establish a disposal plan library.

In the above embodiment, in step S3, the set of disposal schemes is evaluated by the evaluation system of the preparation result evaluation system of the power grid operation simulation scheme, and the optimal disposal scheme is obtained, including:

Search and evaluate the solution set based on knowledge reasoning, and output the fault solution when the search and evaluation results match and meet the rules in the rule set;

Based on the evaluation system for the preparation results of the power grid operation simulation plan, the fault disposal plan with the highest score is selected as the optimal disposal plan; the evaluation system for the preparation results of the power grid operation simulation plan is as follows:

Score _i ＝w _e S _ei +w _o S _oi

In the formula, Score _i is the comprehensive score of the disposal scheme Ai, w _e and w _o are the weights of electrical indicators and non-electrical indicators, S _ei and S _oi are the scores of electrical indicators and non-electrical indicators of the disposal scheme Ai;

Electrical index score S _ei is the sum of electrical index scores, including the number of over-limit equipment, over-limit power percentage, number of heavy-duty equipment, percentage of heavy-load equipment, and network loss of the entire network; non-electrical index S _oi is the sum of non-electrical index scores, including operation The number of steps, the scope involved in dispatching; S _ei and S _oi are weighted and added to obtain the comprehensive score Score _i of the disposal plan Ai, and all the disposal plans are selected according to the comprehensive score with the highest score as the optimal disposal plan of the power grid operation simulation plan.

In the above embodiment, in step S4, the initial operation mode of the power grid operation simulation scheme, the preset fault of the power grid operation simulation scheme and the optimal disposal scheme are combined to form a preliminary power grid operation simulation scheme; The simulation theme classifies the preliminary power grid operation simulation schemes and generates a power grid operation simulation scheme library, which specifically includes:

Convert the generated power grid operation simulation scheme preset faults and optimal disposal schemes into power grid operation simulation scheme events step by step; a device failure in the power grid operation simulation scheme preset faults is regarded as a power grid operation simulation scheme event, and one time in the optimal disposal scheme The scheduling operation is a power grid operation simulation plan event, which is sorted in chronological order to form a power grid operation simulation plan event sequence; the result triggered by the plan event is the change of the operating state of the power grid equipment, including switch opening and closing, generator output change, and load power change ;

On the basis of the initial operation mode of the generated power grid operation simulation scheme, the faults in the event sequence of the power grid operation simulation scheme are triggered sequentially, and topology calculation and power flow calculation are performed to simulate the change of power grid operation status before and after the fault;

Classify the generated power grid operation simulation scheme according to the power grid operation simulation theme to generate a power grid operation simulation scheme library.

Example 2

Each step of the present invention will be described in detail below in conjunction with optional embodiments.

As shown in Figure 2 and Figure 3, the present invention proposes a method and system for automatically constructing a power grid operation simulation scheme library, and the automatically generated power grid operation simulation scheme includes the power grid operation simulation scheme power grid initial operation mode, preset faults and fault handling schemes . include:

Firstly, by acquiring and analyzing the power grid operation simulation theme and grid operation simulation program constraint conditions, combined with the power grid physical model and data extraction power grid characteristic model, the initial power grid operation mode is generated based on the section matching algorithm;

Secondly, generate the preset faults of the power grid operation simulation scheme, and improve the characteristic model of the power grid operation simulation scheme;

Then, based on the dispatching knowledge base and the disposal scheme database, the disposal scheme is obtained by knowledge reasoning, and the customized optimal disposal scheme is obtained through the evaluation system of the grid operation simulation scheme preparation results.

Finally, the initial operation mode of the power grid operation simulation scheme, the preset faults of the power grid operation simulation scheme and the optimal disposal scheme are combined to form a customized power grid operation simulation scheme, and the customized power grid operation simulation scheme library is generated according to the classification of the power grid operation simulation theme.

The customized power grid operation simulation scheme library generated by the invention can be applied to advanced applications such as DTS to realize power grid operation simulation and training drills, and improve the dispatching skills and business level of dispatching operators.

Example 3

Figure 2 is a flow chart of the automatic construction method for the power grid operation simulation scheme library provided in this embodiment, which specifically includes the following steps:

1) Select the theme of power grid operation simulation.

The customized power grid operation simulation scheme includes the initial grid operation mode, preset faults and fault handling schemes of the power grid operation simulation scheme. The theme of the normal operation power grid operation simulation scheme only involves normal dispatching operations, so the preset fault is empty, and the fault handling theme includes customization All parts of the power grid operation simulation scheme.

2) Input the constraints of the power grid operation simulation scheme.

By acquiring and analyzing the power grid operation simulation theme and the constraints of the power grid operation simulation scheme, combining the power grid model and data to extract the power grid characteristic model, and generating the initial power grid operation mode based on the section matching algorithm;

3) Generate preset faults in the power grid operation simulation scheme, and improve the characteristic model of the power grid operation simulation scheme.

Aiming at the theme of power grid operation simulation scheme for fault handling, different types of preset faults are generated according to different fault handling themes. Based on step 2) the characteristic model of the power grid and the theme of the power grid operation simulation scheme, the characteristic model of the power grid operation simulation scheme is improved, and a power grid characteristic model that can be used for subsequent scheduling knowledge reasoning is generated.

4) Based on the dispatching knowledge base and the disposal plan database, the disposal plan is obtained by knowledge reasoning, and the result evaluation system is compiled based on the power grid operation simulation plan, and the disposal plan with the highest score is selected as the optimal disposal plan.

5) Combining the initial operation mode of the power grid operation simulation scheme generated in steps 2), 3) and 4), a customized power grid operation simulation scheme is generated, and a customized power grid is generated according to the classification of the power grid operation simulation theme Run the library of simulation scenarios.

Based on the method given in this embodiment, applying the power grid operation simulation scheme library generated by this system to DTS, dispatchers can conduct power grid dispatching simulation and autonomous training without instructors, and improve dispatcher dispatching skills and business level.

In the above-mentioned embodiment of the present invention, as shown in Figure 3, it is the automatic generation step of the customized power grid operation simulation scheme, and each step includes in detail:

The step 1) is to select the theme of power grid operation simulation, including the theme of power grid operation simulation scheme such as normal operation and fault handling.

The theme of normal operation power grid operation simulation scheme is used to familiarize yourself with the grid structure and the basic operation of training and dispatching, solve the risk of grid overrun, loss of load and change the operation mode of the grid, etc. The preset fault is empty, that is, no preset fault, including: ( 1) The system frequency exceeds the limit; (2) The bus voltage exceeds the limit; (3) The line power exceeds the limit and the load power exceeds the limit; (4) Loss of load; (5) The operation mode changes.

Fault Handling The theme of power grid operation simulation scheme is used to train fault handling ability, and faults need to be preset. Troubleshooting topics include: DC faults, streaming faults, and cascading faults.

In the above embodiments of the present invention, the step 2) is to input the constraints of the power grid operation simulation scheme. Based on the topological structure of power grid equipment and the operation status of power grid equipment, the constraint conditions of the power grid operation simulation scheme are set, including the total load of the whole network, the total power generation of the whole network, the power of key tie lines, the power of key sections, the output of key generators, the power of key DC systems, and the key Load power and key equipment commissioning status, etc.

All or part of the constraints can be selected as the constraints of the customized grid operation simulation scheme, and the effective grid operation simulation scheme constraints can be used as the grid characteristic model. In order to ensure that the initial operation mode of the power grid operation simulation scheme and subsequent dispatching operations have good power flow convergence and rationality, it is necessary to select the state estimation section that is most similar to the constraints of the power grid operation simulation scheme as the original operation mode of the power grid, and carry out calculations on the original operation mode. Adjust and generate the initial operation mode of the power grid operation simulation scheme. Use the section matching algorithm to perform similarity matching with the historical state estimation section (usually QS file). The similarity matching formula is as follows:

SIM _t = α _i C _it

SIM _t represents the matching degree between the power grid section at the historical time t and the operation section required by the power grid operation simulation scheme, C _it is the matching degree between the i-th constraint condition required by the power grid operation simulation scheme and the section at time t, and α _i is the i-th The weight coefficient of item constraints. The calculation method of C _it is as follows, "||" represents the absolute value of the value:

Select the state estimation section at time t of the minimum value of SIM _t as the original operation mode of the power grid operation simulation scheme, and adjust the original operation mode according to the constraints of the power grid operation simulation scheme to make it meet the constraints of the power grid operation simulation scheme and pass the power flow calculation verification It satisfies the convergence of the power flow. If the power flow does not converge, the constraints of the power grid operation simulation scheme need to be changed. According to the size of the C _it score as a reference, students can focus on modifying the constraints of the power grid operation simulation scheme with a smaller C _it score. The adjusted section that satisfies the convergence of the power flow is used as the initial operation mode of the power grid operation simulation scheme.

In the above embodiments of the present invention, step 3) generates preset faults of the grid operation simulation scheme based on the fault theme of the grid operation simulation scheme and the grid fault handling plan, and improves the characteristic model of the grid operation simulation scheme. The power grid fault handling plan is a necessary reference text in the fault handling process, including important data such as substation overview, fault phenomena, and emergency handling measures.

Since the fault handling plan is relatively regular, with unified content and consistent editing format, it belongs to semi-structured data, and knowledge extraction can be realized by means of keyword extraction through regular expressions. The extracted faults are divided into three categories: DC faults, AC faults and cascading faults, which are preset faults in the power grid operation simulation scheme, to form a preset fault library. The specific types of preset faults are as follows:

1) DC faults: The topic of DC faults mainly involves DC system faults, which include DC line grounding and disconnection faults, valve group faults, converter faults, AC field faults, etc. Among them, the failure of the valve group includes unipolar locking and bipolar locking.

2) AC faults: including transformers, busbars, AC lines, generators, switches and other equipment faults.

3) Cascading faults: Cascading faults in which a series of other devices are out of service due to the failure of a certain device in the power system, which belongs to the more complex faults in the power system. For example, after the line switch refuses to move, the line fails and the transformer protection action causes the transformer to lose power.

In addition, according to the type of equipment, the preset fault library can be expanded to increase the diversity of faults in the power grid operation simulation scheme.

For example, if the AC fault classification of the original contingency plan library includes the ground fault of transformer A, the ground fault of transformer B can be added to the default fault library as an extended fault.

Aiming at different power grid operation simulation topics for fault handling, randomly select faults that meet the requirements from the preset fault library to generate preset faults for customized power grid operation simulation schemes.

Based on the grid characteristic model generated in step 2), combined with grid operation simulation scheme preset faults, topology calculation and power flow calculation are performed, and grid working condition data (such as grid topology, power flow results, operation mode, etc.) before and after the fault are combined with grid operation simulation scheme As a characteristic model of power grid operation simulation scheme, preset faults can be used for subsequent scheduling knowledge reasoning.

In the above-mentioned embodiment of the present invention, step 4) first obtains the disposal plan based on the scheduling knowledge base and the disposal plan database, specifically including:

The power grid fault handling plan is analyzed. The general plan is divided into the anticipated failure of the plan, the initial operation mode of the power grid in the plan, the operation mode after the failure of the plan, and the fault handling measures affecting the plan. The predicted faults of the scenario have been extracted in step 2) and used as the preset faults of the power grid operation simulation scheme to form a preset fault library. Knowledge extraction is carried out on the power grid fault disposal plan, and the dispatching knowledge base and disposal plan database are established by using the decision-making knowledge map method, specifically including:

The power grid dispatching control management regulations are the rules and regulations based on the power grid dispatching control management work, and are important auxiliary decision-making reference data in the power grid fault handling work. This data belongs to unstructured data, and the phenomena and treatment measures contained in it are all Chinese texts explaining the fault situation and specific operations. There is no fixed word frequency, keywords, etc. for description, and the description forms are diverse, so it is difficult to apply the regular expression method Extraction, and the amount of data is small, using deep learning technology to carry out entity recognition for such small sample data in the power grid field, and improve the scheduling knowledge base and disposal plan library.

The specific solution given in this embodiment is: use the deep learning method to carry out entity recognition on the power grid dispatching control management procedures, improve the dispatching knowledge base, and establish a decision-making knowledge map;

Establish a decision-making knowledge graph (decision graph, referred to as DG) as follows:

DG=(E,C,R,a)

DG is the decision-making knowledge graph engine; E is the entity set of power grid operating conditions, including power grid topology and power flow result data, E={e1,e2,...,em}, including circuit breaker, knife switch opening status, load power , generator output, line power, transformer power, section power, bus voltage, number of generators running, number of condensers running, etc.; C is a set of condition definitions, a set of grid operation modes, C={c1,c2,…,cl }; R is the rule set, in order to meet the rules of condition C trigger operation, knowledge extraction, knowledge fusion and knowledge reasoning generation are carried out according to the power grid fault plan and dispatch control management regulations; A action set is the fault handling dispatch operation set, A={ a1,a2,…,an}, including the power grid failure plan and dispatching control management procedures including switch switch operation, unit output adjustment, power plant output adjustment, plant station, regional load power, control section power and DC power modulation, etc. .

Based on the constructed decision-making knowledge graph, input the characteristic model of the power grid operation simulation scheme generated according to step 3) into the decision engine, as the power grid operating condition entity E and the operation mode before and after the fault as the condition C, and intelligently search based on knowledge reasoning and rule set R Evaluation, when the matching meets certain types of rules in the rule set, the output action set A1~An is used as a fault handling plan.

In the above-mentioned embodiments of the present invention, step 4) after obtaining the disposal schemes A1-An, based on the grid operation simulation scheme compilation result evaluation system, the disposal scheme with the highest score is selected as the optimal disposal scheme. The evaluation system for the preparation results of the power grid operation simulation scheme is as follows:

Score _i = _e S _ei + _o S _oi

Score _i is the comprehensive score of the disposal scheme Ai, w _e and w _o are the weights of electrical indicators and non-electrical indicators, S _ei and S _oi are the scores of electrical indicators and non-electrical indicators of the disposal scheme Ai.

The above-mentioned electrical index score S _ei includes the sum of electrical index scores such as the number of off-limit equipment, the percentage of off-limit power, the number of heavy-duty equipment, the percentage of heavy-duty equipment, and the network loss of the entire network; the non-electrical index S _oi includes the number of operation steps and the scope of scheduling and other non-electrical index scores. S _ei and S _oi are weighted and added to obtain the comprehensive score Score _i of the disposal scheme Ai, and all disposal schemes are selected according to the comprehensive score and the most customized optimal disposal scheme of the power grid operation simulation scheme with the highest score.

In addition, the minimum value limit is set to γ for the scoring results of the power grid operation simulation program compilation. When Score<γ, the instructor can manually correct it to improve the dispatching knowledge base and disposal plan library.

In summary, combined with the initial operation mode of the power grid operation simulation scheme generated in steps 2), 3) and 4), the preset faults and the optimal disposal scheme of the power grid operation simulation scheme, a customized power grid operation simulation scheme is generated, specifically including:

The preset faults and optimal disposal schemes generated in step 3) and step 4) are converted step by step into grid operation simulation scheme events. An equipment failure in the default fault is a power grid operation simulation event, and a dispatch operation in the optimal disposal plan is a power grid operation simulation event, which is sorted in chronological order to form a power grid operation simulation event sequence. The result triggered by the event of the scheme is the change of the operation state of the grid equipment, including the opening and closing of switches, the change of generator output, and the change of load power.

After the DTS training exercise is started, on the basis of the initial operation mode of the grid operation simulation scheme generated in step 2), the faults in the grid operation simulation scheme event sequence are sequentially triggered, and topology calculation and power flow calculation are performed to simulate the change of grid operation status before and after the fault.

Dispatchers can conduct customized grid operation simulation program training drills according to the disposal plan in the event of the grid operation simulation program. For the normal operation grid operation simulation scenario topic, since the preset fault is empty, no fault is triggered.

In this embodiment, based on the power grid fault disposal plan and the power grid dispatching control management regulations, the knowledge extraction, knowledge fusion and knowledge reasoning methods are used to construct the dispatching knowledge base and the disposal plan library, and the optimal disposal is obtained through the evaluation system of the power grid operation simulation plan according to the preset faults. The program can meet the needs of dispatchers for specific training drill content in online training, and assist dispatchers to conduct training without the guidance of instructors.

Of course, the solution given in this embodiment is a preferred solution, not a specific solution, and the purpose of this embodiment can also be achieved by using other means that serve the same purpose as the knowledge extraction, which is not specifically limited here.

Refer to Figure 4 for details, which is the composition of the customized power grid operation simulation scheme library. Classify the generated grid operation simulation schemes according to the grid operation simulation topics to generate a customized grid operation simulation scheme library.

Furthermore, according to the power grid operation simulation theme selected in step 1), the customized power grid operation simulation scheme library is divided into normal operation theme and fault operation theme, and targeted drill training can be carried out according to relevant themes.

As shown in Figure 5, the present invention provides a system for automatically building a power grid operation simulation scheme library, which mainly includes:

The initial operation mode generation module is used to obtain and analyze the power grid operation simulation theme and the constraints of the power grid operation simulation scheme, combine the power grid physical model and data to extract the power grid characteristic model, and generate the initial operation mode of the power grid operation simulation scheme based on the section matching algorithm;

The preset fault generation module is used to generate different grid operation simulation scheme preset faults according to different power grid operation simulation themes for fault handling;

The optimal disposal plan generation module is used to obtain the disposal plan set by using knowledge reasoning based on the scheduling knowledge base and the disposal plan library, and evaluate the disposal plan set through the grid operation simulation plan preparation result evaluation system to obtain the optimal disposal plan;

The simulation scheme library generation module is used to combine the initial operation mode of the power grid operation simulation scheme, the preset fault of the power grid operation simulation scheme and the optimal disposal scheme to form a preliminary power grid operation simulation scheme; The power grid operation simulation schemes are classified to generate a power grid operation simulation scheme library.

In the initial operation mode generation module, the power grid operation simulation theme includes a power grid operation simulation scheme theme for normal operation and a power grid operation simulation scheme theme for fault handling;

The subjects of the normal operation power grid operation simulation scheme include bus voltage exceeding the limit, line power exceeding the limit, load power exceeding the limit, load loss and operation mode change;

The themes of the grid operation simulation scheme for fault handling include DC faults, AC faults and cascading faults;

The constraint conditions of the power grid operation simulation scheme include the total load of the entire network, the total power generation of the entire network, the power of key tie lines, the power of key sections, the output of key generators, the power of key DC systems, the power of key loads, and the state of operation of key equipment; The constraints of the power grid operation simulation scheme are set based on the topological structure of the grid equipment and the operating state of the grid equipment, and the effective grid operation simulation scheme constraint conditions are used as the grid characteristic model.

In the initial operation mode generation module, the generation of the initial operation mode of the power grid operation simulation scheme based on the section matching algorithm includes:

Use the section matching algorithm to perform similarity matching with the historical state estimation section. The similarity matching method is as follows:

SIM _t = α _i C _it

In the formula, SIM _t represents the matching degree between the grid section at the historical time t and the operation section required by the power grid operation simulation scheme, C _it is the matching degree between the i-th constraint condition required by the grid operation simulation scheme and the section at time t, α _i is the weight coefficient of the i-th constraint condition;

Select the state estimation section at time t of the minimum value of SIM _t as the original operation mode of the power grid operation simulation scheme, adjust the original operation mode according to the constraints of the power grid operation simulation program, and verify whether the original operation mode meets the power flow convergence through power flow calculation, if If the power flow does not converge, it is necessary to change the constraint conditions of the power grid operation simulation scheme. According to the size of the C _it score as a reference, modify the corresponding grid operation simulation scheme constraint conditions of the smaller C _it score; the adjusted state of the power flow convergence will be satisfied The estimated section is used as the initial operation mode of the power grid operation simulation scheme.

In the preset fault generation module, the preset faults of different power grid operation simulation schemes are generated according to different power grid operation simulation themes for fault handling, including:

The power grid fault handling plan includes substation overview, fault phenomenon and emergency response measures data;

Knowledge extraction of fault handling plans by means of keyword extraction through regular expressions;

The extracted faults are divided into DC faults, AC faults and cascading faults of preset faults in the power grid operation simulation scheme to form a preset fault library;

According to the type of equipment, the preset fault library is expanded; for different grid operation simulation themes of fault handling, the faults that meet the requirements are randomly selected from the expanded preset fault library to generate different grid operation simulation scheme preset faults.

In the preset fault generation module, after the preset faults of different power grid operation simulation schemes are generated, the method further includes:

Based on the extracted power grid characteristic model, combined with the preset faults of the power grid operation simulation scheme, topology calculation and power flow calculation are performed, and the power grid working condition data before and after the fault and the preset faults of the power grid operation simulation scheme are used as the characteristic model of the power grid operation simulation scheme.

As a further improvement of the present invention, in the optimal treatment plan generation module, the set of treatment plans obtained by knowledge reasoning based on the scheduling knowledge base and the treatment plan library includes:

Analyze the power grid fault handling plan, which is divided into the expected failure of the plan, the initial operation mode of the power grid in the plan, the operation mode after the failure of the plan, and the fault handling measures affecting the plan;

Knowledge extraction is carried out on the analyzed power grid fault disposal plan, and knowledge reasoning is carried out by using the method of decision-making knowledge graph to establish a disposal plan library.

In the optimal disposal scheme generation module, the knowledge extraction is performed on the analyzed power grid fault disposal plan, and the knowledge reasoning is carried out by using the method of decision-making knowledge map to establish a disposal scheme library, including:

Use the deep learning method to identify the entities of the power grid dispatching control management procedures, improve the dispatching knowledge base, and establish a decision-making knowledge graph;

Establish a decision-making knowledge map as:

DG=(E,C,R,A)

DG is the decision-making knowledge graph engine; E is the entity set of power grid operating conditions, including power grid topology and power flow result data, E={e1,e2,...,em}, including circuit breaker, knife switch opening status, load power , generator output, line power, transformer power, cross-section power, bus voltage, number of generators running and condensers running; C is a set of condition definitions and a set of grid operation modes, C={c1,c2,…,cl} ; R is a rule set, in order to meet the rules of condition C triggering operation, knowledge extraction, knowledge fusion and knowledge reasoning generation are carried out according to the power grid fault plan and dispatching control management regulations; A is the set of fault handling dispatching operations, A={a1,a2, …, an}, including the operation of switch switch, adjustment of unit output, adjustment of power plant output, adjustment of power station, regional load power, control section power and DC power modulation included in the power grid failure plan and dispatch control management regulations;

Carry out knowledge extraction on the power grid fault disposal plan, and use the established decision-making knowledge map method to perform knowledge reasoning on the extracted data to establish a disposal plan library.

In the optimal disposal plan generation module, the evaluation system for the compilation result evaluation system of the power grid operation simulation plan evaluates the set of disposal plans to obtain the optimal disposal plan, including:

Search and evaluate the solution set based on knowledge reasoning, and output the fault solution when the search and evaluation results match and meet the rules in the rule set;

Based on the evaluation system for the preparation results of the power grid operation simulation plan, the fault disposal plan with the highest score is selected as the optimal disposal plan; the evaluation system for the preparation results of the power grid operation simulation plan is as follows:

Score _i ＝w _e S _ei +w _o S _oi

In the formula, Score _i is the comprehensive score of the disposal scheme Ai, w _e and w _o are the weights of electrical indicators and non-electrical indicators, S _ei and S _oi are the scores of electrical indicators and non-electrical indicators of the disposal scheme Ai;

The electrical index score S _ei is the sum of the electrical index scores, including the number of off-limit equipment, the percentage of off-limit power, the number of heavy-duty equipment, the percentage of heavy-duty equipment, and the network loss of the entire network; the non-electrical index S _oi is the sum of the non-electrical index scores, including the operation The number of steps, the scope involved in dispatching; S _ei and S _oi are weighted and added to obtain the comprehensive score Score _i of the disposal scheme Ai, and all disposal schemes are selected according to the comprehensive score with the highest score as the optimal disposal scheme of the power grid operation simulation scheme.

In the simulation scheme library generation module, the initial operation mode of the power grid operation simulation scheme, the preset fault of the power grid operation simulation scheme and the optimal disposal scheme are combined to form a preliminary power grid operation simulation scheme; according to the power grid operation simulation The topic classifies the preliminary power grid operation simulation schemes and generates a power grid operation simulation scheme library, including:

Convert the generated power grid operation simulation scheme preset faults and optimal disposal schemes into power grid operation simulation scheme events step by step; a device failure in the power grid operation simulation scheme preset faults is regarded as a power grid operation simulation scheme event, and one time in the optimal disposal scheme The scheduling operation is a power grid operation simulation plan event, which is sorted in chronological order to form a power grid operation simulation plan event sequence; the result triggered by the plan event is the change of the operating state of the power grid equipment, including switch opening and closing, generator output change, and load power change ;

On the basis of the initial operation mode of the generated power grid operation simulation scheme, the faults in the event sequence of the power grid operation simulation scheme are triggered sequentially, and topology calculation and power flow calculation are performed to simulate the change of power grid operation status before and after the fault;

Classify the generated power grid operation simulation scheme according to the power grid operation simulation theme to generate a power grid operation simulation scheme library.

According to the operation situation of the example, the present invention also provides a system structure diagram for automatic generation of a customized grid operation simulation scheme library. Referring to Figure 6, based on the automatic construction method of the power grid operation simulation scheme library, a customized power grid operation simulation scheme library automatic generation system can be formed, which includes:

Power grid operation simulation theme selection module, power grid operation simulation scheme constraint setting module, initial operation mode generation module, preset fault generation module, disposal scheme generation module and customized power grid operation simulation scheme library generation module.

The power grid operation simulation theme selection module is used to obtain and analyze the power grid operation simulation theme;

The power grid operation simulation scheme constraint setting module is used to obtain and analyze the power grid operation simulation scheme constraint conditions;

The initial operation mode generation module is used to generate the initial operation mode of the power grid based on the section matching algorithm by acquiring and analyzing the power grid operation simulation theme and the constraints of the power grid operation simulation scheme, combined with the power grid physical model and data extraction power grid characteristic model;

The preset fault generation module is used to generate the preset faults of the power grid operation simulation scheme according to the theme of the fault handling power grid operation simulation scheme according to the theme of fault handling; improve the characteristic model of the power grid operation simulation scheme;

The preset fault generation module is used to obtain the disposal plan by using knowledge reasoning based on the scheduling knowledge base and the disposal plan database, and obtain the customized optimal disposal plan through the compilation of the result evaluation system of the power grid operation simulation plan.

Customized power grid operation simulation program library generation module, which is used to combine the initial operation mode of the power grid operation simulation program, the preset fault of the power grid operation simulation program and the optimal disposal program to form a customized power grid operation simulation program, which is classified and generated according to the power grid operation simulation theme Customized power grid operation simulation program library.

The customized power grid operation simulation scheme library generation module can combine the initial operation mode of the power grid operation simulation scheme, preset faults and fault handling schemes to generate grid operation simulation scheme file formats recognizable by the DTS system and classify them to form a customized scheme library, which can be used by dispatchers The DTS system activates the schemes in the power grid operation simulation scheme library to carry out dispatching simulation simulation, and conducts autonomous training anytime, anywhere without instructors, so as to improve dispatching skills and business level.

As shown in FIG. 7 , the third aspect of the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and operable on the processor, and the processor executes the The computer program is the step of realizing the automatic construction method of the power grid operation simulation scheme library considering the delay characteristics of multi-interaction functions.

The fourth aspect of the present invention is to provide a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the power grid operation that takes into account the delay characteristics of multiple interactive functions is realized. Simulate the steps of the solution library automatic construction method.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention 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, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the present invention can still be Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall fall within the protection scope of the claims of the present invention.

Claims (12)

1. An automatic construction method of a power grid operation simulation scheme library is characterized by comprising the following steps:

acquiring and analyzing a power grid operation simulation theme and a power grid operation simulation scheme constraint condition, extracting a power grid characteristic model by combining a power grid physical model and data, and generating an initial operation mode of the power grid operation simulation scheme based on a section matching algorithm;

Aiming at different power grid operation simulation topics of fault treatment, different power grid operation simulation schemes are generated to preset faults;

based on a scheduling knowledge base and a treatment scheme base, a treatment scheme set is obtained by utilizing knowledge reasoning, and the treatment scheme set is evaluated through a power grid operation simulation scheme compiling result evaluation system to obtain an optimal treatment scheme;

combining the initial operation mode of the power grid operation simulation scheme, the preset fault of the power grid operation simulation scheme and the optimal treatment scheme to form a preliminary power grid operation simulation scheme; and classifying the preliminary power grid operation simulation schemes according to the power grid operation simulation theme to generate a power grid operation simulation scheme library.

2. The method for automatically constructing a power grid operation simulation scheme library according to claim 1, wherein the power grid operation simulation topics include normal operation power grid operation simulation scheme topics and fault handling power grid operation simulation scheme topics;

the normal operation power grid operation simulation scheme theme comprises bus voltage out-of-limit, line power out-of-limit, load power out-of-limit, lost load and operation mode change;

the fault handling power grid operation simulation scheme theme comprises direct current faults, alternating current faults and cascading faults;

The constraint conditions of the power grid operation simulation scheme comprise total load of the whole grid, total power generation of the whole grid, key tie line power, key section power, key generator output, key direct current system power, key load power and key equipment operation state; the constraint condition of the power grid operation simulation scheme is set based on the topological structure of the power grid equipment and the operation state of the power grid equipment, and the constraint condition of the effective power grid operation simulation scheme is used as a power grid characteristic model.

3. The method for automatically constructing a power grid operation simulation scheme library according to claim 1, wherein the generating the initial operation mode of the power grid operation simulation scheme based on the section matching algorithm comprises:

and performing similarity matching with the historical state estimated section by using a section matching algorithm, wherein a similarity matching formula is as follows:

SIM _t ＝α _i C _it

in the SIM _t Representing the power grid section at the time of history t and the operation section required by the power grid operation simulation schemeMatching degree of C _it Matching degree of ith constraint condition required by power grid operation simulation scheme and section at t moment, alpha _i The weight coefficient occupied by the constraint condition of the i th item;

selecting SIM _t The state estimation section at the time t of the minimum value is used as an original operation mode of the power grid operation simulation scheme, the original operation mode is regulated according to the constraint condition of the power grid operation simulation scheme, whether the original operation mode meets the trend convergence is verified through the trend calculation, if the trend is not converged, the constraint condition of the power grid operation simulation scheme is required to be changed, and according to C _it The magnitude of the score is taken as a reference, and C is modified _it A corresponding constraint condition of the power grid operation simulation scheme with a small score; and taking the adjusted state estimation section meeting the trend convergence as an initial operation mode of the power grid operation simulation scheme.

4. The method for automatically constructing a power grid operation simulation scheme library according to claim 1, wherein the generating different power grid operation simulation scheme preset faults for different power grid operation simulation topics of fault handling comprises:

the grid fault handling scheme includes substation profile, fault phenomena and emergency handling measure data;

carrying out knowledge extraction on the fault treatment plan in a keyword extraction mode through the regular expression;

dividing the extracted faults into direct current faults, alternating current faults and cascading faults of a power grid operation simulation scheme preset fault, and forming a preset fault library;

expanding a preset fault library according to the type of the equipment; and aiming at different power grid operation simulation topics for fault treatment, randomly selecting the faults meeting the requirements from the expanded preset fault library to generate different power grid operation simulation scheme preset faults.

5. The method for automatically constructing a power grid operation simulation scheme library according to claim 1, wherein after generating the preset faults of different power grid operation simulation schemes, the method further comprises:

The method for improving the characteristic model of the power grid operation simulation scheme specifically comprises the following steps:

based on the extracted power grid characteristic model, the power grid operation simulation scheme is combined to preset faults, topology calculation and tide calculation are carried out, and the power grid working condition data before and after the faults and the power grid operation simulation scheme preset faults are used as the power grid operation simulation scheme characteristic model.

6. The automatic construction method of a power grid operation simulation scheme library according to claim 1, wherein the obtaining a treatment scheme set based on a scheduling knowledge base and a treatment scheme library by using knowledge reasoning comprises:

analyzing the power grid fault handling plan, wherein the power grid fault handling plan is divided into a plan expected fault, a plan power grid initial operation mode, a plan fault post operation mode and a plan fault influencing treatment measure;

and carrying out knowledge extraction on the analyzed power grid fault treatment plan, and carrying out knowledge reasoning by using a method of decision knowledge graph to establish a treatment plan library.

7. The method for automatically constructing a power grid operation simulation scheme library according to claim 6, wherein the step of performing knowledge extraction on the parsed power grid fault treatment scheme and performing knowledge reasoning by using a method of decision knowledge graph to establish a treatment scheme library comprises the steps of:

Performing entity identification on the power grid dispatching control management regulation by adopting a deep learning method, perfecting a dispatching knowledge base, and establishing a decision knowledge map;

the decision knowledge graph is established as follows:

DG＝(E,C,R,A)

DG is the decision knowledge graph engine; e is a power grid operation condition entity set, and comprises power grid topological structure and power grid tide result data, wherein E= { E1, E2, …, em }, and comprises a breaker, a disconnecting link on-off state, load power, generator output, line power, transformer power, section power, bus voltage, generator start-up number and a camera start-up number; c is a condition definition set, which is a power grid operation mode set, c= { C1, C2, …, cl }; r is a rule set, and knowledge extraction, knowledge fusion and knowledge reasoning generation are carried out according to the power grid fault plan and the dispatching control management rule in order to meet the rule of the condition C triggering operation; a is a fault handling scheduling operation set, and a= { a1, a2, …, an }, including switch knife operation, unit output adjustment, power plant output adjustment, plant station adjustment, regional load power adjustment, control section power adjustment and direct current power modulation contained in a power grid fault plan and scheduling control management procedure;

and carrying out knowledge extraction on the power grid fault treatment plan, and carrying out knowledge reasoning on the extracted data by utilizing the established method for deciding the knowledge graph to establish a treatment plan library.

8. The method for automatically constructing a power grid operation simulation scheme library according to claim 1, wherein the step of evaluating the treatment scheme set by a power grid operation simulation scheme compiling result evaluation system to obtain an optimal treatment scheme comprises the steps of:

searching and evaluating the treatment scheme set based on knowledge reasoning, and outputting a fault treatment scheme when the searching and evaluating results are matched and the rules in the rule set are met;

based on a power grid operation simulation scheme compiling result evaluation system, selecting a fault treatment scheme with the highest score as an optimal treatment scheme; the power grid operation simulation scheme programming result evaluation system is as follows:

Score _i ＝w _e S _ei +w _o S _oi

in the formula, score _i To treat the composite score of the regimen Ai, w _e And w _o For electrical index and non-electrical index weight, S _ei And S is _oi An electrical index score and a non-electrical index score for treatment regimen Ai;

electrical index score S _ei The electrical index scoring sum comprises the number of out-of-limit devices, the out-of-limit power percentage, the number of heavy-load devices, the percentage of heavy-load devices and the total network loss; non-electrical index S _oi Is a non-electrical index score sum comprising the number of operational steps, a scheduling context; s is S _ei And S is _oi Weighted addition to obtain a composite Score of the treatment plan Ai _i The overall treatment scheme selects the optimal treatment scheme with the highest score according to the comprehensive score as the power grid operation simulation scheme.

9. The method for automatically constructing a power grid operation simulation scheme library according to claim 1, wherein the initial operation mode of the power grid operation simulation scheme, the preset fault of the power grid operation simulation scheme and the optimal treatment scheme are combined to form a preliminary power grid operation simulation scheme; classifying the preliminary power grid operation simulation schemes according to the power grid operation simulation theme to generate a power grid operation simulation scheme library, which specifically comprises the following steps:

step-by-step converting the preset faults and the optimal treatment schemes of the generated power grid operation simulation scheme into power grid operation simulation scheme events; the method comprises the steps that one equipment fault in a power grid operation simulation scheme preset fault is used as a power grid operation simulation scheme event, one-time scheduling operation in an optimal treatment scheme is used as a power grid operation simulation scheme event, and sequencing is carried out according to time sequence to form a power grid operation simulation scheme event sequence; the result of scheme event triggering is the running state change of the power grid equipment, including switch on-off, generator output change and load power change;

Sequentially triggering faults in an event sequence of the power grid operation simulation scheme on the basis of the initial operation mode of the generated power grid operation simulation scheme, performing topology calculation and tide calculation, and simulating the change of the power grid operation state before and after the faults;

and classifying the generated power grid operation simulation scheme according to the power grid operation simulation theme to generate a power grid operation simulation scheme library.

10. An automatic construction system for a power grid operation simulation scheme library, which is characterized by comprising the following components:

the initial operation mode generation module is used for acquiring and analyzing the power grid operation simulation theme and the constraint condition of the power grid operation simulation scheme, extracting a power grid characteristic model by combining a power grid physical model and data, and generating an initial operation mode of the power grid operation simulation scheme based on a section matching algorithm;

the preset fault generation module is used for aiming at the fault to treat different power grid operation simulation topics and generating different power grid operation simulation schemes to preset faults;

the optimal treatment scheme generation module is used for obtaining a treatment scheme set based on a scheduling knowledge base and a treatment scheme base by utilizing knowledge reasoning, and evaluating the treatment scheme set through a power grid operation simulation scheme compiling result evaluation system to obtain an optimal treatment scheme;

The simulation scheme library generation module is used for combining the initial operation mode of the power grid operation simulation scheme, the preset fault of the power grid operation simulation scheme and the optimal treatment scheme to form a preliminary power grid operation simulation scheme; and classifying the preliminary power grid operation simulation schemes according to the power grid operation simulation theme to generate a power grid operation simulation scheme library.

11. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the grid operation simulation scheme library automatic construction method of any one of claims 1-9 when the computer program is executed.

12. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the steps of the grid operation simulation scheme library automatic construction method of any one of claims 1-9.