A power grid operation simulation scheme library automatic construction method and system

Abstract

This invention belongs to the field of power dispatch automation technology, and provides a method and system for automatically constructing a power grid operation simulation scheme library. The method includes acquiring and parsing power grid operation simulation themes and constraints of power grid operation simulation schemes; extracting power grid feature models by combining power grid physical models and data; and generating initial operation modes for power grid operation simulation schemes based on cross-section matching algorithms. For different power grid operation simulation themes related to fault handling, different preset faults are generated for each power grid operation simulation scheme. Based on a dispatch knowledge base and a fault handling scheme library, a set of fault handling schemes is obtained through knowledge reasoning. The set of fault handling schemes is evaluated using a power grid operation simulation scheme compilation result evaluation system to obtain the optimal fault handling scheme. Finally, the preliminary power grid operation simulation schemes are classified according to the power grid operation simulation themes to generate a power grid operation simulation scheme library. This invention provides dispatchers with a large number of categorized and practical power grid operation simulation schemes.

Description

Technical Field

[0001] This invention belongs to the field of power dispatch automation technology, specifically relating to a method and system for automatically constructing a power grid operation simulation scheme library. Background Technology

[0002] The Dispatcher Training System (DTS) provides an efficient and convenient platform for dispatcher professional skills training and joint emergency response drills, playing a crucial role in improving dispatchers' business analysis and research capabilities and comprehensive accident handling abilities. With the continuous advancement of AC / DC hybrid power grid construction and the explosive growth in the scale of new energy grid connection, the characteristics of power grid operation are becoming increasingly complex, thus increasing the difficulty of generating initial operating modes and debugging power flow in power grid dispatching and operation simulation schemes. However, the current DTS (Distributed Response System) has a low level of intelligence, and the debugging process for power grid operation simulation schemes is complex. It still relies on experienced instructors to manually develop power grid operation simulation schemes and to participate in the entire process of training and simulation to guide trainees in pre-stored power grid faults in the solutions. This is a large workload and time-consuming. In addition, the current DTS training and simulation power grid operation scheme resources are severely insufficient. Power grid operation simulation schemes are often targeted at specific fault types and are not systematically classified and managed. They cannot meet the needs of dispatchers for specific training and simulation content in online training and simulation. This results in dispatchers' learning and training being unsystematic and insufficient, and the training content is not targeted or practical. It is difficult to meet the needs of multiple dispatchers participating in training at the same time and for personalized training and simulation. As a result, DTS cannot become a routine and autonomous simulation tool for dispatchers to conduct "on-demand training" anytime, anywhere.

[0003] Existing training plan generation methods only focus on whether the initial power grid operating conditions generated by the DTS system are consistent with the training plan content. They do not consider the complex and ever-changing power grid fault scenarios included in the plan, nor do they provide methods for automatically generating standard solutions to power grid faults, thus failing to enable autonomous and personalized training for trainees. Furthermore, if a feasible solution cannot be obtained by changing the operating parameters of power grid equipment based on power flow calculations, it is necessary to modify the constraints of the training plan. However, this method does not explain how to automatically adjust the initial constraints of the training plan; instructors still need to rely on their manual experience to adjust the original plan before using this method to obtain a feasible solution. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention provides a method and system for automatically constructing a power grid operation simulation scheme library. This invention reduces the workload of instructors and provides dispatchers with a large number of categorized and practical power grid operation simulation schemes through an automated and intelligent power grid operation simulation scheme generation process.

[0005] To achieve the above objectives, the present invention employs the following technical solution:

[0006] In a first aspect, the present invention provides a method for automatically constructing a power grid operation simulation scheme library, comprising:

[0007] The system acquires and analyzes the power grid operation simulation theme and the constraints of the power grid operation simulation scheme. It then combines the power grid physical model and data to extract the power grid characteristic model and generates the initial operation mode of the power grid operation simulation scheme based on the cross section matching algorithm.

[0008] Different power grid operation simulation schemes with preset faults are generated for different power grid operation simulation themes for fault handling;

[0009] Based on the scheduling knowledge base and the disposal plan base, a set of disposal plans is obtained by knowledge reasoning. The set of disposal plans is evaluated by the power grid operation simulation plan compilation result evaluation system to obtain the optimal disposal plan.

[0010] The initial operation mode of the power grid operation simulation scheme, the preset faults of the power grid operation simulation scheme, and the optimal handling scheme are combined to form a preliminary power grid operation simulation scheme; the preliminary power grid operation simulation schemes are classified according to the power grid operation simulation theme to generate a power grid operation simulation scheme library.

[0011] As a further improvement of the present invention, 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;

[0012] The normal operation power grid simulation scheme includes topics such as bus voltage exceeding limits, line power exceeding limits, load power exceeding limits, load loss, and changes in operating mode.

[0013] The power grid operation simulation scheme for fault handling includes DC faults, AC faults, and cascading faults.

[0014] The constraints 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 interconnection lines, the power of key sections, the output of key generators, the power of key DC systems, the power of key loads, and the commissioning status of key equipment. The constraints of the power grid operation simulation scheme are set based on the topology of the power grid equipment and the operating status of the power grid equipment, and the effective constraints of the power grid operation simulation scheme are used as the power grid characteristic model.

[0015] As a further improvement of the present invention, the initial operation mode of the power grid operation simulation scheme generated based on the cross-section matching algorithm includes:

[0016] The similarity matching algorithm is used to perform similarity matching with historical state estimated cross sections. The similarity matching method is as follows:

[0017] SIMt =α i C it

[0018] In the formula, SIM t C represents the degree of matching between the power grid section at historical time t and the operating section required by the power grid operation simulation scheme. it Let α be the degree of matching between the i-th constraint required by the power grid operation simulation scheme and the section at time t. i This represents the weighting coefficient of the i-th constraint.

[0019] Select SIM t The state estimation section at time t, representing the minimum value, serves as the original operating mode in the power grid operation simulation scheme. The original operating mode is adjusted according to the constraints of the power grid operation simulation scheme, and power flow calculations are used to verify whether the original operating mode satisfies power flow convergence. If the power flow does not converge, the constraints of the power grid operation simulation scheme need to be changed, based on C... it Using the score as a reference, modify C. it The constraint condition of the power grid operation simulation scheme corresponding to the item with the smaller score; the adjusted state estimation section that satisfies power flow convergence is used as the initial operation mode of the power grid operation simulation scheme.

[0020] As a further improvement of the present invention, the step of generating different power grid operation simulation schemes for different power grid operation simulation themes for fault handling includes:

[0021] The power grid fault handling plan includes substation overview, fault phenomena, and emergency response measures data;

[0022] Knowledge extraction from fault handling plans is performed using keyword extraction via regular expressions.

[0023] The extracted faults are categorized into DC faults, AC faults, and cascading faults, which are preset faults in the power grid operation simulation scheme, to form a preset fault database.

[0024] Based on the equipment type, the preset fault database is expanded; for different power grid operation simulation themes for fault handling, faults that meet the requirements are randomly selected from the expanded preset fault database to generate different preset faults for power grid operation simulation schemes.

[0025] As a further improvement of the present invention, after pre-setting faults in generating different power grid operation simulation schemes, the method further includes:

[0026] Improve the characteristic model of the power grid operation simulation scheme, specifically including:

[0027] Based on the extracted power grid feature model, combined with the preset faults in the power grid operation simulation scheme, topology calculation and power flow calculation are performed. The power grid operating condition data before and after the fault and the preset faults in the power grid operation simulation scheme are used as the feature model of the power grid operation simulation scheme.

[0028] As a further improvement of the present invention, the step of obtaining a set of disposal schemes based on the scheduling knowledge base and the disposal scheme base using knowledge reasoning includes:

[0029] The power grid fault handling plan is analyzed, which is divided into the anticipated faults in the plan, the initial operation mode of the power grid in the plan, the operation mode after the fault in the plan, and the measures that affect the fault handling plan.

[0030] Knowledge is extracted from the analyzed power grid fault handling plan, and a handling plan database is established by using the decision knowledge graph method for knowledge reasoning.

[0031] As a further improvement of the present invention, the step of extracting knowledge from the parsed power grid fault handling plan and establishing a handling plan library using the decision knowledge graph method includes:

[0032] Deep learning methods are used to identify entities in power grid dispatch control and management procedures, improve the dispatch knowledge base, and establish a decision knowledge graph.

[0033] The decision knowledge graph is established as follows:

[0034] DG = (E, C, R, A)

[0035] DG is the decision knowledge graph engine; E is the set of entities for power grid operation conditions, including power grid topology and power flow result data, E = {e1, e2, ..., em}, including circuit breaker, disconnector status, load power, generator output, line power, transformer power, cross-sectional power, bus voltage, number of generators in operation, and number of synchronous condensers in operation; C is the set of condition definitions, which is the set of power grid operation modes, C = {c1, c2, ..., cl}; R is the set of rules, which are the rules for triggering operations to meet condition C, and are generated by knowledge extraction, knowledge fusion, and knowledge reasoning based on power grid fault contingency plans and dispatch control management procedures; A is the set of fault handling dispatch operations, A = {a1, a2, ..., an}, including disconnector switching operations, unit output adjustment, power plant output adjustment, substation and regional load power adjustment, control section power, and DC power modulation contained in power grid fault contingency plans and dispatch control management procedures;

[0036] Knowledge is extracted from the power grid fault handling plan, and the extracted data is used to establish a handling plan database by applying the established decision knowledge graph method.

[0037] As a further improvement of the present invention, the evaluation of the set of disposal schemes through the evaluation system of the power grid operation simulation scheme compilation results to obtain the optimal disposal scheme includes:

[0038] The set of handling solutions is searched and evaluated based on knowledge reasoning. When the search and evaluation results match and satisfy the rules in the rule set, the fault handling solution is output.

[0039] Based on the evaluation system for the results of the power grid operation simulation scheme, the fault handling scheme with the highest score is selected as the optimal handling scheme; the evaluation system for the results of the power grid operation simulation scheme is as follows:

[0040] Score i =w e S ei +w o S oi

[0041] In the formula, Score i To determine the overall score of the treatment plan Ai, w e and w o S represents the weights of electrical and non-electrical indicators. ei and S oi The electrical and non-electrical performance scores for the solution Ai;

[0042] Electrical indicator score S ei It is the sum of electrical performance indicators, including the number of devices exceeding limits, the percentage of power exceeding limits, the number of heavily loaded devices, the percentage of heavily loaded devices, and the total network loss; non-electrical performance indicators S oi It is the sum of non-electrical indicator scores, including the number of operation steps and the scope of dispatch; S ei and S oi The weighted sums are used to obtain the overall score of the solution Ai. i All disposal plans are selected based on their comprehensive scores, with the highest score being chosen as the optimal disposal plan in the power grid operation simulation scheme.

[0043] As a further improvement of the present invention, the initial operation mode of the power grid operation simulation scheme, the preset faults of the power grid operation simulation scheme, and the optimal handling scheme are combined to form a preliminary power grid operation simulation scheme; the preliminary power grid operation simulation schemes are classified according to the power grid operation simulation theme to generate a power grid operation simulation scheme library, specifically including:

[0044] The generated power grid operation simulation scheme pre-sets faults and optimal handling schemes are converted into power grid operation simulation scheme events step by step; a device fault in the pre-set faults of the power grid operation simulation scheme is a power grid operation simulation scheme event, and a dispatch operation in the optimal handling scheme is a power grid operation simulation scheme event. They are sorted in chronological order to form a power grid operation simulation scheme event sequence; the result of the scheme event triggering is a change in the operating status of power grid equipment, including switch opening and closing, generator output change, and load power change.

[0045] Based on 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 changes in the power grid operation state before and after the faults.

[0046] The generated power grid operation simulation schemes are categorized according to the power grid operation simulation theme to create a power grid operation simulation scheme library.

[0047] Secondly, the present invention provides an automatic construction system for a power grid operation simulation scheme library, comprising:

[0048] The initial operation mode generation module is used to acquire and parse the power grid operation simulation theme and the power grid operation simulation scheme constraints, combine the power grid physical model and data to extract the power grid feature model, and generate the initial operation mode of the power grid operation simulation scheme based on the cross section matching algorithm.

[0049] The preset fault generation module is used to generate different preset faults for different power grid operation simulation themes for fault handling.

[0050] The optimal disposal plan generation module is used to obtain a set of disposal plans based on the scheduling knowledge base and the disposal plan base by using knowledge reasoning. The set of disposal plans is evaluated by the power grid operation simulation plan compilation result evaluation system to obtain the optimal disposal plan.

[0051] The simulation scheme library generation module is used to combine the initial operation mode of the power grid operation simulation scheme, the preset faults of the power grid operation simulation scheme, and the optimal handling scheme to form a preliminary power grid operation simulation scheme; and to classify the preliminary power grid operation simulation scheme according to the power grid operation simulation theme to generate a power grid operation simulation scheme library.

[0052] 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;

[0053] The normal operation power grid simulation scheme includes topics such as bus voltage exceeding limits, line power exceeding limits, load power exceeding limits, load loss, and changes in operating mode.

[0054] The power grid operation simulation scheme for fault handling includes DC faults, AC faults, and cascading faults.

[0055] The constraints 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 interconnection lines, the power of key sections, the output of key generators, the power of key DC systems, the power of key loads, and the commissioning status of key equipment. The constraints of the power grid operation simulation scheme are set based on the topology of the power grid equipment and the operating status of the power grid equipment, and the effective constraints of the power grid operation simulation scheme are used as the power grid characteristic model.

[0056] 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 cross-section matching algorithm includes:

[0057] The similarity matching algorithm is used to perform similarity matching with historical state estimated cross sections. The similarity matching method is as follows:

[0058] SIM t =α i C it

[0059] In the formula, SIM t C represents the degree of matching between the power grid section at historical time t and the operating section required by the power grid operation simulation scheme. it Let α be the degree of matching between the i-th constraint required by the power grid operation simulation scheme and the section at time t. i This represents the weighting coefficient of the i-th constraint.

[0060] Select SIM t The state estimation section at time t, representing the minimum value, serves as the original operating mode in the power grid operation simulation scheme. The original operating mode is adjusted according to the constraints of the power grid operation simulation scheme, and power flow calculations are used to verify whether the original operating mode satisfies power flow convergence. If the power flow does not converge, the constraints of the power grid operation simulation scheme need to be changed, based on C... it Using the score as a reference, modify C. it The constraint condition of the power grid operation simulation scheme corresponding to the item with the smaller score; the adjusted state estimation section that satisfies power flow convergence is used as the initial operation mode of the power grid operation simulation scheme.

[0061] As a further improvement of the present invention, the preset fault generation module, which generates different preset faults for different power grid operation simulation themes for different fault handling, includes:

[0062] The power grid fault handling plan includes substation overview, fault phenomena, and emergency response measures data;

[0063] Knowledge extraction from fault handling plans is performed using keyword extraction via regular expressions.

[0064] The extracted faults are categorized into DC faults, AC faults, and cascading faults, which are preset faults in the power grid operation simulation scheme, to form a preset fault database.

[0065] Based on the equipment type, the preset fault database is expanded; for different power grid operation simulation themes for fault handling, faults that meet the requirements are randomly selected from the expanded preset fault database to generate different preset faults for power grid operation simulation schemes.

[0066] As a further improvement of the present invention, in the preset fault generation module, after generating preset faults for different power grid operation simulation schemes, the method further includes:

[0067] Based on the extracted power grid feature model, combined with the preset faults in the power grid operation simulation scheme, topology calculation and power flow calculation are performed. The power grid operating condition data before and after the fault and the preset faults in the power grid operation simulation scheme are used as the feature model of the power grid operation simulation scheme.

[0068] As a further improvement of the present invention, in the optimal disposal solution generation module, the step of obtaining a set of disposal solutions based on the scheduling knowledge base and the disposal solution base using knowledge reasoning includes:

[0069] The power grid fault handling plan is analyzed, which is divided into the anticipated faults in the plan, the initial operation mode of the power grid in the plan, the operation mode after the fault in the plan, and the measures that affect the fault handling plan.

[0070] Knowledge is extracted from the analyzed power grid fault handling plan, and a handling plan database is established by using the decision knowledge graph method for knowledge reasoning.

[0071] As a further improvement of the present invention, in the optimal handling scheme generation module, the step of extracting knowledge from the parsed power grid fault handling plan and establishing a handling scheme library using the decision knowledge graph method includes:

[0072] Deep learning methods are used to identify entities in power grid dispatch control and management procedures, improve the dispatch knowledge base, and establish a decision knowledge graph.

[0073] The decision knowledge graph is established as follows:

[0074] DG = (E, C, R, A)

[0075] DG is the decision knowledge graph engine; E is the set of entities for power grid operation conditions, including power grid topology and power flow result data, E = {e1, e2, ..., em}, including circuit breaker, disconnector status, load power, generator output, line power, transformer power, cross-sectional power, bus voltage, number of generators in operation, and number of synchronous condensers in operation; C is the set of condition definitions, which is the set of power grid operation modes, C = {c1, c2, ..., cl}; R is the set of rules, which are the rules for triggering operations to meet condition C, and are generated by knowledge extraction, knowledge fusion, and knowledge reasoning based on power grid fault contingency plans and dispatch control management procedures; A is the set of fault handling dispatch operations, A = {a1, a2, ..., an}, including disconnector switching operations, unit output adjustment, power plant output adjustment, substation and regional load power adjustment, control section power, and DC power modulation contained in power grid fault contingency plans and dispatch control management procedures;

[0076] Knowledge is extracted from the power grid fault handling plan, and the extracted data is used to establish a handling plan database by applying the established decision knowledge graph method.

[0077] As a further improvement of the present invention, in the optimal disposal solution generation module, the step of evaluating the set of disposal solutions through the power grid operation simulation scheme compilation result evaluation system to obtain the optimal disposal solution includes:

[0078] The set of handling solutions is searched and evaluated based on knowledge reasoning. When the search and evaluation results match and satisfy the rules in the rule set, the fault handling solution is output.

[0079] Based on the evaluation system for the results of the power grid operation simulation scheme, the fault handling scheme with the highest score is selected as the optimal handling scheme; the evaluation system for the results of the power grid operation simulation scheme is as follows:

[0080] Score i =w e S ei +w o S oi

[0081] In the formula, Score i To determine the overall score of the treatment plan Ai, w e and w o S represents the weights of electrical and non-electrical indicators. ei and S oi The electrical and non-electrical performance scores for the solution Ai;

[0082] Electrical indicator score S ei It is the sum of electrical performance indicators, including the number of devices exceeding limits, the percentage of power exceeding limits, the number of heavily loaded devices, the percentage of heavily loaded devices, and the total network loss; non-electrical performance indicators Soi It is the sum of non-electrical indicator scores, including the number of operation steps and the scope of dispatch; S ei and S oi The weighted sums are used to obtain the overall score of the solution Ai. i All disposal plans are selected based on their comprehensive scores, with the highest score being chosen as the optimal disposal plan in the power grid operation simulation scheme.

[0083] 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 handling scheme are combined to form a preliminary power grid operation simulation scheme; the preliminary power grid operation simulation schemes are classified according to the power grid operation simulation theme to generate a power grid operation simulation scheme library, specifically including:

[0084] The generated power grid operation simulation scheme pre-sets faults and optimal handling schemes are converted into power grid operation simulation scheme events step by step; a device fault in the pre-set faults of the power grid operation simulation scheme is a power grid operation simulation scheme event, and a dispatch operation in the optimal handling scheme is a power grid operation simulation scheme event. They are sorted in chronological order to form a power grid operation simulation scheme event sequence; the result of the scheme event triggering is a change in the operating status of power grid equipment, including switch opening and closing, generator output change, and load power change.

[0085] Based on 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 changes in the power grid operation state before and after the faults.

[0086] The generated power grid operation simulation schemes are categorized according to the power grid operation simulation theme to create a power grid operation simulation scheme library.

[0087] Thirdly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the automatic construction method for the power grid operation simulation scheme library.

[0088] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the automatic construction method for the power grid operation simulation scheme library.

[0089] Compared with the prior art, the present invention has the following beneficial effects:

[0090] This invention proposes an automatic construction method for a power grid operation simulation scheme library. Based on a selected power grid operation simulation theme, it automatically generates customized power grid operation simulation schemes, including the initial operation mode, preset faults, and handling plans, and categorizes them into a customized power grid operation simulation scheme library. The method automatically generates customized power grid operation simulation schemes based on the selected power grid operation simulation theme and categorizes them into a customized power grid operation simulation scheme library. It utilizes a cross-section matching algorithm to perform similarity matching with historical state estimation cross-sections to obtain the state estimation cross-section with the highest similarity. Based on this, the operation mode is adjusted to generate the initial operation mode of the customized power grid operation simulation scheme. After generating preset faults, the optimal handling plan is obtained based on a decision knowledge graph using knowledge reasoning methods. Combining the initial operation mode, preset faults, and handling plans of the power grid operation simulation scheme, the method generates customized power grid operation simulation schemes, realizing the automatic generation of power grid operation simulation schemes and reducing the workload of instructors. Through an automated and intelligent power grid operation simulation scheme generation process, the method reduces the workload of instructors and provides dispatchers with a large number of categorized and practical power grid operation simulation schemes.

[0091] Furthermore, this invention proposes a method for generating fault handling plans based on a dispatch knowledge base and a handling plan library. Based on power grid fault handling plans and power grid dispatch control management procedures, a dispatch knowledge base and a handling plan library are constructed using knowledge extraction, knowledge fusion, and knowledge reasoning methods. The optimal handling plan is obtained by evaluating the results of power grid operation simulation schemes based on preset faults. This method meets the needs of dispatchers for specific training and exercise content in online training and assists dispatchers in conducting training without instructor guidance.

[0092] Furthermore, the automatic construction system for the power grid operation simulation scheme library of the present invention allows dispatchers to use DTS to launch the customized power grid operation simulation scheme, enabling them to conduct power grid dispatching simulation and training anytime, anywhere, independently and on demand, without the need for instructors, thereby improving dispatchers' dispatching skills and professional competence. Attached Figure Description

[0093] Figure 1 This is a flowchart of an automatic construction method for a power grid operation simulation scheme library according to the present invention;

[0094] Figure 2 A flowchart illustrating a method for automatically constructing a power grid operation simulation scheme library;

[0095] Figure 3 Automatically generate flowcharts for customized power grid operation simulation schemes;

[0096] Figure 4 This constitutes a library of customized power grid operation simulation solutions;

[0097] Figure 5A schematic diagram of the automatic construction system for the power grid operation simulation scheme library provided by this invention;

[0098] Figure 6 Automatically generate system structure diagrams for customized power grid operation simulation scheme library;

[0099] Figure 7 This is a schematic diagram of an electronic device provided by the present invention. Detailed Implementation

[0100] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0101] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0102] Terminology Explanation

[0103] 1) Dispatcher Training Simulator (DTS).

[0104] The Dispatcher Training Simulation (DTS) is a digital simulation system that uses computer technology to create a mathematical model of the actual power system. It reproduces various dispatching operations and system conditions after faults, and transmits this information to the model in the power system control center. This provides dispatchers with a realistic training environment, achieving the goal of providing dispatchers with immersive practical training without affecting the actual operation of the power system. DTS is the best tool for power grid training and research analysis.

[0105] 2) Instructor: The instructor is responsible for monitoring, controlling and evaluating the power grid operation simulation process. He is usually an experienced dispatcher.

[0106] 3) Trainees: Dispatchers or other personnel who participate in power grid operation simulation and receive training to improve their dispatching skills and business level.

[0107] Currently, there is a severe shortage of power grid operation simulation solutions. These solutions often target specific fault types and lack systematic classification and management, failing to meet the needs of dispatchers for specific power grid operation simulations during operation drills and training. This results in unsystematic and insufficient learning and training for dispatchers. Furthermore, inexperienced trainees are unfamiliar with the power grid structure and complex faults, requiring instructors to be fully involved in dispatch drills and training to complete the exercises without fault solutions.

[0108] In addition, the current DTS power grid operation simulation schemes rely on manual creation. Instructors not only need to set the initial operation mode of the power grid, but also need to verify the standard handling schemes in the DTS simulation. If the verification fails, the initial cross-section needs to be repeatedly adjusted, which makes the instructors' workload heavy. The process of creating power grid operation simulation schemes is time-consuming and laborious, and it is not possible to create power grid operation simulation schemes in a timely manner to meet the needs of dispatchers' self-training exercises. There is an urgent need to build an automated and intelligent power grid operation simulation scheme generation system to automatically generate training and exercise power grid operation simulation schemes and fault handling schemes, thereby reducing the workload of instructors.

[0109] like Figure 1 As shown in the figure, this invention proposes a method and system for automatically constructing a power grid operation simulation scheme library, including:

[0110] S1: Obtain and parse the power grid operation simulation theme and the power grid operation simulation scheme constraints, 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 cross section matching algorithm;

[0111] S2 generates different power grid operation simulation schemes with preset faults for different power grid operation simulation themes for fault handling;

[0112] S3: Based on the scheduling knowledge base and the disposal plan base, a set of disposal plans is obtained by using knowledge reasoning. The set of disposal plans is evaluated by the power grid operation simulation plan compilation result evaluation system to obtain the optimal disposal plan.

[0113] S4, 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 handling scheme to form a preliminary power grid operation simulation scheme; classify the preliminary power grid operation simulation scheme according to the power grid operation simulation theme to generate a power grid operation simulation scheme library.

[0114] The system automatically generates customized power grid operation simulation schemes based on the selected fault type, including the operation mode of the power grid operation simulation scheme, preset faults, and fault handling schemes. This allows dispatchers to conduct drills and training simulations using customized power grid operation simulation schemes without instructors, reducing instructors' workload and improving training efficiency and effectiveness. Applying the customized power grid operation simulation scheme library to advanced power grid applications such as DTS can enhance the practicality and intelligence of the DTS system.

[0115] Example 1

[0116] The steps of each embodiment of the present invention will be described in detail below.

[0117] In the above embodiments, in step S1, the power grid operation simulation topic includes a normal operation power grid operation simulation scheme topic and a fault handling power grid operation simulation scheme topic;

[0118] The normal operation power grid simulation scheme includes topics such as bus voltage exceeding limits, line power exceeding limits, load power exceeding limits, load loss, and changes in operating mode.

[0119] The power grid operation simulation scheme for fault handling includes DC faults, AC faults, and cascading faults.

[0120] The constraints 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 interconnection lines, the power of key sections, the output of key generators, the power of key DC systems, the power of key loads, and the commissioning status of key equipment. The constraints of the power grid operation simulation scheme are set based on the topology of the power grid equipment and the operating status of the power grid equipment, and the effective constraints of the power grid operation simulation scheme are used as the power grid characteristic model.

[0121] In the above embodiments, step S1, which involves generating the initial operating mode of the power grid operation simulation scheme based on the cross-section matching algorithm, includes:

[0122] The similarity matching algorithm is used to perform similarity matching with historical state estimated cross sections. The similarity matching method is as follows:

[0123] SIM t =α i C it

[0124] In the formula, SIM t C represents the degree of matching between the power grid section at historical time t and the operating section required by the power grid operation simulation scheme. it Let α be the degree of matching between the i-th constraint required by the power grid operation simulation scheme and the section at time t. i This represents the weighting coefficient of the i-th constraint.

[0125] Select SIMt The state estimation section at time t, representing the minimum value, serves as the original operating mode in the power grid operation simulation scheme. The original operating mode is adjusted according to the constraints of the power grid operation simulation scheme, and power flow calculations are used to verify whether the original operating mode satisfies power flow convergence. If the power flow does not converge, the constraints of the power grid operation simulation scheme need to be changed, based on C... it Using the score as a reference, modify C. it The constraint condition of the power grid operation simulation scheme corresponding to the item with the smaller score; the adjusted state estimation section that satisfies power flow convergence is used as the initial operation mode of the power grid operation simulation scheme.

[0126] In the above embodiments, step S2, which involves generating different power grid operation simulation schemes with preset faults for different power grid operation simulation themes for fault handling, includes:

[0127] The power grid fault handling plan includes substation overview, fault phenomena, and emergency response measures data;

[0128] Knowledge extraction from fault handling plans is performed using keyword extraction via regular expressions.

[0129] The extracted faults are categorized into DC faults, AC faults, and cascading faults, which are preset faults in the power grid operation simulation scheme, to form a preset fault database.

[0130] Based on the equipment type, the preset fault database is expanded; for different power grid operation simulation themes for fault handling, faults that meet the requirements are randomly selected from the expanded preset fault database to generate different preset faults for power grid operation simulation schemes.

[0131] In the above embodiments, after generating different power grid operation simulation schemes with preset faults in step S2, the method further includes:

[0132] Based on the extracted power grid feature model, combined with the preset faults in the power grid operation simulation scheme, topology calculation and power flow calculation are performed. The power grid operating condition data before and after the fault and the preset faults in the power grid operation simulation scheme are used as the feature model of the power grid operation simulation scheme.

[0133] In the above embodiments, step S3, which involves obtaining a set of disposal solutions based on the scheduling knowledge base and the disposal solution base using knowledge reasoning, includes:

[0134] The power grid fault handling plan is analyzed, which is divided into the anticipated faults in the plan, the initial operation mode of the power grid in the plan, the operation mode after the fault in the plan, and the measures that affect the fault handling plan.

[0135] Knowledge is extracted from the analyzed power grid fault handling plan, and a handling plan database is established by using the decision knowledge graph method for knowledge reasoning.

[0136] In the above embodiment, step S3, which involves extracting knowledge from the parsed power grid fault handling plan and establishing a handling plan library using a decision knowledge graph method, includes:

[0137] Deep learning methods are used to identify entities in power grid dispatch control and management procedures, improve the dispatch knowledge base, and establish a decision knowledge graph.

[0138] The decision knowledge graph is established as follows:

[0139] DG = (E, C, R, A)

[0140] DG is the decision knowledge graph engine; E is the set of entities for power grid operation conditions, including power grid topology and power flow result data, E = {e1, e2, ..., em}, including circuit breaker, disconnector status, load power, generator output, line power, transformer power, cross-sectional power, bus voltage, number of generators in operation, and number of synchronous condensers in operation; C is the set of condition definitions, which is the set of power grid operation modes, C = {c1, c2, ..., cl}; R is the set of rules, which are the rules for triggering operations to meet condition C, and are generated by knowledge extraction, knowledge fusion, and knowledge reasoning based on power grid fault contingency plans and dispatch control management procedures; A is the set of fault handling dispatch operations, A = {a1, a2, ..., an}, including disconnector switching operations, unit output adjustment, power plant output adjustment, substation and regional load power adjustment, control section power, and DC power modulation contained in power grid fault contingency plans and dispatch control management procedures;

[0141] Knowledge is extracted from the power grid fault handling plan, and the extracted data is used to establish a handling plan database by applying the established decision knowledge graph method.

[0142] In the above embodiment, step S3, which involves evaluating the set of disposal schemes through a power grid operation simulation scheme compilation result evaluation system to obtain the optimal disposal scheme, includes:

[0143] The set of handling solutions is searched and evaluated based on knowledge reasoning. When the search and evaluation results match and satisfy the rules in the rule set, the fault handling solution is output.

[0144] Based on the evaluation system for the results of the power grid operation simulation scheme, the fault handling scheme with the highest score is selected as the optimal handling scheme; the evaluation system for the results of the power grid operation simulation scheme is as follows:

[0145] Score i =w e S ei +w o S oi

[0146] In the formula, Score i To determine the overall score of the treatment plan Ai, w e and w o S represents the weights of electrical and non-electrical indicators. ei and S oi The electrical and non-electrical performance scores for the solution Ai;

[0147] Electrical indicator score S ei It is the sum of electrical performance indicators, including the number of devices exceeding limits, the percentage of power exceeding limits, the number of heavily loaded devices, the percentage of heavily loaded devices, and the total network loss; non-electrical performance indicators S oi It is the sum of non-electrical indicator scores, including the number of operation steps and the scope of dispatch; S ei and S oi The weighted sums are used to obtain the overall score of the solution Ai. i All disposal plans are selected based on their comprehensive scores, with the highest score being chosen as the optimal disposal plan in the power grid operation simulation scheme.

[0148] In the above embodiments, step S4, which involves 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 handling 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, specifically includes:

[0149] The generated power grid operation simulation scheme pre-sets faults and optimal handling schemes are converted into power grid operation simulation scheme events step by step; a device fault in the pre-set faults of the power grid operation simulation scheme is a power grid operation simulation scheme event, and a dispatch operation in the optimal handling scheme is a power grid operation simulation scheme event. They are sorted in chronological order to form a power grid operation simulation scheme event sequence; the result of the scheme event triggering is a change in the operating status of power grid equipment, including switch opening and closing, generator output change, and load power change.

[0150] Based on 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 changes in the power grid operation state before and after the faults.

[0151] The generated power grid operation simulation schemes are categorized according to the power grid operation simulation theme to create a power grid operation simulation scheme library.

[0152] Example 2

[0153] The various steps of the present invention will be described in detail below with reference to optional embodiments.

[0154] like Figure 2 and Figure 3 As shown, this invention proposes a method and system for automatically constructing a power grid operation simulation scheme library. The automatically generated power grid operation simulation scheme includes the initial operation mode of the power grid, preset faults, and fault handling schemes. It includes:

[0155] First, by acquiring and analyzing the power grid operation simulation theme and the constraints of the power grid operation simulation scheme, and combining the power grid physical model and the data extraction power grid feature model, the initial operation mode of the power grid is generated based on the cross section matching algorithm.

[0156] Secondly, generate preset faults for the power grid operation simulation scheme and improve the feature model of the power grid operation simulation scheme;

[0157] Then, based on the scheduling knowledge base and the disposal plan base, the disposal plan is obtained by knowledge reasoning, and the customized optimal disposal plan is obtained by the evaluation system of the power grid operation simulation plan compilation results.

[0158] Finally, the initial operation mode, preset faults, and optimal handling schemes of the power grid operation simulation scheme are combined to form a customized power grid operation simulation scheme. A customized power grid operation simulation scheme library is generated by classifying the power grid operation simulation themes.

[0159] The customized power grid operation simulation scheme library generated by this invention can be applied to advanced applications such as DTS to realize power grid operation simulation and training exercises, thereby improving the dispatching skills and business level of dispatching operators.

[0160] Example 3

[0161] like Figure 2 The flowchart of the automatic construction method for the power grid operation simulation scheme library provided in this embodiment includes the following steps:

[0162] 1) Select the power grid operation simulation theme.

[0163] The customized power grid operation simulation scheme includes the initial operation mode of the power grid, preset faults, and fault handling schemes. The normal operation power grid operation simulation scheme only involves normal dispatch operations, so the preset faults are empty. The fault handling scheme includes all parts of the customized power grid operation simulation scheme.

[0164] 2) Input the constraints of the power grid operation simulation scheme.

[0165] By acquiring and analyzing the power grid operation simulation theme and the constraints of the power grid operation simulation scheme, and combining the power grid model and data to extract the power grid feature model, the initial operation mode of the power grid is generated based on the cross section matching algorithm.

[0166] 3) Generate preset faults for the power grid operation simulation scheme and improve the feature model of the power grid operation simulation scheme.

[0167] For the power grid operation simulation scheme theme of fault handling, different types of preset faults are generated according to the different fault handling themes. Based on the power grid characteristic model in step 2) and the power grid operation simulation scheme theme, the power grid operation simulation scheme characteristic model is improved, and a power grid characteristic model that can be used for subsequent scheduling knowledge reasoning is generated.

[0168] 4) Based on the scheduling knowledge base and the disposal scheme base, disposal schemes are obtained by using knowledge reasoning, and a result evaluation system is developed based on the power grid operation simulation scheme. The disposal scheme with the highest score is selected as the optimal disposal scheme.

[0169] 5) Combining the initial operation mode, preset faults and optimal handling schemes of the power grid operation simulation scheme generated in steps 2), 3), and 4), generate a customized power grid operation simulation scheme, and classify it according to the power grid operation simulation theme to generate a customized power grid operation simulation scheme library.

[0170] Based on the method provided in this embodiment, the power grid operation simulation scheme library generated by this system is applied to DTS, enabling dispatchers to conduct power grid dispatch simulation and self-training without instructors, thereby improving dispatchers' dispatching skills and professional competence.

[0171] In the above embodiments of the present invention, such as Figure 3 The steps for automatically generating customized power grid operation simulation schemes are detailed below:

[0172] Step 1) is to select a power grid operation simulation theme, including power grid operation simulation scheme themes such as normal operation and fault handling.

[0173] The normal operation power grid simulation scheme is used to familiarize users with the power grid structure and train basic dispatch operations, and to solve the risks of power grid exceeding limits, load loss and changes in power grid operation mode. The preset faults are empty, that is, no preset faults are included: (1) system frequency exceeding limits; (2) bus voltage exceeding limits; (3) line power exceeding limits and load power exceeding limits; (4) load loss; (5) change in operation mode.

[0174] The fault handling power grid operation simulation program is used to train fault handling capabilities and requires preset faults. The fault handling topics include: DC faults, current faults, and cascading faults.

[0175] In the above embodiments of the present invention, step 2) involves inputting constraints for the power grid operation simulation scheme. Constraints for the power grid operation simulation scheme are set based on the power grid equipment topology and operating status, including total grid load, total grid generation, power of key tie lines, power of key sections, output of key generators, power of key DC systems, power of key loads, and operational status of key equipment.

[0176] All or some constraints can be selected as constraints for the customized power grid operation simulation scheme, and the effective constraints of the power grid operation simulation scheme are used as the power grid characteristic model. To ensure good power flow convergence and rationality in the initial operation mode and subsequent scheduling operations of the power grid operation simulation scheme, it is necessary to select the state estimation section most similar to the constraints of the power grid operation simulation scheme as the original power grid operation mode. Adjustments are then made on the original operation mode to generate the initial operation mode of the power grid operation simulation scheme. A section matching algorithm is used to perform similarity matching with historical state estimation sections (generally QS files). The similarity matching formula is as follows:

[0177] SIM t =α i C it

[0178] SIM t C represents the degree of matching between the power grid section at historical time t and the operating section required by the power grid operation simulation scheme. it Let α be the degree of matching between the i-th constraint required by the power grid operation simulation scheme and the section at time t. i C represents the weighting coefficient of the i-th constraint. it The calculation method is as follows, where "||" represents the absolute value of the value:

[0179]

[0180] Select SIM t The state estimation section at time t, representing the minimum value, serves as the original operating mode in the power grid operation simulation scheme. The original operating mode is adjusted according to the constraints of the power grid operation simulation scheme to ensure it meets these constraints. Power flow calculations verify that it satisfies power flow convergence. If power flow does not converge, the constraints of the power grid operation simulation scheme need to be changed, based on C... it The score should be used as a reference; students can focus on revising their C. it The constraint condition of the power grid operation simulation scheme with the lower score. The adjusted section that satisfies power flow convergence is used as the initial operating mode of the power grid operation simulation scheme.

[0181] In the above embodiments of the present invention, step 3) generates preset faults for the power grid operation simulation scheme based on the fault theme and the power grid fault handling plan, thereby improving the feature model of the power 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 response measures.

[0182] Because the fault handling plans are relatively well-organized, with uniform content and consistent editing format, they belong to semi-structured data. Knowledge extraction can be achieved through keyword extraction using regular expressions. The extracted faults are categorized into three types based on the preset faults in the power grid operation simulation scheme: DC faults, AC faults, and cascading faults, forming a preset fault database. The specific types of preset faults are as follows:

[0183] 1) DC Faults: The topic of DC faults mainly involves DC system faults, including grounding and open circuit faults in DC lines, valve group faults, converter transformer faults, and AC field faults. Among them, valve group faults include single-pole blocking and double-pole blocking.

[0184] 2) AC faults: including equipment faults such as transformers, busbars, AC lines, generators, and switches.

[0185] 3) Chain reaction faults: These are cascading faults in power systems where a failure in one piece of equipment leads to the shutdown of a series of other devices. They are considered relatively complex faults in power systems. For example, if a line switch fails to operate, a line fault may cause the transformer protection to trip, resulting in transformer de-energization.

[0186] In addition, the preset fault database can be expanded according to the type of equipment to increase the diversity of faults in the power grid operation simulation scheme.

[0187] For example, if the AC fault category in the original contingency plan database includes transformer A grounding fault, then transformer B grounding fault can be added to the preset fault database as an expanded fault.

[0188] For different power grid operation simulation themes for fault handling, preset faults that meet the requirements are randomly selected from the preset fault database to generate preset faults for customized power grid operation simulation schemes.

[0189] Based on the power grid feature model generated in step 2), and combined with the preset faults in the power grid operation simulation scheme, topology calculation and power flow calculation are performed. The power grid operating condition data before and after the fault (such as power grid topology, power flow results, operation mode, etc.) and the preset faults in the power grid operation simulation scheme are used as the feature model of the power grid operation simulation scheme, which can be used for subsequent scheduling knowledge reasoning.

[0190] In the above embodiments of the present invention, step 4) first obtains a disposal plan based on the scheduling knowledge base and the disposal plan base, specifically including:

[0191] The power grid fault handling plan is analyzed. Generally, the plan is divided into anticipated faults, the initial operation mode of the power grid, the post-fault operation mode, and measures affecting the fault handling plan. The anticipated faults have already been extracted in step 2) and used as preset faults in the power grid operation simulation scheme to form a preset fault database. Knowledge extraction is performed on the power grid fault handling plan, and a scheduling knowledge base and a handling plan database are established using decision knowledge graph methods. Specifically, this includes:

[0192] The power grid dispatch control and management regulations are the procedures and rules upon which power grid dispatch control and management work is based, and serve as important auxiliary decision-making reference data in power grid fault handling. This data is unstructured, containing only Chinese text describing fault conditions and specific operations, without fixed word frequencies or keywords. The diverse descriptive formats make it difficult to extract information using regular expressions, and the data volume is relatively small. Therefore, deep learning technology is employed to perform entity recognition on this type of small-sample data in the power grid field, thereby improving the dispatch knowledge base and fault handling solution database.

[0193] The specific solution provided in this embodiment is as follows: using deep learning methods to perform entity recognition on power grid dispatch control and management procedures, improving the dispatch knowledge base, and establishing a decision knowledge graph;

[0194] The decision knowledge graph (DG) is constructed as follows:

[0195] DG = (E, C, R, a)

[0196] DG is the decision knowledge graph engine; E is the set of entities for power grid operation conditions, including power grid topology and power flow result data, E = {e1, e2, ..., em}, including circuit breaker, disconnector opening status, load power, generator output, line power, transformer power, cross-sectional power, bus voltage, number of generators in operation, number of synchronous condensers in operation, etc.; C is the set of condition definitions, which is the set of power grid operation modes, C = {c1, c2, ..., cl}; R is the set of rules, which are the rules for triggering operations to meet condition C, and are generated by knowledge extraction, knowledge fusion, and knowledge reasoning based on power grid fault contingency plans and dispatch control management procedures; A is the set of actions, i.e. the set of fault handling dispatch operations, A = {a1, a2, ..., an}, including disconnector switching operations, adjusting unit output, adjusting power plant output, adjusting substation and regional load power, control section power, and DC power modulation, etc., contained in power grid fault contingency plans and dispatch control management procedures.

[0197] Based on the constructed decision knowledge graph, the power grid operation simulation scheme feature model generated according to step 3) is input into the decision engine as the power grid operation condition entity E and the operation mode before and after the fault as condition C. Based on knowledge reasoning, intelligent search and evaluation are performed according to the rule set R. When a certain set of rules in the rule set is matched and satisfied, the action set A1~An is output as the fault handling scheme.

[0198] In the above embodiments of the present invention, after obtaining the disposal schemes A1 to An in step 4), an evaluation system for the results of the power grid operation simulation scheme is established, and the disposal scheme with the highest score is selected as the optimal disposal scheme. The evaluation system for the results of the power grid operation simulation scheme is as follows:

[0199] Score i = e S ei + o S oi

[0200] Score i To determine the overall score of the treatment plan Ai, w e and w o S represents the weights of electrical and non-electrical indicators. ei and S oi The electrical and non-electrical performance scores are used to determine the handling plan Ai.

[0201] The above electrical indicator score S ei This includes the sum of electrical indicators such as the number of devices exceeding limits, the percentage of power exceeding limits, the number of heavily loaded devices, the percentage of heavily loaded devices, and the total network loss; and non-electrical indicators S. oi The total score includes non-electrical indicators such as the number of operation steps and the scope of dispatch. ei and S oi The weighted sums are used to obtain the overall score of the solution Ai. i The optimal solution is selected based on the comprehensive score of all solutions, with the highest score being the most customized power grid operation simulation solution.

[0202] In addition, the minimum score for the power grid operation simulation scheme is set to γ. When the score is less than γ, the instructor can manually correct it to improve the dispatch knowledge base and the disposal scheme base.

[0203] In summary, combining the initial operation mode, preset faults, and optimal handling schemes of the power grid operation simulation scheme generated in steps 2), 3), and 4), a customized power grid operation simulation scheme is generated, specifically including:

[0204] The preset faults and optimal handling schemes generated in steps 3) and 4) are transformed into power grid operation simulation scheme events step by step. In the preset faults, one equipment fault constitutes one power grid operation simulation scheme event, and in the optimal handling scheme, one dispatch operation constitutes one power grid operation simulation scheme event. These events are ordered chronologically to form a sequence of power grid operation simulation scheme events. The result of triggering these scheme events is a change in the operating state of power grid equipment, including switch opening and closing, generator output changes, and load power changes.

[0205] After the DTS training exercise is launched, based on the initial operation mode of the power grid operation simulation scheme generated in step 2), 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 changes in the power grid operation state before and after the fault.

[0206] Dispatchers can conduct customized training exercises on power grid operation simulation schemes based on the handling plans for events in the power grid operation simulation scheme. For normal operation power grid operation simulation scheme topics, no faults are triggered because the preset faults are empty.

[0207] This embodiment constructs a dispatch knowledge base and a disposal plan base based on power grid fault handling plans and power grid dispatch control management procedures, using knowledge extraction, knowledge fusion and knowledge reasoning methods. Based on preset faults, it obtains the optimal disposal plan through the evaluation system of power grid operation simulation plan compilation results. It can meet the needs of dispatchers for specific training and exercise content in online training, and assist dispatchers in conducting training without instructor guidance.

[0208] Of course, the solution given in this embodiment is a preferred solution and not a specific solution. Other means that achieve the same purpose as knowledge extraction can also achieve the purpose of this embodiment, and no specific limitation is made here.

[0209] See details Figure 4 This constitutes a customized power grid operation simulation scheme library. The generated power grid operation simulation schemes are categorized according to power grid operation simulation themes to create the customized power grid operation simulation scheme library.

[0210] Furthermore, based on 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 drills and training can be carried out according to the relevant theme.

[0211] like Figure 5 As shown, this invention provides an automatic construction system for a power grid operation simulation scheme library, mainly comprising:

[0212] The initial operation mode generation module is used to acquire and parse the power grid operation simulation theme and the power grid operation simulation scheme constraints, combine the power grid physical model and data to extract the power grid feature model, and generate the initial operation mode of the power grid operation simulation scheme based on the cross section matching algorithm.

[0213] The preset fault generation module is used to generate different preset faults for different power grid operation simulation themes for fault handling.

[0214] The optimal disposal plan generation module is used to obtain a set of disposal plans based on the scheduling knowledge base and the disposal plan base by using knowledge reasoning. The set of disposal plans is evaluated by the power grid operation simulation plan compilation result evaluation system to obtain the optimal disposal plan.

[0215] The simulation scheme library generation module is used to combine the initial operation mode of the power grid operation simulation scheme, the preset faults of the power grid operation simulation scheme, and the optimal handling scheme to form a preliminary power grid operation simulation scheme; and to classify the preliminary power grid operation simulation scheme according to the power grid operation simulation theme to generate a power grid operation simulation scheme library.

[0216] In the initial operation mode generation module, the power grid operation simulation topics include the normal operation power grid operation simulation scheme topic and the fault handling power grid operation simulation scheme topic;

[0217] The normal operation power grid simulation scheme includes topics such as bus voltage exceeding limits, line power exceeding limits, load power exceeding limits, load loss, and changes in operating mode.

[0218] The power grid operation simulation scheme for fault handling includes DC faults, AC faults, and cascading faults.

[0219] The constraints 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 interconnection lines, the power of key sections, the output of key generators, the power of key DC systems, the power of key loads, and the commissioning status of key equipment. The constraints of the power grid operation simulation scheme are set based on the topology of the power grid equipment and the operating status of the power grid equipment, and the effective constraints of the power grid operation simulation scheme are used as the power grid characteristic model.

[0220] In the initial operation mode generation module, the generation of the initial operation mode of the power grid operation simulation scheme based on the cross-section matching algorithm includes:

[0221] The similarity matching algorithm is used to perform similarity matching with historical state estimated cross sections. The similarity matching method is as follows:

[0222] SIM t =α i C it

[0223] In the formula, SIM t C represents the degree of matching between the power grid section at historical time t and the operating section required by the power grid operation simulation scheme. it Let α be the degree of matching between the i-th constraint required by the power grid operation simulation scheme and the section at time t. i This represents the weighting coefficient of the i-th constraint.

[0224] Select SIM t The state estimation section at time t, representing the minimum value, serves as the original operating mode in the power grid operation simulation scheme. The original operating mode is adjusted according to the constraints of the power grid operation simulation scheme, and power flow calculations are used to verify whether the original operating mode satisfies power flow convergence. If the power flow does not converge, the constraints of the power grid operation simulation scheme need to be changed, based on C...it Using the score as a reference, modify C. it The constraint condition of the power grid operation simulation scheme corresponding to the item with the smaller score; the adjusted state estimation section that satisfies power flow convergence is used as the initial operation mode of the power grid operation simulation scheme.

[0225] In the preset fault generation module, the preset faults for generating different power grid operation simulation schemes for different power grid operation simulation themes for fault handling include:

[0226] The power grid fault handling plan includes substation overview, fault phenomena, and emergency response measures data;

[0227] Knowledge extraction from fault handling plans is performed using keyword extraction via regular expressions.

[0228] The extracted faults are categorized into DC faults, AC faults, and cascading faults, which are preset faults in the power grid operation simulation scheme, to form a preset fault database.

[0229] Based on the equipment type, the preset fault database is expanded; for different power grid operation simulation themes for fault handling, faults that meet the requirements are randomly selected from the expanded preset fault database to generate different preset faults for power grid operation simulation schemes.

[0230] In the preset fault generation module, after generating preset faults for different power grid operation simulation schemes, the method further includes:

[0231] Based on the extracted power grid feature model, combined with the preset faults in the power grid operation simulation scheme, topology calculation and power flow calculation are performed. The power grid operating condition data before and after the fault and the preset faults in the power grid operation simulation scheme are used as the feature model of the power grid operation simulation scheme.

[0232] As a further improvement of the present invention, in the optimal disposal solution generation module, the step of obtaining a set of disposal solutions based on the scheduling knowledge base and the disposal solution base using knowledge reasoning includes:

[0233] The power grid fault handling plan is analyzed, which is divided into the anticipated faults in the plan, the initial operation mode of the power grid in the plan, the operation mode after the fault in the plan, and the measures that affect the fault handling plan.

[0234] Knowledge is extracted from the analyzed power grid fault handling plan, and a handling plan database is established by using the decision knowledge graph method for knowledge reasoning.

[0235] In the optimal handling plan generation module, the step of extracting knowledge from the parsed power grid fault handling plan and establishing a handling plan library using decision knowledge graph methods includes:

[0236] Deep learning methods are used to identify entities in power grid dispatch control and management procedures, improve the dispatch knowledge base, and establish a decision knowledge graph.

[0237] The decision knowledge graph is established as follows:

[0238] DG = (E, C, R, A)

[0239] DG is the decision knowledge graph engine; E is the set of entities for power grid operation conditions, including power grid topology and power flow result data, E = {e1, e2, ..., em}, including circuit breaker, disconnector status, load power, generator output, line power, transformer power, cross-sectional power, bus voltage, number of generators in operation, and number of synchronous condensers in operation; C is the set of condition definitions, which is the set of power grid operation modes, C = {c1, c2, ..., cl}; R is the set of rules, which are the rules for triggering operations to meet condition C, and are generated by knowledge extraction, knowledge fusion, and knowledge reasoning based on power grid fault contingency plans and dispatch control management procedures; A is the set of fault handling dispatch operations, A = {a1, a2, ..., an}, including disconnector switching operations, unit output adjustment, power plant output adjustment, substation and regional load power adjustment, control section power, and DC power modulation contained in power grid fault contingency plans and dispatch control management procedures;

[0240] Knowledge is extracted from the power grid fault handling plan, and the extracted data is used to establish a handling plan database by applying the established decision knowledge graph method.

[0241] In the optimal disposal solution generation module, the evaluation of the disposal solution set through the power grid operation simulation scheme compilation result evaluation system to obtain the optimal disposal solution includes:

[0242] The set of handling solutions is searched and evaluated based on knowledge reasoning. When the search and evaluation results match and satisfy the rules in the rule set, the fault handling solution is output.

[0243] Based on the evaluation system for the results of the power grid operation simulation scheme, the fault handling scheme with the highest score is selected as the optimal handling scheme; the evaluation system for the results of the power grid operation simulation scheme is as follows:

[0244] Score i =w e S ei +w o S oi

[0245] In the formula, Score i To determine the overall score of the treatment plan Ai, w e and w o S represents the weights of electrical and non-electrical indicators. ei and Soi The electrical and non-electrical performance scores for the solution Ai;

[0246] Electrical indicator score S ei It is the sum of electrical performance indicators, including the number of devices exceeding limits, the percentage of power exceeding limits, the number of heavily loaded devices, the percentage of heavily loaded devices, and the total network loss; non-electrical performance indicators S oi It is the sum of non-electrical indicator scores, including the number of operation steps and the scope of dispatch; S ei and S oi The weighted sums are used to obtain the overall score of the solution Ai. i All disposal plans are selected based on their comprehensive scores, with the highest score being chosen as the optimal disposal plan in the power grid operation simulation scheme.

[0247] In the simulation scheme library generation module, the initial operation mode of the power grid operation simulation scheme, the preset faults of the power grid operation simulation scheme, and the optimal handling scheme are combined to form a preliminary power grid operation simulation scheme; the preliminary power grid operation simulation schemes are classified according to the power grid operation simulation theme to generate a power grid operation simulation scheme library, specifically including:

[0248] The generated power grid operation simulation scheme pre-sets faults and optimal handling schemes are converted into power grid operation simulation scheme events step by step; a device fault in the pre-set faults of the power grid operation simulation scheme is a power grid operation simulation scheme event, and a dispatch operation in the optimal handling scheme is a power grid operation simulation scheme event. They are sorted in chronological order to form a power grid operation simulation scheme event sequence; the result of the scheme event triggering is a change in the operating status of power grid equipment, including switch opening and closing, generator output change, and load power change.

[0249] Based on 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 changes in the power grid operation state before and after the faults.

[0250] The generated power grid operation simulation schemes are categorized according to the power grid operation simulation theme to create a power grid operation simulation scheme library.

[0251] Based on practical examples, this invention also provides an automatic generation system structure diagram for a customized power grid operation simulation scheme library. See also... Figure 6 A customized power grid operation simulation scheme library automatic generation system can be formed based on the automatic construction method of the power grid operation simulation scheme library. This system includes:

[0252] The module includes a power grid operation simulation theme selection module, a power grid operation simulation scheme constraint setting module, an initial operation mode generation module, a preset fault generation module, a disposal scheme generation module, and a customized power grid operation simulation scheme library generation module.

[0253] The power grid operation simulation topic selection module is used to acquire and parse power grid operation simulation topics.

[0254] The power grid operation simulation scheme constraint setting module is used to acquire and parse the constraint conditions of the power grid operation simulation scheme.

[0255] The initial operation mode generation module is used to generate the initial operation mode of the power grid by acquiring and parsing the power grid operation simulation theme and the power grid operation simulation scheme constraints, combining the power grid physical model and the data extraction power grid feature model, and based on the cross section matching algorithm.

[0256] The preset fault generation module is used to generate preset faults for the power grid operation simulation scheme based on the fault handling theme; and improve the feature model of the power grid operation simulation scheme.

[0257] A pre-defined fault generation module is used to obtain a disposal plan based on the scheduling knowledge base and disposal plan base using knowledge reasoning. The results evaluation system is compiled through power grid operation simulation scheme to obtain a customized optimal disposal plan.

[0258] The module for generating a customized power grid operation simulation scheme library is used to combine the initial operation mode, preset faults, and optimal handling schemes of the power grid operation simulation scheme to form a customized power grid operation simulation scheme. It also generates a customized power grid operation simulation scheme library by classifying the power grid operation simulation themes.

[0259] The customized power grid operation simulation scheme library generation module can combine the initial operation mode, preset faults and fault handling schemes of the power grid operation simulation scheme to generate a power grid operation simulation scheme file format that can be recognized by the DTS system and classify them into a customized scheme library. Dispatchers can use the DTS system to start the schemes in the power grid operation simulation scheme library to carry out dispatch simulation, and conduct self-training anytime and anywhere without instructors, thereby improving dispatching skills and business level.

[0260] like Figure 7 As shown, a 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 executable on the processor, wherein the processor executes the computer program to implement the steps of the automatic construction method for a power grid operation simulation scheme library that takes into account the delay characteristics of multiple interactive functions.

[0261] A fourth aspect of the present invention is to provide a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the method for automatically constructing a power grid operation simulation scheme library that takes into account the delay characteristics of multiple interactive functions.

[0262] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can 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.) containing computer-usable program code.

[0263] This 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 will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0264] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0265] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0266] 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 it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for automatically constructing a power grid operation simulation scheme library, characterized in that, include: The system acquires and analyzes the power grid operation simulation topics and constraints of the power grid operation simulation scheme, extracts power grid characteristic models by combining the power grid physical model and data, and generates the initial operation mode of the power grid operation simulation scheme based on the cross-section matching algorithm; the power grid operation simulation topics include the normal operation power grid operation simulation scheme topic and the fault handling power grid operation simulation scheme topic. The normal operation power grid simulation scheme includes topics such as bus voltage exceeding limits, line power exceeding limits, load power exceeding limits, load loss, and changes in operating mode. The power grid operation simulation scheme for fault handling includes DC faults, AC faults, and cascading faults. The constraints 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 commissioning status of key equipment. The constraints of the power grid operation simulation scheme are set based on the topology of the power grid equipment and the operating status of the power grid equipment, and the effective constraints of the power grid operation simulation scheme are used as the power grid characteristic model. The initial operation mode of the power grid operation simulation scheme generated based on the cross-section matching algorithm includes: The similarity matching algorithm is used to perform similarity matching with historical state estimated cross sections. The similarity matching formula is as follows: In the formula, This represents the degree of matching between the power grid section at historical time t and the operating section required by the power grid operation simulation scheme. Let be the degree of matching between the i-th constraint required by the power grid operation simulation scheme and the section at time t. This represents the weighting coefficient of the i-th constraint. Select The state estimation section at time t, representing the minimum value, serves as the original operating mode in the power grid operation simulation scheme. The original operating mode is adjusted according to the constraints of the power grid operation simulation scheme, and power flow calculations are used to verify whether the original operating mode satisfies power flow convergence. If the power flow does not converge, the constraints of the power grid operation simulation scheme need to be changed. The score should be used as a reference for modification. The constraint condition of the power grid operation simulation scheme corresponding to the item with the smaller score; the adjusted state estimation section that satisfies power flow convergence is used as the initial operation mode of the power grid operation simulation scheme; Different power grid operation simulation schemes with preset faults are generated for different power grid operation simulation themes for fault handling; Based on the scheduling knowledge base and the disposal plan base, a set of disposal plans is obtained through knowledge reasoning. The set of disposal plans is then evaluated using a power grid operation simulation scheme development result evaluation system to obtain the optimal disposal plan; including: The power grid fault handling plan is analyzed, which is divided into the anticipated faults in the plan, the initial operation mode of the power grid in the plan, the operation mode after the fault in the plan, and the measures that affect the fault handling plan. Knowledge extraction is performed on the analyzed power grid fault handling plan, and a handling plan base is established using decision knowledge graph methods for knowledge reasoning; including: Deep learning methods are used to identify entities in power grid dispatch control and management procedures, improve the dispatch knowledge base, and establish a decision knowledge graph. The decision knowledge graph is established as follows: DG is the decision knowledge graph engine; E is the set of entities for power grid operation conditions, including power grid topology and power flow result data, E={e1, e2, …, em}, including circuit breaker, disconnector status, load power, generator output, line power, transformer power, cross-sectional power, bus voltage, number of generators in operation, and number of synchronous condensers in operation; C is the set of condition definitions, which is the set of power grid operation modes, C={c1, c2, …, cl}; R is the set of rules, which are the rules for triggering operations to meet condition C, and are generated by knowledge extraction, knowledge fusion, and knowledge reasoning based on power grid fault contingency plans and dispatch control management procedures; A is the set of fault handling dispatch operations, A={a1, a2, …, an}, including disconnector switching operations, unit output adjustment, power plant output adjustment, substation and regional load power adjustment, control section power, and DC power modulation contained in power grid fault contingency plans and dispatch control management procedures; Knowledge is extracted from the power grid fault handling plan, and the extracted data is used to establish a handling plan library by using the established decision knowledge graph method. The initial operation mode of the power grid operation simulation scheme, the preset faults of the power grid operation simulation scheme, and the optimal handling scheme are combined to form a preliminary power grid operation simulation scheme; the preliminary power grid operation simulation schemes are classified 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, characterized in that, The aforementioned method generates different power grid operation simulation schemes for different power grid operation simulation themes related to fault handling, including preset faults such as: The power grid fault handling plan includes substation overview, fault phenomena, and emergency response measures data; Knowledge extraction from fault handling plans is performed using keyword extraction via regular expressions. The extracted faults are categorized into DC faults, AC faults, and cascading faults, which are preset faults in the power grid operation simulation scheme, to form a preset fault database. Based on the equipment type, the preset fault database is expanded; for different power grid operation simulation themes for fault handling, faults that meet the requirements are randomly selected from the expanded preset fault database to generate different preset faults for power grid operation simulation schemes.

3. The method for automatically constructing a power grid operation simulation scheme library according to claim 1, characterized in that, After generating different power grid operation simulation schemes and pre-setting faults, the method further includes: Improve the characteristic model of the power grid operation simulation scheme, specifically including: Based on the extracted power grid feature model, combined with the preset faults in the power grid operation simulation scheme, topology calculation and power flow calculation are performed. The power grid operating condition data before and after the fault and the preset faults in the power grid operation simulation scheme are used as the feature model of the power grid operation simulation scheme.

4. The method for automatically constructing a power grid operation simulation scheme library according to claim 1, characterized in that, The evaluation system for the results of the power grid operation simulation scheme is used to assess the set of disposal schemes and obtain the optimal disposal scheme, including: The set of handling solutions is searched and evaluated based on knowledge reasoning. When the search and evaluation results match and satisfy the rules in the rule set, the fault handling solution is output. Based on the evaluation system for the results of the power grid operation simulation scheme, the fault handling scheme with the highest score is selected as the optimal handling scheme; the evaluation system for the results of the power grid operation simulation scheme is as follows: In the formula, The overall score for the solution Ai is... and Weights are assigned to electrical and non-electrical indicators. and The electrical and non-electrical performance scores for the solution Ai; Electrical indicator score It is the sum of electrical performance indicators, including the number of devices exceeding limits, the percentage of power exceeding limits, the number of heavily loaded devices, the percentage of heavily loaded devices, and the total network loss; non-electrical performance indicators It is the sum of non-electrical indicator scores, including the number of operation steps and the scope of dispatching; and The weighted sum is used to obtain the overall score of the treatment plan Ai. All disposal plans are selected based on their comprehensive scores, with the highest score being chosen as the optimal disposal plan in the power grid operation simulation scheme.

5. The method for automatically constructing a power grid operation simulation scheme library according to claim 1, characterized in that, The initial operation mode of the power grid operation simulation scheme, the preset faults of the power grid operation simulation scheme, and the optimal handling scheme are combined to form a preliminary power grid operation simulation scheme; Preliminary power grid operation simulation schemes are categorized according to the power grid operation simulation theme, generating a power grid operation simulation scheme library, specifically including: The generated power grid operation simulation scheme pre-sets faults and optimal handling schemes are converted into power grid operation simulation scheme events step by step; a device fault in the pre-set faults of the power grid operation simulation scheme is a power grid operation simulation scheme event, and a dispatch operation in the optimal handling scheme is a power grid operation simulation scheme event. They are sorted in chronological order to form a power grid operation simulation scheme event sequence; the result of the scheme event triggering is a change in the operating status of power grid equipment, including switch opening and closing, generator output change, and load power change. Based on 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 changes in the power grid operation state before and after the faults. The generated power grid operation simulation schemes are categorized according to the power grid operation simulation theme to create a power grid operation simulation scheme library.

6. An automatic construction system for a power grid operation simulation scheme library, comprising executing the automatic construction method for a power grid operation simulation scheme library as described in any one of claims 1 to 5, characterized in that, include: The initial operation mode generation module is used to acquire and parse the power grid operation simulation theme and the power grid operation simulation scheme constraints, combine the power grid physical model and data to extract the power grid feature model, and generate the initial operation mode of the power grid operation simulation scheme based on the cross section matching algorithm. The preset fault generation module is used to generate different preset faults for different power grid operation simulation themes for fault handling. The optimal disposal plan generation module is used to obtain a set of disposal plans based on the scheduling knowledge base and the disposal plan base by using knowledge reasoning. The set of disposal plans is evaluated by the power grid operation simulation plan compilation 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 faults of the power grid operation simulation scheme, and the optimal handling scheme to form a preliminary power grid operation simulation scheme; and to classify the preliminary power grid operation simulation scheme according to the power grid operation simulation theme to generate a power grid operation simulation scheme library.

7. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the automatic construction method for the power grid operation simulation scheme library according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the automatic construction method for the power grid operation simulation scheme library according to any one of claims 1-5.

Images