Construction method of electric power system operation risk assessment model, model, equipment and medium thereof

Abstract

The invention relates to the field of power systems, and discloses a power system operation risk assessment model construction method, a power system operation risk assessment model, equipment and a medium, and the method comprises the steps: obtaining historical operation data of a power system; according to the historical operation data, determining an evaluation index by a plurality of evaluation dimensions, and determining an initial weight of the evaluation index by adopting an analytic hierarchy process for the evaluation index; and carrying out particle swarm optimization on the initial weight to obtain an optimal weight of the evaluation index so as to obtain a power system operation risk evaluation model. According to the method, the evaluation indexes can be determined according to a plurality of evaluation dimensions, and the weight of each evaluation index is dynamically optimized, so that a model capable of accurately evaluating the operation risk of the power system is constructed.

Description

Technical Field

[0001] This invention relates to the field of power systems, and in particular to a method for constructing a power system operation risk assessment model, as well as the model, equipment, and medium thereof. Background Technology

[0002] Against the strategic backdrop of energy transition and the "dual carbon" target, the risk connotation of the power system has undergone profound changes. To achieve carbon emission reduction goals, a large amount of clean energy is rapidly replacing traditional fossil fuels, and this deep adjustment of the energy structure has led to a continuous increase in the power system's dependence on new energy sources. However, insufficient new energy absorption capacity and lagging development of energy storage technology have resulted in the power system facing greater power supply gaps and security pressures when dealing with extreme weather and peak electricity demand. Simultaneously, with the advancement of power market reforms, electricity trading models are becoming increasingly diversified, and factors such as the interplay of interests among market participants and electricity price fluctuations have brought new challenges to the safe and stable operation of the power system. How to effectively assess the operational risks of the power system and ensure a safe and reliable energy supply in the complex environment of energy transition has become a focus of common concern in the global energy sector.

[0003] Existing assessment models for power system operation risks often approach the issue from a single dimension, lacking a systematic consideration of these risks. For example, some methods focus solely on equipment failure probabilities, predicting future risks by statistically analyzing historical failure frequencies, while neglecting the impact of external factors such as the intermittency of renewable energy sources and changes in grid structure on system stability. Furthermore, in determining the weights of evaluation indicators, some traditional assessment methods are highly subjective and lack scientific and reasonable justification. Expert scoring methods rely heavily on experts' personal experience and subjective judgment to assign scores on the importance of indicators. Differences in scoring standards and perceptions among different experts can lead to significant deviations in weighting results, making it difficult to objectively reflect the true importance of indicators. Some methods use fixed weight allocation methods, failing to consider the dynamic changes in the power system's operating status. This prevents weights from being adjusted according to the actual system conditions, reducing the credibility and practicality of the assessment results. Such unscientific weight determination methods can lead to biases in risk assessment and affect the scientific nature of power system risk management decisions. In conclusion, existing assessment models for power system operation risks have a single assessment dimension and fixed indicator weights, failing to accurately evaluate the operational risks of power systems. Summary of the Invention

[0004] This invention aims to address at least one of the technical problems existing in the prior art. To this end, this invention proposes a method for constructing a power system operation risk assessment model, which can determine assessment indicators based on several assessment dimensions and dynamically optimize the weights of each assessment indicator, thereby constructing a model capable of accurately assessing the operation risk of a power system.

[0005] The present invention also proposes a model, device, and medium for constructing the above-mentioned power system operation risk assessment model.

[0006] A method for constructing a power system operation risk assessment model according to a first aspect of the present invention, applied to a power system, includes: Obtain historical operating data of the power system; Based on the historical operational data, evaluation indicators are determined using several evaluation dimensions; The initial weights of the evaluation indicators are determined using the analytic hierarchy process (AHP). The initial weights are applied using a particle swarm optimization algorithm to obtain the optimal weights for the evaluation indicators, thereby obtaining the power system operation risk assessment model.

[0007] A method for constructing a power system operation risk assessment model according to an embodiment of the present invention has at least the following beneficial effects: The present invention first determines assessment indicators affecting power system operation risk from several assessment dimensions using historical operation data. It then applies the analytic hierarchy process (AHP) to stratify and analyze these indicators, thereby determining their initial weights. Next, it applies the global search capability of the particle swarm optimization algorithm to iteratively optimize the initial weights of the assessment indicators, ultimately obtaining the optimal weights to assess the power system operation risk. The present invention can determine assessment indicators from several assessment dimensions and dynamically optimize the weights of each indicator, thereby constructing a model that can accurately assess the operation risk of a power system.

[0008] According to some embodiments of the present invention, determining the evaluation indicators based on the historical operating data using several evaluation dimensions includes: The historical operational data were extracted, organized, and merged in sequence according to the probability of medium risk occurrence, the severity of risk consequences, and the system's resistance and recovery capabilities, and the corresponding evaluation indicators for each evaluation dimension were determined.

[0009] According to some embodiments of the present invention, the step of using the analytic hierarchy process (AHP) to determine the initial weights of the evaluation indicators includes: The probability of medium-risk occurrence, the severity of risk consequences, and the system's resilience and recovery capability are used as the criterion layer in the analytic hierarchy process (AHP). The evaluation indicators corresponding to each evaluation dimension are used as the indicator layer in the AHP. The initial weights of each evaluation indicator are used as the target layer in the AHP. Each evaluation indicator in the indicator layer corresponds to a certain evaluation dimension in the criterion layer. Based on the evaluation indicators, construct the judgment matrix in the analytic hierarchy process; Based on the judgment matrix, the initial weights of the evaluation indicators are determined.

[0010] According to some embodiments of the present invention, constructing the judgment matrix in the analytic hierarchy process based on the evaluation index includes: Use the evaluation indicators corresponding to a certain evaluation dimension as rows and the evaluation indicators corresponding to the other evaluation dimensions as columns to initialize the judgment matrix corresponding to each evaluation dimension in the analytic hierarchy process. For each row and column of the judgment matrix, the row indicators and column indicators are compared respectively. The row indicators are then compared relative to the values ​​specified in some embodiments of the present invention. The step of determining the initial weights of the evaluation indicators based on the judgment matrix further includes: The weight vector for each row of the judgment matrix is ​​obtained by summarizing and normalizing each row in turn. Based on the weight vector of each row and the judgment matrix, the consistency of the judgment matrix is ​​verified. If the verification passes, the weight vector of each row becomes the initial weight of the evaluation index.

[0011] According to some embodiments of the present invention, the step of applying a particle swarm optimization algorithm to the initial weights to obtain the optimal weights of the evaluation index includes: The evaluation index is used as the particles in the particle swarm optimization algorithm, the initial weight is used as the initial position of some particles, and the initial position of the remaining particles is randomly generated within a preset weight range. Consistency deviation and weight balance are taken as the optimization objectives of particle swarm optimization. The initial parameters of particle swarm optimization are set in advance, and the particle swarm optimization is iterated in this way. The particles obtained by the iteration are the optimal weights of the corresponding evaluation indicators.

[0012] According to some embodiments of the present invention, it further includes: Each evaluation indicator was normalized separately. The operational risk level of the power system is obtained by using the evaluation indicators corresponding to each evaluation dimension after normalization.

[0013] A power system operation risk assessment model according to a second aspect of the present invention, constructed using the method for constructing a power system operation risk assessment model according to any one of the first aspects, includes: The data acquisition module is used to acquire the operating data of the power system; The processing module, connected to the data acquisition module, is used to receive the operating data sent by the data acquisition module and obtain the operating risk level of the power system based on the operating data.

[0014] An electronic device according to a third aspect of the present invention includes: Memory, used to store programs; A processor for executing a program stored in the memory, wherein when the processor executes the program stored in the memory, the processor is configured to perform the method as described in any one of the first aspects.

[0015] According to a fourth aspect of the present invention, a storage medium stores computer-executable instructions for performing the method as described in any one of the first aspects.

[0016] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0017] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0018] Figure 1 This is a flowchart of a method for constructing a power system operation risk assessment model according to an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0020] It should be understood that in the description of the embodiments of the present invention, "multiple" (or "amounts") means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. If "first," "second," etc., are used in the description, they are only for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0021] like Figure 1 As shown, this embodiment of the invention provides a method for constructing a power system operation risk assessment model, applicable to power systems, including: Step S100: Obtain historical operating data of the power system; Step S200: Determine the evaluation indicators based on historical operating data and several evaluation dimensions; Step S300: Use the analytic hierarchy process (AHP) to determine the initial weights of the evaluation indicators. Step S400: Apply particle swarm optimization to the initial weights to obtain the optimal weights of the evaluation indicators, thereby obtaining the power system operation risk assessment model.

[0022] This invention first identifies assessment indicators affecting the operational risk of a power system from several evaluation dimensions using historical operational data. It then applies the Analytic Hierarchy Process (AHP) to stratify and analyze these indicators, thereby determining their initial weights. Next, it utilizes the global search capability of the Particle Swarm Optimization (PSO) algorithm to iteratively optimize the initial weights, ultimately obtaining the optimal weights to assess the operational risk of the power system. This invention enables the determination of assessment indicators across several dimensions and the dynamic optimization of the weights for each indicator, thereby constructing a model capable of accurately assessing the operational risk of a power system.

[0023] In one embodiment, in step S100, the historical operating data of the power system includes: Monitoring data of the power system, operation and maintenance records of power equipment, and meteorological data for the corresponding time period; After obtaining historical operating data of the power system, the historical operating data is cleaned to remove duplicate, erroneous and invalid data. The cleaned historical operating data is then organized, and historical operating data of different risk factors (such as weather, electricity consumption periods, emergency equipment repairs, and scheduled equipment maintenance) are stored in the corresponding databases or data tables.

[0024] In one embodiment, in step S200, determining the evaluation indicators based on historical operating data using several evaluation dimensions includes: Historical operational data were extracted, organized, and merged in sequence according to the probability of medium-risk occurrence, the severity of risk consequences, and the system's resistance and recovery capabilities, and the corresponding evaluation indicators for each evaluation dimension were determined.

[0025] Step S200 actually involves analyzing and integrating data that can be directly obtained from the power system (i.e., historical operating data, which represents the operating data of the power system), classifying and merging the historical operating data according to the evaluation dimensions, extracting the operating data from the evaluation indicators determined by the following dimensions, and the rest being redundant data.

[0026] In one embodiment, the assessment indicators determined by the probability of medium risk occurrence include: the probability of forced outage of power generation units, the probability of transmission line failure, the probability of load forecasting error exceeding the standard, and the probability of forced outage of transformers. The probability of forced outage of a power generation unit (FOR) is specifically calculated as: FOR = Forced outage hours of the unit (FOH) / (Forced outage hours of the unit + Available hours of the unit (AH)); where power generation units include: thermal power generation units, hydropower generation units, and wind power generation units. Transmission line fault probability λ_L = Number of faults per year / Years of operation of the line; The probability of exceeding the load forecast error limit, P_ERR, is calculated as follows: (Number of times the annual load deviation exceeds the limit) / (Total number of forecasts in the year). The probability of forced transformer outage FOR_T = number of hours of forced transformer outage / (forced outage hours + available hours); Assessment indicators determined by the severity of risk consequences include: power flow over-limit consequences, transient stability and instability consequences, load reduction, proportion of users experiencing power outages, direct economic losses from risk events, economic losses from frequency deviations, and economic losses from voltage deviations. The power flow over-limit consequence value C_OL = the sum of [(over-limit component power flow value - rated power flow value) / rated power flow value × preset over-limit component weight × preset power outage loss coefficient] for each section; The transient stability failure consequence value C_TS = power outage load caused by instability × power outage loss per unit load × average recovery time; Load reduction LC = Total system load - Load that can be safely supplied after a fault; The percentage of users experiencing power outages, R_CU, is calculated as: (Number of users experiencing power outages / Total number of users in the system) × 100%. Direct economic loss from a risk event C_EC = equipment repair cost + (power outage load × unit power outage loss × power outage time) + emergency repair costs; Frequency deviation economic loss C_DEV = Total active load of the system × Frequency deviation loss coefficient × |Actual frequency of the power system – Rated frequency of the power system|; Voltage deviation economic loss C_DEV(U) = Total reactive load of the system × Voltage deviation loss coefficient × |Actual voltage per unit value - Rated voltage per unit value|; Evaluation indicators determined by the system's disturbance rejection and recovery capabilities include: frequency stability margin, voltage stability margin, mean time to recovery from fault, and reserve capacity adequacy ratio. Frequency stability reserve coefficient K_f = total primary frequency regulation capacity of the system / (total system load × preset frequency deviation); Voltage stability margin V_SM = (maximum load power - actual load power) / actual load power × 100%; Mean Time To Repair (MTTR) = Total Time To Repair / Total Number of Faults; Reserve capacity adequacy ratio R_SC = (spinning reserve + cold reserve) / maximum system load × 100%.

[0027] The data in the calculation formulas of the above evaluation indicators, including the number of forced outage hours and the number of available hours of the units, can be directly obtained from the operating data of the power system, which facilitates actual evaluation.

[0028] In one embodiment, in step S300, the analytic hierarchy process (AHP) is used to determine the initial weights of the evaluation indicators, including: The probability of medium-risk occurrence, the severity of risk consequences, and the system's resilience and recovery capability are used as the criterion layer in the analytic hierarchy process (AHP). The evaluation indicators corresponding to each evaluation dimension are used as the indicator layer in the AHP. The initial weights of each evaluation indicator are used as the target layer in the AHP. Each evaluation indicator in the indicator layer corresponds to a certain evaluation dimension in the criterion layer. Based on the evaluation indicators, construct the judgment matrix in the analytic hierarchy process; Based on the judgment matrix, determine the initial weights of the evaluation indicators.

[0029] It is easy to understand that the use of the analytic hierarchy process (AHP) does not sever the connections between evaluation dimensions and their corresponding evaluation indicators. In one embodiment, based on the evaluation indicators, a judgment matrix in the AHP is constructed, including: Use the evaluation indicators corresponding to a certain evaluation dimension as rows and the evaluation indicators corresponding to the other evaluation dimensions as columns to initialize the judgment matrix corresponding to each evaluation dimension in the analytic hierarchy process. For each row and column of the judgment matrix, the row indicators and column indicators are compared respectively, and the importance of the row indicators relative to the column indicators is used as the elements of the judgment matrix.

[0030] It is easy to understand that there are 4 evaluation dimensions, so 4 judgment matrices are constructed.

[0031] Specifically, methods for determining the importance of row indicators relative to column indicators include: inviting experts to make judgments; if there are multiple experts, summarizing the judgment matrices of multiple experts to obtain the final judgment matrix.

[0032] In one embodiment, determining the initial weights of the evaluation indicators based on the judgment matrix further includes: The weight vector for each row in the judgment matrix is ​​obtained by summarizing and normalizing each row in turn. Based on the weight vector and judgment matrix of each row, verify the consistency of the judgment matrix. If the verification passes, the weight vector of each row is the initial weight of the evaluation index corresponding to the evaluation dimension row.

[0033] Specifically, the elements of each row in the judgment matrix are multiplied to obtain the total product of the elements in each row. Taking the construction matrix with the evaluation dimension of the probability of medium risk occurrence as an example, the k-th root of the total product of the elements in each row is calculated, where k is the number of columns, to obtain the weight vector of each row. ; Verifying the consistency of the judgment matrix includes determining the maximum eigenvalue λmax, expressed as follows: , Where A is the judgment matrix, W is the weight vector, and n is the number of rows in the judgment matrix; The consistency index (CI) is calculated as follows: , Where λmax is the largest eigenvalue and n is the number of rows in the judgment matrix; Calculate the consistency ratio CR = CI / RI. If the consistency ratio is less than the preset consistency ratio threshold, the judgment matrix has satisfactory consistency and the weight vector is valid; otherwise, the judgment matrix needs to be readjusted until the consistency test is passed.

[0034] In one embodiment, in step S400, the particle swarm optimization algorithm is used to obtain the optimal weights for the evaluation index, including: The evaluation index is used as the particles in the particle swarm optimization algorithm, the initial weight is used as the initial position of some particles, and the initial position of the remaining particles is randomly generated within the preset weight range. Consistency deviation and weight balance are taken as the optimization objectives of particle swarm optimization. The initial parameters of particle swarm optimization are set in advance, and the particle swarm optimization is iterated in this way. The particles obtained by the iteration are the optimal weights of the corresponding evaluation indicators.

[0035] In one embodiment, the consistency deviation is specifically the difference between each particle in the particle swarm optimization algorithm and its corresponding initial weight. The smaller the difference, the better. The weight balance is specifically determined by using the entropy method or the variance method to determine whether a particle is over-concentrated. The expression for the optimization objective of the particle swarm optimization algorithm is as follows:

[0036] in, Let be the consistency deviation function. α represents the number of rows for weight balance, and α is the preset optimization weight.

[0037] Specifically, the iterative process of the particle swarm optimization algorithm includes: Set the initial parameters for the particle swarm optimization algorithm, including: inertia coefficient and learning factor; Initialize the particle swarm, including: the first i The initial position of each particle Some particles take the initial weights of the AHP judgment matrix. W The remaining particles are randomly generated within the constrained domain (e.g., through normalized random number generation); the initial velocity is set. , randomly generated within the velocity boundary; Iterative updates of particle position and velocity include: iteratively updating the velocity and position of each particle according to the following formula until the maximum number of iterations is reached or the fitness function converges, where the velocity update formula is as follows: ,in, For the first i The particle up to the [number]th t The optimal position of an individual (the position with the lowest fitness). For the first t The "global optimal position" (the position with the lowest fitness among all individual particle optimal positions) is determined by the generation of the "global optimal position". r 1, r 2 represents a random number in the range [0,1] to increase the randomness of the search; the rest are initial parameters for the particle swarm optimization algorithm; the position update formula is as follows: After the position is updated, it needs to be projected onto the constraint domain; Record the optimal position, including: calculating the fitness value of each particle after each iteration. Update individual optimal and global optimal :like ,but ,like ,but .

[0038] In one embodiment, after obtaining the optimal weight of the evaluation index, a consistency check is also required to determine whether the deviation between the optimal weight of the evaluation index and the corresponding judgment matrix exceeds a preset threshold.

[0039] In one embodiment, it further includes: Each evaluation indicator was normalized separately. The operational risk level of the power system is obtained by using the evaluation indicators corresponding to each evaluation dimension after normalization.

[0040] In one embodiment, the total risk value R_total is calculated as follows: R_total = Σ (the index value of the evaluation index corresponding to the probability of occurrence of medium risk × the index value of the evaluation index corresponding to the severity of risk consequences × the corresponding weight) - Σ (the index value of the evaluation index corresponding to the system's immunity and recovery capability × the corresponding weight). The power system's operational risk level is classified according to its total risk value, as shown in the table below:

[0041] This invention also provides a power system operation risk assessment model, constructed using the aforementioned power system operation risk assessment method, comprising: The data acquisition module is used to acquire the operating data of the power system; The processing module, connected to the data acquisition module, is used to obtain the operational risk level of the power system based on the operational data.

[0042] This invention also provides an electronic device, which includes, but is not limited to: Memory, used to store programs; The processor is used to execute programs stored in memory. When the processor executes programs stored in memory, it is used to execute the aforementioned method for constructing the power system operation risk assessment model.

[0043] The processor and memory can be connected via a bus or other means.

[0044] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs, such as the method described in the embodiments of the present invention. The processor implements the above method by running the non-transitory software program and instructions stored in the memory.

[0045] The memory may include a program storage area and a data storage area, wherein the program storage area may store the operating system and application programs required for at least one function; the data storage area may store data for executing the methods described above. Furthermore, the memory may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, which can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0046] The non-transitory software program and instructions required to implement the above terminal selection method are stored in memory and are executed by one or more processors.

[0047] This invention also provides a storage medium storing computer-executable instructions for performing the above-described methods.

[0048] In one embodiment, the storage medium stores computer-executable instructions that are executed by one or more control processors.

[0049] The embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0050] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0051] This document describes embodiments of the invention, including preferred embodiments known to the inventors for carrying out the invention. Variations of these embodiments will become apparent to those skilled in the art upon reading the foregoing description. The inventors encourage those skilled in the art to adopt such variations as appropriate, and the inventors intend to practice embodiments of the invention in ways other than those specifically described herein. Therefore, the scope of the invention includes all modifications and equivalents of the subject matter set forth in the appended claims, as permitted by applicable law. Furthermore, the scope of the invention covers any combination of the foregoing elements in all possible variations thereof, unless otherwise indicated herein or otherwise clearly contradicted by the context.

Claims

1. A method for constructing a power system operation risk assessment model, applied to power systems, characterized in that, include: Obtain historical operating data of the power system; Based on the historical operational data, evaluation indicators are determined using several evaluation dimensions; The initial weights of the evaluation indicators are determined using the analytic hierarchy process (AHP). The initial weights are applied using a particle swarm optimization algorithm to obtain the optimal weights for the evaluation indicators, thereby obtaining the power system operation risk assessment model.

2. The method for constructing a power system operation risk assessment model according to claim 1, characterized in that, The determination of evaluation indicators based on the historical operational data and using several evaluation dimensions includes: The historical operational data were extracted, organized, and merged in sequence according to the probability of medium risk occurrence, the severity of risk consequences, and the system's resistance and recovery capabilities, and the corresponding evaluation indicators for each evaluation dimension were determined.

3. The method for constructing a power system operation risk assessment model according to claim 2, characterized in that, The process of determining the initial weights of the evaluation indicators using the analytic hierarchy process (AHP) includes: The probability of medium-risk occurrence, the severity of risk consequences, and the system's resilience and recovery capability are used as the criterion layer in the analytic hierarchy process (AHP). The evaluation indicators corresponding to each evaluation dimension are used as the indicator layer in the AHP. The initial weights of each evaluation indicator are used as the target layer in the AHP. Each evaluation indicator in the indicator layer corresponds to a certain evaluation dimension in the criterion layer. Based on the evaluation indicators, construct the judgment matrix in the analytic hierarchy process; Based on the judgment matrix, the initial weights of the evaluation indicators are determined.

4. The method for constructing a power system operation risk assessment model according to claim 3, characterized in that, The step of constructing the judgment matrix in the analytic hierarchy process based on the evaluation indicators includes: Use the evaluation indicators corresponding to a certain evaluation dimension as rows and the evaluation indicators corresponding to the other evaluation dimensions as columns to initialize the judgment matrix corresponding to each evaluation dimension in the analytic hierarchy process. For each row and column of the judgment matrix, the row indicators and column indicators are compared respectively, and the importance of the row indicators relative to the column indicators is used as the element of the judgment matrix.

5. The method for constructing a power system operation risk assessment model according to claim 3, characterized in that, The step of determining the initial weights of the evaluation indicators based on the judgment matrix further includes: The weight vector for each row of the judgment matrix is ​​obtained by summarizing and normalizing each row in turn. Based on the weight vector of each row and the judgment matrix, the consistency of the judgment matrix is ​​verified. If the verification passes, the weight vector of each row becomes the initial weight of the evaluation index.

6. The method for constructing a power system operation risk assessment model according to claim 1, characterized in that, The process of applying a particle swarm optimization algorithm to the initial weights to obtain the optimal weights for the evaluation index includes: The evaluation index is used as the particles in the particle swarm optimization algorithm, the initial weight is used as the initial position of some particles, and the initial position of the remaining particles is randomly generated within a preset weight range. Consistency deviation and weight balance are taken as the optimization objectives of particle swarm optimization. The initial parameters of particle swarm optimization are set in advance, and the particle swarm optimization is iterated in this way. The particles obtained by the iteration are the optimal weights of the corresponding evaluation indicators.

7. The method for constructing a power system operation risk assessment model according to claim 1, characterized in that, Also includes: Each evaluation indicator was normalized separately. The operational risk level of the power system is obtained by using the evaluation indicators corresponding to each evaluation dimension after normalization.

8. A power system operation risk assessment model, characterized in that, Constructed by the method of any one of claims 1 to 7, comprising: The data acquisition module is used to acquire the operating data of the power system; The processing module, connected to the data acquisition module, is used to receive the operating data sent by the data acquisition module and obtain the operating risk level of the power system based on the operating data.

9. An electronic device, characterized in that, include: Memory, used to store programs; A processor for executing a program stored in the memory, wherein when the processor executes the program stored in the memory, the processor is configured to perform the method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The device stores computer-executable instructions for performing the method as described in any one of claims 1 to 7.

Images