Multi-source power grid comprehensive evaluation method and system of comprehensive power system and medium

Abstract

The invention provides a comprehensive evaluation method and system for a multi-source power grid of a comprehensive power system and a medium, and relates to the technical field of power grid evaluation, and the method comprises the steps: constructing a training data set for the comprehensive evaluation of the multi-source power grid of the comprehensive power system according to the evaluation indexes and original data of the multi-source power grid of the comprehensive power system; taking the classification accuracy of the five-fold cross validation SVM of the training data set as a target function; according to the objective function, searching an optimal penalty factor C of the SVM and an optimal RBF kernel function by adopting an improved Wuyu-gull optimization algorithm; taking the optimal penalty factor C and the RBF kernel function as SVM parameters to obtain a multi-source power grid comprehensive evaluation model of the comprehensive power system; and acquiring data of the current comprehensive power system multi-source power grid, and performing prediction through the comprehensive power system multi-source power grid comprehensive evaluation model to obtain an evaluation prediction result. The method can accurately evaluate the multi-source power grid operation state of the comprehensive power system.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid evaluation, and particularly to a comprehensive evaluation method, system and medium for a multi-source power grid of an integrated power system. Background Art

[0002] The load types of the multi-source power grid of the vehicle-mounted integrated power system are diversified, and the operation mechanism of multi-source networking and the characteristics of constant power loads and pulse loads are complex. Therefore, in-depth research on the comprehensive evaluation method of the multi-source power grid of the vehicle-mounted integrated power system to evaluate the operation health status and fault warning of the multi-source power grid of the integrated power system has great theoretical significance and practical significance for improving the stability margin of the integrated power system.

[0003] As one of the research contents of machine learning, the support vector machine (SVM) is widely used in comprehensive evaluations such as power systems. During the SVM training process, the selection quality of the penalty factor C and the RBF kernel function parameter g of the SVM directly affects the accuracy of the final comprehensive evaluation result of the multi-source power grid of the integrated power system. The intelligent optimization algorithm is an effective method for optimizing SVM model parameters. The sooty tern optimization algorithm (STOA) is a new intelligent optimization algorithm that simulates the foraging behavior of sooty terns and can also be applied to the comprehensive evaluation problem of the multi-source power grid of the integrated power system. However, the sooty tern optimization algorithm still has some defects, making the algorithm prone to falling into local optima and having low convergence accuracy, reducing the effect of optimizing SVM model parameters, and resulting in inaccurate evaluation and prediction effects when using this model for comprehensive evaluation and prediction of the multi-source power grid of the integrated power system. Summary of the Invention

[0004] The present invention provides a comprehensive evaluation method for a multi-source power grid of an integrated power system, which can form an effective power grid comprehensive evaluation and prediction model and obtain more accurate evaluation and prediction results.

[0005] The present invention proposes a comprehensive evaluation method for a multi-source power grid of an integrated power system, specifically including the following steps:

[0006] Construct a training data set for the comprehensive evaluation of the multi-source power grid of the integrated power system according to the evaluation indicators and original data of the multi-source power grid of the integrated power system;

[0007] Determine the upper and lower limits of the penalty factor C and the RBF kernel function parameter g;

[0008] Take the grid evaluation accuracy rate of the 5-fold cross-validation SVM of the training data set as the objective function and calculate the fitness value according to the objective function;

[0009] The improved Sooty Tern optimization algorithm is used to search for the optimal penalty factor C and RBF kernel function of the SVM corresponding to the optimal fitness value. Among them, the improved Sooty Tern optimization algorithm introduces the position update mechanisms of the lotus effect algorithm and the escape optimization algorithm, and updates the position of the Sooty Tern by integrating the optimal position of the Sooty Tern in this iteration, different position update modes, and the cohesion and panic index factors of the Sooty Tern.

[0010] According to the optimal penalty factor C and RBF kernel function as SVM parameters, a comprehensive evaluation model for multi-source power grids of an integrated power system is obtained.

[0011] Obtain the data of the multi-source power grid of the current integrated power system, and predict and obtain the evaluation and prediction results through the comprehensive evaluation model of the multi-source power grid of the integrated power system.

[0012] Preferably, the evaluation indexes of the multi-source power grid of the integrated power system include stability, security, and adaptability. The stability, security, and adaptability are divided into three evaluation levels: high, medium, and low, which are used as the evaluation results of the comprehensive evaluation model of the multi-source power grid of the integrated power system.

[0013] Preferably, the original data includes: energy benchmark parameters, power production data, operation monitoring data, and equipment maintenance data in the power generation link; transmission line parameters, transmission loss data, and transmission stability data in the transmission link; substation operation data, substation equipment status data, and substation loss data in the transformation link; distribution network parameters, distribution loss data, and distribution reliability data in the distribution link; user power consumption data, smart meter data, and user power consumption behavior data in the power consumption link.

[0014] Preferably, the step of using the improved Sooty Tern optimization algorithm to search for the optimal penalty factor C and RBF kernel function of the SVM includes the following steps:

[0015] Take the penalty factor C and RBF kernel function of the SVM as the individuals of the Sooty Tern, determine the upper and lower limits of the penalty factor C and RBF kernel function of the SVM, initialize the position of the Sooty Tern population through Gaussian mapping, and calculate the optimal fitness value and the optimal position of the Sooty Tern according to the objective function.

[0016] Introduce the position update mechanisms of the lotus effect algorithm and the escape optimization algorithm to improve the position update method in the original Sooty Tern optimization algorithm; perform position update through the improved position update method, and record the optimal fitness value and position after the current iteration.

[0017] Perform two-way sine mutation on the optimal position of the Sooty Tern, and use the position of the Sooty Tern with the optimal fitness value before and after mutation as the updated optimal position of the Sooty Tern.

[0018] Update the optimal sooty tern position according to the preset maximum number of iterations in sequence to determine the optimal sooty tern position; determine the penalty factor C and the RBF kernel function of the optimal SVM according to the optimal sooty tern position.

[0019] Preferably, the initialization of the sooty tern population position by Gaussian mapping includes the following steps:

[0020] Determine the population size N, the lower boundary LB for sooty tern optimization, and the upper boundary UB for sooty tern optimization;

[0021] Generate the next random number x through Gaussian mapping t+1 :

[0022]

[0023] In the formula, mod(·) is the remainder function, and x t is the current random number;

[0024] Initialize the sooty tern position using the generated Gaussian random number:

[0025] P s (t) = (UB - LB) × x t + LB.

[0026] Preferably, the position update is performed by the improved position update method, and the optimal fitness value and position after the current iteration are recorded, including the following steps:

[0027] Simulate the migration behavior of sooty terns, including collision avoidance, aggregation, and update;

[0028] Collision avoidance: Simulate the process of the collision avoidance behavior of sooty terns, which is expressed by the following formula:

[0029] C s (t) = S A × P s (t)

[0030] In the formula: P s (t) represents the position of the sooty tern at the current t-th iteration; C s (t) represents the new position of the sooty tern without colliding with other sooty terns; S A represents a variable factor for collision avoidance, which is used to calculate the position after collision avoidance, and its constraint condition formula is as follows:

[0031] S A = C f -(t × C f / Miter)

[0032] In the formula: C f is used to adjust S AThe control variable; t represents the current iteration number; S A As the number of iterations increases, from C f Gradually decreases to 0; Assume C f Is 2, S A Will gradually decrease from 2 to 0; Miter is the number of iterations;

[0033] Aggregation: Aggregation means that the current sooty tern moves closer to the best position among adjacent sooty terns on the premise of avoiding conflicts, that is, moves closer to the optimal position. Its mathematical expression is as follows:

[0034] M s (t) = C B ×(P bs (t) - P s (t))

[0035] In the formula: P bs (t) is the optimal position of the sooty tern at the t-th iteration; M s (t) represents the process of moving from different positions P s (t) towards the optimal position P bs (t); C B Is a random variable and changes according to the following formula:

[0036] C B = 0.5 × rand

[0037] In the formula: rand is a random number from 0 to 1;

[0038] Update: Make the current sooty tern move in the direction of the optimal position and update the position. Its mathematical expression is:

[0039] D s (t) = C s (t) + M s (t)

[0040] In the formula: D s (t) is the distance that the sooty tern moves from the current position towards the optimal position;

[0041] Attack behavior: During the migration process, the sooty tern raises its flight altitude by flapping its wings, adjusts its own speed and attack angle. When attacking prey, their hovering behavior in the air is defined by the following mathematical model:

[0042]

[0043] In the formula: x, y, and z are the coordinates in three directions respectively; r is the radius of each helix; θ is a random angle value within the range of [0, 2π]; u and v are related constants defining the helix shape, both set to 1; e is the base of the natural logarithm;

[0044] Introduce the position update mechanism of the lotus effect algorithm and the escape optimization algorithm, and update the position of the sooty tern by integrating the optimal position of the sooty tern in this iteration, different position update modes, and the cohesion and panic index factors of the sooty tern:

[0045]

[0046] Where:

[0047]

[0048] In the formula: P s (t + 1) is the position of the sooty tern at the (t + 1)-th iteration after update; P bs (t) represents the best position at the t-th iteration; P s (t) is the current position of the sooty tern; P i (t) is the position of the sooty tern with index i at the t-th iteration; C i (t) is the cohesion of the sooty tern with index i at the t-th iteration; Z(t) is the panic index of the sooty tern at the t-th iteration; α is a random number between [0, 1]; λ 1 is a random number within [0, 1];

[0049] Calculate the fitness value:

[0050] fitness(t) = F f (P s (t + 1))

[0051] In the formula, F f (·) is the fitness value calculation function;

[0052] Record the optimal sooty tern in the current iteration.

[0053] Preferably, perform two-way sine mutation on the position of the optimal sooty tern, and use the position of the sooty tern with the optimal fitness value before and after mutation as the updated optimal sooty tern position, including the following steps:

[0054] For dimension j, calculate the sine chaos value according to the current iteration number and switch the positive and negative directions with equal probability:

[0055] sinValue = sin(πx 0 )

[0056]

[0057] In the formula, rand is a random number from 0 to 1; x 0 is the iteration sequence value;

[0058] Mutate and perturb the optimal position:

[0059] P bs(j) (t + 1)' = P bs(j) (t + 1) + SinValue × P bs(j) (t + 1)

[0060] In the formula: P bs(j) (t + 1) represents the optimal position P of the (t + 1)-th iteration bs of the j-th dimension of P bs(j) (t + 1)' is the optimal position P after mutation and perturbation bs of the j-th dimension of P

[0061] Greedy update:

[0062]

[0063] In the formula, after mutation in each dimension, the mutation stops.

[0064] The present invention also provides a comprehensive evaluation system for a multi-source power grid of a comprehensive power system, and the system includes:

[0065] A processor;

[0066] A memory, on which a computer program that can run on the processor is stored;

[0067] Wherein, when the computer program is executed by the processor, the steps of the comprehensive evaluation method for the multi-source power grid of the comprehensive power system are implemented.

[0068] The present invention also provides a computer-readable storage medium, on which a data processing program is stored, and when the data processing program is executed by a processor, the steps of the comprehensive evaluation method for the multi-source power grid of the comprehensive power system are implemented.

[0069] Advantages of the present invention:

[0070] The present invention provides a comprehensive evaluation method for a multi-source power grid of a comprehensive power system. This method improves the position update method of the sooty tern by introducing the position update mechanisms of the lotus effect algorithm and the escape optimization algorithm to improve the position update method of the sooty tern. It comprehensively considers factors such as the optimal position of the sooty tern in the current iteration, different position update modes, the cohesion of the sooty tern, and the panic index to update the position of the sooty tern, realizes an increase in the search range of the algorithm, enhances the adaptability of the algorithm, obtains the optimal parameters of the SVM model to construct an evaluation prediction model with a relatively high prediction accuracy, further accurately evaluates the operating health status of the multi-source power grid of the comprehensive power system, and provides a basis for fault early warning, which helps to improve the stability margin of the comprehensive power system subsequently. Description of the Drawings

[0071] Figure 1 It is a flowchart of the comprehensive evaluation method for multi-source power grids in the integrated power system of the present invention embodiment. Detailed implementation manners

[0072] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present 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 only used to explain the present invention and are not used to limit the present invention.

[0073] Embodiment 1

[0074] The current Sooty tern optimization algorithm still has some defects, which makes the algorithm prone to falling into local optimum and having low convergence accuracy, reducing the effect of optimizing the SVM model parameters, and resulting in inaccurate evaluation and prediction effects when using this model for comprehensive evaluation and prediction of multi-source power grids in the integrated power system. For this reason, the present invention combines the basic steps of STOA and proposes an improved Sooty tern optimization algorithm (ISTOA) for several problems existing in STOA and uses it for the comprehensive evaluation of multi-source power grids in the integrated power system. The flow of the comprehensive evaluation method for multi-source power grids in the integrated power system is as Figure 1 shown, and the specific steps are as follows:

[0075] S1: According to the evaluation indexes and original data of the multi-source power grid in the integrated power system, construct a training data set for the comprehensive evaluation of the multi-source power grid in the integrated power system.

[0076] Among them, the evaluation indexes of the multi-source power grid in the integrated power system include stability, security and adaptability. The stability, security and adaptability are divided into three evaluation levels: high, medium and low, which are used as the evaluation results of the comprehensive evaluation model for the multi-source power grid in the integrated power system. The original data of the multi-source power grid in the integrated power system include: energy reference parameters, electric energy production data, operation monitoring data and equipment maintenance data in the power generation link; transmission line parameters, transmission loss data and transmission stability data in the transmission link; substation operation data, substation equipment status data and substation loss data in the transformation link; distribution network parameters, distribution loss data and distribution reliability data in the distribution link; user power consumption data, smart meter data and user power consumption behavior data in the power consumption link, etc.

[0077] S2: Take the classification accuracy of the 5-fold cross-validation SVM of the training data set as the objective function, that is, the fitness function; at the same time, set the corresponding constraint conditions: the upper and lower limits of the penalty factor C and the RBF kernel function parameter g of the SVM.

[0078] S3: Perform parameter settings, mainly including: the size N of the sooty tern population, that is, the number of sooty tern individuals; the maximum number of iterations Miter, that is, the condition for stopping the iteration; the lower bound LB for sooty tern optimization; and the upper bound UB for sooty tern optimization.

[0079] S4: Initialize the position of the sooty tern population using the Gaussian mapping:

[0080] Generation of Gaussian mapping random numbers:

[0081]

[0082] Initialize the position of the sooty tern using the generated Gaussian random numbers:

[0083] P s (t) = (UB - LB) × x t + LB

[0084] S5: The migration behavior of the sooty tern:

[0085] The migration behavior of the sooty tern, that is, the exploration part of the algorithm, is mainly divided into three stages: collision avoidance, aggregation, and update.

[0086] a) Collision avoidance.

[0087] Simulate the process of the sooty tern's collision avoidance behavior, which is expressed by the following formula:

[0088] C s (t) = S A × P s (t)

[0089] In the formula: P s (t) represents the position of the sooty tern at the current t-th iteration; C s (t) represents the new position of the sooty tern without colliding with other sooty terns; S A represents a variable factor for collision avoidance, which is used to calculate the position after collision avoidance. Its constraint condition formula is as follows:

[0090] S A = C f -(t × C f / Miter)

[0091] In the formula: C f is the control variable used to adjust S A ; t represents the current iteration number; S A gradually decreases from C f to 0 as the number of iterations increases; for example, assuming C f is 2, S A will gradually decrease from 2 to 0.

[0092] b) Aggregation.

[0093] Aggregation means that the current Sooty Tern moves closer to the best position among adjacent Sooty Terns while avoiding conflicts, that is, moving closer to the optimal position. Its mathematical expression is as follows:

[0094] M s (t) = C B ×(P bs (t) - P s (t))

[0095] In the formula: P bs (t) is the optimal position of the Sooty Tern at the t-th iteration; M s (t) represents the process of moving from different positions P s (t) towards the optimal position P bs (t); C B is a random variable that makes the exploration more comprehensive and changes according to the following formula:

[0096] C B = 0.5 × rand

[0097] In the formula: rand is a random number within the range of [0, 1].

[0098] c) Update.

[0099] Update means that the current Sooty Tern moves towards the direction where the optimal position is located and updates its position. Its mathematical expression is:

[0100] D s (t) = C s (t) + M s (t)

[0101] In the formula: D s (t) is the distance that the Sooty Tern moves from the current position towards the optimal position.

[0102] S6: Attack behavior:

[0103] During migration, the Sooty Tern can increase its flight altitude by flapping its wings, and can also adjust its own speed and attack angle. When attacking prey, their hovering behavior in the air can be defined by the following mathematical model:

[0104]

[0105] In the formula: r is the radius of each helix; θ is a random angle value within the range of [0, 2π]; u and v are related constants that define the helix shape and can both be set to 1; e is the base of the natural logarithm.

[0106] In the original Sooty Tern algorithm, only the optimal Sooty Tern position is used to guide and update the Sooty Tern position. To more effectively improve the global search ability of the Sooty Tern, the position update mechanisms of the Lotus Effect algorithm and the Escape Optimization algorithm are introduced to improve the Sooty Tern position update method. The Sooty Tern position is updated by comprehensively considering factors such as the optimal Sooty Tern position in this iteration, different position update modes, the cohesion of the Sooty Tern, and the panic index, avoiding local optima in each iteration, and thus improving the global search ability of the Sooty Tern algorithm.

[0107] The Lotus Effect algorithm and the Escape Optimization algorithm are introduced, and the improved Sooty Tern position update formula is as follows:

[0108]

[0109] Where:

[0110]

[0111]

[0112] In the formula: P s (t + 1) is the position of the Sooty Tern at the (t + 1)-th iteration after update; P bs (t) represents the best position at the t-th iteration; P s (t) is the current position of the Sooty Tern; P i (t) is the position of the Sooty Tern with index i at the t-th iteration; C i (t) is the cohesion of the Sooty Tern with index i at the t-th iteration; Z(t) is the panic index of the Sooty Tern at the t-th iteration; α is a random number between [0, 1]; λ 1 is a random number within [0, 1].

[0113] S7: Calculate the fitness value.

[0114] fitness(t) = F f (P s (t + 1))

[0115] In the formula, F f (·) is the fitness function when calculating the fitness value.

[0116] S8: Record information. Record the optimal Sooty Tern in the current iteration.

[0117] S9: Perform two-dimensional bidirectional sine mutation on the optimal Sooty Tern.

[0118] For dimension j, first calculate the sine chaos value according to the current iteration number and switch the positive and negative directions with equal probability.

[0119] SinValue = sin(πx0 )

[0120]

[0121] Then, perform mutation perturbation on the optimal position:

[0122] P bs(j) (t + 1)' = P bs(j) (t + 1) + SinValue × P bs(j) (t + 1)

[0123] In the formula: P bs(j) (t + 1) represents the optimal position P bs (t + 1) at the j-th dimension.

[0124] Greedy update:

[0125]

[0126] After mutating each dimension, stop the mutation.

[0127] S10: Record information. Record the optimal sooty tern in the current iteration.

[0128] S11: Repeat steps S5 - S11. After reaching the maximum number of iterations Miter, the algorithm stops, and the optimal sooty tern result is output. The optimal sooty tern result is obtained, that is, the optimal penalty factor C and the RBF kernel function of the SVM are obtained.

[0129] S12: Obtain the comprehensive evaluation model of the multi-source power grid of the integrated power system according to the optimal penalty factor C and the RBF kernel function as the SVM parameters.

[0130] S13: Obtain the data of the current multi-source power grid of the integrated power system, and predict and obtain the evaluation prediction result through the comprehensive evaluation model of the multi-source power grid of the integrated power system.

[0131] In this embodiment:

[0132] Select 1000 groups of samples of the multi-source power grid of the integrated power system, and randomly use 800 groups of them as training samples, and the remaining 200 groups as test samples. The multi-source power grid of the integrated power system is evaluated by using STOA-SVM and ISTOA-SVM respectively. Taking MATLAB as the simulation platform, the parameters in the STOA algorithm are: N = 50, Maxiter = 200, and the search ranges of C and g are both between 0 - 100, that is, LB = 0, UB = 100; the parameters in the ISTOA algorithm are: N = 50, Maxiter = 200, and the search ranges of C and g are both between 0 - 100, that is, LB = 0, UB = 100.

[0133] The evaluation metrics for the STOA-SVM model and the ISTOA-SVM model can be selected as: Mean Absolute Error (MAE), Mean Relative Error (MRE), and Root Mean Square Error (RMSE). As shown in Table 1, compared with STOA-SVM, the accuracy of ISTOA-SVM in evaluating the multi-source power grid of the integrated power system is higher. That is to say, the SVM parameters obtained by ISTOA search are better than those obtained by STOA search. The simulation results show that the ISTOA algorithm has stronger search ability than the STOA algorithm, and the evaluation accuracy of ISTOA-SVM is higher than that of STOA-SVM, verifying the effectiveness of the method.

[0134] Table 1 Comparison of evaluation methods

[0135]

[0136] The above is the comprehensive evaluation method for the multi-source power grid of the integrated power system provided by an embodiment of this embodiment. Based on the same idea, this embodiment also provides a corresponding comprehensive evaluation system for the multi-source power grid of the integrated power system. For the specific limitations of the comprehensive evaluation system for the multi-source power grid of the integrated power system, reference can be made to the limitations of the comprehensive evaluation method for the multi-source power grid of the integrated power system in the above text, which will not be elaborated here. Each module in the above comprehensive evaluation system for the multi-source power grid of the integrated power system can be implemented in whole or in part through software, hardware, and their combinations. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0137] This embodiment also provides a computer-readable storage medium, which stores a computer program that can be used to execute the above Figure 1 provided comprehensive evaluation method for the multi-source power grid of the integrated power system.

[0138] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0139] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A comprehensive evaluation method for multi-source power grids in an integrated power system, characterized in that: The following steps are involved: According to the evaluation indicators and original data of the multi-source power grid of the integrated power system, a training data set for comprehensive evaluation of the multi-source power grid of the integrated power system is constructed; Determine the upper and lower limits of the penalty factor C and the RBF kernel function parameter g; The power grid assessment accuracy of the 5-fold cross-validation SVM of the training data set is used as the objective function, and the fitness value is calculated based on the objective function; An improved sooty tern optimization algorithm is used to search for the optimal SVM penalty factor C and RBF kernel function corresponding to the optimal fitness value; wherein the improved sooty tern optimization algorithm introduces the position update mechanism of the lotus effect algorithm and the escape optimization algorithm, and updates the position of the sooty tern based on the optimal position of the sooty tern in this iteration, different position update modes, and the cohesion and panic index of the sooty tern; The comprehensive evaluation model of multi-source power grid in integrated power system is obtained by using the optimal penalty factor C and RBF kernel function as SVM parameters; The data of the multi-source power grid of the current integrated power system is obtained, and the evaluation prediction results are obtained through the comprehensive evaluation model prediction of the multi-source power grid of the integrated power system.

2. The comprehensive evaluation method for multi-source power grids of an integrated power system according to claim 1 is characterized in that: The evaluation indicators of the multi-source power grid of the integrated power system include stability, security and adaptability, which are divided into three evaluation levels: high, medium and low, as the evaluation results of the comprehensive evaluation model of the multi-source power grid of the integrated power system.

3. The comprehensive evaluation method for multi-source power grids of an integrated power system according to claim 1 is characterized in that: The original data include: energy benchmark parameters, electric energy production data, operation monitoring data and equipment maintenance data in the power generation link, transmission line parameters, transmission loss data and transmission stability data in the transmission link, substation operation data, substation equipment status data and substation loss data in the substation link, distribution network parameters, distribution loss data and distribution reliability data in the distribution link, user electricity consumption data, smart meter data and user electricity consumption behavior data in the electricity consumption link.

4. The comprehensive evaluation method for multi-source power grids of an integrated power system according to claim 1, characterized in that: The improved Sooty Tern optimization algorithm is used to search for the optimal SVM penalty factor C and RBF kernel function, comprising the following steps: The penalty factor C of SVM and the RBF kernel function are used as the individual sooty terns, the upper and lower limits of the penalty factor C of SVM and the RBF kernel function are determined, and the position of the sooty tern population is initialized by Gaussian mapping, and the optimal fitness value and the optimal sooty tern position are calculated according to the objective function; The position update mechanism of the Lotus Effect Algorithm and the Escape Optimization Algorithm is introduced to improve the position update method in the original Sooty Tern Optimization Algorithm; the position is updated through the improved position update method, and the optimal fitness value and position after the current iteration are recorded; Perform bidirectional sine mutation on the optimal sooty tern position, and use the sooty tern position with the best fitness value before and after mutation as the updated optimal sooty tern position; The optimal sooty tern position is updated in sequence according to the preset maximum number of iterations to determine the optimal sooty tern position; and the optimal SVM penalty factor C and RBF kernel function are determined according to the optimal sooty tern position.

5. The comprehensive evaluation method for multi-source power grids of an integrated power system according to claim 4 is characterized in that: The process of initializing the position of the black tern population by Gaussian mapping comprises the following steps: Determine the population size N, the lower boundary LB and the upper boundary UB of the sooty tern; Generate the next random number x through Gaussian mapping t+1 : In the formula, mod(·) is the remainder function, x t is the current random number; Use the generated Gaussian random numbers to initialize the positions of the sooty terns: P s (t)=(UB-LB)×x t +LB。 6. The comprehensive evaluation method for multi-source power grids of an integrated power system according to claim 4 is characterized in that: The method of performing position updating by using the improved position updating method and recording the optimal fitness value and position after the current iteration includes the following steps: Simulating the migration behavior of sooty terns, including conflict avoidance, aggregation, and regeneration; Conflict avoidance: The conflict avoidance behavior process of the sooty tern is simulated and expressed as follows: C s (t)=S A ×P s (t) Where: P s (t) represents the position of the sooty tern at the current iteration t; C s (t) represents the new position of the sooty tern if it does not collide with other sooty terns; S A Represents a variable factor to avoid collision, which is used to calculate the position after avoiding collision. Its constraint formula is as follows: S A =C f -(t×C f / Miter) Where: C f To adjust S A The control variable of; t represents the current iteration number; S A As the number of iterations increases, C f Gradually decreases to 0; assuming C f is 2, S A will gradually decrease from 2 to 0; Miter is the number of iterations; Aggregation: Aggregation means that the current sooty tern moves closer to the best position among the adjacent sooty terns under the premise of avoiding conflict, that is, moves closer to the optimal position. Its mathematical expression is as follows: M s (t)=C B ×(P bs (t)-P s (t)) Where: P bs (t) is the optimal position of the sooty tern at the tth iteration; M s (t) indicates different positions P s (t) Towards the optimal position P bs (t) the process of movement; C B is a random variable that changes according to the following formula: C B =0.5×rand Where: rand is a random number between 0 and 1; Update: Move the current sooty tern toward the direction of the optimal position and update the position. The mathematical expression is: D s (t)=C s (t)+M s (t) Where: D s (t) is the distance the sooty tern moves from the current position to the optimal position; Attack behavior: During migration, sooty terns use their wings to increase their flight altitude, adjust their speed and attack angle, and when attacking prey, their hovering behavior in the air is defined by the following mathematical model: Where: x, y, z are the coordinates in three directions respectively; r is the radius of each spiral; θ is a random angle value in the range of [0, 2π]; u and v are related constants that define the spiral shape, both set to 1; e is the base of the natural logarithm; The position update mechanism of the Lotus Effect Algorithm and the Escape Optimization Algorithm is introduced to update the position of the sooty tern based on the optimal position of the sooty tern in this iteration, different position update modes, and the cohesion and panic index of the sooty tern: in: Where: P s (t+1) is the updated position of the sooty tern at the t+1th iteration; P bs (t) represents the best position of the tth iteration; P s (t) is the current position of the sooty tern; P i (t) is the position of the sooty tern with index i at the tth iteration; C i (t) is the cohesion of the sooty tern with index i at the t-th iteration; Z(t) is the panic index of the sooty tern at the t-th iteration; α is a random number between [0,1]; λ1 is a random number between [0,1]; Calculate the fitness value: fitness(t)=F f (P s (t+1)) In the formula, F f (·) is the fitness value calculation function; Record the best sooty tern in the iteration.

7. The comprehensive evaluation method for multi-source power grids of an integrated power system according to claim 6 is characterized in that: The method of performing a bidirectional sine mutation on the optimal sooty tern position and taking the sooty tern position with the best fitness value before and after the mutation as the updated optimal sooty tern position includes the following steps: For dimension j, the sine chaos value is calculated according to the current number of iterations, and the positive and negative directions are switched with equal probability: sin Value = sin(πx0) In the formula, rand is a random number between 0 and 1; x0 is the iteration sequence value; Perform mutation perturbation on the optimal position: P bs(j) (t+1)'=P bs(j) (t+1)+sin Value×P bs(j) (t+1) Where: P bs(j) (t+1) represents the optimal position P of the t+1th iteration bs The jth dimension of (t+1); P bs(j) (t+1)' is the optimal position P after the mutation disturbance bs The jth dimension of (t+1); Greedy Update: In the formula, after each dimension is mutated, the mutation stops.

8. A comprehensive evaluation system for multi-source power grids of an integrated power system, characterized in that: The system comprises: processor; a memory having stored thereon a computer program executable on the processor; Wherein, when the computer program is executed by the processor, the steps of the comprehensive evaluation method of multi-source power grid of the integrated power system as described in any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a data processing program, and when the data processing program is executed by a processor, the steps of the comprehensive evaluation method for multi-source power grids of an integrated power system as described in any one of claims 1 to 7 are implemented.

Images