Method and system for evaluating power supply reliability of power distribution network

Abstract

The invention relates to a power distribution network power supply reliability evaluation method and system, and the method comprises the steps: building a fault power failure influence factor evaluation system based on the analysis of power distribution network fault power failure influence factors of an analytic hierarchy process; building an improved firefly algorithm and relevance vector machine combined FA-RVM prediction model, and predicting a power distribution network fault power failure index; based on a simulated annealing-particle swarm optimization algorithm, constructing an SA-PSO-RVM prediction model; and designing a double-model complementary power distribution network fault power failure prediction platform, and predicting power distribution network fault power failure indexes, the double models being an IFA-RVM prediction model and an SA-PSO-RVM prediction model. The advanced algorithm model is utilized to predict the distribution network fault power failure, the requirements of safe, reliable and economical operation of the power system are met, the reliability of the power grid can be improved, accidents of the power system are reduced, and the economic benefits of power grid operation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution and power supply reliability, and in particular to a method and system for evaluating the power supply reliability of a distribution network. Background Art

[0002] The distribution network is the "last mile" for electricity to reach power customers. It is most closely connected with users and has the most direct impact on users. Reducing power outages caused by distribution network faults and improving power supply reliability are of great value in ensuring the quality of power consumption for users and safeguarding social and economic influence. With the deepening of the market-oriented reform of the power system, power outages caused by distribution system faults will inevitably cause economic losses to power users and have an impact on society. The power outage time can reflect the level of power supply reliability of a country. However, there is still a certain gap between the power supply reliability of the distribution network in my country and that in developed countries.

[0003] Most urban power distribution systems use radial wiring, which is sensitive to single faults and has a high fault rate. In addition, they are directly connected to users. If a fault occurs, it will directly lead to power outages for users, affecting residents' lives. Therefore, improving the reliability of the power distribution system is most in line with the actual needs of the majority of residents. Accurate fault power outage prediction provides decision-making references for fault repair and grid reinforcement, further reducing the probability and duration of fault power outages and ensuring safe and stable operation of the grid.

[0004] The power supply reliability index of the distribution network reflects the software and hardware level of the power supply quality of the distribution network. It is a comprehensive indicator that includes equipment level, technical level, management level and service level. Therefore, based on the analysis of the current power supply reliability of the power grid, the power supply reliability management level is strengthened, and measures to improve the power supply reliability are formulated to make the distribution network grid more reasonable and the power supply capacity safe and stable. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method and system for evaluating the reliability of power supply in a distribution network.

[0006] To solve the above problems, the technical solution adopted by the present invention is:

[0007] In one aspect, a method for evaluating power supply reliability of a distribution network is provided, the method comprising:

[0008] Step 1: Analyze the influencing factors of power outage caused by distribution network faults based on the analytic hierarchy process and build an evaluation system for the influencing factors of power outage caused by faults;

[0009] Step 2: Build a FA-RVM prediction model combining the improved firefly algorithm and the relevance vector machine to predict the distribution network fault outage index;

[0010] Step 3: Based on simulated annealing-particle swarm algorithm, SA-PSO-RVM prediction model is constructed;

[0011] Step 4: Design a distribution network fault outage prediction platform with dual complementary models to predict distribution network fault outage indicators. The dual models are the IFA-RVM prediction model and the SA-PSO-RVM prediction model.

[0012] As an embodiment of the present invention, step one includes:

[0013] Step S101, various influencing factors of power outage are divided into several interrelated levels in order;

[0014] Step S102: judge through the expert scoring system, compare and analyze the relative importance of each layer of factors, use the indicator weight to sort the influencing factors, and then establish a fault power outage influencing factor evaluation system.

[0015] As an embodiment of the present invention, step 2 includes:

[0016] Step S201, performing FA-RVM denoising on the data after correction of outliers and missing values ​​to obtain denoised signal data;

[0017] Step S202: synthesize acceleration of the denoised signal data using the following formula:

[0018]

[0019] Among them: A x , A y , A z They are the acceleration signals after denoising on the x, y, and z axes respectively.

[0020] As an embodiment of the present invention, step 2 includes:

[0021] Step 211, solving the optimal variational mode decomposition method parameters K and α based on the firefly algorithm FA; the specific process is:

[0022] (1) Setting the value range of K and α in the variational mode decomposition (VMD) algorithm; K is the number of modes of the decomposition target, and α is the quadratic penalty factor; 3≤K≤20, 500≤α≤2500;

[0023] (2) Initialize the basic parameters of the firefly algorithm FA, which are the problem dimension, population size, maximum attraction β0, light absorption coefficient, step factor, number of iterations, and the value range of K and α;

[0024] (3) Randomly initialize the K value and α value of the i-th firefly as the initial position in the space, i = 1, 2, ..., 25;

[0025] (4) Calculate the fitness function of the i-th firefly as the fluorescein value l of the i-th firefly at time t i (t), as the maximum fluorescence brightness I0 of the i-th firefly;

[0026] (5) Update the spatial position of the i-th firefly, that is, the new K value and α value;

[0027] Step 2012: Using the K value and the α value obtained in step 2011, perform variational mode decomposition on the collected historical data of power outages in the distribution network, and determine the dominant signal component, the interference signal component, and the noise signal component.

[0028] As an implementation mode of the present invention, step three includes:

[0029] Step S301, based on the historical data of power outages in the distribution network, initialize the particle swarm and randomly generate particle positions and velocities;

[0030] Step S302, assigning the position and velocity of each particle to the quantization factor and the proportional factor in the fuzzy controller in turn; measuring the individual performance by the integral of the product of time and the absolute value of the error, and constructing the objective function; and adjusting the inertia weight in an adaptive manner;

[0031] Step S303: select SA;

[0032] Step S304: When the termination condition is met, the iteration is terminated, the optimal particle fitness value is output, and the particle position and speed at the next moment are updated.

[0033] On the other hand, a distribution network power supply reliability evaluation system is provided, comprising:

[0034] A system construction module, which is used to analyze the influencing factors of power outages caused by power distribution network failures based on the analytic hierarchy process and to build an evaluation system for the influencing factors of power outages caused by power distribution network failures;

[0035] The prediction module is used to build a FA-RVM prediction model combining an improved firefly algorithm and a relevance vector machine to predict the distribution network fault outage indicators;

[0036] A model building module, which is used to build a SA-PSO-RVM prediction model based on simulated annealing-particle swarm algorithm;

[0037] The prediction module is used to design a distribution network fault power outage prediction platform with dual complementary models to predict distribution network fault power outage indicators. The dual models are the IFA-RVM prediction model and the SA-PSO-RVM prediction model.

[0038] As an embodiment of the present invention, the prediction module is also used for:

[0039] Divide various influencing factors of power outage into several interrelated levels in order;

[0040] The expert scoring system is used to make judgments, and the relative importance of factors at each level is compared and analyzed. The index weights are used to rank the influencing factors, and then an evaluation system for the influencing factors of fault power outages is established.

[0041] As an embodiment of the present invention, the prediction module is also used for:

[0042] The data after correction of outliers and missing values ​​are subjected to FA-RVM denoising to obtain denoised signal data;

[0043] The following formula is used to synthesize the acceleration of the denoised signal data:

[0044]

[0045] Among them: A x , A y , A z They are the acceleration signals after denoising on the x, y, and z axes respectively.

[0046] As an embodiment of the present invention, the prediction module is also used for:

[0047] The optimal variational mode decomposition method parameters K and α are solved based on the firefly algorithm FA; the specific process is:

[0048] (1) Setting the value range of K and α in the variational mode decomposition (VMD) algorithm; K is the number of modes of the decomposition target, and α is the quadratic penalty factor; 3≤K≤20, 500≤α≤2500;

[0049] (2) Initialize the basic parameters of the firefly algorithm FA, which are the problem dimension, population size, maximum attraction β0, light absorption coefficient, step factor, number of iterations, and the value range of K and α;

[0050] (3) Randomly initialize the K value and α value of the i-th firefly as the initial position in the space, i = 1, 2, ..., 25;

[0051] (4) Calculate the fitness function of the i-th firefly as the fluorescein value l of the i-th firefly at time t i (t), as the maximum fluorescence brightness I0 of the i-th firefly;

[0052] (5) Update the spatial position of the i-th firefly, that is, the new K value and α value;

[0053] Through the obtained K value and α value, the collected distribution network power outage historical data is subjected to variational mode decomposition, and the dominant signal component, interference signal component, and noise signal component are determined.

[0054] As an embodiment of the present invention, the model building module is also used for:

[0055] Based on the historical data of power outages in the distribution network, the particle swarm is initialized and the particle positions and velocities are randomly generated;

[0056] The position and velocity of each particle are assigned to the quantization factor and the proportional factor in the fuzzy controller in turn; the individual performance is measured by the integral of the product of time and the absolute value of the error to construct the objective function; the inertia weight is adjusted in an adaptive manner;

[0057] Make SA selection;

[0058] When the termination condition is met, the iteration is terminated, the optimal particle fitness value is output, and the particle position and velocity at the next moment are updated.

[0059] The beneficial effects of adopting the above technical solution are:

[0060] The evaluation method of power supply reliability of distribution network provided by the present invention includes: analyzing the influencing factors of power outage caused by distribution network faults based on the hierarchical analysis method, and constructing an evaluation system of influencing factors of power outage caused by faults; building a FA-RVM prediction model combining an improved firefly algorithm and a related vector machine to predict the power outage index of distribution network faults; building a SA-PSO-RVM prediction model based on simulated annealing-particle swarm algorithm; designing a distribution network fault power outage prediction platform with dual models complementing each other, and predicting the power outage index of distribution network faults, wherein the dual models are the IFA-RVM prediction model and the SA-PSO-RVM prediction model. The present invention uses advanced algorithm models to predict power outage caused by distribution network faults, meets the requirements of safe and reliable power system and economic operation, can improve the reliability of power grid, reduce the occurrence of power system accidents, and improve the economic benefits of power grid operation. At the same time, the improvement of distribution network reliability can better optimize the power supply environment and effectively improve the satisfaction of power users. DETAILED DESCRIPTION

[0061] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention is clearly and completely described below in conjunction with specific embodiments.

[0062] Example 1

[0063] An embodiment of the present invention provides a method for evaluating power supply reliability of a distribution network, the method comprising:

[0064] Step 1: Analyze the influencing factors of power outage caused by distribution network faults based on the analytic hierarchy process and build an evaluation system for the influencing factors of power outage caused by faults;

[0065] This step includes:

[0066] Step S101, various influencing factors of power outage are divided into several interrelated levels in order;

[0067] Step S102: judge through the expert scoring system, compare and analyze the relative importance of each layer of factors, use the indicator weight to sort the influencing factors, and then establish a fault power outage influencing factor evaluation system.

[0068] Step 2: Build a FA-RVM prediction model combining the improved firefly algorithm and the relevance vector machine to predict the distribution network fault outage index;

[0069] This step includes:

[0070] Step S201, performing FA-RVM denoising on the data after correction of outliers and missing values ​​to obtain denoised signal data;

[0071] Specifically include:

[0072] Step 211, solving the optimal variational mode decomposition method parameters K and α based on the firefly algorithm FA; the specific process is:

[0073] (1) Setting the value range of K and α in the variational mode decomposition (VMD) algorithm; K is the number of modes of the decomposition target, and α is the quadratic penalty factor; 3≤K≤20, 500≤α≤2500;

[0074] (2) Initialize the basic parameters of the firefly algorithm FA, which are the problem dimension, population size, maximum attraction β0, light absorption coefficient, step factor, number of iterations, and the value range of K and α;

[0075] (3) Randomly initialize the K value and α value of the i-th firefly as the initial position in the space, i = 1, 2, ..., 25;

[0076] (4) Calculate the fitness function of the i-th firefly as the fluorescein value l of the i-th firefly at time t i (t), as the maximum fluorescence brightness I0 of the i-th firefly;

[0077] (5) Update the spatial position of the i-th firefly, that is, the new K value and α value;

[0078] Step 2012: Using the K value and the α value obtained in step 2011, perform variational mode decomposition on the collected historical data of power outages in the distribution network, and determine the dominant signal component, the interference signal component, and the noise signal component.

[0079] Step S202: synthesize acceleration of the denoised signal data using the following formula:

[0080]

[0081] Among them: A x , A y , A z They are the acceleration signals after denoising on the x, y, and z axes respectively.

[0082] Step 3: Based on simulated annealing-particle swarm algorithm, SA-PSO-RVM prediction model is constructed;

[0083] This step specifically includes:

[0084] Step S301, based on the historical data of power outages in the distribution network, initialize the particle swarm and randomly generate particle positions and velocities;

[0085] Step S302, assigning the position and velocity of each particle to the quantization factor and the proportional factor in the fuzzy controller in turn; measuring the individual performance by the integral of the product of time and the absolute value of the error, and constructing the objective function; and adjusting the inertia weight in an adaptive manner;

[0086] Step S303: select SA;

[0087] Step S304: When the termination condition is met, the iteration is terminated, the optimal particle fitness value is output, and the particle position and speed at the next moment are updated.

[0088] Step 4: Design a distribution network fault outage prediction platform with dual complementary models to predict distribution network fault outage indicators. The dual models are the IFA-RVM prediction model and the SA-PSO-RVM prediction model.

[0089] The evaluation method of power supply reliability of distribution network provided by the present invention includes: analyzing the influencing factors of power outage caused by distribution network faults based on the hierarchical analysis method, and constructing an evaluation system of influencing factors of power outage caused by faults; building a FA-RVM prediction model combining an improved firefly algorithm and a related vector machine to predict the power outage index of distribution network faults; building a SA-PSO-RVM prediction model based on simulated annealing-particle swarm algorithm; designing a distribution network fault power outage prediction platform with dual models complementing each other, and predicting the power outage index of distribution network faults, wherein the dual models are the IFA-RVM prediction model and the SA-PSO-RVM prediction model. The present invention uses advanced algorithm models to predict power outage caused by distribution network faults, meets the requirements of safe and reliable power system and economic operation, can improve the reliability of power grid, reduce the occurrence of power system accidents, and improve the economic benefits of power grid operation. At the same time, the improvement of distribution network reliability can better optimize the power supply environment and effectively improve the satisfaction of power users.

[0090] Example 2

[0091] An embodiment of the present invention provides a system for evaluating the reliability of power supply of a distribution network, which includes:

[0092] A system construction module, which is used to analyze the influencing factors of power outages caused by power distribution network failures based on the analytic hierarchy process and to build an evaluation system for the influencing factors of power outages caused by power distribution network failures;

[0093] The prediction module is used to build a FA-RVM prediction model combining an improved firefly algorithm and a relevance vector machine to predict the distribution network fault outage indicators;

[0094] A model building module, which is used to build a SA-PSO-RVM prediction model based on simulated annealing-particle swarm algorithm;

[0095] The prediction module is used to design a distribution network fault power outage prediction platform with dual complementary models to predict distribution network fault power outage indicators. The dual models are the IFA-RVM prediction model and the SA-PSO-RVM prediction model.

[0096] Furthermore, the prediction module is also used to:

[0097] Divide various influencing factors of power outage into several interrelated levels in order;

[0098] The expert scoring system is used to make judgments, and the relative importance of factors at each level is compared and analyzed. The index weights are used to rank the influencing factors, and then an evaluation system for the influencing factors of fault power outages is established.

[0099] Furthermore, the prediction module is also used to:

[0100] The data after correction of outliers and missing values ​​are subjected to FA-RVM denoising to obtain denoised signal data;

[0101] The following formula is used to synthesize the acceleration of the denoised signal data:

[0102]

[0103] Among them: A x , A y , A z They are the acceleration signals after denoising on the x, y, and z axes respectively.

[0104] Furthermore, the prediction module is also used to:

[0105] The optimal variational mode decomposition method parameters K and α are solved based on the firefly algorithm FA; the specific process is:

[0106] (1) Setting the value range of K and α in the variational mode decomposition (VMD) algorithm; K is the number of modes of the decomposition target, and α is the quadratic penalty factor; 3≤K≤20, 500≤α≤2500;

[0107] (2) Initialize the basic parameters of the firefly algorithm FA, which are the problem dimension, population size, maximum attraction β0, light absorption coefficient, step factor, number of iterations, and the value range of K and α;

[0108] (3) Randomly initialize the K value and α value of the i-th firefly as the initial position in the space, i = 1, 2, ..., 25;

[0109] (4) Calculate the fitness function of the i-th firefly as the fluorescein value l of the i-th firefly at time t i (t), as the maximum fluorescence brightness I0 of the i-th firefly;

[0110] (5) Update the spatial position of the i-th firefly, that is, the new K value and α value;

[0111] Through the obtained K value and α value, the collected distribution network power outage historical data is subjected to variational mode decomposition, and the dominant signal component, interference signal component, and noise signal component are determined.

[0112] Furthermore, the model building module is also used to:

[0113] Based on the historical data of power outages in the distribution network, the particle swarm is initialized and the particle positions and velocities are randomly generated;

[0114] The position and velocity of each particle are assigned to the quantization factor and the proportional factor in the fuzzy controller in turn; the individual performance is measured by the integral of the product of time and the absolute value of the error to construct the objective function; the inertia weight is adjusted in an adaptive manner;

[0115] Make SA selection;

[0116] When the termination condition is met, the iteration is terminated, the optimal particle fitness value is output, and the particle position and velocity at the next moment are updated.

[0117] The evaluation system of power supply reliability of distribution network provided by the present invention includes: a system construction module, which is used for analyzing the influencing factors of distribution network fault power outage based on the hierarchical analysis method, and constructing an evaluation system of influencing factors of fault power outage; a prediction module, which is used to build a FA-RVM prediction model combining an improved firefly algorithm and a related vector machine, and predict the distribution network fault power outage index; a model construction module, which is used to build a SA-PSO-RVM prediction model based on a simulated annealing-particle swarm algorithm; a prediction module, which is used to design a distribution network fault power outage prediction platform with dual models complementing each other, and predict the distribution network fault power outage index, wherein the dual models are an IFA-RVM prediction model and a SA-PSO-RVM prediction model. The present invention uses an advanced algorithm model to predict distribution network fault power outages, meets the requirements of safe and reliable power system and economic operation, can improve the reliability of the power grid, reduce the occurrence of power system accidents, and improve the economic benefits of power grid operation. At the same time, the improvement of the reliability of the distribution network can better optimize the power supply environment and effectively improve the satisfaction of electricity users.

[0118] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art may still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating the reliability of power supply of a distribution network, characterized in that: The method comprises: Step 1: Analyze the influencing factors of power outage caused by distribution network faults based on the analytic hierarchy process and build an evaluation system for the influencing factors of power outage caused by faults; Step 2: Build a FA-RVM prediction model combining the improved firefly algorithm and the relevance vector machine to predict the distribution network fault outage index; Step 3: Based on simulated annealing-particle swarm algorithm, SA-PSO-RVM prediction model is constructed; Step 4: Design a distribution network fault outage prediction platform with dual complementary models to predict distribution network fault outage indicators. The dual models are the IFA-RVM prediction model and the SA-PSO-RVM prediction model.

2. A method for evaluating power supply reliability of a distribution network according to claim 1, characterized in that: Step one includes: Step S101, various influencing factors of power outage are divided into several interrelated levels in order; Step S102: judge through the expert scoring system, compare and analyze the relative importance of each layer of factors, use the indicator weight to sort the influencing factors, and then establish a fault power outage influencing factor evaluation system.

3. A method for evaluating the reliability of power supply of a distribution network according to claim 2, characterized in that: Step 2 includes: Step S201, performing FA-RVM denoising on the data after correction of outliers and missing values ​​to obtain denoised signal data; Step S202: synthesize acceleration of the denoised signal data using the following formula: Among them: A x , A y , A z They are the acceleration signals after denoising on the x, y, and z axes respectively.

4. A method for evaluating power supply reliability of a distribution network according to claim 3, characterized in that: Step 2 includes: Step 211, solving the optimal variational mode decomposition method parameters K and α based on the firefly algorithm FA; the specific process is: (1) Setting the value range of K and α in the variational mode decomposition (VMD) algorithm; K is the number of modes of the decomposition target, and α is the quadratic penalty factor; 3≤K≤20, 500≤α≤2500; (2) Initialize the basic parameters of the firefly algorithm FA, which are the problem dimension, population size, maximum attraction β0, light absorption coefficient, step factor, number of iterations, and the value range of K and α; (3) Randomly initialize the K value and α value of the i-th firefly as the initial position in the space, i = 1, 2, ..., 25; (4) Calculate the fitness function of the i-th firefly as the fluorescein value l of the i-th firefly at time t i (t), as the maximum fluorescence brightness I0 of the i-th firefly; (5) Update the spatial position of the i-th firefly, that is, the new K value and α value; Step 2012: Using the K value and the α value obtained in step 2011, perform variational mode decomposition on the collected historical data of power outages in the distribution network, and determine the dominant signal component, the interference signal component, and the noise signal component.

5. The method for evaluating the reliability of power supply of a distribution network according to claim 1, characterized in that: Step three includes: Step S301, based on the historical data of power outages in the distribution network, initialize the particle swarm and randomly generate particle positions and velocities; Step S302, assigning the position and velocity of each particle to the quantization factor and the proportional factor in the fuzzy controller in turn; measuring the individual performance by the integral of the product of time and the absolute value of the error, and constructing the objective function; and adjusting the inertia weight in an adaptive manner; Step S303: select SA; Step S304: When the termination condition is met, the iteration is terminated, the optimal particle fitness value is output, and the particle position and speed at the next moment are updated.

6. A distribution network power supply reliability evaluation system, characterized in that: It includes: A system construction module, which is used to analyze the influencing factors of power outages caused by power distribution network failures based on the analytic hierarchy process and to build an evaluation system for the influencing factors of power outages caused by power distribution network failures; The prediction module is used to build a FA-RVM prediction model combining an improved firefly algorithm and a relevance vector machine to predict the distribution network fault outage indicators; A model building module, which is used to build a SA-PSO-RVM prediction model based on simulated annealing-particle swarm algorithm; The prediction module is used to design a distribution network fault power outage prediction platform with dual complementary models to predict distribution network fault power outage indicators. The dual models are the IFA-RVM prediction model and the SA-PSO-RVM prediction model.

7. A distribution network power supply reliability evaluation system according to claim 6, characterized in that: The prediction module is also used to: Divide various influencing factors of power outage into several interrelated levels in order; The expert scoring system is used to make judgments, and the relative importance of factors at each level is compared and analyzed. The index weights are used to rank the influencing factors, and then an evaluation system for the influencing factors of fault power outages is established.

8. A distribution network power supply reliability evaluation system according to claim 7, characterized in that: The prediction module is also used to: The data after correction of outliers and missing values ​​are subjected to FA-RVM denoising to obtain denoised signal data; The following formula is used to synthesize the acceleration of the denoised signal data: Among them: A x , A y , A z They are the acceleration signals after denoising on the x, y, and z axes respectively.

9. A distribution network power supply reliability evaluation system according to claim 8, characterized in that: The prediction module is also used to: The optimal variational mode decomposition method parameters K and α are solved based on the firefly algorithm FA; the specific process is: (1) Setting the value range of K and α in the variational mode decomposition (VMD) algorithm; K is the number of modes of the decomposition target, and α is the quadratic penalty factor; 3≤K≤20, 500≤α≤2500; (2) Initialize the basic parameters of the firefly algorithm FA, which are the problem dimension, population size, maximum attraction β0, light absorption coefficient, step factor, number of iterations, and the value range of K and α; (3) Randomly initialize the K value and α value of the i-th firefly as the initial position in the space, i = 1, 2, ..., 25; (4) Calculate the fitness function of the i-th firefly as the fluorescein value l of the i-th firefly at time t i (t), as the maximum fluorescence brightness I0 of the i-th firefly; (5) Update the spatial position of the i-th firefly, that is, the new K value and α value; Through the obtained K value and α value, the collected distribution network power outage historical data is subjected to variational mode decomposition, and the dominant signal component, interference signal component, and noise signal component are determined.

10. A distribution network power supply reliability evaluation system according to claim 6, characterized in that: The model building module is also used to: Based on the historical data of power outages in the distribution network, the particle swarm is initialized and the particle positions and velocities are randomly generated; The position and velocity of each particle are assigned to the quantization factor and the proportional factor in the fuzzy controller in turn; the individual performance is measured by the integral of the product of time and the absolute value of the error to construct the objective function; the inertia weight is adjusted in an adaptive manner; Make SA selection; When the termination condition is met, the iteration is terminated, the optimal particle fitness value is output, and the particle position and velocity at the next moment are updated.

Images