Power distribution area reactive compensation control method based on energy storage PCS converter

Abstract

The invention discloses a power distribution area reactive compensation control method based on an energy storage PCS converter, and the method comprises the following steps: 1, data collection and processing: collecting the power parameters of a power distribution area in real time through employing the technology of Internet of Things, such as voltage, current, active power, reactive power, and frequency; the data preprocessing module is used for cleaning, filtering and normalizing the collected data to ensure the accuracy and consistency of the data; 2, constructing a multi-objective optimization model; designing an objective function; and constructing a multi-objective optimization model comprising reactive power compensation, active power optimization, voltage stability and energy efficiency improvement. According to the invention, the performance and reliability of the reactive compensation control method for the power distribution area based on the energy storage PCS converter are effectively improved, and more efficient and more stable power grid operation is realized; the system can quickly isolate a fault unit after detecting a fault, realizes cooperative work among multiple PCS converters through distributed optimization, and ensures stable operation of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of converter control, and in particular to a reactive power compensation control method for a distribution station area based on an energy storage PCS converter. Background Art

[0002] The application of energy storage PCS converters in reactive power compensation in distribution substations aims to improve power quality and grid stability. Traditional reactive power compensation methods have problems such as slow response and poor adaptability, and it is difficult to achieve efficient reactive power compensation, especially in complex grid environments.

[0003] Therefore, the introduction of multi-objective optimization control and self-healing control system can significantly improve the performance and reliability of the system. To this end, we propose a reactive power compensation control method for distribution station area based on energy storage PCS converter. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above problems existing in the existing reactive power compensation control method of distribution station area based on energy storage PCS converter, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide a reactive power compensation control method for a distribution station area based on an energy storage PCS converter, which effectively improves the performance and reliability of the reactive power compensation control method for a distribution station area based on an energy storage PCS converter, and realizes more efficient and stable power grid operation.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a reactive power compensation control method for a distribution station area based on an energy storage PCS converter, comprising the following steps:

[0008] Step 1: Data collection and processing:

[0009] Use IoT technology to collect power parameters of distribution stations in real time, such as voltage, current, active power, reactive power, and frequency; use the data preprocessing module to clean, filter, and normalize the collected data to ensure data accuracy and consistency;

[0010] Step 2: Multi-objective optimization model construction:

[0011] Objective function design: Construct a multi-objective optimization model including reactive power compensation, active power optimization, voltage stability and energy efficiency improvement. The objective function is expressed as:

[0012] Minimize f(x)=w1·Q(x)+w2·P(x)+w3·V(x)+w4·η(x)

[0013] Among them, Q(x) represents reactive power compensation, P(x) represents active power optimization, V(x) represents voltage stability, η(x) represents energy efficiency improvement, and w i is the weight coefficient of each objective; Constraints: including voltage, current, and safe operation parameters to ensure the feasibility of the optimization results in practical applications;

[0014] Step 3: Optimization algorithm:

[0015] Use the function in step 2 to solve the multi-objective optimization model and obtain the optimal control strategy; use parallel computing and distributed computing technology to accelerate the optimization process and improve computing efficiency;

[0016] Step 4: Dynamic adjustment and feedback control:

[0017] Monitor the grid status in real time, dynamically adjust the reactive power compensation strategy according to the actual operation situation, ensure the optimal operation of the system under different load conditions, and continuously modify the optimization parameters and control strategy through the feedback control mechanism to improve the system's adaptive ability and response speed;

[0018] Step 5: Fault detection and diagnosis:

[0019] Adopt intelligent sensors and fault detection algorithms to monitor system operation status in real time, detect potential faults and anomalies, build fault diagnosis models, and quickly locate fault locations and fault types;

[0020] Step 6: Self-healing control strategies include:

[0021] Fault isolation: After a fault is detected, the faulty unit is quickly isolated to prevent the fault from spreading and ensure the normal operation of the rest of the system;

[0022] Fault recovery: Utilize backup modules and redundant design to automatically switch to backup channels or devices to restore normal operation of the system;

[0023] Dynamic reconstruction: Dynamically adjust reactive power compensation strategy and system structure according to grid status and load changes to achieve adaptive reconstruction and improve system robustness and stability.

[0024] As a preferred solution of the reactive power compensation control method for distribution station area based on energy storage PCS converter described in the present invention, the constraints of the multi-objective optimization model in step 2 are:

[0025] Voltage limit: V min ≤V(x)≤V max ;

[0026] Reactive power limitation: Q min ≤Q(x)≤Q max ;

[0027] Active power limit: P min ≤P(x)≤P max ;

[0028] Energy efficiency limit: η min ≤η(x)≤η max .

[0029] As a preferred solution of the reactive power compensation control method of the distribution station area based on the energy storage PCS converter of the present invention, the optimization algorithm in step three adopts the particle swarm optimization algorithm, and the specific steps are as follows:

[0030] S1, initialization: randomly generate a particle swarm, each particle represents a possible solution, and initialize the particle position and velocity;

[0031] S2, fitness function: calculate the fitness of each particle, the fitness function is our objective function f(x);

[0032] S3. Update particle speed and position:

[0033] v i (t+1)=wv i (t)+c1r1(p i (t)-x i (t))+c2r2(g(t)-x i (t))

[0034] x i (t+1)=x i (t)+v i (t+1)

[0035] Among them, v i is the particle velocity, x i is the particle position, p i is the best historical position of the particle, g is the global best position, w is the inertia weight, c1 and c2 are acceleration constants, and r1 and r2 are random numbers;

[0036] S4, update individual and global best positions: compare the fitness of each particle and update its historical best position p i and the global optimal position g;

[0037] S5. Termination condition: The algorithm is terminated when the preset number of iterations is reached or the particle position no longer changes significantly.

[0038] As a preferred solution of the reactive power compensation control method of the distribution station area based on the energy storage PCS converter of the present invention, the optimization algorithm in step three can also select a genetic algorithm, and the specific algorithm steps are:

[0039] B1. Initialization: Randomly generate the initial population, each individual represents a possible solution;

[0040] B2. Fitness function: Calculate the fitness of each individual. The fitness function is our objective function.

[0041] B3, Selection: Select the individuals with better fitness to enter the next generation, using roulette and tournament selection methods;

[0042] B4. Crossover: Perform crossover operation on the selected individuals to generate new individuals;

[0043] B5. Mutation: Perform mutation operations on individuals after crossover to increase the diversity of the population;

[0044] B6. Update population: replace part or all of the old population with newly generated individuals;

[0045] B7. Termination condition: The algorithm is terminated when the preset number of iterations is reached or the population fitness is no longer significantly improved.

[0046] As a preferred solution of the reactive power compensation control method of the distribution station area based on the energy storage PCS converter of the present invention, the optimization algorithm in step three can also select a multi-objective optimization algorithm, and the specific steps are as follows:

[0047] C1. Initialization: randomly generate the initial population;

[0048] C2, non-dominated sorting: non-dominated sorting of the population, divided into different non-dominated frontiers;

[0049] C3, Crowding calculation: Calculate the crowding degree of each individual to maintain the diversity of the population;

[0050] C4, selection, crossover and mutation: select individuals for crossover and mutation according to non-dominated rank and crowding degree to generate a new population;

[0051] C5, merge population: merge the parent and offspring populations;

[0052] C6. Select the next generation population: Select the next generation population based on non-dominated sorting and crowding;

[0053] C7. Termination condition: The algorithm is terminated when the preset number of iterations is reached.

[0054] As a preferred solution of the reactive power compensation control method of the distribution station area based on the energy storage PCS converter of the present invention, wherein: the step 4 obtains the optimal reactive power compensation control strategy through the optimization algorithm in step 3, and the specific implementation steps of the control strategy are as follows:

[0055] A1. Parameter initialization: Initialize various parameters of the reactive power compensation system;

[0056] A2. Real-time data collection: Use IoT technology to collect power grid operation data in real time;

[0057] A3. Optimization calculation: According to the real-time data input multi-objective optimization algorithm, the optimal reactive power compensation control parameters are calculated;

[0058] A4. Control execution: input the control parameters obtained by the optimization algorithm into the PCS converter to execute reactive power compensation control;

[0059] A5. Feedback adjustment: monitor the control effect in real time, and dynamically adjust the control parameters according to the feedback data to ensure the optimal operation of the system.

[0060] As a preferred solution of the reactive power compensation control method for distribution station area based on energy storage PCS converter of the present invention, the fault detection algorithm in step 5 adopts support vector machine for fault detection, which specifically includes:

[0061] Set the input feature x, the corresponding classification label y, and the classifier function f(x):

[0062] f(x)=w T x+b

[0063] Determine the optimal w and b through the training set, and implement detection during operation to see if the input features meet the fault conditions;

[0064] The fault diagnosis model uses a neural network to perform fault diagnosis. Assuming the input is x and the output is the fault type y, the output of the neural network is:

[0065] y=σ(Wx+b)

[0066] Among them, W is the weight matrix, b is the bias vector, and σ is the activation function.

[0067] As a preferred solution of the reactive power compensation control method for distribution station area based on energy storage PCS converter according to the present invention, in the fault isolation process of step 6, it is assumed that there are n PCS converters in the system and the faulty converter is the i-th one, then:

[0068] If the function f(x) represents a fault, isolate the PCS i

[0069] During the fault recovery process, it is assumed that the backup module is the PCS backup ,but:

[0070] During the fault recovery process, assume that the standby device module is the PCS backup , then activate PCS backup And reconfigure system parameters;

[0071] In the dynamic reconstruction process, the published control algorithm is used, assuming that x i is the control parameter of the i-th PCS, and the objective function is f(x):

[0072]

[0073] Dynamic adjustment is achieved through interactive optimization;

[0074] Distributed optimization algorithm is used to achieve collaborative work between multiple PCS converters:

[0075] initialization:

[0076] Each PCS converter initializes control parameters x i ;

[0077] Local gradient calculation:

[0078] Each PCS converter calculates its own objective function gradient:

[0079]

[0080] Global gradient summary:

[0081] Utilize the communication between neighbor nodes to summarize the global gradient:

[0082]

[0083] Parameter update:

[0084] Each PCS converter updates its control parameters according to the global gradient:

[0085] x i ←x i -αg

[0086] Here, α is the learning rate.

[0087] Beneficial effects of the present invention: The present invention constructs a multi-objective optimization model, and the objective function of the model can comprehensively consider reactive power compensation, active power optimization, voltage stability and energy efficiency improvement, effectively improving the performance and reliability of the reactive compensation control method of the distribution station area based on the energy storage PCS converter, and realizing more efficient and stable power grid operation; in addition, through the self-healing control algorithm, the system can quickly isolate the faulty unit after detecting the fault, activate the backup module, and realize the coordinated work between multiple PCS converters through distributed optimization, so as to ensure the stable operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0089] Figure 1 The present invention is a method block diagram of a reactive power compensation control method for a distribution station area based on an energy storage PCS converter. DETAILED DESCRIPTION

[0090] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0091] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0092] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0093] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0094] Reference Figure 1, provides a reactive power compensation control method for a distribution station area based on an energy storage PCS converter, comprising the following steps:

[0095] Step 1: Data collection and processing:

[0096] Use IoT technology to collect power parameters of distribution stations in real time, such as voltage, current, active power, reactive power, and frequency; use the data preprocessing module to clean, filter, and normalize the collected data to ensure data accuracy and consistency;

[0097] Step 2: Multi-objective optimization model construction:

[0098] Objective function design: Construct a multi-objective optimization model including reactive power compensation, active power optimization, voltage stability and energy efficiency improvement. The objective function is expressed as:

[0099] Minimize f(x)=w1·Q(x)+w2·P(x)+w3·V(x)+w4·η(x)

[0100] Among them, Q(x) represents reactive power compensation, P(x) represents active power optimization, V(x) represents voltage stability, η(x) represents energy efficiency improvement, and w i is the weight coefficient of each objective; Constraints: including voltage, current, and safe operation parameters to ensure the feasibility of the optimization results in practical applications;

[0101] Step 3: Optimization algorithm:

[0102] Use the function in step 2 to solve the multi-objective optimization model and obtain the optimal control strategy; use parallel computing and distributed computing technology to accelerate the optimization process and improve computing efficiency;

[0103] Step 4: Dynamic adjustment and feedback control:

[0104] Monitor the grid status in real time, dynamically adjust the reactive power compensation strategy according to the actual operation situation, ensure the optimal operation of the system under different load conditions, and continuously modify the optimization parameters and control strategy through the feedback control mechanism to improve the system's adaptive ability and response speed;

[0105] Step 5: Fault detection and diagnosis:

[0106] Adopt intelligent sensors and fault detection algorithms to monitor system operation status in real time, detect potential faults and anomalies, build fault diagnosis models, and quickly locate fault locations and fault types;

[0107] Step 6: Self-healing control strategies include:

[0108] Fault isolation: After a fault is detected, the faulty unit is quickly isolated to prevent the fault from spreading and ensure the normal operation of the rest of the system;

[0109] Fault recovery: Utilize backup modules and redundant design to automatically switch to backup channels or devices to restore normal operation of the system;

[0110] Dynamic reconstruction: Dynamically adjust reactive power compensation strategy and system structure according to grid status and load changes to achieve adaptive reconstruction and improve system robustness and stability.

[0111] Among them, the constraints of the multi-objective optimization model in step 2 are:

[0112] Voltage limit: V min ≤V(x)≤V max ;

[0113] Reactive power limitation: Q min ≤Q(x)≤Q max ;

[0114] Active power limit: P min ≤P(x)≤P max ;

[0115] Energy efficiency limit: η min ≤η(x)≤η max .

[0116] Specifically, the optimization algorithm in step 3 adopts a particle swarm optimization algorithm, and the specific steps are as follows:

[0117] S1, initialization: randomly generate a particle swarm, each particle represents a possible solution, and initialize the particle position and velocity;

[0118] S2, fitness function: calculate the fitness of each particle, the fitness function is our objective function f(x);

[0119] S3. Update particle speed and position:

[0120] v i (t+1)=wv i (t)+c1r1(p i (t)-x i (t))+c2r2(g(t)-x i (t))

[0121] x i (t+1)=x i (t)+v i (t+1)

[0122] Among them, v iis the particle velocity, x i is the particle position, p i is the best historical position of the particle, g is the global best position, w is the inertia weight, c1 and c2 are acceleration constants, and r1 and r2 are random numbers;

[0123] S4, update individual and global best positions: compare the fitness of each particle and update its historical best position p i and the global optimal position g;

[0124] S5. Termination condition: The algorithm is terminated when the preset number of iterations is reached or the particle position no longer changes significantly.

[0125] The optimization algorithm in step 3 can also be a genetic algorithm, and the specific algorithm steps are:

[0126] B1. Initialization: Randomly generate the initial population, each individual represents a possible solution;

[0127] B2. Fitness function: Calculate the fitness of each individual. The fitness function is our objective function.

[0128] B3, Selection: Select the individuals with better fitness to enter the next generation, using roulette and tournament selection methods;

[0129] B4. Crossover: Perform crossover operation on the selected individuals to generate new individuals;

[0130] B5. Mutation: Perform mutation operations on individuals after crossover to increase the diversity of the population;

[0131] B6. Update population: replace part or all of the old population with newly generated individuals;

[0132] B7. Termination condition: The algorithm is terminated when the preset number of iterations is reached or the population fitness is no longer significantly improved.

[0133] Furthermore, the optimization algorithm in step three can also select a multi-objective optimization algorithm, and the specific steps are as follows:

[0134] C1. Initialization: randomly generate the initial population;

[0135] C2, non-dominated sorting: non-dominated sorting of the population, divided into different non-dominated frontiers;

[0136] C3, Crowding calculation: Calculate the crowding degree of each individual to maintain the diversity of the population;

[0137] C4, selection, crossover and mutation: select individuals for crossover and mutation according to non-dominated rank and crowding degree to generate a new population;

[0138] C5, merge population: merge the parent and offspring populations;

[0139] C6. Select the next generation population: Select the next generation population based on non-dominated sorting and crowding;

[0140] C7. Termination condition: The algorithm is terminated when the preset number of iterations is reached.

[0141] Among them, the step 4 obtains the optimal reactive power compensation control strategy through the optimization algorithm in step 3, and the specific implementation steps of the control strategy are as follows:

[0142] A1. Parameter initialization: Initialize various parameters of the reactive power compensation system;

[0143] A2. Real-time data collection: Use IoT technology to collect power grid operation data in real time;

[0144] A3. Optimization calculation: According to the real-time data input multi-objective optimization algorithm, the optimal reactive power compensation control parameters are calculated;

[0145] A4. Control execution: input the control parameters obtained by the optimization algorithm into the PCS converter to execute reactive power compensation control;

[0146] A5. Feedback adjustment: monitor the control effect in real time, and dynamically adjust the control parameters according to the feedback data to ensure the optimal operation of the system.

[0147] Furthermore, the fault detection algorithm in step 5 uses a support vector machine to perform fault detection, specifically including:

[0148] Set the input feature x, the corresponding classification label y, and the classifier function f(x):

[0149] f(x)=w T x+b

[0150] Determine the optimal w and b through the training set, and implement detection during operation to see if the input features meet the fault conditions;

[0151] The fault diagnosis model uses a neural network to perform fault diagnosis. Assuming the input is x and the output is the fault type y, the output of the neural network is:

[0152] y=σ(Wx+b)

[0153] Among them, W is the weight matrix, b is the bias vector, and σ is the activation function.

[0154] Furthermore, in the fault isolation process of step 6, it is assumed that there are n PCS converters in the system and the faulty converter is the i-th one, then:

[0155] If the function f(x) represents a fault, isolate the PCS i

[0156] During the fault recovery process, it is assumed that the backup module is the PCS backup ,but:

[0157] During the fault recovery process, assume that the standby device module is the PCS backup , then activate PCS backup And reconfigure system parameters;

[0158] In the dynamic reconstruction process, the published control algorithm is used, assuming that x i is the control parameter of the i-th PCS, and the objective function is f(x):

[0159]

[0160] Dynamic adjustment is achieved through interactive optimization;

[0161] Distributed optimization algorithm is used to achieve collaborative work between multiple PCS converters:

[0162] initialization:

[0163] Each PCS converter initializes control parameters x i ;

[0164] Local gradient calculation:

[0165] Each PCS converter calculates its own objective function gradient:

[0166]

[0167] Global gradient summary:

[0168] Utilize the communication between neighbor nodes to summarize the global gradient:

[0169]

[0170] Parameter update:

[0171] Each PCS converter updates its control parameters according to the global gradient:

[0172] x i ←x i -αg

[0173] Here, α is the learning rate.

[0174] Specific embodiments:

[0175] Assume there are three PCS converters, namely PCS1, PCS2, and PCS3. The specific interactions of the system are as follows:

[0176] initialization:

[0177] PCS1: x1 = x 1,0

[0178] PCS2: x2=x 2,0

[0179] PCS3:X3=X 3,0

[0180] Fault detection and diagnosis:

[0181] PCS2 detects the fault, SVM outputs the fault signal, and the neural network diagnoses the fault type;

[0182] Fault isolation: Isolate PCS2;

[0183] Failure recovery:

[0184] Activate the backup module PCS backup Replaces PCS2;

[0185] Reconfigure system parameters;

[0186] Dynamic Reconstruction:

[0187] Through distributed control algorithms, PCS1, PCS3 and PCS backup Jointly optimize control parameters;

[0188] Local gradient calculation:

[0189]

[0190]

[0191]

[0192] Global gradient summary:

[0193] g=g1+g3+g backup

[0194] Parameter update:

[0195] x1←x1-αg

[0196] x3←x3-αg

[0197] x backup ←x backup -αg

[0198] System Monitoring:

[0199] The operation status of the entire system is monitored through the Internet of Things platform to ensure the effective implementation of the self-healing control strategy.

[0200] Through the above self-healing control algorithm, the system can quickly isolate the faulty unit after detecting a fault, activate the backup module, and achieve collaborative work between multiple PCS converters through distributed optimization to ensure stable operation of the system.

[0201] A computer device includes a memory and a processor. The computer device may be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device may be a touch layer covering the display screen, or may be a key, trackball or touchpad provided on the housing of the computer device, or may be an external keyboard, touchpad or mouse, etc.

[0202] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements a reactive power compensation control method for a distribution station area based on an energy storage PCS converter as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (Static Random Access Memory, referred to as SRAM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), an erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), a programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), a read-only memory (Read-Only Memory, referred to as ROM), a magnetic memory, a flash memory, a disk or an optical disk.

[0203] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A reactive power compensation control method for distribution station area based on energy storage PCS converter, characterized in that: The following steps are involved: Step 1: Data collection and processing: Use IoT technology to collect power parameters of distribution stations in real time, such as voltage, current, active power, reactive power, and frequency; use the data preprocessing module to clean, filter, and normalize the collected data to ensure data accuracy and consistency; Step 2: Multi-objective optimization model construction: Objective function design: Construct a multi-objective optimization model including reactive power compensation, active power optimization, voltage stability and energy efficiency improvement. The objective function is expressed as: Minimize f(x)=w1·Q(x)+w2·P(x)+w3·V(x)+w4·η(x) Among them, Q(x) represents reactive power compensation, P(x) represents active power optimization, V(x) represents voltage stability, η(x) represents energy efficiency improvement, and w i is the weight coefficient of each objective; Constraints: including voltage, current, and safe operation parameters to ensure the feasibility of the optimization results in practical applications; Step 3: Optimization algorithm: Use the function in step 2 to solve the multi-objective optimization model and obtain the optimal control strategy; use parallel computing and distributed computing technology to accelerate the optimization process and improve computing efficiency; Step 4: Dynamic adjustment and feedback control: Monitor the grid status in real time, dynamically adjust the reactive power compensation strategy according to the actual operation situation, ensure the optimal operation of the system under different load conditions, and continuously modify the optimization parameters and control strategy through the feedback control mechanism to improve the system's adaptive ability and response speed; Step 5: Fault detection and diagnosis: Adopt intelligent sensors and fault detection algorithms to monitor system operation status in real time, detect potential faults and anomalies, build fault diagnosis models, and quickly locate fault locations and fault types; Step 6: Self-healing control strategies include: Fault isolation: After a fault is detected, the faulty unit is quickly isolated to prevent the fault from spreading and ensure the normal operation of the rest of the system; Fault recovery: Utilize backup modules and redundant design to automatically switch to backup channels or devices to restore normal operation of the system; Dynamic reconstruction: Dynamically adjust reactive power compensation strategy and system structure according to grid status and load changes to achieve adaptive reconstruction and improve system robustness and stability.

2. The reactive power compensation control method for distribution station area based on energy storage PCS converter according to claim 1 is characterized in that: The constraints of the multi-objective optimization model in step 2 are: Voltage limit: V min ≤V(x)≤V max ; Reactive power limitation: Q min ≤Q(x)≤Q max ; Active power limit: P min ≤P(x)≤P max ; Energy efficiency limit: η min ≤η(x)≤η max .

3. The reactive power compensation control method for distribution station area based on energy storage PCS converter according to claim 2 is characterized in that: The optimization algorithm in step 3 adopts the particle swarm optimization algorithm, and the specific steps are as follows: S1, initialization: randomly generate a particle swarm, each particle represents a possible solution, and initialize the particle position and velocity; S2, fitness function: calculate the fitness of each particle, the fitness function is our objective function f(x); S3. Update particle speed and position: v i (t+1)=wv i (t)+c1r1(p i (t)-x i (t))+c2r2(g(t)-x i (t)) x i (t+1)=x i (t)+v i (t+1) Among them, v i is the particle velocity, x i is the particle position, p i is the best historical position of the particle, g is the global best position, w is the inertia weight, c1 and c2 are acceleration constants, and r1 and r2 are random numbers; S4, update individual and global best positions: compare the fitness of each particle and update its historical best position p i and the global optimal position g; S5. Termination condition: The algorithm is terminated when the preset number of iterations is reached or the particle position no longer changes significantly.

4. The reactive power compensation control method for distribution station area based on energy storage PCS converter according to claim 1 is characterized in that: The optimization algorithm in step 3 can also select a genetic algorithm, and the specific algorithm steps are: B1. Initialization: Randomly generate the initial population, each individual represents a possible solution; B2. Fitness function: Calculate the fitness of each individual. The fitness function is our objective function. B3, Selection: Select the individuals with better fitness to enter the next generation, using roulette and tournament selection methods; B4. Crossover: Perform crossover operation on the selected individuals to generate new individuals; B5. Mutation: Perform mutation operations on individuals after crossover to increase the diversity of the population; B6. Update population: replace part or all of the old population with newly generated individuals; B7. Termination condition: The algorithm is terminated when the preset number of iterations is reached or the population fitness is no longer significantly improved.

5. The reactive power compensation control method for distribution station area based on energy storage PCS converter according to claim 1 is characterized in that: The optimization algorithm in step 3 can also select a multi-objective optimization algorithm, and the specific steps are as follows: C1. Initialization: randomly generate the initial population; C2, non-dominated sorting: non-dominated sorting of the population, divided into different non-dominated frontiers; C3, Crowding calculation: Calculate the crowding degree of each individual to maintain the diversity of the population; C4, selection, crossover and mutation: select individuals for crossover and mutation according to non-dominated rank and crowding degree to generate a new population; C5, merge population: merge the parent and offspring populations; C6. Select the next generation population: Select the next generation population based on non-dominated sorting and crowding; C7. Termination condition: The algorithm is terminated when the preset number of iterations is reached.

6. The reactive power compensation control method for distribution station area based on energy storage PCS converter according to claim 5 is characterized in that: The step 4 obtains the optimal reactive power compensation control strategy through the optimization algorithm in step 3. The specific implementation steps of the control strategy are as follows: A1. Parameter initialization: Initialize various parameters of the reactive power compensation system; A2. Real-time data collection: Use IoT technology to collect power grid operation data in real time; A3. Optimization calculation: According to the real-time data input multi-objective optimization algorithm, the optimal reactive power compensation control parameters are calculated; A4. Control execution: input the control parameters obtained by the optimization algorithm into the PCS converter to execute reactive power compensation control; A5. Feedback adjustment: monitor the control effect in real time, and dynamically adjust the control parameters according to the feedback data to ensure the optimal operation of the system.

7. The reactive power compensation control method for distribution station area based on energy storage PCS converter according to claim 1 is characterized in that: The fault detection algorithm in step 5 uses a support vector machine to perform fault detection, which specifically includes: Set the input feature x, the corresponding classification label y, and the classifier function f(x): f(x)=w T x+b Determine the optimal w and b through the training set, and implement detection during operation to see if the input features meet the fault conditions; The fault diagnosis model uses a neural network to perform fault diagnosis. Assuming the input is x and the output is the fault type y, the output of the neural network is: y=σ(Wx+b) Among them, W is the weight matrix, b is the bias vector, and σ is the activation function.

8. The reactive power compensation control method for distribution station area based on energy storage PCS converter according to claim 7 is characterized in that: In the fault isolation process of step 6, it is assumed that there are n PCS converters in the system and the faulty converter is the i-th one, then: If the function f(x) represents a fault, isolate the PCS i During the fault recovery process, it is assumed that the backup module is the PCS backup ,but: During the fault recovery process, assume that the standby device module is the PCS backup , then activate PCS backup And reconfigure system parameters; In the dynamic reconstruction process, the published control algorithm is used, assuming that x i is the control parameter of the i-th PCS, and the objective function is f(x); Distributed optimization algorithm is used to achieve collaborative work between multiple PCS converters: initialization: Each PCS converter initializes control parameters x i ; Local gradient calculation: Each PCS converter calculates its own objective function gradient: Global gradient summary: Utilize the communication between neighbor nodes to summarize the global gradient: Parameter update: Each PCS converter updates its control parameters according to the global gradient: x i ←x i -αg Here, α is the learning rate.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a reactive power compensation control method for a distribution station area based on an energy storage PCS converter as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a reactive power compensation control method for a distribution station area based on an energy storage PCS converter as described in any one of claims 1 to 7 are implemented.

Images