Dynamic voltage control method considering voltage risk assessment and network reconstruction

Abstract

The invention discloses a dynamic voltage control method considering voltage risk assessment and network reconstruction, and the method comprises the following steps: S1, data collection and preprocessing: data collection: monitoring the voltage, current and load of a power grid and the power generation data of a distributed power supply in real time through a high-precision sensor and an Internet of Things technology; data preprocessing: performing cleaning, normalization and feature extraction on the acquired data to form a data set for model training; s2, model training and optimization: model selection: selecting a suitable adaptive learning algorithm, and constructing a voltage risk prediction model; according to the invention, the voltage stability and the power supply reliability of the power grid can be effectively improved, and the method has obvious advantages especially when facing a complex power system and large-scale distributed power supply access; the adaptive learning algorithm can adjust the control strategy in real time and predict and prevent the voltage risk, and the intelligent scheduling algorithm can optimize the utilization of the distributed power supply and improve the overall efficiency of the power grid.

Description

Technical Field

[0001] The present invention belongs to the technical field of voltage control, and in particular relates to a dynamic voltage control method considering voltage risk assessment and network reconstruction. Background Art

[0002] The three major risks in power system operation are grid risk, personal risk, and equipment risk. With the continuous development of society, the scale of grid operation is expanding and the operation mode of the grid is becoming more and more complex. It is very important for grid operators to clearly identify grid operation risks and quickly take countermeasures to reduce grid risks. Therefore, it is extremely important to accurately and quickly identify real-time grid risks in complex large grids with full voltage levels.

[0003] In the prior art, during use, traditional voltage control methods are usually based on static models and cannot be adjusted in real time to cope with voltage fluctuations. When faced with complex power systems and large-scale distributed power source access, their advantages are reduced, thereby reducing the overall efficiency of the power grid.

[0004] To this end, we propose a dynamic voltage control method that considers voltage risk assessment and network reconstruction. Summary of the invention

[0005] The object of the present invention is to provide a dynamic voltage control method considering voltage risk assessment and network reconstruction, so as to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a dynamic voltage control method considering voltage risk assessment and network reconstruction, comprising the following steps: S1, data acquisition and preprocessing:

[0007] Data collection: Real-time monitoring of the voltage, current, load and distributed power generation data of the power grid through high-precision sensors and Internet of Things technology;

[0008] Data preprocessing: Clean, normalize and extract features of the collected data to form a data set for model training;

[0009] S2. Model training and optimization:

[0010] Model selection: Select a suitable adaptive learning algorithm to build a voltage risk prediction model;

[0011] Training and optimization: Use historical data and real-time data to train the model, and improve the prediction accuracy of the model through cross-validation and hyperparameter optimization;

[0012] S3, Real-time prediction and adjustment:

[0013] Real-time prediction: Use the trained model to predict the voltage risk of the power grid in real time;

[0014] Adaptive adjustment: Adaptively adjust the voltage control strategy according to the prediction results;

[0015] S4. Network reconstruction:

[0016] Network status assessment: real-time monitoring of the topology and operating status of the power grid, and identification of existing faults and risks;

[0017] Reconstruction strategy formulation: Based on the voltage risk prediction results and network status, formulate network reconstruction strategies, including adjusting transformer taps, reactive power compensation, and switch operations;

[0018] Reconstruction optimization algorithm: Use heuristic algorithms to optimize network reconstruction strategies and consider multi-objective optimization;

[0019] Reconfiguration execution: According to the optimized reconstruction strategy, the grid topology is dynamically adjusted to execute switching operations and load transfer measures.

[0020] Preferably, the data collection sources in S1 specifically include:

[0021] Historical voltage data: obtained from the historical operation records of the power grid;

[0022] Real-time voltage data: collected in real time through smart meters and sensors;

[0023] Load data: including historical and real-time load demand data;

[0024] Distributed power output data: Distributed energy: historical and real-time output data of solar and wind power;

[0025] Environmental data: temperature, humidity, wind speed, and other external factors that affect voltage fluctuations.

[0026] Preferably, the model in S2:

[0027] Input layer: receives multiple input features, including historical voltage, real-time voltage, load data, distributed power output, and environmental data;

[0028] Hidden layer: multi-layer neural network for feature extraction and pattern recognition;

[0029] Output layer: output voltage risk assessment results, including voltage fluctuation risk probability and risk level.

[0030] Preferably, the adaptive learning algorithm comprises:

[0031] Data collection and preprocessing in S1:

[0032] Let V(t) represent the voltage data at time t, I(t) represent the current data, P(t) represent the load power data, and R(t) represent the power generation data of the distributed power source;

[0033] Data collection formula:

[0034] X(t)={V(t),I(t),P(t),R(t)}

[0035] Data preprocessing and normalization:

[0036]

[0037] Model training and optimization in S2:

[0038] Use the long short-term memory network (LSTM) in deep learning to predict voltage risk. Assume that the input data is X′(t) and the output is the voltage prediction value at the future moment.

[0039] LSTM model formula:

[0040] f t =σ(W f ·[h t-1 ,X′(t)]+bf)

[0041] i t =σ(W i ·[h t-1 ,X′(t)]+bi)

[0042] C t =f t ·C t-1 +i t tanh(W C ·[h t-1 ,X′(t)]+b C )

[0043] o t =σ(W o ·[h t-1 ,X′(t)]+b o )

[0044] ht=ot·tanh(Ct)

[0045] Among them, f t It is the forget gate, t is the input gate, C t is the cell state, o t is the output gate, h t is the hidden state and σ is the sigmoid activation function.

[0046] Preferably, the real-time prediction and adjustment in S3:

[0047] Predicting voltage risks:

[0048]

[0049] Adaptive adjustment strategy:

[0050]

[0051] Preferably, the predicted voltage risk judgment condition is as follows:

[0052] if If it is lower than the safety threshold: 220V, the voltage needs to be increased;

[0053] if If it is higher than the safety threshold: 240V, the voltage needs to be reduced;

[0054] When predicted If it is within the safe range of 220V-240V, no adjustment is required.

[0055] Preferably, S3 also includes risk level determination:

[0056] Determine the risk level of current voltage fluctuation based on the predicted risk score;

[0057] And make risk warnings based on risk level:

[0058] When the risk level reaches medium or high risk, the early warning mechanism is triggered to notify the power grid control center or relevant personnel;

[0059] The voltage control strategy for the power grid is adjusted according to the risk level as follows:

[0060] High risk: Immediately adjust voltage settings, enable backup power supplies, and reconfigure the network;

[0061] Medium risk: monitor voltage fluctuations and prepare for emergency measures;

[0062] Low risk: Normal operation, no additional actions required.

[0063] Preferably, the heuristic optimization algorithm in S4 comprises the following steps:

[0064] Network status assessment in S4:

[0065] Input: topology and operation status data of the power grid;

[0066] Output: Current grid status assessment, including node voltage, branch power, and potential risk points;

[0067] 1. Initialize the population:

[0068] Population initialization: Randomly generate an initial population of N individuals, each of which represents a network reconstruction scheme;

[0069] 2. Individual representation: Each individual is represented by a binary string, where each gene represents the state of a switch: on or off;

[0070] 3. Fitness function calculation:

[0071] Define the fitness function f(x) to evaluate the quality of each individual. The fitness function comprehensively considers voltage stability, power supply reliability and energy efficiency.

[0072] 4. Select:

[0073] Selection: select individuals for reproduction based on fitness values. Common methods include roulette wheel selection.

[0074] Crossover: Randomly select two individuals, exchange some of their genes, and generate new individuals. The crossover operation improves the diversity of the population.

[0075] Mutation: Randomly change some genes of individuals to prevent the population from falling into local optimality;

[0076] 5. Refactoring Execution

[0077] Reconfiguration strategy execution: Based on the optimized individual optimal solution, switch operations and load transfer network reconstruction measures are executed to adjust the grid topology;

[0078] Evaluate new status: monitor the new status of the power grid in real time to ensure voltage stability and reliable power supply;

[0079] 6. Iterative Optimization

[0080] Iteration: Repeat steps S3 to S5 until the predetermined number of iterations is reached or the fitness value converges;

[0081] Among them, the fitness function in S3 is:

[0082] f(x)=α·Voltage Stability(x)+β·Supply Reliability(x)+γ·EnergyEfficiency(x)

[0083] Among them, α, β, and γ are weight coefficients, which can be adjusted according to specific needs;

[0084] Roulette Selection:

[0085]

[0086] Among them, P(i) is the probability of selecting the i-th individual, f(x i ) is the fitness value of the ith individual, and N is the population size;

[0087] Crossover operation:

[0088] x′ i =x i [0:k]+x j [k:n]

[0089] Among them, x′ i is a new individual, x i [0:k] is the first k genes of the ith individual, x j [k:n] is the last nk genes of the jth individual;

[0090] Mutation operation:

[0091] x′ i =x i ⊕m

[0092] Where m is the mutation mask and ⊕ represents the bitwise XOR operation.

[0093] To achieve the above object, the present invention also provides the following technical solutions:

[0094] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for dynamic voltage control considering voltage risk assessment and network reconstruction described in any one of the above is implemented.

[0095] To achieve the above object, the present invention also provides the following technical solutions:

[0096] A computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the method for dynamic voltage control considering voltage risk assessment and network reconstruction as claimed in any one of the claims is implemented.

[0097] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention can effectively improve the voltage stability and power supply reliability of the power grid, especially when facing complex power systems and large-scale distributed power source access, it has significant advantages; the adaptive learning algorithm can adjust the control strategy in real time, predict and prevent voltage risks, and the intelligent scheduling algorithm can optimize the utilization of distributed power sources and improve the overall efficiency of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] Figure 1 A schematic diagram of the structure of a method for dynamic voltage control considering voltage risk assessment and network reconstruction according to the present invention;

[0099] Figure 2 Schematic diagram of the internal structure of the computer device of the present invention. DETAILED DESCRIPTION

[0100] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0101] See also Figure 1-2 , the present invention provides a technical solution: Step 1: Data collection and preprocessing:

[0102] Data collection: Real-time monitoring of the voltage, current, load and distributed power generation data of the power grid through high-precision sensors and Internet of Things technology;

[0103] Data preprocessing: Clean, normalize and extract features of the collected data to form a data set for model training;

[0104] Step 2: Model training and optimization

[0105] Model selection: Select a suitable adaptive learning algorithm to build a voltage risk prediction model;

[0106] Training and optimization: Use historical data and real-time data to train the model, and improve the prediction accuracy of the model through cross-validation and hyperparameter optimization;

[0107] Step 3: Real-time prediction and adjustment

[0108] Real-time prediction: Use the trained model to predict the voltage risk of the power grid in real time;

[0109] Adaptive adjustment: Adaptively adjust the voltage control strategy based on the prediction results.

[0110] The data collection sources in step 1 specifically include:

[0111] Historical voltage data: obtained from the historical operation records of the power grid;

[0112] Real-time voltage data: collected in real time through smart meters and sensors;

[0113] Load data: including historical and real-time load demand data;

[0114] Distributed power output data: historical and real-time output data of distributed energy (solar energy, wind energy);

[0115] Environmental data: temperature, humidity, wind speed, and other external factors that affect voltage fluctuations.

[0116] Furthermore, the model architecture in step 2 is:

[0117] Input layer: receives multiple input features, including historical voltage, real-time voltage, load data, distributed power output, and environmental data;

[0118] Hidden layer: multi-layer neural network for feature extraction and pattern recognition;

[0119] Output layer: output voltage risk assessment results, including voltage fluctuation risk probability and risk level.

[0120] Specifically, the adaptive learning algorithm in step 2 includes:

[0121] S1. Data collection and preprocessing:

[0122] Let V(t) represent the voltage data at time t, I(t) represent the current data, P(t) represent the load power data, and R(t) represent the power generation data of the distributed power source;

[0123] Data collection formula:

[0124] X(t)={V(t),I(t),P(t),R(t)}

[0125] Data preprocessing (normalization):

[0126]

[0127] S2. Model training and optimization:

[0128] Use the long short-term memory network (LSTM) in deep learning to predict voltage risk. Assume that the input data is X′(t) and the output is the voltage prediction value at the future moment.

[0129] LSMT model formula:

[0130] f t =σ(W f ·[h t-1 ,X(t)]+b f )

[0131] i t =σ(W i ·[h t-1 ,X′(t)]+b i )

[0132] C t =f t ·C t-1+i t tanh(W C ·[h t-1 ,X′(t)]+b C )

[0133] o t =σ(W o ·[h t-1 ,X′(t)]+b o )

[0134] h t =o t tanh(C t )

[0135] Among them, f t It is the forget gate, t is the input gate, C t is the cell state, o t is the output gate, h t is the hidden state and σ is the sigmoid activation function.

[0136] Real-time prediction and adjustment in step 3:

[0137] Predicting voltage risks:

[0138]

[0139] Adaptive adjustment strategy:

[0140]

[0141] The predicted voltage risk judgment conditions are as follows:

[0142] if If it is lower than the safety threshold: 220V, the voltage needs to be increased;

[0143] if If it is higher than the safety threshold: 240V, the voltage needs to be reduced;

[0144] When predicted If it is within the safe range of 220V-240V, no adjustment is required.

[0145] The interaction examples are as follows:

[0146] Step 1: Data collection and preprocessing:

[0147] Collect data: X(t):

[0148] V(t)=230V, I(t)=15A, P(t)=3.45kw, R(t)=1.5kw;

[0149] Data normalization (assuming min(X) = 0, max(X) = 400):

[0150]

[0151] Step 2: Model training and prediction:

[0152] Training using the LSTM model:

[0153]

[0154] Real-time forecast of voltage for the next hour:

[0155]

[0156] Step 3: Interactive judgment and adjustment strategy:

[0157] Within the safe range (220V-240V), the system does not need to be adjusted;

[0158] if If the voltage is lower than 220V, the system needs to adjust the voltage:

[0159] Do the following:

[0160] Raise the transformer tap position: increase the transformer output voltage;

[0161] Reactive power compensation: Increase reactive power compensation and improve voltage level.

[0162] Furthermore, the step three also includes risk level determination:

[0163] Determine the risk level of current voltage fluctuation based on the predicted risk score;

[0164] And make risk warnings based on risk level:

[0165] When the risk level reaches medium or high risk, the early warning mechanism is triggered to notify the power grid control center or relevant personnel.

[0166] The voltage control strategy for the power grid is adjusted according to the risk level as follows:

[0167] High risk: Immediately adjust voltage settings, enable backup power supplies, and reconfigure the network;

[0168] Medium risk: monitor voltage fluctuations and prepare for emergency measures;

[0169] Low risk: Normal operation, no additional actions required.

[0170] Specifically, the heuristic optimization algorithm in step 4 includes the following steps:

[0171] S1. Network status assessment

[0172] Input: topology and operation status data of the power grid;

[0173] Output: Current grid status assessment, including node voltage, branch power, and potential risk points;

[0174] S2. Initialize the population

[0175] Population initialization: Randomly generate an initial population of N individuals, each of which represents a network reconstruction scheme;

[0176] Individual representation: Each individual is represented by a binary string, where each gene represents the state of a switch: on or off;

[0177] S3. Fitness function calculation

[0178] Define the fitness function f(x) to evaluate the quality of each individual. The fitness function comprehensively considers voltage stability, power supply reliability and energy efficiency.

[0179] S4. Selection

[0180] Selection: select individuals for reproduction based on fitness values. Common methods include roulette wheel selection.

[0181] Crossover: Randomly select two individuals, exchange some of their genes, and generate new individuals. The crossover operation improves the diversity of the population.

[0182] Mutation: Randomly change some genes of individuals to prevent the population from falling into local optimality;

[0183] S5. Reconstruction execution

[0184] Reconfiguration strategy execution: Based on the optimized individual optimal solution, switch operations and load transfer network reconstruction measures are executed to adjust the grid topology;

[0185] Evaluate new status: monitor the new status of the power grid in real time to ensure voltage stability and reliable power supply;

[0186] S6. Iterative Optimization

[0187] Iteration: Repeat steps S3 to S5 until a predetermined number of iterations is reached or the fitness value converges;

[0188] Among them, the fitness function in S3 is:

[0189] f(x)=α·Voltage Stability(x)+β·Supply Reliability(x)+γ·EnergyEfficiency(x)

[0190] Among them, α, β, and γ are weight coefficients, which can be adjusted according to specific needs;

[0191] Roulette selection in S4:

[0192] Roulette Selection:

[0193]

[0194] Among them, P(i) is the probability of selecting the i-th individual, f(x i ) is the fitness value of the ith individual, and N is the population size;

[0195] Crossover operation:

[0196] x′ i =x i [0:k]+x j [k:n]

[0197] Among them, x′ i is a new individual, x i [0:k] is the first k genes of the ith individual, x j [k:n] is the last nk genes of the jth individual;

[0198] Mutation operation:

[0199] x′ i =x i ⊕m

[0200] Where m is the mutation mask and ⊕ represents the bitwise XOR operation.

[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, a dynamic voltage control method considering voltage risk assessment and network reconstruction as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0203] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A dynamic voltage control method considering voltage risk assessment and network reconstruction, characterized in that: The following steps are involved: S1. Data collection and preprocessing: Data collection: Real-time monitoring of the voltage, current, load and distributed power generation data of the power grid through high-precision sensors and Internet of Things technology; Data preprocessing: Clean, normalize and extract features of the collected data to form a data set for model training; S2. Model training and optimization: Model selection: Select a suitable adaptive learning algorithm to build a voltage risk prediction model; Training and optimization: Use historical data and real-time data to train the model, and improve the prediction accuracy of the model through cross-validation and parameter optimization; S3, Real-time prediction and adjustment: Real-time prediction: Use the trained model to predict the voltage risk of the power grid in real time; Adaptive adjustment: Adaptively adjust the voltage control strategy according to the prediction results; S4. Network reconstruction: Network status assessment: real-time monitoring of the topology and operating status of the power grid, and identification of existing faults and risks; Reconstruction strategy formulation: Based on the voltage risk prediction results and network status, formulate network reconstruction strategies, including adjusting transformer taps, reactive power compensation, and switch operations; Reconstruction optimization algorithm: Use heuristic algorithms to optimize network reconstruction strategies and consider multi-objective optimization; Reconfiguration execution: According to the optimized reconstruction strategy, the grid topology is dynamically adjusted to execute switching operations and load transfer measures.

2. A dynamic voltage control method considering voltage risk assessment and network reconstruction according to claim 1, characterized in that: The data collection sources in S1 specifically include: Historical voltage data: obtained from the historical operation records of the power grid; Real-time voltage data: collected in real time through smart meters and sensors; Load data: including historical and real-time load demand data; Distributed power output data: Distributed energy is historical and real-time output data of solar energy and wind energy; Environmental data: temperature, humidity, wind speed, and other external factors that affect voltage fluctuations.

3. The method for dynamic voltage control considering voltage risk assessment and network reconstruction according to claim 1, characterized in that: The S2 model: Input layer: receives input features, including historical voltage, real-time voltage, load data, distributed power output, and environmental data; Hidden layer: multi-layer neural network for feature extraction and pattern recognition; Output layer: output voltage risk assessment results, including voltage fluctuation risk probability and risk level.

4. The method for dynamic voltage control considering voltage risk assessment and network reconstruction according to claim 1, characterized in that: Adaptive learning algorithms include: Data collection and preprocessing in S1: Let V(t) represent the voltage data at time t, I(t) represent the current data, P(t) represent the load power data, and R(t) represent the power generation data of the distributed power source; Data collection formula: X(t)={V(t),I(t),P(t),R(t)} Data preprocessing and normalization: Model training and optimization in S2: Use the long short-term memory network (LSTM) in deep learning to predict voltage risk. Assume that the input data is X′(t) and the output is the voltage prediction value at the future moment. LSTM model formula: f t =σ(W f ·[h t-1 ,X′(t)]+b f ) i t =σ(W i ·[h t-1 ,X′(t)]+b i ) C t =f t ·C t-1 +i t ·tanh(W C ·[h t-1 ,X′(t)]+b C ) o t =σ(W o ·[h t-1 ,X′(t)]+b o ) h t =o t ·tanh·C t ) Among them, f t It is the forget gate, t is the input gate, C t is the cell state, o t is the output gate, h t is the hidden state and σ is the sigmoid activation function.

5. The method for dynamic voltage control considering voltage risk assessment and network reconstruction according to claim 1, characterized in that: Real-time prediction and adjustment in S3: Predicting voltage risks: Adaptive adjustment strategy:

6. A dynamic voltage control method considering voltage risk assessment and network reconstruction according to claim 5, characterized in that: The predicted voltage risk judgment conditions are as follows: if If it is lower than the safety threshold: 220V, the voltage needs to be increased; if If it is higher than the safety threshold: 240V, the voltage needs to be reduced; When predicted If it is within the safe range of 220V-240V, no adjustment is required.

7. A dynamic voltage control method considering voltage risk assessment and network reconstruction according to claim 1, characterized in that: S3 also includes risk level determination: Determine the risk level of current voltage fluctuation based on the predicted risk score; And make risk warnings based on risk level: When the risk level reaches medium or high risk, the early warning mechanism is triggered to notify the power grid control center or relevant personnel; The voltage control strategy for the power grid is adjusted according to the risk level as follows: High risk: Immediately adjust voltage settings, enable backup power supplies, and reconfigure the network; Medium risk: monitor voltage fluctuations and prepare for emergency measures; Low risk: Normal operation, no additional actions required.

8. The method for dynamic voltage control considering voltage risk assessment and network reconstruction according to claim 1, characterized in that: The heuristic optimization algorithm in S4 includes the following steps: Network status assessment in S4: Input: topology and operation status data of the power grid; Output: Current grid status assessment, including node voltage, branch power, and potential risk points; 1. Initialize the population: Population initialization: Randomly generate an initial population of N individuals, each of which represents a network reconstruction scheme; 2. Individual representation: Each individual is represented by a binary string, where each gene represents the state of a switch: on or off; 3. Fitness function calculation: Define the fitness function f(x) to evaluate the quality of each individual. The fitness function comprehensively considers voltage stability, power supply reliability and energy efficiency.

4. Select: Selection: select individuals for reproduction based on fitness values. Common methods include roulette wheel selection. Crossover: Randomly select two individuals, exchange some of their genes, and generate new individuals. The crossover operation improves the diversity of the population. Mutation: Randomly change some genes of individuals to prevent the population from falling into local optimality; 5. Refactoring Execution Reconfiguration strategy execution: Based on the optimized individual optimal solution, switch operations and load transfer network reconstruction measures are executed to adjust the grid topology; Evaluate new status: monitor the new status of the power grid in real time to ensure voltage stability and reliable power supply; 6. Iterative Optimization Iteration: Repeat steps S3 to S5 until the predetermined number of iterations is reached or the fitness value converges; Among them, the fitness function in S3 is: f(x)=α·Voltage Stability(x)+β·Supply Reliability(x)+γ·EnergyEfficiency(x) Among them, α, β, and γ are weight coefficients, which can be adjusted according to specific needs; Roulette Selection: Among them, P(i) is the probability of selecting the i-th individual, f(x i ) is the fitness value of the i-th individual, and N is the population size; Crossover operation: x′ i =x i [0:k]+x j [k:n] Among them, x′ i For the new individual, x i [0:k] is the first k genes of the ith individual, x j [k:n] is the last nk genes of the jth individual; Mutation operation: x′ i =x i ⊕m Where m is the mutation mask and ⊕ represents the bitwise XOR operation.

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 dynamic voltage control method considering voltage risk assessment and network reconstruction as described in any one of claims 1 to 8 is 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 dynamic voltage control method considering voltage risk assessment and network reconstruction as described in any one of claims 1 to 8 is implemented.

Images