Power quality regulation method and device of optical storage system, equipment and storage medium

Abstract

The application relates to a power quality regulation method and device of a light storage system. The method comprises the following steps: constructing a disturbance characteristic vector sequence according to operation state data of each node in the light storage system; generating a disturbance characteristic evolution track according to the disturbance characteristic vector sequence within a preconfigured sliding time window; performing disturbance level identification on the disturbance characteristic evolution track to obtain a current disturbance level. According to the current disturbance level, the weight coefficient and the initial regulation boundary parameter of a multi-objective optimization function corresponding to the light storage system are dynamically adjusted. Based on the operation state data, the adjusted weight coefficient and the regulation boundary parameter, the light storage system is subjected to optimization solving of a regulation strategy parameter to obtain optimal strategy parameters. The power quality is regulated according to a quality regulation strategy generated according to the optimal strategy parameters. The quality regulation strategy is optimized according to next-round operation state data after the power quality regulation. The method can improve the power quality guarantee capability of the light storage system under a complex disturbance scene.

Description

Technical Field

[0001] This application relates to the field of power technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for power quality control of a photovoltaic-storage system. Background Technology

[0002] With the development of power technology and the large-scale integration of new energy sources such as distributed photovoltaics, power quality disturbances such as voltage fluctuations and harmonic distortion in the distribution network are becoming more frequent, placing higher demands on the stability of system operation, power supply quality, and the responsiveness of control resources.

[0003] Existing operation strategies for photovoltaic and energy storage systems mainly revolve around the matching relationship between resource capacity settings and system performance. By constructing control models, the rationality of parameter settings can be sought among factors such as cost, power balance, and power quality constraints. Furthermore, operation strategies are usually formulated in conjunction with typical operating periods, representative load scenarios, or equipment characteristics to improve the system's regulation capabilities and operational performance.

[0004] However, the existing operation strategies of photovoltaic and energy storage systems are mostly based on static settings, with parameter boundaries usually fixed. They lack the ability to continuously perceive changes in operating status such as the intensity and type of disturbances. In the face of the actual operating environment of frequent disturbances and dynamic fluctuations in power quality, these strategies have certain limitations in terms of response speed, matching accuracy and resource allocation efficiency. They are difficult to adjust in a timely manner, which can easily lead to lag in regulation, unreasonable resource allocation or insufficient regulation capacity, affecting the system's operational flexibility and power quality assurance effect. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for power quality control of a photovoltaic and energy storage system that can improve the real-time adaptability and power quality assurance effect of the photovoltaic and energy storage system under complex disturbance scenarios, in order to address the above-mentioned technical problems.

[0006] In a first aspect, this application provides a power quality control method for a photovoltaic-storage system, comprising: collecting operational status data of each node in the photovoltaic-storage system, and constructing a disturbance feature vector sequence based on the operational status data; generating a disturbance feature evolution trajectory based on the disturbance feature vector sequence within a pre-configured sliding time window, and identifying the disturbance level of the disturbance feature evolution trajectory to obtain the current disturbance level; dynamically adjusting the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic-storage system based on the current disturbance level to obtain adjusted weight coefficients and control boundary parameters; optimizing the control strategy parameters of the photovoltaic-storage system based on the operational status data and the adjusted weight coefficients and control boundary parameters to obtain optimal strategy parameters; generating a power quality control strategy based on the optimal strategy parameters, performing power quality control based on the power quality control strategy, and collecting operational status data for the next round after power quality control to optimize the power quality control strategy based on the next round of operational status data.

[0007] Secondly, this application also provides a power quality control device for a photovoltaic-storage system, comprising: a disturbance feature vector sequence construction module, used to collect operating status data of each node in the photovoltaic-storage system and construct a disturbance feature vector sequence based on the operating status data; a current disturbance level identification module, used to generate a disturbance feature evolution trajectory based on the disturbance feature vector sequence within a pre-configured sliding time window, and to identify the disturbance level of the disturbance feature evolution trajectory to obtain the current disturbance level; and a parameter adjustment module, used to dynamically adjust the multi-objective optimization corresponding to the photovoltaic-storage system based on the current disturbance level. The system uses the function's weighting coefficients and initial control boundary parameters to obtain adjusted weighting coefficients and control boundary parameters; an optimal strategy parameter determination module is used to optimize the control strategy parameters of the photovoltaic-storage system based on the operating status data and the adjusted weighting coefficients and control boundary parameters to obtain optimal strategy parameters; a power quality control module is used to generate a quality control strategy based on the optimal strategy parameters, perform power quality control according to the quality control strategy, and collect the next round of operating status data after power quality control to optimize the quality control strategy based on the next round of operating status data.

[0008] Thirdly, this application also provides a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: collecting operating status data of each node in the photovoltaic-storage system, and constructing a disturbance feature vector sequence based on the operating status data; generating a disturbance feature evolution trajectory based on the disturbance feature vector sequence within a pre-configured sliding time window, and identifying the disturbance level of the disturbance feature evolution trajectory to obtain the current disturbance level; dynamically adjusting the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic-storage system based on the current disturbance level to obtain the adjusted weight coefficients and control boundary parameters; optimizing the control strategy parameters of the photovoltaic-storage system based on the operating status data and the adjusted weight coefficients and control boundary parameters to obtain the optimal strategy parameters; generating a quality control strategy based on the optimal strategy parameters, performing power quality control based on the quality control strategy, and collecting the next round of operating status data after power quality control to optimize the quality control strategy based on the next round of operating status data.

[0009] Fourthly, this application also provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program performs the following steps: collecting operating status data of each node in the photovoltaic-storage system and constructing a disturbance feature vector sequence based on the operating status data; generating a disturbance feature evolution trajectory based on the disturbance feature vector sequence within a pre-configured sliding time window, and identifying the disturbance level of the disturbance feature evolution trajectory to obtain the current disturbance level; dynamically adjusting the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic-storage system based on the current disturbance level to obtain the adjusted weight coefficients and control boundary parameters; optimizing the control strategy parameters of the photovoltaic-storage system based on the operating status data and the adjusted weight coefficients and control boundary parameters to obtain the optimal strategy parameters; generating a quality control strategy based on the optimal strategy parameters, performing power quality control based on the quality control strategy, and collecting the next round of operating status data after power quality control to optimize the quality control strategy based on the next round of operating status data.

[0010] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps: collecting operational status data of each node in a photovoltaic-storage system, and constructing a disturbance feature vector sequence based on the operational status data; generating a disturbance feature evolution trajectory based on the disturbance feature vector sequence within a pre-configured sliding time window, and identifying the disturbance level of the disturbance feature evolution trajectory to obtain the current disturbance level; dynamically adjusting the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic-storage system based on the current disturbance level to obtain adjusted weight coefficients and control boundary parameters; optimizing the control strategy parameters of the photovoltaic-storage system based on the operational status data and the adjusted weight coefficients and control boundary parameters to obtain optimal strategy parameters; generating a quality control strategy based on the optimal strategy parameters, performing power quality control based on the quality control strategy, and collecting the next round of operational status data after power quality control to optimize the quality control strategy based on the next round of operational status data.

[0011] In the aforementioned power quality control methods, devices, computer equipment, computer-readable storage media, and computer program products for photovoltaic-storage systems, operational status data of each node in the system is collected. Based on this data, a disturbance feature vector sequence is constructed. Within a pre-configured sliding time window, a disturbance feature evolution trajectory is generated based on this sequence. This trajectory is used to identify the disturbance level and determine the current disturbance level. This allows for the perception of system operational status changes through a sliding time window, reducing inaccuracies in disturbance change identification. Furthermore, based on the current disturbance level, the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic-storage system are dynamically adjusted. Adjusted weight coefficients and control boundary parameters are then obtained. Based on the operational status data and the adjusted weight coefficients and control boundary parameters, the control strategy parameters for the photovoltaic-storage system are optimized to obtain the optimal strategy parameters. This achieves dynamic adjustment of target weights and control parameter boundaries driven by a disturbance level judgment mechanism. Generating a quality control strategy based on the optimal strategy parameters enables adaptive optimization of key system parameters. Furthermore, a quality control strategy is generated based on the optimal strategy parameters, and power quality is controlled according to the quality control strategy. The next round of operating status data after power quality control is collected, so as to optimize the quality control strategy based on the next round of operating status data. This achieves deep synergy between disturbance perception and optimization mechanisms, thereby improving the real-time adaptability and power quality assurance capability of the photovoltaic-storage system under complex disturbance scenarios and meeting the intelligent control requirements under dynamic evolution of operating status. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is an application environment diagram of a power quality control method for a photovoltaic-storage system in one embodiment.

[0014] Figure 2 This is a flowchart illustrating a power quality control method for a photovoltaic-storage system in one embodiment.

[0015] Figure 3 This is a flowchart illustrating the process of outputting the optimal strategy parameters in one embodiment;

[0016] Figure 4 This is a schematic diagram of the optimization process of a perturbation-aware particle swarm optimization and genetic hybrid algorithm in one embodiment;

[0017] Figure 5 This is a flowchart illustrating the power quality control method for a photovoltaic-storage system in another embodiment.

[0018] Figure 6 This is a schematic diagram of the overall processing procedure of a power quality control method for a photovoltaic-storage system in one embodiment.

[0019] Figure 7 This is a structural block diagram of the power quality control device of a photovoltaic energy storage system in one embodiment;

[0020] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0022] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0023] The power quality control method for photovoltaic-storage systems provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal device 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located on the cloud or other network servers. Terminal device 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0024] Both terminal device 102 and server 104 can be used independently to execute the power quality control method for the photovoltaic-storage system provided in this embodiment, or they can work together to execute the same method. For example, taking the collaborative execution of the power quality control method by terminal device 102 and server 104, server 104 collects the operating status data of each node in the photovoltaic-storage system (specifically, the operating status data of each terminal device 102 in the system), constructs a disturbance feature vector sequence based on the operating status data, and generates a disturbance feature evolution trajectory within a pre-configured sliding time window based on the disturbance feature vector sequence. It then identifies the disturbance level of the disturbance feature evolution trajectory to obtain the current disturbance level. Furthermore, server 104 dynamically adjusts the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic-storage system based on the current disturbance level, obtaining the adjusted weight coefficients and control boundary parameters. Based on the operating status data and the adjusted weight coefficients and control boundary parameters, server 104 optimizes the control strategy parameters of the photovoltaic-storage system to obtain the optimal strategy parameters. Finally, server 104 generates a power quality control strategy based on the optimal strategy parameters, performs power quality control on each terminal device 102 according to the power quality control strategy, and collects the next round of operating status data after power quality control to optimize the power quality control strategy based on the next round of operating status data.

[0025] In one exemplary embodiment, such as Figure 2As shown, a power quality control method for a photovoltaic-storage system is provided, which can be applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps S202 to S210. Wherein:

[0026] Step S202: Collect the operating status data of each node in the optical storage system, and construct a perturbation feature vector sequence based on the operating status data.

[0027] Specifically, the server collects real-time operating status data of each node in the photovoltaic-storage system (or distribution network), including but not limited to node voltage, photovoltaic output power, energy storage power and state of charge (SOC), which constitute the basic data source for the disturbance feature input vector. The sampling period is consistent with the sliding refresh frequency. At the same time, the collected operating status data is preprocessed, including normalization, noise suppression and outlier removal, to improve the stability of the disturbance feature expression and the recognition accuracy.

[0028] Step S204: Within a pre-configured sliding time window, generate a perturbation feature evolution trajectory based on the perturbation feature vector sequence, identify the perturbation level of the perturbation feature evolution trajectory, and obtain the current perturbation level.

[0029] Specifically, within a pre-configured sliding time window, the server performs statistical analysis on the perturbation feature vector sequence to obtain the changing trend and overall perturbation level corresponding to the perturbation feature vector sequence, and constructs the perturbation feature evolution trajectory based on the changing trend and overall perturbation level corresponding to the perturbation feature vector sequence.

[0030] Furthermore, to achieve automatic determination of the disturbance level, the server extracts the last value of the disturbance feature vector sequence as the disturbance feature input at the current moment, and performs disturbance level identification on the disturbance feature input according to the pre-configured disturbance level evaluation rules to obtain the current disturbance level.

[0031] The server extracts the last value of the perturbation feature vector sequence. As the disturbance characteristic input at the current moment, in order to identify the disturbance level of the system's operating state, a piecewise function method is used to classify the various disturbance indicators into levels, and based on this, disturbance level evaluation rules are constructed, specifically including:

[0032] 1) For any disturbance index The disturbance level segmentation mapping function is set as follows:

[0033] ;

[0034] Among them, the above threshold and It can be set according to the statistical distribution characteristics of different disturbance indicators in actual engineering, or given in combination with historical operation data. The average fluctuation ratio or standard limit value within the sliding window of the corresponding indicator can be used as a reference.

[0035] 2) Calculate the disturbance scores for the three indicators respectively. , , And set the weighted summation formula: ,in, , ,as well as The fusion weighting coefficients for the perturbation scores are generally set to equal weights and are determined based on the total score. The value determines the current disturbance level. The details are as follows:

[0036] ;

[0037] The disturbance level result serves as the basis for dynamically adjusting the weights of the objective function and updating the control boundary, driving the adaptive evolution of the strategy.

[0038] Step S206: Based on the current disturbance level, dynamically adjust the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic-storage system to obtain the adjusted weight coefficients and control boundary parameters.

[0039] Specifically, the server determines the current disturbance level based on the identification. Dynamically adjust the weight coefficients in the multi-objective optimization function The process involves correcting the control boundary parameters of the photovoltaic-storage system, and includes the following steps:

[0040] Step a) Dynamically adjust the objective function weights, assuming the initial objective function weights are... Regarding the disturbance level The following dynamic adjustment relationship is constructed: ,in, The disturbance response coefficient is... This is the disturbance level mapping function. Typical values ​​for the disturbance level mapping function are:

[0041] ;

[0042] Step b) Adaptive adjustment of control boundary parameters: To enhance control flexibility when the disturbance level increases, the power boundary and state of charge range of the energy storage system are appropriately relaxed, and the following adaptive boundary setting method is constructed:

[0043] 1) The expression for adjusting the energy storage output power boundary is: ,in, The disturbance level is The maximum output power of the energy storage system at that time The power limit set for initialization, The disturbance response adjustment factor at the power boundary. This is a disturbance level mapping function;

[0044] 2) The expression for the charge state range is constructed as follows: , ,in, , These represent the minimum and maximum states of charge of the energy storage system for the current cycle. , The upper and lower boundaries of the initial charge state are set. This is the disturbance response adjustment factor at the charged state boundary.

[0045] Among them, control cycle Slide refresh cycle and power adjustment step size These parameters can also be combined with the trend of disturbance level changes, and weighted relaxation or compression can be achieved according to the set proportional factor to improve the dynamic response granularity of the operation strategy.

[0046] Step S208: Based on the operating status data, the adjusted weight coefficients, and the control boundary parameters, optimize the control strategy parameters of the photovoltaic-storage system to obtain the optimal strategy parameters.

[0047] Specifically, the server can use a genetic algorithm to construct the initial population, perform individual crossover and mutation operations based on the running status data, as well as the adjusted weight coefficients and control boundary parameters, and use a particle swarm optimization algorithm to update the population position and adjust the boundary, and output the optimal strategy parameters.

[0048] Under the current disturbance level, the server initializes the population structure and disturbance level information based on the operating status data, the adjusted weight coefficients, and the control boundary parameters, and adjusts the initial distribution range of particles according to the current disturbance level.

[0049] Furthermore, the server generates an initial set of individual solutions through random encoding, uses a fitness function to calculate the initial fitness value of each individual in the initial set, and performs crossover and mutation operations on the individuals in the initial set to construct an initial solution space with uniform fitness distribution. Based on this uniformly distributed initial solution space, the positions and velocities of the individuals in the multiple populations can be updated to obtain the updated individuals in the multiple populations.

[0050] In this process, after obtaining multiple updated individuals from the population, the initial fitness values ​​of these individuals are dynamically adjusted based on the current perturbation level to obtain the adjusted target fitness values. Then, when the update cessation condition is met based on the target fitness values, the parameter variables corresponding to the optimal individual after the update cessation are extracted to obtain the optimal policy parameters.

[0051] Step S210: Generate a quality control strategy based on the optimal strategy parameters, perform power quality control according to the quality control strategy, and collect the next round of operating status data after power quality control, so as to optimize the quality control strategy based on the next round of operating status data.

[0052] Specifically, the server generates a power quality control strategy based on the optimal strategy parameters, and then performs power quality control based on the power quality control strategy.

[0053] Specifically, the server executes the optimized control strategy parameters as the control strategy, and the specific execution content includes:

[0054] 1) Based on the current disturbance level and system operating status, the energy storage charging and discharging power parameters contained in the selected optimal individual are sent to the energy storage converter or the corresponding control interface as the target power command for that period, used to directly control the charging and discharging behavior of the energy storage system. ;

[0055] 2) Set the upper and lower limits of the charge state in the optimal individual. and The control boundary for the current round of energy storage operation is updated synchronously to ensure the rationality of the SOC operating range and prevent overcharging and over-discharging.

[0056] 3) Dynamically adjust the control cycle by combining the disturbance level-driven mechanism. Power adjustment step size These parameters enhance the flexibility and speed of regulation.

[0057] In an exemplary embodiment, after power quality regulation, the server collects the next round of operating status data after power quality regulation, determines the next round of disturbance level based on the next round of operating status data, and compares the next round of disturbance level with the current disturbance level.

[0058] Specifically, if the next round of disturbance level is inconsistent with the current disturbance level, the next round of strategy optimization process will be initiated to optimize the quality control strategy. If the next round of disturbance level is consistent with the current disturbance level, power quality control will be carried out according to the quality control strategy.

[0059] If the system is under a sustained high disturbance level, the strategy will maintain the same update frequency and the current optimized parameters to enhance power quality assurance capabilities. If the disturbance level decreases, the strategy will enter a waiting state, the current parameters will continue to be executed, and the data acquisition and control judgment process of the next sliding window cycle will begin.

[0060] Understandably, by constructing a disturbance feature input structure under a sliding time window mechanism, multi-dimensional disturbance indicators such as voltage deviation, voltage fluctuation amplitude, and harmonic distortion are extracted. These indicators are then combined with a defined mapping function to classify disturbance levels, thereby driving a dynamic adjustment strategy for the weights of the multi-objective optimization function and the control boundary. This power quality control method for a photovoltaic-storage system achieves adaptive adjustment of the controlled object under disturbance classification scenarios by integrating a disturbance level-guided optimization objective perception mechanism with a flexible control boundary correction mechanism. This effectively enhances the agility and adaptability of the strategy and improves the dynamic response performance of the photovoltaic-storage system to power quality disturbances.

[0061] The key technologies involved include a target weight and boundary parameter linkage adjustment method driven by disturbance hierarchy, a dynamic correction strategy for optimization inertia factor guided by disturbance response coefficient, and a hybrid intelligent optimization structure integrating genetic algorithm and particle swarm optimization algorithm. Specifically, by introducing a disturbance level perception mechanism and dynamic optimization strategy, real-time matching of control targets and execution parameters is achieved, effectively improving the regulation accuracy and response robustness of the photovoltaic-storage system under complex disturbance environments. Simultaneously, the strategy execution possesses continuous and adaptive characteristics, automatically adjusting the control rhythm and parameter boundaries according to the disturbance intensity, enhancing the system's dynamic response capability and regulation stability to power quality fluctuations.

[0062] In the aforementioned power quality control method for the photovoltaic-storage system, operational status data of each node in the system is collected. Based on this data, a disturbance feature vector sequence is constructed. Within a pre-configured sliding time window, a disturbance feature evolution trajectory is generated based on this sequence. This trajectory is used to identify the disturbance level and determine the current disturbance level. This method enables the perception of system operational status changes through a sliding time window, reducing inaccuracies in disturbance change identification. Furthermore, based on the current disturbance level, the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic-storage system are dynamically adjusted. These adjusted coefficients and parameters are then used to optimize the control strategy parameters based on the operational status data and the adjusted parameters. This yields the optimal strategy parameters, allowing for dynamic adjustment of target weights and control parameter boundaries driven by a disturbance level judgment mechanism. The generation of a quality control strategy based on the optimal parameters enables adaptive optimization of key system parameters. Furthermore, a quality control strategy is generated based on the optimal strategy parameters, and power quality is controlled according to the quality control strategy. The next round of operating status data after power quality control is collected, so as to optimize the quality control strategy based on the next round of operating status data. This achieves deep synergy between disturbance perception and optimization mechanisms, thereby improving the real-time adaptability and power quality assurance capability of the photovoltaic-storage system under complex disturbance scenarios and meeting the intelligent control requirements under dynamic evolution of operating status.

[0063] In one exemplary embodiment, such as Figure 3 As shown, the steps for outputting the optimal strategy parameters, namely, based on the running state data, the adjusted weight coefficients, and the control boundary parameters, using a genetic algorithm to construct the initial population, perform individual crossover and mutation operations, and using a particle swarm optimization algorithm to update the population position and adjust the boundary, to output the optimal strategy parameters, specifically include the following steps S302 to S312. Wherein:

[0064] Step S302: Under the current disturbance level, based on the operating status data, the adjusted weight coefficients and the control boundary parameters, initialize the population structure and disturbance level information, and adjust the initial distribution range of particles according to the current disturbance level.

[0065] Specifically, under the current perturbation level, the server invokes the DGPSO-GA (Disturbance-Guided Particle Swarm–Genetic Algorithm, which can be understood as a perturbation-aware particle swarm and genetic hybrid algorithm) algorithm. Based on the running state data, adjusted weight coefficients, and control boundary parameters, it solves the current optimization model and outputs the optimal control strategy parameters that satisfy the perturbation level. This perturbation-aware particle swarm and genetic hybrid algorithm combines the global search capability of the genetic algorithm with the convergence speed advantage of the particle swarm algorithm.

[0066] The process of initializing population structure and perturbation level information, and adjusting the initial particle distribution range according to the current perturbation level, includes:

[0067] Initialize the population structure and perturbation level information, and combine the constructed objective function and boundary parameters to determine the appropriate perturbation level at the current perturbation level. Below, we set the population size N and the maximum number of iterations for the perturbation-aware particle swarm optimization and genetic hybrid algorithm. It also adjusts the initial particle distribution range based on the perturbation level and initializes the crossover probability in the genetic operation. With the probability of mutation and the inertia factor in particle swarm operations With learning factors , .

[0068] Step S304: Generate an initial set of solution individuals through random encoding, and use a fitness function to calculate the initial fitness value of each individual in the initial set of solution individuals.

[0069] Specifically, the server generates an initial set of individual solutions through random encoding. Furthermore, each individual in the initial solution set contains energy storage regulation parameters. By using the fitness function to calculate its objective function value, the initial fitness values ​​corresponding to each of the multiple population individuals in the initial solution set can also be calculated.

[0070] Step S306: Perform crossover and mutation operations on multiple population individuals in the initial solution individual set to construct an initial solution space with uniform fitness distribution.

[0071] Specifically, the server can construct an initial solution space with uniform fitness distribution by performing crossover and mutation operations on multiple population individuals in the initial solution individual set.

[0072] Each individual in the population This represents a set of regulatory strategy variables, with the following structure: ,in, This represents the current charging and discharging power control variable of the energy storage system, which serves as the master decision variable in the multi-objective optimization process. These represent the minimum and maximum states of charge of the energy storage system for the current cycle. To control the cycle, This is the power adjustment step size.

[0073] Step S308: Based on the initial solution space with uniform fitness distribution, update the position and velocity of multiple population individuals to obtain updated population individuals.

[0074] Specifically, based on an initial solution space with uniform fitness distribution, the server updates the positions and velocities of multiple individuals in the population, resulting in updated population individuals. The search strategy during the update process includes: , ,in, For the velocity of individual i, Its current location, For the individual's optimal position, The optimal position globally. It is a random number, and , , This is the weighting factor.

[0075] Step S310: Based on the current perturbation level, dynamically correct the initial fitness values ​​of multiple individuals in the updated population to obtain the corrected target fitness values.

[0076] Specifically, to enhance search sensitivity and local escape capability under perturbation, a perturbation-aware particle swarm optimization and genetic hybrid algorithm is used, introducing a perturbation level during the particle swarm optimization update phase. By participating in the dynamic correction of the inertia factor, that is, by dynamically correcting the initial fitness values ​​of multiple individuals in the population after the update, the corrected target fitness value can be obtained.

[0077] Among them, disturbance levels are introduced. The expression for the dynamic correction of the inertia factor is as follows: ,

[0078] in, The initial inertia factor, This is the disturbance response adjustment factor. This is the disturbance level response function.

[0079] Furthermore, the server will adjust the disturbance level. Relevant weights are injected into the objective function to make the fitness evaluation index more sensitive to power quality objectives, and based on the fitness function... Continuously update the population: ,in, For the first Sub-objective function values, Adaptive target weights driven by perturbation level.

[0080] Step S312: When the update stopping condition is met based on the target fitness value, extract the parameter variables corresponding to the best individual after the update stops to obtain the optimal policy parameters.

[0081] Specifically, when determining that the update stopping condition is met based on the target fitness value, that is, if the maximum number of iterations is reached or the optimal solution has not improved for several consecutive times, the iteration is terminated, and the optimal individual after the update stops is extracted. The corresponding parameter variables are used as the output of the control strategy, which means obtaining the optimal strategy parameters.

[0082] Among the parameter variables extracted for the optimal individual, the regulation strategy parameters include the energy storage power control quantity for the current period. Upper and lower limits of energy storage state of charge and Control cycle setting and power adjustment step size Key variables, such as these, are sent as control commands to the equipment controller for execution.

[0083] In one exemplary embodiment, such as Figure 4 As shown, an optimization process based on a perturbation-aware particle swarm optimization and genetic hybrid algorithm is presented, referring to... Figure 4 The optimization process specifically includes: Step S401, setting the perturbation level and optimization parameters; Step S402, initializing the optimization parameters; Step S403, constructing an initial population and calculating fitness; Step S404, updating the individual optimum and global optimum; Step S405, dynamically adjusting the inertia factor and updating the particle position and velocity; Step S406, performing crossover and mutation operations to generate a new population; Step S407, injecting perturbation level weights and updating fitness; Step S408, determining whether the maximum number of iterations or the convergence condition is met; Step S409, when the maximum number of iterations or the convergence condition is met, outputting the optimal individual and generating the control strategy parameters; wherein, if the maximum number of iterations or the convergence condition is not met, returning to step S405 until the maximum number of iterations or the convergence condition is met to generate the control strategy parameters.

[0084] In this embodiment, under the current perturbation level, the population structure and perturbation level information are initialized based on the operating state data, adjusted weight coefficients, and control boundary parameters, and the initial particle distribution range is adjusted according to the current perturbation level. An initial solution individual set is generated through random encoding, and the initial fitness value corresponding to each of the multiple population individuals in the initial solution individual set is calculated using a fitness function. Crossover and mutation operations are performed on the multiple population individuals in the initial solution individual set to construct an initial solution space with uniform fitness distribution. Based on the initial solution space with uniform fitness distribution, the positions and velocities of the multiple population individuals are updated to obtain updated multiple population individuals. According to the current perturbation level, the initial fitness values ​​of the updated multiple population individuals are dynamically corrected to obtain the corrected target fitness value. When the update stopping condition is determined based on the target fitness value, the parameter variables corresponding to the optimal individual after the update stops are extracted to obtain the optimal strategy parameters.

[0085] In one exemplary embodiment, such as Figure 5 As shown, a power quality control method for a photovoltaic-storage system is provided, which can be applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps S501 to S516. Wherein:

[0086] Step S501: Set the sliding time window length and refresh cycle, and initialize the initial weight coefficients of the perturbation feature input structure, the control boundary parameters and the multi-objective optimization function to obtain the initialized weight coefficients and initial control boundary parameters.

[0087] Specifically, the server constructs a dynamic input framework for perturbation features by setting a sliding time window structure and refresh frequency, and completes the initial configuration of relevant control parameters and optimization target weights. The initial configuration process includes:

[0088] Step a) Set the sliding time window length T and refresh cycle. It also initializes the perturbation feature input structure, adjusts the boundary parameters, and sets the initial weight coefficients of the multi-objective optimization function.

[0089] In the sliding time window mechanism, let the current time be t, and define the perturbation feature vector sequence as follows: ,in Given a perturbation sequence with a sliding window length of T. Let be the perturbation eigenvector at time t.

[0090] Step b) Initialize the control boundary parameters of the photovoltaic-storage system and the initial weights of the multi-objective optimization function to construct the variable range and objective tendency for subsequent strategy optimization, including the following settings:

[0091] 1) Set the maximum charge and discharge power boundary based on the rated power capacity of the energy storage equipment. ;in, Let t be the charging and discharging power of the energy storage system at node I. The maximum allowable output power can be set with reference to the equipment nameplate parameters or experience in typical operating scenarios, and generally corresponds to 80% to 100% of the rated installed capacity of the node.

[0092] 2) Initialize the energy boundary of the energy storage system: ;in, Let be the actual energy value of the energy storage system at node i at time t. and These are the minimum and maximum allowable energy quantities for the energy storage system at node i, respectively.

[0093] 3) Transition to a charged state (charged state): , ;in, Let be the state of charge of the energy storage system at node i at time t. Let be the actual energy value of the energy storage system at node i at time t. The rated energy capacity of the node energy storage system. and These are the upper and lower limits of the state of charge, typically set at 10% to 90% of the rated capacity of the energy storage system;

[0094] 4) Set the default adjustment cycle and control rhythm parameters, including control cycle, refresh step size, response delay, and adjustment range; among which, the control cycle... With the scroll refresh cycle Response delay is set according to the control granularity. Power adjustment step size is set according to the equipment's response capability. It can be dynamically set as a percentage of the maximum output power: .

[0095] The above parameters can serve as the basic settings for dynamic control and can be dynamically adjusted according to the disturbance level during operation.

[0096] 5) The weight vector of the multi-objective optimization function is initialized as follows: ;in, The initial weights for the voltage deviation target term are: The initial weights for the voltage fluctuation objective term are: The initial weights are used for the total harmonic distortion rate objective term. This initial weight vector is used to construct the disturbance-aware multi-objective function and will serve as the basis for the dynamic weight adjustment mechanism after the disturbance level is identified.

[0097] Step S502: Obtain multiple power indicators characterizing the power quality of the photovoltaic-storage system, and construct a disturbance feature vector based on the multiple power indicators.

[0098] Specifically, the server acquires multiple power indicators characterizing the power quality of the photovoltaic-storage system, including voltage deviation, voltage fluctuation amplitude, and total harmonic distortion (THD). Based on these power indicators, it constructs a disturbance feature vector.

[0099] Furthermore, the server constructs perturbation feature vectors. : It includes three core indicators representing the power quality of the system. For voltage deviation, For voltage fluctuation amplitude, This represents the total harmonic distortion (THD) of the voltage.

[0100] The calculation methods for each electrical energy index include:

[0101] 1) Voltage deviation This represents the relative difference between the node voltage and its rated nominal voltage, used to measure whether the voltage level is stable within the allowable range. Its expression is: ,in, Let i be the actual voltage value of node i at time t. Let be the nominal voltage of node i;

[0102] 2) Voltage fluctuation amplitude This indicates the degree of rapid change in voltage caused by disturbances such as photovoltaic power output within a short period of time, reflecting the strength of the instantaneous voltage disturbance. Its expression is: ,in, Here, K is the photovoltaic perturbation normalization factor, and K is the number of samples within the current sliding window. Let be the resistance of the line upstream of node i. Let be the photovoltaic output power of the i-th node at the k-th sampling point. Let be the rated voltage value of node i.

[0103] Among them, the photovoltaic disturbance normalization factor The calculation formula is: ,in, This represents the maximum instantaneous change in photovoltaic power output per unit time. This refers to the rated output power of the photovoltaic module.

[0104] 3) Total harmonic distortion of voltage This represents the combined proportion of all harmonic components other than the fundamental frequency in a voltage signal, used to measure the degree of distortion in the voltage waveform. Its expression is: ,in, The effective value of the h-th harmonic voltage at the grid connection point. H represents the effective value of the fundamental voltage, and H represents the upper limit of the harmonic order.

[0105] Furthermore, the above indicators are normalized, and their expression is as follows: ,in, For the k-th perturbation, , These are the minimum and maximum values ​​of the indicator within the historical sliding window, respectively. This is the normalized perturbation input.

[0106] Step S503: Collect the operating status data of each node in the optical storage system, and construct a perturbation feature vector sequence based on the operating status data.

[0107] Step S504: Within a pre-configured sliding time window, perform statistical analysis on the perturbation feature vector sequence to obtain the changing trend and overall perturbation level corresponding to the perturbation feature vector sequence.

[0108] Step S505: Construct the perturbation feature evolution trajectory based on the changing trend corresponding to the perturbation feature vector sequence and the overall perturbation level.

[0109] Step S506: Extract the last value of the disturbance feature vector sequence as the disturbance feature input at the current time, and identify the disturbance level of the disturbance feature input according to the pre-configured disturbance level evaluation rules to obtain the current disturbance level.

[0110] Step S507: Based on the current disturbance level, dynamically adjust the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic-storage system to obtain the adjusted weight coefficients and control boundary parameters.

[0111] Step S508: Under the current disturbance level, based on the operating status data, the adjusted weight coefficients and the control boundary parameters, initialize the population structure and disturbance level information, and adjust the initial distribution range of particles according to the current disturbance level.

[0112] Step S509: Generate an initial set of solution individuals through random coding, and use a fitness function to calculate the initial fitness value of each individual in the initial set of solution individuals.

[0113] Step S510: Perform crossover and mutation operations on multiple population individuals in the initial solution individual set to construct an initial solution space with uniform fitness distribution. Based on the initial solution space with uniform fitness distribution, update the position and velocity of multiple population individuals to obtain updated multiple population individuals.

[0114] Step S511: Based on the current perturbation level, dynamically correct the initial fitness values ​​of multiple individuals in the updated population to obtain the corrected target fitness values.

[0115] Step S512: When the update stopping condition is met based on the target fitness value, extract the parameter variables corresponding to the best individual after the update stops to obtain the optimal policy parameters.

[0116] Step S513: Generate a quality control strategy based on the optimal strategy parameters, and perform power quality control based on the quality control strategy.

[0117] Step S514: Collect the next round of operating status data after power quality regulation, so as to determine the next round of disturbance level based on the next round of operating status data, and compare the next round of disturbance level with the current disturbance level.

[0118] Step S515: If the disturbance level in the next round is inconsistent with the current disturbance level, proceed to the next round of strategy optimization process to optimize the quality control strategy.

[0119] Step S516: If the disturbance level in the next round is the same as the current disturbance level, power quality control shall be carried out according to the power quality control strategy.

[0120] In one exemplary embodiment, such as Figure 6 As shown, an overall processing procedure for a power quality control method for a photovoltaic-storage system is provided, referring to... Figure 6 The specific processing steps include: Step S601, initializing the sliding time window and parameter settings; Step S602, collecting system operating status data; Step S603, constructing and preprocessing the disturbance feature vector; Step S604, constructing the disturbance evolution trajectory within the sliding window; Step S605, determining the disturbance level; Step S606, dynamically adjusting the control parameters and resource boundaries; Step S607, calling the disturbance-aware particle swarm and genetic hybrid algorithm to construct the control strategy; Step S608, outputting the policy strategy and issuing it for execution; Step S609, collecting a new round of system operating status data; Step S610, determining whether a strategy reconstruction is needed; where, if a strategy reconstruction is needed, returning to step S607; Step S611, if a strategy reconstruction is not needed, performing power quality control for the next cycle.

[0121] It is understandable that by constructing an integrated mechanism for disturbance identification and strategy control, the photovoltaic-storage system achieves adaptive dynamic response control to various types of power quality disturbances. Specifically, a sliding window can be used to perceive the evolution trajectory of disturbance characteristics, accurately determine the disturbance level, and dynamically adjust the control boundary and multi-objective optimization weights based on the disturbance level. This allows the control objectives to switch flexibly according to disturbance changes, improving strategy adaptability. Furthermore, an evolutionary optimization algorithm is used to generate the optimal control strategy under the disturbance level, and the optimization result is executed in real time as a control command, effectively improving the dynamic adjustment capability and power quality assurance capability of the photovoltaic-storage system. This power quality control method for the photovoltaic-storage system has advantages such as high disturbance identification accuracy, flexible control response, and strong system robustness, overcoming the problems of rigid control strategies and poor adaptability in traditional methods, and meeting the actual needs of power quality-oriented control of photovoltaic-storage systems in complex operating scenarios.

[0122] In the aforementioned power quality control method for the photovoltaic-storage system, operational status data of each node in the system is collected. Based on this data, a disturbance feature vector sequence is constructed. Within a pre-configured sliding time window, a disturbance feature evolution trajectory is generated based on this sequence. This trajectory is used to identify the disturbance level and determine the current disturbance level. This method enables the perception of system operational status changes through a sliding time window, reducing inaccuracies in disturbance change identification. Furthermore, based on the current disturbance level, the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic-storage system are dynamically adjusted. These adjusted coefficients and parameters are then used to optimize the control strategy parameters based on the operational status data and the adjusted parameters. This yields the optimal strategy parameters, allowing for dynamic adjustment of target weights and control parameter boundaries driven by a disturbance level judgment mechanism. The generation of a quality control strategy based on the optimal parameters enables adaptive optimization of key system parameters. Furthermore, a quality control strategy is generated based on the optimal strategy parameters, and power quality is controlled according to the quality control strategy. The next round of operating status data after power quality control is collected, so as to optimize the quality control strategy based on the next round of operating status data. This achieves deep synergy between disturbance perception and optimization mechanisms, thereby improving the real-time adaptability and power quality assurance capability of the photovoltaic-storage system under complex disturbance scenarios and meeting the intelligent control requirements under dynamic evolution of operating status.

[0123] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0124] Based on the same inventive concept, this application also provides a power quality control device for a photovoltaic-storage system to implement the power quality control method for the photovoltaic-storage system described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the power quality control device for a photovoltaic-storage system provided below can be found in the limitations of the power quality control method for the photovoltaic-storage system described above, and will not be repeated here.

[0125] In one exemplary embodiment, such as Figure 7 As shown, a power quality control device for a photovoltaic-storage system is provided, comprising: a disturbance feature vector sequence construction module 702, a current disturbance level identification module 704, a parameter adjustment module 706, an optimal strategy parameter determination module 708, and a power quality control module 710, wherein:

[0126] The disturbance feature vector sequence construction module 702 is used to collect the operating status data of each node in the photovoltaic-storage system and construct a disturbance feature vector sequence based on the operating status data. The current disturbance level identification module 704 is used to generate a disturbance feature evolution trajectory based on the disturbance feature vector sequence within a pre-configured sliding time window, and to identify the disturbance level of the disturbance feature evolution trajectory to obtain the current disturbance level. The parameter adjustment module 706 is used to dynamically adjust the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic-storage system according to the current disturbance level to obtain the adjusted weight coefficients and control boundary parameters. The optimal strategy parameter determination module 708 is used to optimize the control strategy parameters of the photovoltaic-storage system based on the operating status data and the adjusted weight coefficients and control boundary parameters to obtain the optimal strategy parameters. The power quality control module 710 is used to generate a power quality control strategy based on the optimal strategy parameters, perform power quality control according to the power quality control strategy, and collect the next round of operating status data after power quality control to optimize the power quality control strategy based on the next round of operating status data.

[0127] In the power quality control device of the aforementioned photovoltaic-storage system, operational status data of each node in the system is collected. Based on this data, a disturbance feature vector sequence is constructed. Within a pre-configured sliding time window, a disturbance feature evolution trajectory is generated based on this sequence. This trajectory is used to identify the disturbance level and determine the current disturbance level. This allows for the perception of system operational status changes through a sliding time window, reducing inaccuracies in disturbance change identification. Furthermore, based on the current disturbance level, the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic-storage system are dynamically adjusted. These adjusted coefficients and parameters are then used to optimize the control strategy parameters based on the operational status data and the adjusted parameters. This yields the optimal strategy parameters, enabling dynamic adjustment of target weights and control parameter boundaries through a disturbance level judgment mechanism. The generation of a quality control strategy based on the optimal parameters allows for adaptive optimization of key system parameters. Furthermore, a quality control strategy is generated based on the optimal strategy parameters, and power quality is controlled according to the quality control strategy. The next round of operating status data after power quality control is collected, so as to optimize the quality control strategy based on the next round of operating status data. This achieves deep synergy between disturbance perception and optimization mechanisms, thereby improving the real-time adaptability and power quality assurance capability of the photovoltaic-storage system under complex disturbance scenarios and meeting the intelligent control requirements under dynamic evolution of operating status.

[0128] In an exemplary embodiment, the current disturbance level identification module is further configured to: perform statistical analysis on the disturbance feature vector sequence within a pre-configured sliding time window to obtain the changing trend and overall disturbance level corresponding to the disturbance feature vector sequence; construct the disturbance feature evolution trajectory based on the changing trend and overall disturbance level corresponding to the disturbance feature vector sequence; extract the last value of the disturbance feature vector sequence as the disturbance feature input at the current moment, and perform disturbance level identification on the disturbance feature input according to the pre-configured disturbance level evaluation rules to obtain the current disturbance level.

[0129] In an exemplary embodiment, the optimal strategy parameter determination module is further configured to: construct an initial population, perform individual crossover and mutation operations using a genetic algorithm based on the running state data, as well as the adjusted weight coefficients and control boundary parameters, and update the population position and adjust the boundary using a particle swarm optimization algorithm to output the optimal strategy parameters.

[0130] In an exemplary embodiment, the optimal strategy parameter determination module is further configured to: initialize the population structure and perturbation level information based on the running state data, adjusted weight coefficients, and control boundary parameters under the current perturbation level, and adjust the initial distribution range of particles according to the current perturbation level; generate an initial solution individual set through random encoding, and calculate the initial fitness value corresponding to each of the multiple population individuals in the initial solution individual set using a fitness function; perform crossover and mutation operations on the multiple population individuals in the initial solution individual set to construct an initial solution space with uniform fitness distribution; update the position and velocity of the multiple population individuals based on the initial solution space with uniform fitness distribution to obtain updated multiple population individuals; dynamically correct the initial fitness values ​​of the updated multiple population individuals according to the current perturbation level to obtain the corrected target fitness value; and extract the parameter variables corresponding to the optimal individual after the update stops when the update stopping condition is determined based on the target fitness value to obtain the optimal strategy parameters.

[0131] In an exemplary embodiment, the power quality control module is further configured to: determine the disturbance level for the next round based on the next round of operating status data; compare the disturbance level for the next round with the current disturbance level; if the disturbance level for the next round is inconsistent with the current disturbance level, proceed to the next round of strategy optimization process to optimize the power quality control strategy; and if the disturbance level for the next round is consistent with the current disturbance level, perform power quality control according to the power quality control strategy.

[0132] In one exemplary embodiment, a power quality control device for a photovoltaic-storage system is provided, further comprising a parameter initialization module for:

[0133] Set the sliding time window length and refresh cycle, and initialize the initial weight coefficients of the disturbance feature input structure, control boundary parameters and multi-objective optimization function to obtain the initialized weight coefficients and initial control boundary parameters; obtain multiple power indicators characterizing the power quality of the photovoltaic-storage system, and construct a disturbance feature vector based on the multiple power indicators.

[0134] The various modules in the power quality control device of the aforementioned photovoltaic-storage system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0135] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores operational status data of each node in the optical storage system, perturbation feature vector sequences, pre-configured sliding time windows, perturbation feature evolution trajectories, current perturbation levels, weight coefficients of the multi-objective optimization function, initial control boundary parameters, adjusted weight coefficients and control boundary parameters, optimal strategy parameters, quality control strategies, and operational status data for the next round. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a power quality control method for a photovoltaic energy storage system.

[0136] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0137] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0138] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0139] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0140] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0141] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0142] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this application. The above embodiments only illustrate several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of this application. It should be noted that for those skilled in the art, several modifications and improvements can be made without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for power quality control in a photovoltaic-storage system, characterized in that, The method includes: Collect the operating status data of each node in the optical storage system, and construct a perturbation feature vector sequence based on the operating status data; Within a pre-configured sliding time window, a perturbation feature evolution trajectory is generated based on the perturbation feature vector sequence, and the perturbation level is identified on the perturbation feature evolution trajectory to obtain the current perturbation level. Based on the current disturbance level, the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic storage system are dynamically adjusted to obtain the adjusted weight coefficients and control boundary parameters. Based on the operational status data, as well as the adjusted weighting coefficients and control boundary parameters, the control strategy parameters of the photovoltaic-storage system are optimized to obtain the optimal strategy parameters. A quality control strategy is generated based on the optimal strategy parameters, power quality is controlled according to the quality control strategy, and the next round of operating status data after power quality control is collected, so as to optimize the quality control strategy based on the next round of operating status data.

2. The method according to claim 1, characterized in that, Within a pre-configured sliding time window, based on the perturbation feature vector sequence, a perturbation feature evolution trajectory is generated, and the perturbation level is identified on the perturbation feature evolution trajectory to obtain the current perturbation level, including: Within a pre-configured sliding time window, statistical analysis is performed on the perturbation feature vector sequence to obtain the changing trend and overall perturbation level corresponding to the perturbation feature vector sequence; Based on the changing trend and overall disturbance level corresponding to the disturbance feature vector sequence, a disturbance feature evolution trajectory is constructed; The last value of the disturbance feature vector sequence is extracted as the disturbance feature input at the current time. The disturbance level is identified based on the pre-configured disturbance level evaluation rules to obtain the current disturbance level.

3. The method according to claim 1, characterized in that, The process of optimizing the control strategy parameters of the photovoltaic-storage system based on the operational status data, the adjusted weighting coefficients, and the control boundary parameters to obtain the optimal strategy parameters includes: Based on the operational status data, the adjusted weight coefficients, and the control boundary parameters, a genetic algorithm is used to construct the initial population, perform individual crossover and mutation operations, and a particle swarm optimization algorithm is used to update the population position and adjust the boundary, outputting the optimal strategy parameters.

4. The method according to claim 3, characterized in that, Based on the operational status data, the adjusted weight coefficients, and the control boundary parameters, a genetic algorithm is used to construct the initial population, perform individual crossover and mutation operations, and a particle swarm optimization algorithm is used to update the population position and adjust the boundary, outputting the optimal strategy parameters, including: Under the current disturbance level, based on the operating status data, the adjusted weight coefficients, and the control boundary parameters, the population structure and disturbance level information are initialized, and the initial particle distribution range is adjusted according to the current disturbance level. An initial set of individual solutions is generated by random encoding, and the initial fitness value of each individual in the initial set of individual solutions is calculated using a fitness function. Crossover and mutation operations are performed on multiple individuals in the initial solution set to construct an initial solution space with uniform fitness distribution; Based on the initial solution space with uniform fitness distribution, the positions and velocities of the multiple population individuals are updated to obtain the updated multiple population individuals; Based on the current perturbation level, the initial fitness values ​​of the updated multiple population individuals are dynamically corrected to obtain the corrected target fitness values. When the update stopping condition is met based on the target fitness value, the parameter variables corresponding to the best individual after the update stops are extracted to obtain the optimal policy parameters.

5. The method according to any one of claims 1 to 4, characterized in that, The optimization of the quality control strategy based on the next round of operational status data includes: Based on the next round of operating status data, determine the next round of orbital motion level; The next round of disturbance level is compared with the current disturbance level; If the next round of disturbance level is inconsistent with the current disturbance level, proceed to the next round of strategy optimization process to optimize the quality control strategy; If the next round of disturbance level is the same as the current disturbance level, power quality regulation shall be performed according to the quality regulation strategy.

6. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Set the sliding time window length and refresh period, and initialize the initial weight coefficients of the perturbation feature input structure, the control boundary parameters and the multi-objective optimization function to obtain the initialized weight coefficients and the initial control boundary parameters; Multiple power indicators characterizing the power quality of the photovoltaic-storage system are obtained, and a disturbance feature vector is constructed based on the multiple power indicators.

7. A power quality control device for a photovoltaic-storage system, characterized in that, The device includes: The perturbation feature vector sequence construction module is used to collect the operating status data of each node in the optical storage system and construct a perturbation feature vector sequence based on the operating status data. The current disturbance level identification module is used to generate a disturbance feature evolution trajectory based on the disturbance feature vector sequence within a pre-configured sliding time window, and to identify the disturbance level of the disturbance feature evolution trajectory to obtain the current disturbance level. The parameter adjustment module is used to dynamically adjust the weight coefficients and initial control boundary parameters of the multi-objective optimization function corresponding to the photovoltaic storage system according to the current disturbance level, so as to obtain the adjusted weight coefficients and control boundary parameters. The optimal strategy parameter determination module is used to optimize and solve the control strategy parameters of the photovoltaic storage system based on the operating status data, the adjusted weight coefficients and control boundary parameters, and obtain the optimal strategy parameters. The power quality control module is used to generate a power quality control strategy based on the optimal strategy parameters, perform power quality control according to the power quality control strategy, and collect the next round of operating status data after power quality control, so as to optimize the power quality control strategy based on the next round of operating status data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images