Power quality multi-level adaptive control method, device, equipment and storage medium

Abstract

This application relates to a multi-level adaptive control method, apparatus, device, and storage medium for power quality, belonging to the field of power grid service technology. The method includes: determining the disturbance condition type of the power grid based on target indicator data; selecting a first control strategy from a control strategy template based on the disturbance condition type; updating the strategy parameters of the first control strategy based on the target indicator data and the disturbance condition type to obtain a second control strategy; and managing power quality of the power grid according to the second control strategy. This application effectively improves the efficiency and effectiveness of power grid power quality management, while relying on data-driven strategy selection and parameter optimization to reduce the blindness of management and ensure the scientific nature and effectiveness of power grid power quality management.

Description

Technical Field

[0001] This application relates to the field of power grid service technology, and in particular to a method, apparatus, equipment and storage medium for multi-level adaptive control of power quality. Background Technology

[0002] With the large-scale integration of power electronic equipment, frequency converters, and new energy devices, power quality problems in the power grid are becoming increasingly prominent. Phenomena such as harmonic pollution, voltage fluctuations, and three-phase imbalance occur frequently, seriously affecting the safety of the power supply system and the stable operation of electrical equipment. As a result, various power quality management devices have been gradually developed, including active filters, reactive power compensators, and dynamic voltage restorers. However, existing equipment generally suffers from low integration, slow response, poor adaptability, and complex module maintenance, making it difficult to meet the dynamic management needs of multiple scenarios. In particular, in actual engineering projects, the power grid operating conditions are complex and changeable, and the management strategies required under different operating conditions vary greatly.

[0003] Traditional multi-level adaptive power quality control methods are mostly statically set and lack flexible strategy scheduling capabilities, resulting in poor power quality management performance. Summary of the Invention

[0004] Therefore, it is necessary to provide a multi-level adaptive control method, device, equipment, and storage medium for power quality that can effectively improve the power quality management effect, addressing the aforementioned technical problems.

[0005] Firstly, this application provides a multi-level adaptive control method for power quality. The method includes:

[0006] Based on the target index data of the power grid, determine the type of disturbance condition of the power grid;

[0007] Select the first control strategy from the control strategy template based on the type of disturbance condition.

[0008] Based on the target index data and the type of disturbance condition, the strategy parameters of the first control strategy are updated to obtain the second control strategy.

[0009] According to the second control strategy, power quality management is carried out on the power grid.

[0010] In one embodiment, the type of disturbance condition of the power grid is determined based on the target index data of the power grid, including:

[0011] Feature extraction is performed on the target index data of the power grid to obtain disturbance index data;

[0012] Based on the disturbance index data, determine the type of disturbance condition of the power grid.

[0013] In one embodiment, after power quality management of the power grid according to the second control strategy, the method further includes:

[0014] Obtain power grid quality management effectiveness indicators;

[0015] Determine the overall management effectiveness score based on the quality management effectiveness indicators;

[0016] Based on the comprehensive management effectiveness score, the second control strategy is updated to obtain the third control strategy;

[0017] Power quality management of the power grid is carried out according to the third control strategy.

[0018] In one embodiment, the quality management performance indicators include at least one of the following: current total harmonic distortion, voltage deviation, frequency fluctuation amplitude, distortion rate benchmark, voltage deviation benchmark, and maximum fluctuation amplitude.

[0019] Based on the quality management effectiveness indicators, a comprehensive management effectiveness score is determined, including:

[0020] Determine the first ratio of the current total harmonic distortion to the baseline distortion value;

[0021] Determine a second ratio between the voltage deviation and the voltage deviation reference value;

[0022] Determine the third ratio of the frequency fluctuation amplitude to the maximum fluctuation amplitude;

[0023] The first ratio, the second ratio, and the third ratio are weighted and summed to obtain the overall management effectiveness score.

[0024] In one embodiment, the second control strategy is updated based on the comprehensive management effectiveness score to obtain a third control strategy, including:

[0025] The residual energy value is determined based on the comprehensive management effectiveness score and the model prediction value;

[0026] The strategy update status is determined based on the residual energy value and the energy threshold;

[0027] If the strategy update status is "updated", the second control strategy is updated based on the comprehensive management effectiveness score to obtain the third control strategy.

[0028] In one embodiment, the second control strategy includes at least two associated control strategies;

[0029] Based on the comprehensive management effectiveness score, the second control strategy is updated to obtain the third control strategy, which includes:

[0030] For each associated control strategy, obtain the residual energy and mean residual energy of the associated control strategy during the execution process, as well as the average score and maximum comprehensive management effect score of the associated control strategy within a preset historical period.

[0031] The optimization gain index of the correlation control strategy is determined based on the residual energy, mean residual energy, average score of comprehensive management effect, and maximum comprehensive management effect score.

[0032] Based on the optimization gain index of each associated control strategy, the target control strategy is selected from the associated control strategies;

[0033] The target control strategy is used as the third control strategy.

[0034] In one embodiment, the optimization gain index of the correlation control strategy is determined based on the residual energy, mean residual energy, average score of comprehensive management effect, and maximum comprehensive management effect score, including:

[0035] Determine the fourth ratio of the residual energy to the mean residual energy;

[0036] Determine the difference between the preset value and the fourth ratio;

[0037] Determine the fifth ratio between the average score of comprehensive management effectiveness and the highest score of comprehensive management effectiveness;

[0038] Based on the difference and the fifth ratio, the optimal gain index of the associated control strategy is determined.

[0039] Secondly, this application also provides a multi-level adaptive power quality control device. The device includes:

[0040] The first determining module is used to determine the type of disturbance condition of the power grid based on the target index data of the power grid.

[0041] The selection module is used to select the first control strategy from the control strategy template based on the type of disturbance condition.

[0042] The first update module is used to update the strategy parameters of the first control strategy based on the target index data and the type of disturbance condition to obtain the second control strategy.

[0043] The first management module is used to manage the power quality of the power grid according to the second control strategy.

[0044] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0045] Based on the target index data of the power grid, determine the type of disturbance condition of the power grid;

[0046] Select the first control strategy from the control strategy template based on the type of disturbance condition.

[0047] Based on the target index data and the type of disturbance condition, the strategy parameters of the first control strategy are updated to obtain the second control strategy.

[0048] According to the second control strategy, power quality management is carried out on the power grid.

[0049] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0050] Based on the target index data of the power grid, determine the type of disturbance condition of the power grid;

[0051] Select the first control strategy from the control strategy template based on the type of disturbance condition.

[0052] Based on the target index data and the type of disturbance condition, the strategy parameters of the first control strategy are updated to obtain the second control strategy.

[0053] According to the second control strategy, power quality management is carried out on the power grid.

[0054] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0055] Based on the target index data of the power grid, determine the type of disturbance condition of the power grid;

[0056] Select the first control strategy from the control strategy template based on the type of disturbance condition.

[0057] Based on the target index data and the type of disturbance condition, the strategy parameters of the first control strategy are updated to obtain the second control strategy.

[0058] According to the second control strategy, power quality management is carried out on the power grid.

[0059] The aforementioned multi-level adaptive power quality control method, device, equipment, and storage medium determine the disturbance condition type of the power grid based on the target indicator data. According to the disturbance condition type, a first control strategy is selected from the control strategy template. Based on the target indicator data and the disturbance condition type, the strategy parameters of the first control strategy are updated to obtain a second control strategy. Power quality management is then performed on the power grid according to the second control strategy. By accurately determining the disturbance condition type based on the target indicator data, selecting a suitable control strategy template, and dynamically updating and optimizing the strategy parameters based on the target indicator data and the condition type, power quality management is carried out. This achieves precise matching between the control strategy and the actual operating state of the power grid, making power quality management more targeted and adaptable, effectively improving the efficiency and effectiveness of power grid power quality management. Furthermore, relying on data-driven strategy selection and parameter optimization reduces the blindness of management and ensures the scientific nature and effectiveness of power grid power quality management. Attached Figure Description

[0060] Figure 1 This is an application environment diagram of the multi-level adaptive power quality control method provided in this embodiment;

[0061] Figure 2 This is a flowchart illustrating the first multi-level adaptive power quality control method provided in this embodiment.

[0062] Figure 3 This is a flowchart illustrating the process of determining the type of power grid disturbance provided in this embodiment.

[0063] Figure 4 This is a schematic diagram of the power quality management process for the power grid provided in this embodiment;

[0064] Figure 5 This is a flowchart illustrating the second type of multi-level adaptive power quality control method provided in this embodiment.

[0065] Figure 6 This is a structural block diagram of a multi-level adaptive power quality control device provided in this embodiment;

[0066] Figure 7 This is an internal structural diagram of the computer device provided in this embodiment. Detailed Implementation

[0067] 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.

[0068] With the large-scale integration of power electronic equipment, frequency converters, and new energy devices, power quality problems in the power grid are becoming increasingly prominent. Phenomena such as harmonic pollution, voltage fluctuations, and three-phase imbalance occur frequently, seriously affecting the safety of the power supply system and the stable operation of electrical equipment. As a result, various power quality management devices have been gradually developed, including active filters, reactive power compensators, and dynamic voltage restorers. However, existing equipment generally suffers from low integration, slow response, poor adaptability, and complex module maintenance, making it difficult to meet the dynamic management needs of multiple scenarios. In particular, in actual engineering projects, the power grid operating conditions are complex and changeable, and the management strategies required under different operating conditions vary greatly.

[0069] Traditional multi-level adaptive power quality control methods are mostly statically set and lack flexible strategy scheduling capabilities, resulting in poor power quality management performance.

[0070] To address the aforementioned technical problems, the multi-level adaptive power quality control method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, upon receiving a power quality management request initiated by client 102, server 104 determines the disturbance condition type of the power grid based on the target indicator data of the power grid, selects a first control strategy from the control strategy template according to the disturbance condition type, updates the strategy parameters of the first control strategy according to the target indicator data and the disturbance condition type to obtain a second control strategy, and finally performs power quality management of the power grid according to the second control strategy.

[0071] The server can be a standalone server or a server cluster, and it can be a server associated with the power grid management platform. The client refers to the user-side terminal device, such as a mobile phone, computer, or other smart terminal.

[0072] In one embodiment, such as Figure 2 As shown, a multi-level adaptive control method for power quality is provided, which is applied to... Figure 1 Taking the server in the example, the following steps are included:

[0073] S201, Based on the target index data of the power grid, determine the type of disturbance condition of the power grid.

[0074] Among them, target indicator data refers to the indicator data of the target indicators of the power grid, such as indicator values.

[0075] Optionally, the target indicators in this embodiment include, but are not limited to, harmonics, voltage, frequency, and three-phase balance.

[0076] Optionally, one possible implementation of obtaining target indicator data for the power grid in this embodiment is to obtain the original indicators of the power grid (which may be all indicators of the power grid). For each original indicator, the correlation analysis result between the original indicator and the power grid quality data is determined, and the target indicator is selected from the original indicators based on the correlation analysis result. In this embodiment, the linear correlation between the original indicators and the power grid quality data is quantified by calculating the Pearson correlation coefficient r (within the range of [−1,1]): |r| is closer to 1, the stronger the linear correlation; r>0 indicates a positive correlation, r<0 indicates a negative correlation; and r close to 0 indicates no significant linear correlation.

[0077] An optional implementation method is to set graded threshold ranges (normal range, mild disturbance range, moderate disturbance range, and severe disturbance range) for each target indicator data according to the State Grid power quality standards (such as GB / T 14549-1993 and GB / T12325-2008), compare the real-time collected target indicator data with the threshold ranges one by one, and directly determine the disturbance condition type based on the type of indicator exceeding the standard and the exceeding range.

[0078] Another alternative implementation involves abstracting various typical disturbance conditions into standardized feature vectors, with the vector dimension consistent with the power grid target index dimension (e.g., dimension [THD, voltage deviation, frequency fluctuation amplitude, three-phase imbalance]). Each typical disturbance condition corresponds to a unique standardized feature vector (including the disturbance characteristic value and over-limit weight of each index). The power grid target index data is constructed into real-time feature vectors. By calculating the similarity (e.g., cosine similarity, Euclidean distance) between the real-time feature vectors and the standardized feature vectors of each typical disturbance condition, the typical disturbance condition with the highest similarity is selected as the disturbance condition type.

[0079] Optionally, in this embodiment, the disturbance conditions include single disturbance conditions and compound disturbance conditions. A single disturbance condition may include harmonic pollution conditions, voltage deviation conditions, voltage fluctuation / flicker conditions, frequency fluctuation conditions, and three-phase imbalance conditions. Compound disturbance conditions include harmonic + voltage deviation compound conditions, harmonic + voltage fluctuation compound conditions, frequency fluctuation + voltage deviation compound conditions, and three-phase imbalance + harmonic compound conditions, etc.

[0080] S202, Select the first control strategy from the control strategy template according to the disturbance condition type.

[0081] The control strategy template refers to a strategy template that contains several control strategies. The first control strategy is the selected control strategy corresponding to the disturbance condition type, used to improve the disturbance condition in the power grid.

[0082] One optional implementation involves selecting a first control strategy from a control strategy template based on the disturbance condition type and a condition list. The condition list records various disturbance conditions and the corresponding control strategies for each type of disturbance condition.

[0083] Another optional implementation is to construct standardized feature vectors for each type of disturbance condition and control strategy template. The condition feature vector includes dimensions such as the type and degree of index exceeding the standard, while the strategy feature vector includes dimensions such as governance objectives, adaptation indicators, and control parameters. After determining the disturbance condition, the similarity between the disturbance condition feature vector and all control strategy feature vectors in the control strategy template is calculated. The control strategy with the highest similarity is selected as the first control strategy. Cosine similarity and Euclidean distance are commonly used to complete the quantitative calculation.

[0084] S203, based on the target index data and the type of disturbance condition, update the strategy parameters of the first control strategy to obtain the second control strategy.

[0085] The second control strategy refers to the modified or optimized first control strategy.

[0086] One possible implementation is to pre-establish the threshold range for exceeding the power grid target index data and the linkage correction rules for each parameter of the first control strategy, clarify the parameter adjustment direction and specific amplitude corresponding to the degree of exceeding the target index data (mild / moderate / severe) under different operating conditions, match the corresponding rule set with the current disturbance operating condition type, and then quantitatively correct the parameters of the first control strategy according to the rules based on the actual exceeding value of the real-time target index data to obtain the second control strategy.

[0087] Another optional implementation method is to construct a mathematical model with the optimization objective of "meeting the target index data and achieving the best governance effect" based on the goal of power grid power quality management. The disturbance condition type is used as the model constraint, and the parameters of the first control strategy are used as the model optimization variables. The model is solved by optimization algorithms such as gradient descent and particle swarm optimization to obtain the optimal solution of parameters that meets the current operating conditions and index requirements. The first control strategy parameters are updated with this solution to form the second control strategy.

[0088] Another optional implementation involves retrieving historical power grid operation records that are consistent with the current disturbance condition type and have similar target index data, extracting the optimal parameter values ​​of the control strategy from these records, fitting the numerical correlation between the target index data and the strategy parameters using data analysis methods such as linear fitting and polynomial fitting, then substituting the current real-time target index data to calculate the appropriate parameter values, and updating the first control strategy to obtain the second control strategy.

[0089] S204, Power quality management of the power grid is carried out according to the second control strategy.

[0090] One optional implementation involves breaking down the power quality management task into sub-tasks such as harmonic mitigation, voltage stabilization, frequency regulation, and three-phase balance, based on the governance dimension of the second control strategy. These sub-tasks are then assigned to the corresponding functional modules of the equipment. Each functional module is configured with the corresponding control parameters and coordination rules from the control strategy. Each functional module starts synchronously, controls independently, and interacts with the others in real time according to the control parameters and coordination rules. Through the coordinated cooperation of multiple modules, overall power quality management is completed, suitable for comprehensive management of complex disturbance conditions. Based on this, an optional implementation of a multi-level adaptive power quality control method involves acquiring the operating status and performance parameters of each functional module. Based on these operating status and performance parameters, the performance status of each functional module is determined. If the performance status is lower than preset conditions, the associated backup module is started, and the control status and parameters of the backup module are kept consistent with those of the functional module, improving the stability and redundancy of power quality management.

[0091] Another optional implementation is to parse the second control strategy into direct execution instructions for power quality management equipment. The instructions include the action parameters, regulation amplitude and execution sequence of each management unit. The system directly sends the instructions to hardware execution units such as active filters and reactive power compensators. Each unit completes operations such as harmonic suppression, voltage regulation and reactive power compensation according to the instructions, which directly affects the power grid to realize power quality management. This is suitable for scenarios with single disturbances and clear management needs.

[0092] The aforementioned multi-level adaptive power quality control method determines the disturbance condition type of the power grid based on the grid's target indicator data. According to the disturbance condition type, a first control strategy is selected from the control strategy template. Based on the target indicator data and the disturbance condition type, the strategy parameters of the first control strategy are updated to obtain a second control strategy. Power quality management is then performed on the power grid according to the second control strategy. By accurately determining the disturbance condition type based on the target indicator data, selecting a suitable control strategy template, and dynamically updating and optimizing the strategy parameters based on the target indicator data and the condition type, power quality management is carried out. This achieves precise matching between the control strategy and the actual operating state of the power grid, making power quality management more targeted and adaptable, effectively improving the efficiency and effectiveness of power grid power quality management. Furthermore, relying on data-driven strategy selection and parameter optimization reduces the blindness of management and ensures the scientific nature and effectiveness of power grid power quality management.

[0093] In one embodiment, to more accurately determine the type of disturbance condition, such as Figure 3 As shown, based on the target index data of the power grid, the optional implementation methods for determining the disturbance condition type of the power grid include:

[0094] S301, extract features from the target index data of the power grid to obtain disturbance index data.

[0095] One possible implementation is to convert the time-domain time-series data of the power grid target indicators into frequency-domain data through Fourier transform, extract feature values ​​that can characterize disturbances in the frequency dimension as disturbance indicator data, and calculate the amplitude, phase, total harmonic distortion rate, and fundamental component ratio of each harmonic to accurately capture frequency-domain disturbance features such as power grid harmonic pollution.

[0096] Another optional implementation method is to set normal threshold ranges for various target indicators based on power grid power quality standards and actual operating requirements, perform threshold screening on the target indicator data, and extract data such as deviation values, duration of exceeding the standard, and peak value of exceeding the standard as disturbance indicator data. Normal data without disturbance is directly eliminated, and only the core abnormal data that can characterize power grid disturbances are retained, simplifying the dimensions of disturbance indicators and improving the efficiency of subsequent operating condition judgment.

[0097] Another optional implementation involves preprocessing the target indicator data of the power grid by denoising, smoothing, and data completion to eliminate measurement noise and data gaps. Then, basic features are extracted using time-domain, frequency-domain, or statistical feature extraction methods to obtain the first indicator data. The first indicator data is then weighted and enhanced, with higher weights assigned to features strongly correlated with power grid disturbances to amplify the representational role of core disturbance features, resulting in the second indicator data. The second indicator data with feature values ​​greater than a preset threshold is used as the disturbance indicator data.

[0098] S302, Determine the type of disturbance condition of the power grid based on the disturbance index data.

[0099] One possible implementation is to pre-set normal and disturbance classification thresholds and operating condition judgment rules for each disturbance indicator based on the power grid power quality standards. Real-time disturbance indicator data are compared with the thresholds one by one. Based on the type, quantity and degree of exceeding the standard of the indicators, the single or compound disturbance operating condition of the power grid is directly classified and determined. The correspondence between indicators and operating conditions is clear and the judgment logic is simple and direct.

[0100] Another alternative implementation involves pre-constructing standardized feature vectors containing disturbance index features for various typical disturbance conditions, constructing real-time feature vectors from the disturbance index data extracted in real time, and selecting the typical disturbance condition with the highest similarity as the current disturbance condition type of the power grid by calculating quantitative indicators such as the cosine similarity and Euclidean distance between the real-time feature vector and the standardized feature vectors corresponding to each typical disturbance condition, thus adapting to the determination of disturbance index data with clear feature dimensions.

[0101] In this embodiment, precise disturbance index data is obtained by extracting features from the target index data of the power grid. Then, the type of power grid disturbance condition is determined based on the disturbance index data. This achieves precise extraction from the original power grid quality data to the core disturbance features, eliminating invalid data interference and providing a more accurate and reliable core basis for determining the type of disturbance condition. This effectively improves the accuracy and pertinence of power grid disturbance condition identification, laying a solid data and judgment foundation for subsequent selection of appropriate control strategies and efficient power quality management. At the same time, it simplifies the data analysis dimensions for condition determination and improves the efficiency and real-time performance of condition identification.

[0102] In one embodiment, after power quality management of the power grid according to the second control strategy, in order to further improve the governance effect of power quality management, such as... Figure 4 As shown, an optional implementation of a multi-level adaptive power quality control method includes:

[0103] S401, obtain the quality management effectiveness indicators of the power grid.

[0104] Optionally, in this embodiment, the quality management performance indicators include at least one of the following: current total harmonic distortion, voltage deviation, frequency fluctuation amplitude, distortion rate benchmark value, voltage deviation benchmark value, and maximum fluctuation amplitude.

[0105] S402, Determine the comprehensive management effectiveness score based on the quality management effectiveness indicators.

[0106] One possible implementation method is to preset a corresponding weight coefficient for each quality management effectiveness indicator based on its importance to the power grid's power quality. First, the actual monitoring values ​​of each indicator are normalized to eliminate the impact of differences in dimensions. Then, the normalized indicator values ​​are multiplied by the corresponding weight coefficients. Finally, all product results are summed, and the sum is the comprehensive management effectiveness score of the power grid's power quality. The weight coefficients can be dynamically adjusted according to the power grid's operating scenarios and governance priorities.

[0107] Another alternative implementation method is to divide each quality management effectiveness indicator into multiple level ranges and set a corresponding fixed score for each level range. First, match the actual value of each indicator to the corresponding level range and obtain the score. Then, integrate the individual scores of all indicators by simple summation or average calculation to obtain the comprehensive management effectiveness score. The division of indicator level ranges can be based on national power quality standards or grid-defined governance targets.

[0108] Another optional implementation involves determining a first ratio of the current total harmonic distortion to a baseline distortion value. A second ratio of the voltage deviation to a baseline voltage deviation value is also determined. A third ratio of the frequency fluctuation amplitude to the maximum fluctuation amplitude is then determined. The first, second, and third ratios are weighted and summed to obtain a comprehensive management effectiveness score. In this embodiment, the comprehensive management effectiveness score can be determined according to the following formula:

[0109]

[0110] Where THD is the current total harmonic distortion. For voltage deviation, F var The frequency fluctuation amplitude is THD0, the distortion rate reference value is U0, the voltage deviation reference value is F. max For the maximum fluctuation range, w1, w2, and w3 are adjustable weights.

[0111] S403. Based on the comprehensive management effectiveness score, the second control strategy is updated to obtain the third control strategy.

[0112] One possible implementation is to divide the comprehensive management effect score into different level threshold ranges, preset the second control strategy parameter adjustment rules corresponding to each range, clarify the parameter adjustment direction, magnitude and object corresponding to the range in which the score is located, and after obtaining the comprehensive score, match the adjustment rules of the threshold range to which it belongs, and quantitatively correct the parameters of the second control strategy according to the rules. After correction, a third control strategy is obtained. The lower the score, the larger the parameter adjustment magnitude can be, so as to realize the linkage optimization of strategy and governance effect.

[0113] Another optional implementation involves determining the residual energy value based on the comprehensive management effectiveness score and the model prediction value. The strategy update status is then determined based on the residual energy value and the energy threshold. If the strategy update status is "updated," the second control strategy is updated based on the comprehensive management effectiveness score to obtain the third control strategy. Here, the model prediction value refers to the predicted effectiveness score obtained by the preset energy management effectiveness evaluation model based on the second control strategy; for example, the model prediction value output by the energy management effectiveness evaluation model after inputting the second control strategy. In this embodiment, the strategy update status can be determined based on the following formula, the residual energy value, and the energy threshold:

[0114]

[0115] Where E(t) represents the comprehensive index of governance status at time t. t0 represents the model's predicted value, t0 represents the start time of the response curve, and t1 represents the current time.

[0116] In this embodiment, an optional implementation method for determining the strategy update based on residual energy value and energy threshold is as follows: The energy threshold is an energy threshold range. When the residual energy value is within the energy threshold range and greater than a preset value, the strategy parameters of the second control strategy are characterized to obtain the third control strategy. When the residual energy value exceeds the energy threshold range, associated control strategies of the second control strategy are determined (e.g., all other control strategies in the control strategy template besides the second control strategy are considered as associated control strategies), wherein the number of associated control strategies is at least two. For each associated control strategy, the residual energy and mean residual energy during the execution process, as well as the average score and maximum comprehensive management effect score of the associated control strategy within a preset historical period, are obtained. Based on the residual energy, mean residual energy, average comprehensive management effect score, and maximum comprehensive management effect score, the optimization gain index of the associated control strategy is determined. Based on the optimization gain index of each associated control strategy, a target control strategy is selected from the associated control strategies. The target control strategy is used as the third control strategy. In this embodiment, an optional implementation method for determining the optimization gain index of the correlation control strategy based on residual energy, mean residual energy, average score of comprehensive management effect, and maximum comprehensive management effect score is as follows: The optimization gain index of the correlation control strategy is determined by combining the following formula:

[0117]

[0118] Among them, R k R represents the residual energy when using the k-th control strategy. avg P is the mean residual energy. k Let P be the average score of the overall management effectiveness of the k-th control strategy in history. max The score is given to the overall management effectiveness of the strategy in history. For residual weights, Historical weighting.

[0119] In this embodiment, an optional implementation method for selecting the target control strategy from the associated control strategies based on the optimization gain index of each associated control strategy is to take the associated control strategy pointed to by the maximum optimization gain index as the target control strategy.

[0120] S404, based on the third control strategy, performs power quality management of the power grid.

[0121] In this embodiment, by acquiring power grid quality management effectiveness indicators and calculating a comprehensive management effectiveness score, the second control strategy is iteratively updated to obtain a third control strategy, and power quality management is carried out. This constructs a closed-loop control system of "governance-evaluation-optimization-re-governance," providing precise quantitative evaluation criteria for the optimization and adjustment of control strategies, effectively solving the problem of poor governance results caused by strategy fixation. Simultaneously, the comprehensive scoring enables a complete assessment of the power quality management effectiveness, specifically addressing the governance shortcomings of the second control strategy, continuously optimizing strategy parameters and control logic, improving the accuracy and adaptability of power quality governance, and ensuring that the power grid's power quality management effectiveness continuously improves with strategy iteration, adapting to the complex and ever-changing operating conditions of the power grid, and guaranteeing the continuity and effectiveness of governance.

[0122] In one embodiment, such as Figure 5 As shown, one possible implementation of the multi-level adaptive power quality control method is as follows:

[0123] S501 extracts features from the target index data of the power grid to obtain disturbance index data.

[0124] S502, based on disturbance index data, determine the type of disturbance condition of the power grid.

[0125] S503: Select the first control strategy from the control strategy template according to the disturbance condition type.

[0126] S504, based on the target index data and the type of disturbance condition, update the strategy parameters of the first control strategy to obtain the second control strategy.

[0127] S505 manages power quality for the power grid according to the second control strategy.

[0128] S506, Obtain the quality management effectiveness indicators of the power grid.

[0129] S507, determine the first ratio of the current total harmonic distortion to the baseline distortion value.

[0130] S508, determine the second ratio of the voltage deviation to the voltage deviation reference value.

[0131] S509, determine the third ratio of frequency fluctuation amplitude to maximum fluctuation amplitude.

[0132] S510 calculates a weighted sum of the first, second, and third ratios to obtain a comprehensive management effectiveness score.

[0133] S511, determine the residual energy value based on the comprehensive management effectiveness score and the model prediction value.

[0134] S512 determines the policy update status based on the residual energy value and energy threshold.

[0135] S513, when the strategy update status is updated, for each associated control strategy, obtain the residual energy and mean residual energy of the associated control strategy during the execution process, as well as the average score and maximum comprehensive management effect score of the associated control strategy within a preset historical period.

[0136] S514, determine the fourth ratio of residual energy to mean residual energy.

[0137] S515, determine the difference between the preset value and the fourth ratio.

[0138] S516, determine the fifth ratio between the average score of comprehensive management effectiveness and the maximum score of comprehensive management effectiveness.

[0139] S517, based on the difference and the fifth ratio, determine the optimization gain index of the associated control strategy.

[0140] S518, Select the target control strategy from the associated control strategies based on the optimization gain index of each associated control strategy.

[0141] S519 adopts the target control strategy as the third control strategy.

[0142] S520 manages power quality for the power grid according to the third control strategy.

[0143] This application determines the disturbance condition type of the power grid based on target indicator data. A first control strategy is selected from the control strategy template based on the disturbance condition type. The strategy parameters of the first control strategy are updated based on the target indicator data and the disturbance condition type to obtain a second control strategy. Power quality management is then performed on the power grid according to the second control strategy. By accurately determining the disturbance condition type based on target indicator data, selecting a suitable control strategy template, and dynamically updating and optimizing the strategy parameters based on the target indicator data and the condition type, power quality management is carried out. This achieves precise matching between the control strategy and the actual operating state of the power grid, making power quality management more targeted and adaptable, effectively improving the efficiency and effectiveness of power grid power quality management. Furthermore, relying on data-driven strategy selection and parameter optimization reduces the blindness of management and ensures the scientific nature and effectiveness of power grid power quality management.

[0144] It should be understood that although the steps in the flowcharts of the embodiments described above 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 embodiments described above 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 of other steps.

[0145] Based on the same inventive concept, this application also provides a power quality multi-level adaptive control device for implementing the aforementioned power quality multi-level adaptive control method. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more power quality multi-level adaptive control device embodiments provided below can be found in the limitations of the power quality multi-level adaptive control method described above, and will not be repeated here.

[0146] In one embodiment, such as Figure 7 As shown, a multi-level adaptive power quality control device 1 is provided, comprising: a first determining module 10, a selecting module 20, a first updating module 30, and a first management module 40, wherein:

[0147] The first determining module 10 is used to determine the type of disturbance condition of the power grid based on the target index data of the power grid.

[0148] Select module 20 to select the first control strategy from the control strategy template according to the type of disturbance condition;

[0149] The first update module 30 is used to update the strategy parameters of the first control strategy according to the target index data and the disturbance condition type to obtain the second control strategy.

[0150] The first management module 40 is used to manage the power quality of the power grid according to the second control strategy.

[0151] In one embodiment, the first determining module is further specifically used for:

[0152] Feature extraction is performed on the target index data of the power grid to obtain disturbance index data;

[0153] Based on the disturbance index data, determine the type of disturbance condition of the power grid.

[0154] In one embodiment, a power quality multi-level adaptive control device 1 further includes:

[0155] The acquisition module is used to acquire power grid quality management effectiveness indicators.

[0156] The second determination module is used to determine the comprehensive management effectiveness score based on the quality management effectiveness indicators;

[0157] The second update module is used to update the second control strategy based on the comprehensive management effectiveness score, so as to obtain the third control strategy;

[0158] The second management module is used to manage the power quality of the power grid according to the third control strategy.

[0159] In one embodiment, the quality management performance indicators include at least one of the following: current total harmonic distortion, voltage deviation, frequency fluctuation amplitude, distortion rate benchmark, voltage deviation benchmark, and maximum fluctuation amplitude.

[0160] The second determining module is also specifically used for:

[0161] Determine the first ratio of the current total harmonic distortion to the baseline distortion value;

[0162] Determine a second ratio between the voltage deviation and the voltage deviation reference value;

[0163] Determine the third ratio of the frequency fluctuation amplitude to the maximum fluctuation amplitude;

[0164] The first ratio, the second ratio, and the third ratio are weighted and summed to obtain the overall management effectiveness score.

[0165] In one embodiment, the second update module is further specifically used for:

[0166] The residual energy value is determined based on the comprehensive management effectiveness score and the model prediction value;

[0167] The strategy update status is determined based on the residual energy value and the energy threshold;

[0168] If the strategy update status is "updated", the second control strategy is updated based on the comprehensive management effectiveness score to obtain the third control strategy.

[0169] In one embodiment, the second control strategy includes at least two associated control strategies;

[0170] The second update module is also specifically used for:

[0171] For each associated control strategy, obtain the residual energy and mean residual energy of the associated control strategy during the execution process, as well as the average score and maximum comprehensive management effect score of the associated control strategy within a preset historical period.

[0172] The optimization gain index of the correlation control strategy is determined based on the residual energy, mean residual energy, average score of comprehensive management effect, and maximum comprehensive management effect score.

[0173] Based on the optimization gain index of each associated control strategy, the target control strategy is selected from the associated control strategies;

[0174] The target control strategy is used as the third control strategy.

[0175] In one embodiment, the second update module is further specifically used for:

[0176] Determine the fourth ratio of the residual energy to the mean residual energy;

[0177] Determine the difference between the preset value and the fourth ratio;

[0178] Determine the fifth ratio between the average score of comprehensive management effectiveness and the highest score of comprehensive management effectiveness;

[0179] Based on the difference and the fifth ratio, the optimal gain index of the associated control strategy is determined.

[0180] Each module in the aforementioned multi-level adaptive power quality control device 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 computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0181] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7As 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 is used for power quality management-related data. The I / O interfaces are used for exchanging information 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 multi-level adaptive power quality control method.

[0182] Those skilled in the art will understand that Figure 7 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.

[0183] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0184] Based on the target index data of the power grid, determine the type of disturbance condition of the power grid;

[0185] Select the first control strategy from the control strategy template based on the type of disturbance condition.

[0186] Based on the target index data and the type of disturbance condition, the strategy parameters of the first control strategy are updated to obtain the second control strategy.

[0187] According to the second control strategy, power quality management is carried out on the power grid.

[0188] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the type of disturbance condition of the power grid based on the target index data of the power grid, including:

[0189] Feature extraction is performed on the target index data of the power grid to obtain disturbance index data;

[0190] Based on the disturbance index data, determine the type of disturbance condition of the power grid.

[0191] In one embodiment, the processor, when executing the computer program, further implements the following steps: after performing power quality management on the power grid according to a second control strategy, the method further includes:

[0192] Obtain power grid quality management effectiveness indicators;

[0193] Determine the overall management effectiveness score based on the quality management effectiveness indicators;

[0194] Based on the comprehensive management effectiveness score, the second control strategy is updated to obtain the third control strategy;

[0195] Power quality management of the power grid is carried out according to the third control strategy.

[0196] In one embodiment, when the processor executes the computer program, it further performs the following steps: the quality management performance indicators include at least one of the following: current total harmonic distortion, voltage deviation, frequency fluctuation amplitude, distortion rate reference value, voltage deviation reference value, and maximum fluctuation amplitude;

[0197] Based on the quality management effectiveness indicators, a comprehensive management effectiveness score is determined, including:

[0198] Determine the first ratio of the current total harmonic distortion to the baseline distortion value;

[0199] Determine a second ratio between the voltage deviation and the voltage deviation reference value;

[0200] Determine the third ratio of the frequency fluctuation amplitude to the maximum fluctuation amplitude;

[0201] The first ratio, the second ratio, and the third ratio are weighted and summed to obtain the overall management effectiveness score.

[0202] In one embodiment, when the processor executes the computer program, it further performs the following steps: updating the second control strategy based on the comprehensive management effectiveness score to obtain a third control strategy, including:

[0203] The residual energy value is determined based on the comprehensive management effectiveness score and the model prediction value;

[0204] The strategy update status is determined based on the residual energy value and the energy threshold;

[0205] If the strategy update status is "updated", the second control strategy is updated based on the comprehensive management effectiveness score to obtain the third control strategy.

[0206] In one embodiment, when the processor executes a computer program, it further implements the following steps: the second control policy includes at least two associated control policies;

[0207] Based on the comprehensive management effectiveness score, the second control strategy is updated to obtain the third control strategy, which includes:

[0208] For each associated control strategy, obtain the residual energy and mean residual energy of the associated control strategy during the execution process, as well as the average score and maximum comprehensive management effect score of the associated control strategy within a preset historical period.

[0209] The optimization gain index of the correlation control strategy is determined based on the residual energy, mean residual energy, average score of comprehensive management effect, and maximum comprehensive management effect score.

[0210] Based on the optimization gain index of each associated control strategy, the target control strategy is selected from the associated control strategies;

[0211] The target control strategy is used as the third control strategy.

[0212] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the optimization gain index of the correlation control strategy based on the residual energy, mean residual energy, average score of comprehensive management effect, and maximum comprehensive management effect score, including:

[0213] Determine the fourth ratio of the residual energy to the mean residual energy;

[0214] Determine the difference between the preset value and the fourth ratio;

[0215] Determine the fifth ratio between the average score of comprehensive management effectiveness and the highest score of comprehensive management effectiveness;

[0216] Based on the difference and the fifth ratio, the optimal gain index of the associated control strategy is determined.

[0217] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0218] Based on the target index data of the power grid, determine the type of disturbance condition of the power grid;

[0219] Select the first control strategy from the control strategy template based on the type of disturbance condition.

[0220] Based on the target index data and the type of disturbance condition, the strategy parameters of the first control strategy are updated to obtain the second control strategy.

[0221] According to the second control strategy, power quality management is carried out on the power grid.

[0222] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the type of disturbance condition of the power grid based on the target index data of the power grid, including:

[0223] Feature extraction is performed on the target index data of the power grid to obtain disturbance index data;

[0224] Based on the disturbance index data, determine the type of disturbance condition of the power grid.

[0225] In one embodiment, when the computer program is executed by a processor, it further implements the following steps: after performing power quality management on the power grid according to a second control strategy, the method further includes:

[0226] Obtain power grid quality management effectiveness indicators;

[0227] Determine the overall management effectiveness score based on the quality management effectiveness indicators;

[0228] Based on the comprehensive management effectiveness score, the second control strategy is updated to obtain the third control strategy;

[0229] Power quality management of the power grid is carried out according to the third control strategy.

[0230] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: the quality management performance indicators include at least one of the following: current total harmonic distortion, voltage deviation, frequency fluctuation amplitude, distortion rate reference value, voltage deviation reference value, and maximum fluctuation amplitude;

[0231] Based on the quality management effectiveness indicators, a comprehensive management effectiveness score is determined, including:

[0232] Determine the first ratio of the current total harmonic distortion to the baseline distortion value;

[0233] Determine a second ratio between the voltage deviation and the voltage deviation reference value;

[0234] Determine the third ratio of the frequency fluctuation amplitude to the maximum fluctuation amplitude;

[0235] The first ratio, the second ratio, and the third ratio are weighted and summed to obtain the overall management effectiveness score.

[0236] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: updating the second control strategy based on the comprehensive management effectiveness score to obtain a third control strategy, including:

[0237] The residual energy value is determined based on the comprehensive management effectiveness score and the model prediction value;

[0238] The strategy update status is determined based on the residual energy value and the energy threshold;

[0239] If the strategy update status is "updated", the second control strategy is updated based on the comprehensive management effectiveness score to obtain the third control strategy.

[0240] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: the second control strategy includes at least two associated control strategies;

[0241] Based on the comprehensive management effectiveness score, the second control strategy is updated to obtain the third control strategy, which includes:

[0242] For each associated control strategy, obtain the residual energy and mean residual energy of the associated control strategy during the execution process, as well as the average score and maximum comprehensive management effect score of the associated control strategy within a preset historical period.

[0243] The optimization gain index of the correlation control strategy is determined based on the residual energy, mean residual energy, average score of comprehensive management effect, and maximum comprehensive management effect score.

[0244] Based on the optimization gain index of each associated control strategy, the target control strategy is selected from the associated control strategies;

[0245] The target control strategy is used as the third control strategy.

[0246] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the optimization gain index of the correlation control strategy based on the residual energy, mean residual energy, average score of comprehensive management effect, and maximum comprehensive management effect score, including:

[0247] Determine the fourth ratio of the residual energy to the mean residual energy;

[0248] Determine the difference between the preset value and the fourth ratio;

[0249] Determine the fifth ratio between the average score of comprehensive management effectiveness and the highest score of comprehensive management effectiveness;

[0250] Based on the difference and the fifth ratio, the optimal gain index of the associated control strategy is determined.

[0251] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0252] Based on the target index data of the power grid, determine the type of disturbance condition of the power grid;

[0253] Select the first control strategy from the control strategy template based on the type of disturbance condition.

[0254] Based on the target index data and the type of disturbance condition, the strategy parameters of the first control strategy are updated to obtain the second control strategy.

[0255] According to the second control strategy, power quality management is carried out on the power grid.

[0256] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the type of disturbance condition of the power grid based on the target index data of the power grid, including:

[0257] Feature extraction is performed on the target index data of the power grid to obtain disturbance index data;

[0258] Based on the disturbance index data, determine the type of disturbance condition of the power grid.

[0259] In one embodiment, when the computer program is executed by a processor, it further implements the following steps: after performing power quality management on the power grid according to a second control strategy, the method further includes:

[0260] Obtain power grid quality management effectiveness indicators;

[0261] Determine the overall management effectiveness score based on the quality management effectiveness indicators;

[0262] Based on the comprehensive management effectiveness score, the second control strategy is updated to obtain the third control strategy;

[0263] Power quality management of the power grid is carried out according to the third control strategy.

[0264] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: the quality management performance indicators include at least one of the following: current total harmonic distortion, voltage deviation, frequency fluctuation amplitude, distortion rate reference value, voltage deviation reference value, and maximum fluctuation amplitude;

[0265] Based on the quality management effectiveness indicators, a comprehensive management effectiveness score is determined, including:

[0266] Determine the first ratio of the current total harmonic distortion to the baseline distortion value;

[0267] Determine a second ratio between the voltage deviation and the voltage deviation reference value;

[0268] Determine the third ratio of the frequency fluctuation amplitude to the maximum fluctuation amplitude;

[0269] The first ratio, the second ratio, and the third ratio are weighted and summed to obtain the overall management effectiveness score.

[0270] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: updating the second control strategy based on the comprehensive management effectiveness score to obtain a third control strategy, including:

[0271] The residual energy value is determined based on the comprehensive management effectiveness score and the model prediction value;

[0272] The strategy update status is determined based on the residual energy value and the energy threshold;

[0273] If the strategy update status is "updated", the second control strategy is updated based on the comprehensive management effectiveness score to obtain the third control strategy.

[0274] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: the second control strategy includes at least two associated control strategies;

[0275] Based on the comprehensive management effectiveness score, the second control strategy is updated to obtain the third control strategy, which includes:

[0276] For each associated control strategy, obtain the residual energy and mean residual energy of the associated control strategy during the execution process, as well as the average score and maximum comprehensive management effect score of the associated control strategy within a preset historical period.

[0277] The optimization gain index of the correlation control strategy is determined based on the residual energy, mean residual energy, average score of comprehensive management effect, and maximum comprehensive management effect score.

[0278] Based on the optimization gain index of each associated control strategy, the target control strategy is selected from the associated control strategies;

[0279] The target control strategy is used as the third control strategy.

[0280] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the optimization gain index of the correlation control strategy based on the residual energy, mean residual energy, average score of comprehensive management effect, and maximum comprehensive management effect score, including:

[0281] Determine the fourth ratio of the residual energy to the mean residual energy;

[0282] Determine the difference between the preset value and the fourth ratio;

[0283] Determine the fifth ratio between the average score of comprehensive management effectiveness and the highest score of comprehensive management effectiveness;

[0284] Based on the difference and the fifth ratio, the optimal gain index of the associated control strategy is determined.

[0285] Those skilled in the art will understand that all or part of the processes in 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. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile 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, distributed databases based on blockchain. 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, data processing logic devices based on quantum computing, etc., and are not limited to these.

[0286] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0287] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements 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 multi-level adaptive control method for power quality, characterized in that, The method includes: Based on the target index data of the power grid, determine the disturbance condition type of the power grid; Based on the disturbance condition type, select the first control strategy from the control strategy template; Based on the target index data and the disturbance condition type, the strategy parameters of the first control strategy are updated to obtain the second control strategy. According to the second control strategy, power quality management is performed on the power grid.

2. The method according to claim 1, characterized in that, The step of determining the disturbance condition type of the power grid based on the target index data of the power grid includes: Feature extraction is performed on the target index data of the power grid to obtain disturbance index data; Based on the disturbance index data, the disturbance condition type of the power grid is determined.

3. The method according to claim 1, characterized in that, After performing power quality management on the power grid according to the second control strategy, the method further includes: Obtain the quality management effectiveness indicators of the power grid; Based on the aforementioned quality management effectiveness indicators, a comprehensive management effectiveness score is determined; Based on the comprehensive management effectiveness score, the second control strategy is updated to obtain the third control strategy; According to the third control strategy, power quality management is performed on the power grid.

4. The method according to claim 3, characterized in that, The quality management effectiveness indicators include at least one of the following: current total harmonic distortion, voltage deviation, frequency fluctuation amplitude, distortion rate benchmark value, voltage deviation benchmark value, and maximum fluctuation amplitude. Based on the aforementioned quality management effectiveness indicators, a comprehensive management effectiveness score is determined, including: Determine a first ratio between the current total harmonic distortion and the baseline distortion value; Determine a second ratio between the voltage deviation and the voltage deviation reference value; Determine a third ratio between the frequency fluctuation amplitude and the maximum fluctuation amplitude; The first ratio, the second ratio, and the third ratio are weighted and summed to obtain the comprehensive management effectiveness score.

5. The method according to claim 3, characterized in that, The third control strategy is obtained by updating the second control strategy based on the comprehensive management effectiveness score, including: The residual energy value is determined based on the comprehensive management effectiveness score and the model prediction value. The strategy update status is determined based on the residual energy value and the energy threshold. If the strategy update status is "updated", the second control strategy is updated based on the comprehensive management effect score to obtain the third control strategy.

6. The method according to claim 5, characterized in that, The second control strategy includes at least two associated control strategies; The third control strategy is obtained by updating the second control strategy based on the comprehensive management effectiveness score, including: For each associated control strategy, obtain the residual energy and mean residual energy of the associated control strategy during the execution process, as well as the average score and maximum comprehensive management effect score of the associated control strategy within a preset historical period. The optimization gain index of the correlation control strategy is determined based on the residual energy, mean residual energy, average score of comprehensive management effect, and maximum comprehensive management effect score. Based on the optimization gain index of each of the associated control strategies, a target control strategy is selected from each of the associated control strategies; The target control strategy is used as the third control strategy.

7. The method according to claim 6, characterized in that, The step of determining the optimization gain index of the correlation control strategy based on the residual energy, mean residual energy, average score of comprehensive management effect, and maximum comprehensive management effect score includes: Determine a fourth ratio between the residual energy and the mean residual energy; Determine the difference between the preset value and the fourth ratio; Determine the fifth ratio between the average score of the overall management effectiveness and the maximum score of the overall management effectiveness; The optimization gain index of the correlation control strategy is determined based on the difference and the fifth ratio.

8. A multi-level adaptive power quality control device, characterized in that, The device includes: The first determining module is used to determine the disturbance condition type of the power grid based on the target index data of the power grid. The selection module is used to select a first control strategy from the control strategy template according to the type of disturbance condition; The first update module is used to update the strategy parameters of the first control strategy according to the target index data and the disturbance condition type to obtain the second control strategy. The first management module is used to manage the power quality of the power grid according to the second control strategy.

9. 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 power quality multi-level adaptive control method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the power quality multi-level adaptive control method according to any one of claims 1 to 7.

Images