Power distribution network dynamic voltage regulation and power optimization system based on wind power photovoltaic access

Abstract

The invention discloses a power distribution network dynamic voltage regulation and power optimization system based on wind power photovoltaic access, and relates to the field of power distribution network control, and the system comprises a sensing module which is used for sensing multi-source heterogeneous signals of wind power photovoltaic output, power distribution network node voltage and load power in real time; the fusion module is used for receiving the operation sensing signals of the sensing module and carrying out space-time dimension fusion processing on the signals so as to extract coupling characteristics of wind power photovoltaic output volatility, load change trend and voltage deviation and generate a standardized fusion data set; according to the invention, by capturing and optimizing wind power photovoltaic output, voltage and load related signals in real time, multi-factor coupling characteristics are mined accurately, the voltage offset risk and the voltage regulation demand are effectively pre-judged, and new energy consumption maximization, power distribution equalization and regulation and control cost minimization are realized through collaborative optimization.

Description

Technical Field

[0001] This invention relates to the field of power distribution network control technology, specifically to a dynamic voltage regulation and power optimization system for power distribution networks based on wind and solar power integration. Background Technology

[0002] The intelligent control of the distribution network collects real-time operating data from sensors and transmits it to the control platform through the communication network. It combines machine learning and optimization algorithms to analyze load changes and the output characteristics of distributed power sources, and dynamically generates voltage regulation, reactive power compensation, and fault isolation strategies to achieve precise control of distributed energy consumption, power supply reliability improvement, and network loss optimization.

[0003] The invention patent application with application number 202510642735.2 discloses a method for coordinating and optimizing the ratio of wind power, photovoltaic and energy storage. The application aims to solve the problem that "with the acceleration of global energy transition, wind power and photovoltaic, as core renewable energy sources, have a continuously increasing installed capacity share. However, both are affected by natural conditions such as wind speed and light intensity, resulting in significant intermittency and volatility, which exacerbates the difficulty of power grid power balance regulation".

[0004] However, for wind and solar power distribution networks, the output stability of wind and solar power is slightly worse than that of thermal power and nuclear power, which leads to the need for more intelligent dynamic voltage regulation and power optimization management.

[0005] Therefore, a dynamic voltage regulation and power optimization system for distribution networks based on wind and solar power integration is proposed. Summary of the Invention

[0006] In view of the above-mentioned shortcomings of the existing technology, the present invention provides a dynamic voltage regulation and power optimization system for distribution networks based on wind power and photovoltaic access, which can effectively solve the problems of the existing technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions; This invention discloses a dynamic voltage regulation and power optimization system for distribution networks based on wind and solar power integration, comprising: The system comprises the following modules: a sensing module for real-time sensing of multi-source heterogeneous signals from wind and solar power output, distribution network node voltage, and load power; a fusion module for receiving signals from the sensing module, performing spatiotemporal fusion processing to extract the coupling characteristics of wind and solar power output volatility, load change trends, and voltage deviation, and generating a standardized fusion dataset; a prediction module for receiving the standardized fusion dataset from the fusion module, traversing it to predict voltage deviation risk and voltage regulation priority for target periods, and simultaneously outputting quantified voltage regulation targets; an optimization module for receiving the voltage regulation targets and prediction results of voltage deviation risk and voltage regulation priority for target periods from the prediction module, constructing a multi-objective optimization model for coordinated wind and solar power consumption and power allocation, and dynamically generating energy storage scheduling and power optimization strategies; an adaptation module for receiving the energy storage scheduling and power optimization strategies output by the optimization module, adapting them to the distribution network voltage regulation equipment interface protocol, and converting the strategies into a voltage regulation control command set; and a triggering module for monitoring the operating status within a preset time interval after the distribution network voltage regulation control command set is executed, generating quantified evaluation results, and deciding whether to refresh the system or trigger the module to run again based on the evaluation results. The sensing module is interconnected with a fusion module via a wireless network. The fusion module is interconnected with a prediction module via a wireless network. The prediction module is interconnected with an optimization module via a wireless network. The optimization module is interconnected with an adaptation module via a wireless network. The adaptation module is interconnected with a triggering module via a wireless network.

[0008] Furthermore, during the operation of the sensing module, preprocessing operations are simultaneously performed on the multi-source heterogeneous signals: Synchronization alignment is performed on the timestamps of each signal, with the alignment reference being the unified clock signal of the distribution network. Adaptive noise suppression processing is then performed on the synchronized signals. ; In the formula: The value of the i-th type of signal after preprocessing at time t; Let be the original sampled value of the i-th type of signal at time t; Let be the filtering factor for the i-th type of signal at time t; Let be the mean value of the i-th type of signal over a preset historical period; The sensitivity coefficient for signal fluctuations; This is the baseline coefficient for filter strength; The preprocessed signals are then forwarded synchronously to the fusion module.

[0009] Furthermore, the spatiotemporal dimensional fusion processing performed by the fusion module includes: Time dimension fusion: ; In the formula: These are the fluctuation characteristics of wind and solar power output and the load change trend, respectively. The length of the sliding window for time-dimension fusion; Let K be the wind and solar power output at time k. Similarly; The average output of wind and solar power within the preset time period; t is the time marker of the current sampling moment; Spatial Dimension Fusion: ; In the formula: The spatial correlation quantity of the voltage deviation at the j-th node; Let be the voltage value of node j at time t; Let be the rated voltage of the j-th node; Let be the standard deviation of the voltage at node j within a preset historical time period; Let be the voltage sensitivity weight of the j-th node; Then take the time dimension Spatial dimension The standardized fusion dataset is generated by splicing the data according to preset dimensions.

[0010] Furthermore, the prediction module performs a voltage offset risk prediction phase, constructing a voltage offset risk index for the target time period: ; In the formula: The voltage offset risk index is represented by T, which is the duration of the target period. Risk weights for voltage deviation, wind power output fluctuation, and load change trends; It is the set of all nodes in the distribution network; The feature inference model built into the prediction module takes the spatiotemporal coupling feature matrix as input and predicts the voltage value of the j-th node at time t+T by analyzing the temporal evolution of the power output fluctuation, load change trend and node voltage spatial correlation of wind power and photovoltaic power. Let be the rated voltage of the j-th node; This refers to the fluctuation characteristics of wind and solar power output within the predicted target time period; This represents the average value of the fluctuating characteristics of wind power output within a preset time period. This refers to the predicted load change trend within the target time period; The average value of the load change trend within a preset time period; The voltage regulation priority is based on The size is sorted, and the synchronous output quantization voltage regulation target is; ; In the formula: The target voltage for voltage regulation at node j within the target time period; This is the voltage regulation amplitude coefficient; This is a sign function; it outputs 1 when the parameter is positive and -1 when the parameter is negative.

[0011] Furthermore, the optimization module constructs a multi-objective optimization model that coordinates wind power and solar power integration and power distribution, aiming to maximize the wind power and solar power integration capacity C, minimize the power distribution balance deviation D, and minimize voltage regulation and control costs. The objective function is: ; In the formula: The set of time periods for the target time period; , These represent the actual power absorbed by wind power and photovoltaic power at time t, respectively. This refers to the number of nodes in the distribution network. The power allocated to the j-th node at time t; Assign the average target power to all nodes at time t; This represents the unit cost coefficient for energy storage dispatch. , , respectively, represent the charging and discharging power of the stored energy at time t; This is the unit cost coefficient for voltage regulation; Let be the voltage after adjustment at time t of node j; Let be the predicted voltage at time t of node j.

[0012] Furthermore, when the adaptation module performs protocol conversion, it performs semantic parsing on the energy storage scheduling and power optimization strategies output by the optimization module, extracting the control object identifier, control value, control timing, control priority, and control activation conditions from the strategies. Then, based on the interface protocol library of the distribution network voltage regulation equipment, it maps the extracted core semantic fields to the corresponding device's protocol data units. During the mapping process, instruction compatibility verification is performed simultaneously. If the value of the instruction to be converted exceeds the control capability range of the corresponding device, the value is adjusted based on the preset capability compensation rule before generating the protocol data unit. Finally, the generated protocol data units are encapsulated according to the communication protocol format of the corresponding device to form the voltage regulation control instruction set and output to the corresponding voltage regulation device.

[0013] Furthermore, the quantitative evaluation result generated by the triggering module is a comprehensive index of the control effect: ; In the formula: The evaluation weights are assigned to voltage stability, absorption completion rate, and cost control rate. The preset evaluation time interval; The actual operating voltage of node j at time t; for; This refers to the allowable deviation range of the node voltage. This represents the actual amount of wind and solar power absorbed. The target amount of wastewater can be absorbed. Control costs to achieve the target; This refers to the actual cost of regulation.

[0014] Furthermore, the decision logic in the triggering module is as follows: If the comprehensive index of the regulation effect If the value exceeds the preset threshold, the control trigger module will run again to monitor the operating status of the power distribution network. like If the value is less than or equal to the preset threshold, the system refresh operation will be triggered.

[0015] Compared with the known prior art, the technical solution provided by this invention has the following beneficial effects: This invention provides a dynamic voltage regulation and power optimization system for distribution networks based on wind and solar power integration. During operation, the system captures and optimizes signals related to wind and solar power output, voltage, and load in real time, accurately identifies the coupling characteristics of multiple factors, effectively predicts voltage deviation risks and voltage regulation needs, and maximizes renewable energy consumption, balances power distribution, and minimizes regulation costs through collaborative optimization. It is compatible with various voltage regulation devices to ensure efficient execution of commands, dynamically evaluates and continuously optimizes regulation effects, and can flexibly cope with complex operating conditions such as signal fluctuations and electromagnetic interference. This effectively improves the voltage stability and power supply reliability of the distribution network, while taking into account both operational economy and renewable energy utilization efficiency. It can adapt to different load levels and renewable energy integration ratios, providing intelligent and reliable support for the operation of wind and solar power distribution networks. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0017] Figure 1 This is a schematic diagram of a dynamic voltage regulation and power optimization system for a distribution network based on wind and solar power integration. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0019] The present invention will be further described below with reference to embodiments.

[0020] Example: This embodiment presents a dynamic voltage regulation and power optimization system for a distribution network based on wind and solar power integration, such as... Figure 1 As shown, it includes: The sensing module is used to sense multi-source heterogeneous signals such as wind and solar power output, distribution network node voltage, and load power in real time. During the operation of the sensing module, preprocessing operations are performed synchronously on the multi-source heterogeneous signals: Synchronization alignment is performed on the timestamps of each signal, with the alignment reference being the unified clock signal of the distribution network. Adaptive noise suppression processing is then performed on the synchronized signals. ; In the formula: The value of the i-th type of signal after preprocessing at time t; Let be the original sampled value of the i-th type of signal at time t; Let be the filtering factor for the i-th type of signal at time t; Let be the mean value of the i-th type of signal over a preset historical period; The sensitivity coefficient for signal fluctuations; This is the baseline coefficient for filter strength; The above formula combines the characteristics of multi-source heterogeneous signals in the distribution network. It integrates the original sampled value of the i-th type signal at time t with the average value within a preset historical period in a specific ratio. The ratio is determined by the signal fluctuation sensitivity coefficient and the filter strength reference coefficient. The signal fluctuation sensitivity coefficient is dynamically adjusted according to the fluctuation frequency of wind power and photovoltaic output and load power. The filter strength reference coefficient is adapted to the electromagnetic interference intensity of the distribution network operating environment. At the same time, the timestamps of each signal are first synchronized and aligned with a unified clock signal, and then adaptive noise suppression is performed to ensure that the pre-processed signal retains the true and effective information while reducing the impact of noise and interference. The preprocessed signal is synchronously forwarded to the fusion module; in, The preset value range is [1, 5]. When the fluctuation frequency of wind power and photovoltaic output and load power is high, The larger the value, the smoother the signal fluctuation. The smaller the value; The preset value range is between [0.6, 0.9]. When the electromagnetic interference in the power distribution network operating environment is strong, The larger the value, the better when the operating environment has weak interference. The smaller the value; The fusion module is used to receive the sensing signals from the sensing module, perform spatiotemporal dimensional fusion processing on the signals to extract the coupling characteristics of wind power and solar power output fluctuations, load change trends and voltage deviations, and generate a standardized fusion dataset. When the fusion module performs spatiotemporal dimensional fusion processing, it includes: Time dimension fusion: ; In the formula: These are the fluctuation characteristics of wind and solar power output and the load change trend, respectively. The length of the sliding window for time-dimension fusion; Let K be the wind and solar power output at time k. Similarly; The average output of wind and solar power within the preset time period; t is the time marker of the current sampling moment; The above formula addresses the feature extraction requirements in the time dimension by setting the sliding window length and calculating the ratio of the sum of the absolute values ​​of the changes in wind and solar power output at adjacent moments within the window to the window length and the average output. This accurately characterizes the volatility of wind and solar power output. At the same time, it calculates the ratio of the sum of the changes in wind and solar power output at adjacent moments within the window to the window length, clearly presenting the load change trend. Both calculation methods are based on the dynamic changes of time series data and can effectively capture key features in the time dimension, providing reliable time dimension data support for subsequent spatiotemporal fusion. Spatial Dimension Fusion: ; In the formula: The spatial correlation quantity of the voltage deviation at the j-th node; Let be the voltage value of node j at time t; Let be the rated voltage of the j-th node; Let be the standard deviation of the voltage at node j within a preset historical time period; Let be the voltage sensitivity weight of the j-th node; The above formula takes into account the voltage characteristics of different nodes in the distribution network. It uses the rated voltage of the node as the benchmark and combines the voltage standard deviation of the node in the preset historical period to standardize the node voltage at time t. Then, it assigns corresponding voltage sensitivity weights according to the node load level and power supply hub attributes, so that the quantitative result of voltage deviation can reflect the importance of the node in the distribution network. This achieves a reasonable representation of voltage deviation characteristics in the spatial dimension, which is convenient for unified integration with the characteristics in the time dimension. Then take the time dimension Spatial dimension Consolidate the data according to preset dimensions to generate a standardized fusion dataset; in, ∈[0,1], the higher the load level of the node and the stronger its power supply hub attribute in the distribution network, the larger the value; the lower the load level of the node and the stronger its terminal branch attribute in the distribution network, the smaller the value. The prediction module receives the standardized fusion dataset output by the fusion module, iterates through the standardized fusion dataset to predict the voltage deviation risk and voltage regulation priority during the target period, and synchronously outputs the quantified voltage regulation target. The prediction module performs a voltage offset risk prediction phase, constructing a voltage offset risk index for the target time period: ; In the formula: The voltage offset risk index is represented by T, which is the duration of the target period. Risk weights for voltage deviation, wind power output fluctuation, and load change trends; It is the set of all nodes in the distribution network; The feature inference model built into the prediction module takes the spatiotemporal coupling feature matrix as input and predicts the voltage value of the j-th node at time t+T by analyzing the temporal evolution of the power output fluctuation, load change trend and node voltage spatial correlation of wind power and photovoltaic power. Let be the rated voltage of the j-th node; This refers to the fluctuation characteristics of wind and solar power output within the predicted target time period; This represents the average value of the fluctuating characteristics of wind power output within a preset time period. This refers to the predicted load change trend within the target time period; The average value of the load change trend within a preset time period; The above formula integrates three major influencing factors: node voltage deviation, wind and solar power output fluctuation, and load change trend. By assigning different risk weights to the three factors, it integrates the degree of deviation between the predicted node voltage and the rated voltage, the level of wind and solar power output fluctuation relative to the historical average during the target period, and the level of load change trend relative to the historical average during the target period. This comprehensively quantifies the voltage deviation risk during the target period and ensures that the risk assessment can fit the dynamic changes of the actual operation scenario of the distribution network. Voltage regulation priority is based on The size is sorted, and the synchronous output quantization voltage regulation target is; ; In the formula: The target voltage for voltage regulation at node j within the target time period; This is the voltage regulation amplitude coefficient; This is a sign function; it outputs 1 when the parameter is positive and -1 when the parameter is negative. The above formula is based on the rated voltage of the node, combined with the sign function to determine the direction of the predicted voltage deviation relative to the rated voltage, and then the voltage deviation risk index and voltage regulation amplitude coefficient are used to determine the voltage regulation amplitude. The voltage regulation amplitude coefficient will be dynamically adjusted according to the voltage deviation risk index and the control margin of the voltage regulation equipment, so as to ensure that the voltage regulation target can specifically deal with the voltage deviation risk, and avoid exceeding the control capacity of the equipment, and finally achieve a reasonable voltage regulation target setting. in, All numbers are positive, and their sum is 1. This occurs when the distribution network is under heavy load or the node voltage is close to the upper limit of the allowable deviation. The larger the value, the more likely the distribution network is to be operating under light load and the node voltage is stable near the rated voltage. The smaller the value, the more likely the fluctuation in wind and solar power output exceeds the preset fluctuation threshold or the proportion of new energy connected to the grid is higher than the preset connection ratio. The larger the value, the less the power output fluctuation amplitude is than the preset fluctuation threshold or the proportion of new energy access is lower than the preset access ratio. The smaller the value, the more likely the load change rate is to exceed a preset change rate threshold or the proportion of critical loads is to exceed a preset proportion threshold. The larger the value, the lower the load change rate is compared to the preset change rate threshold or the lower the proportion of critical loads is compared to the preset proportion threshold. The smaller the value; ∈[0,0.1], the voltage deviation risk index is larger when it is higher than the preset risk threshold and the control margin of the voltage regulating equipment is greater than the preset margin, and the voltage deviation risk index is smaller when it is lower than the preset risk threshold or the voltage regulating equipment is close to the maximum control capacity. The feature extrapolation model comprises a three-layer structured extrapolation architecture: the first layer is the feature enhancement layer, which performs dimensionality normalization and key feature enhancement on the spatiotemporally coupled feature matrix, with the enhancement weights being positively correlated with the sensitivity of the features to voltage fluctuations; the second layer is the time-series correlation layer, which establishes a correlation mapping between the current moment's features and historical features based on a preset time decay factor, where the time decay factor satisfies... , Let be the decay factor at time k. The attenuation coefficient is... The first layer is the sliding window length; the third layer is the output mapping layer, which outputs the predicted voltage value through linear transformation from feature vector to voltage prediction value and error correction. The model parameters are obtained by calibration through historical operating data of the distribution network, which includes synchronous time-series data of wind and solar power output, load power, and node voltage. The optimization module receives the voltage regulation target and the voltage deviation risk and voltage regulation priority prediction results output by the prediction module, constructs a multi-objective optimization model for the coordination of wind power and photovoltaic power consumption and power distribution, and dynamically generates energy storage scheduling and power optimization strategies. The optimization module constructs a multi-objective optimization model that coordinates wind and solar power integration and power distribution, aiming to maximize wind and solar power integration (C), minimize power distribution balance deviation (D), and minimize voltage regulation costs. The objective function is: ; In the formula: The set of time periods for the target time period; , These represent the actual power absorbed by wind power and photovoltaic power at time t, respectively. This refers to the number of nodes in the distribution network. The power allocated to the j-th node at time t; Assign the average target power to all nodes at time t; This represents the unit cost coefficient for energy storage dispatch. , , respectively, represent the charging and discharging power of the stored energy at time t; This is the unit cost coefficient for voltage regulation; Let be the voltage after adjustment at time t of node j; Let be the predicted voltage at time t of node j; The above formula revolves around three core objectives: wind and solar power integration, balanced power distribution, and voltage regulation cost. It maximizes the integration capacity by accumulating the actual wind and solar power integration capacity within the target time period, optimizes the power distribution balance by calculating the square mean of the deviation between the power distribution at each node and the average target power distribution capacity, and minimizes the regulation cost by accumulating the cost corresponding to the difference in energy storage charging and discharging power and the cost corresponding to the voltage difference before and after voltage regulation at the node. The three objectives work together, while taking into account constraints such as the upper limit of wind and solar power output, energy storage charging and discharging power, the upper and lower limits of node voltage, and the transmission power of the line, thus achieving comprehensive optimization under multiple objectives. in, The value of is within the preset range of [0.01, 10] yuan / (kWh). Its value increases as the remaining lifespan of the energy storage device decreases, the charge-discharge conversion efficiency decreases, or the current energy storage capacity utilization rate increases. It decreases as the remaining lifespan of the energy storage device is sufficient, the charge-discharge conversion efficiency increases, or the current energy storage capacity utilization rate decreases. The value is within the preset range [0.1, 50] yuan / (kV) A) Its value increases with the increase of the operating loss rate of the voltage regulating equipment, the increase of the dynamic response speed requirement, or the aggravation of the equipment aging, and decreases with the decrease of the operating loss rate of the voltage regulating equipment, the relaxation of the dynamic response speed requirement, or the good condition of the equipment; The constraints of the multi-objective optimization model include: upper limit constraint of wind power and photovoltaic output, energy storage charging and discharging power constraint, node voltage upper and lower limit constraint, and line transmission power constraint. The adapter module is used to receive the energy storage scheduling and power optimization strategies output by the optimization module, adapt to the interface protocol of the distribution network voltage regulation equipment, and convert the strategies into a voltage regulation control instruction set. When the adaptation module performs protocol conversion, it performs semantic parsing on the energy storage scheduling and power optimization strategies output by the optimization module, extracting the control object identifier, control value, control timing, control priority, and control activation conditions from the strategies. Then, based on the interface protocol library of the distribution network voltage regulation equipment, it maps the extracted core semantic fields to the corresponding device's protocol data units. During the mapping process, instruction compatibility verification is performed simultaneously. If the value of the instruction to be converted exceeds the control capability range of the corresponding device, the value is adjusted based on the preset capability compensation rule before generating the protocol data unit. Finally, the generated protocol data units are encapsulated according to the communication protocol format of the corresponding device to form a voltage regulation control instruction set and output to the corresponding voltage regulation device. Among them, the preset capacity compensation rules include: adjusting the value by 95% of the upper limit of equipment control, and dynamically correcting the control sequence based on the equipment response delay; The trigger module is used to monitor the operating status within a preset time interval after the voltage regulation control command set of the distribution network is executed, generate quantitative evaluation results, and decide whether the system should refresh the operation or the trigger module should run again based on the evaluation results. The quantitative evaluation result generated by the trigger module is the comprehensive index of the regulation effect: ; In the formula: The evaluation weights are assigned to voltage stability, absorption completion rate, and cost control rate. The preset evaluation time interval; The actual operating voltage of node j at time t; for; This refers to the allowable deviation range of the node voltage. This represents the actual amount of wind and solar power absorbed. The target amount of wastewater can be absorbed. Control costs to achieve the target; For actual regulatory costs; The above formula evaluates the control effect from three key dimensions: voltage stability, absorption completion, and cost control. Voltage stability is obtained by calculating the degree of fit between the actual operating voltage of the node and the allowable deviation range of the rated voltage within the evaluation time interval. Absorption completion is reflected by the ratio of the actual wind and solar power absorption to the target absorption. Cost control is reflected by the ratio of the target control cost to the actual control cost. At the same time, the evaluation weights of the three dimensions are dynamically adjusted according to the distribution network voltage fluctuation risk, absorption pressure, and cost sensitivity, so as to comprehensively and selectively measure the control effect and provide support for subsequent system operation decisions. in, All numbers are positive, and their sum is 1. Furthermore, the distribution network node voltage fluctuation risk is high, and the requirements for power supply reliability are stringent. A larger value indicates smoother voltage fluctuations and less stringent requirements for power supply reliability. The smaller the value, the greater the fluctuation in wind and solar power output, the higher the pressure on grid integration, or the need to prioritize renewable energy grid integration policies. A larger value indicates more stable output, lower pressure to absorb wastewater, or a need to prioritize other objectives. The smaller the value, the higher the unit cost of voltage regulation and energy storage dispatch, and the higher the sensitivity to the economic efficiency of regulation. A larger value indicates lower unit cost and a greater emphasis on voltage stability or absorption capacity targets. The smaller the value; The decision logic in the trigger module is as follows: If the comprehensive index of the regulation effect If the value exceeds the preset threshold, the control trigger module will run again to monitor the operating status of the power distribution network. like If the value is less than or equal to a preset threshold, a system refresh will be triggered. The sensing module interacts with the fusion module via a wireless network. The fusion module interacts with the prediction module via a wireless network. The prediction module interacts with the optimization module via a wireless network. The optimization module interacts with the adaptation module via a wireless network. The adaptation module interacts with the triggering module via a wireless network.

[0021] In this embodiment, the sensing module continuously senses multi-source heterogeneous signals from wind and solar power output, distribution network node voltage, and load power in real time. The fusion module receives the sensing signals from the sensing module and performs spatiotemporal fusion processing to extract the coupling characteristics of wind and solar power output volatility, load change trends, and voltage deviation, generating a standardized fusion dataset. The prediction module further receives the standardized fusion dataset output by the fusion module, traverses the standardized fusion dataset to predict voltage deviation risk and voltage regulation priority for the target time period, and synchronously outputs a quantified voltage regulation target. The optimization module then receives the voltage regulation target output by the prediction module and the prediction results of voltage deviation risk and voltage regulation priority for the target time period, constructs a multi-objective optimization model for the coordinated integration of wind and solar power consumption and power distribution, dynamically generates energy storage scheduling and power optimization strategies, and receives the energy storage scheduling and power optimization strategies output by the optimization module through the adaptation module. It adapts the distribution network voltage regulation equipment interface protocol and converts the strategies into a voltage regulation control command set. Finally, the triggering module monitors the operating status within a preset time interval after the distribution network voltage regulation control command set is executed, generates a quantified evaluation result, and decides whether the system refreshes its operation or the triggering module restarts based on the evaluation result.

[0022] In the above embodiments, the system can accurately respond to fluctuations in wind and solar power output and load changes, effectively predict voltage deviation risks, dynamically optimize power allocation and energy storage scheduling, adapt to the operating needs of power supply equipment, improve the renewable energy absorption rate, ensure the stability of the distribution network voltage, reduce control costs, and enhance the reliability and economy of power supply.

[0023] Referring to the system in the above embodiments, the following is an application example of the system described above: In a certain region, a 10kV distribution network is connected to two wind power stations and three photovoltaic power stations, with loads covering both industrial production and residential loads. The network suffers from large fluctuations in wind and photovoltaic power output and easy deviations in node voltage. Therefore, this system is applied.

[0024] During system operation, the sensing module collects real-time signals of wind and solar power output, voltage of 12 distribution network nodes, and load power. First, it completes the synchronization and alignment of the timestamps of each signal, and then obtains the pre-processed signal data through adaptive noise suppression processing. For example, at a certain moment, the pre-processed wind power output is 8.3MW, the solar power output is 5.7MW, and the pre-processed voltage of each node is between 10.2-10.6kV.

[0025] After receiving the preprocessed signal, the fusion module performs spatiotemporal fusion processing: after time-dimensional fusion, the characteristic quantity of wind power and photovoltaic output fluctuation is 0.13, and the load change trend quantity is 0.28MW / h; after spatial-dimensional fusion, the spatial correlation quantity of voltage deviation of power supply hub node is 0.09, and that of terminal branch node is 0.04. Then, the two types of characteristic quantities are spliced ​​together to generate a standardized fusion dataset.

[0026] Based on this dataset, the prediction module calculates the voltage offset risk index of each node during the target period: 0.87 for node 3 (high priority), 0.45 for node 7 (medium priority), and all other nodes are below 0.3 (low priority). It also outputs the quantitative voltage regulation target: the voltage regulation target voltage for node 3 is 10.1kV, for node 7 it is 10.3kV, and for low priority nodes it is uniformly 10.4kV.

[0027] The optimization module combines the voltage regulation target and risk prediction results to construct a multi-objective optimization model and dynamically generate energy storage scheduling and power optimization strategies: the average wind power absorption is 9.1MW, the average photovoltaic absorption is 6.2MW, the power distribution balance deviation is 0.06, the comprehensive cost of voltage regulation and energy storage scheduling is 880 yuan / hour, and the constraints such as the upper limit of wind and photovoltaic output and the charging and discharging power of energy storage are met.

[0028] The adaptation module performs semantic parsing on the above strategies, extracts core information such as the control object, value, and timing, completes the mapping by referring to the interface protocol library of the distribution network voltage regulating equipment, adjusts the value of the equipment's control capability after compatibility verification, encapsulates it into a voltage regulation control instruction set, and sends it to the energy storage equipment and on-load tap-changing transformer.

[0029] The trigger module monitors the distribution network operation status within one hour after the command is executed and calculates the comprehensive index of the control effect: the voltage stability related evaluation result is 0.95, the absorption completion rate is 0.97, the cost control rate is 0.94, and the comprehensive index is 0.955. This value is greater than the preset threshold of 0.9, so the trigger module continues to monitor the distribution network operation status.

[0030] In summary, the system in the above embodiments captures and optimizes real-time signals related to wind and solar power output, voltage, and load during operation. It accurately mines the coupling characteristics of multiple factors, effectively predicts voltage deviation risks and voltage regulation needs, and maximizes renewable energy consumption, balances power distribution, and minimizes regulation costs through collaborative optimization. It is compatible with various voltage regulation devices to ensure efficient execution of commands, dynamically evaluates and continuously optimizes regulation effects, and can flexibly cope with complex operating conditions such as signal fluctuations and electromagnetic interference. This effectively improves the voltage stability and power supply reliability of the distribution network, takes into account both operational economy and renewable energy utilization efficiency, and can adapt to different load levels and renewable energy access ratios, providing intelligent and reliable support for the operation of wind and solar power distribution networks.

[0031] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A dynamic voltage regulation and power optimization system for distribution networks based on wind and solar power integration, characterized in that, include: The sensing module is used to sense multi-source heterogeneous signals such as wind and solar power output, distribution network node voltage, and load power in real time. The fusion module is used to receive the sensing signals from the sensing module, perform spatiotemporal dimensional fusion processing on the signals to extract the coupling characteristics of wind power and solar power output fluctuations, load change trends and voltage deviations, and generate a standardized fusion dataset. The prediction module receives the standardized fusion dataset output by the fusion module, iterates through the standardized fusion dataset to predict the voltage deviation risk and voltage regulation priority during the target period, and synchronously outputs the quantified voltage regulation target. The optimization module receives the voltage regulation target and the voltage deviation risk and voltage regulation priority prediction results output by the prediction module, constructs a multi-objective optimization model for the coordination of wind power and photovoltaic power consumption and power distribution, and dynamically generates energy storage scheduling and power optimization strategies. The adapter module is used to receive the energy storage scheduling and power optimization strategies output by the optimization module, adapt to the interface protocol of the distribution network voltage regulation equipment, and convert the strategies into a voltage regulation control instruction set. The trigger module is used to monitor the operating status within a preset time interval after the voltage regulation control command set of the distribution network is executed, generate quantitative evaluation results, and make decisions on whether the system should refresh the operation or the trigger module should run again based on the evaluation results.

2. The dynamic voltage regulation and power optimization system for distribution networks based on wind and solar power integration according to claim 1, characterized in that, During the operation of the sensing module, preprocessing operations are performed synchronously on the multi-source heterogeneous signals: Synchronization alignment is performed on the timestamps of each signal, with the alignment reference being the unified clock signal of the distribution network. Adaptive noise suppression processing is then performed on the synchronized signals. ； In the formula: The value of the i-th type of signal after preprocessing at time t; Let be the original sampled value of the i-th type of signal at time t; Let be the filtering factor for the i-th type of signal at time t; Let be the mean value of the i-th type of signal over a preset historical period; The sensitivity coefficient for signal fluctuations; This is the baseline coefficient for filter strength; The preprocessed signals are then forwarded synchronously to the fusion module.

3. The dynamic voltage regulation and power optimization system for distribution networks based on wind and solar power integration according to claim 1, characterized in that, The spatiotemporal dimensional fusion processing performed by the fusion module includes: Time dimension fusion: ; In the formula: These are the fluctuation characteristics of wind and solar power output and the load change trend, respectively. The length of the sliding window for time-dimension fusion; Let K be the wind and solar power output at time k. Similarly; The average output of wind and solar power within the preset time period; t is the time marker of the current sampling moment; Spatial Dimension Fusion: ; In the formula: The spatial correlation quantity of the voltage deviation at the j-th node; Let be the voltage value of node j at time t; Let be the rated voltage of the j-th node; Let be the standard deviation of the voltage at node j within a preset historical time period; Let be the voltage sensitivity weight of the j-th node; Then take the time dimension Spatial dimension The standardized fusion dataset is generated by splicing the data according to preset dimensions.

4. A dynamic voltage regulation and power optimization system for distribution networks based on wind and solar power integration according to claim 1, characterized in that, The prediction module performs a voltage offset risk prediction phase, constructing a voltage offset risk index for the target time period: ； In the formula: Voltage offset risk index; T represents the duration of the target time period; Risk weights for voltage deviation, wind power output fluctuation, and load change trends; It is the set of all nodes in the distribution network; The feature inference model built into the prediction module takes the spatiotemporal coupling feature matrix as input and predicts the voltage value of the j-th node at time t+T by analyzing the temporal evolution of the power output fluctuation, load change trend and node voltage spatial correlation of wind power and photovoltaic power. Let be the rated voltage of the j-th node; This refers to the fluctuation characteristics of wind and solar power output within the predicted target time period; This represents the average value of the fluctuating characteristics of wind power output within a preset time period. This refers to the predicted load change trend within the target time period; The average value of the load change trend within a preset time period; The voltage regulation priority is based on The size is sorted, and the synchronous output quantization voltage regulation target is; ； In the formula: The target voltage for voltage regulation at node j within the target time period; This is the voltage regulation amplitude coefficient; This is a sign function; it outputs 1 when the parameter is positive and -1 when the parameter is negative.

5. A dynamic voltage regulation and power optimization system for distribution networks based on wind and solar power integration according to claim 1, characterized in that, The optimization module constructs a multi-objective optimization model that coordinates wind power and solar power integration and power distribution, aiming to maximize the wind power and solar power integration capacity C, minimize the power distribution balance deviation D, and minimize voltage regulation and control costs. The objective function is: ； In the formula: The set of time periods for the target time period; , These represent the actual power absorbed by wind power and photovoltaic power at time t, respectively. This refers to the number of nodes in the distribution network. The power allocated to the j-th node at time t; Assign the average target power to all nodes at time t; This represents the unit cost coefficient for energy storage dispatch. , , respectively, represent the charging and discharging power of the stored energy at time t; This is the unit cost coefficient for voltage regulation; Let be the voltage after adjustment at time t of node j; Let be the predicted voltage at time t of node j.

6. A dynamic voltage regulation and power optimization system for distribution networks based on wind and solar power integration according to claim 1, characterized in that, When the adaptation module performs protocol conversion, it performs semantic parsing on the energy storage scheduling and power optimization strategies output by the optimization module, extracting the control object identifier, control value, control timing, control priority, and control activation conditions from the strategies. Then, based on the interface protocol library of the distribution network voltage regulation equipment, it maps the extracted core semantic fields to the corresponding device's protocol data units. During the mapping process, instruction compatibility verification is performed simultaneously. If the value of the instruction to be converted exceeds the control capability range of the corresponding device, the value is adjusted based on the preset capability compensation rule before generating the protocol data unit. Finally, the generated protocol data units are encapsulated according to the communication protocol format of the corresponding device to form the voltage regulation control instruction set and output to the corresponding voltage regulation device.

7. A dynamic voltage regulation and power optimization system for distribution networks based on wind and solar power integration according to claim 1, characterized in that, The quantitative evaluation result generated by the triggering module is a comprehensive index of the control effect: ； In the formula: The evaluation weights are assigned to voltage stability, absorption completion rate, and cost control rate. The preset evaluation time interval; The actual operating voltage of node j at time t; for; This refers to the allowable deviation range of the node voltage. This represents the actual amount of wind and solar power absorbed. The target amount of wastewater can be absorbed. Control costs to achieve the target; This refers to the actual cost of regulation.

8. A dynamic voltage regulation and power optimization system for distribution networks based on wind and solar power integration according to claim 7, characterized in that, The decision logic in the triggering module is as follows: If the comprehensive index of the regulation effect If the value exceeds the preset threshold, the control trigger module will run again to monitor the operating status of the power distribution network. like If the value is less than or equal to the preset threshold, the system refresh operation will be triggered.

9. A dynamic voltage regulation and power optimization system for distribution networks based on wind and solar power integration according to claim 1, characterized in that, The sensing module is interconnected with a fusion module via a wireless network. The fusion module is interconnected with a prediction module via a wireless network. The prediction module is interconnected with an optimization module via a wireless network. The optimization module is interconnected with an adaptation module via a wireless network. The adaptation module is interconnected with a triggering module via a wireless network.

Images