A micro-grid power quality treatment method, system, device and medium based on time series prediction and source-load-storage coordination

Abstract

The present application relates to the technical field of micro-grid power quality management, and discloses a micro-grid power quality management method, system, device and medium based on time sequence prediction and source-load-storage cooperation, which comprises the following steps: acquiring meteorological and electrical data; inputting the data into a time sequence prediction model to obtain power quality prediction values at future time; constructing a multi-optimization target model, using a multi-objective optimization algorithm to cooperatively optimize the capacity configuration parameters and power distribution control parameters of the system to obtain a set of benchmark configuration parameters; executing a hierarchical cooperative management control strategy according to whether the power quality prediction values exceed the limit and in combination with the real-time state of the system; and based on the dynamically adjusted parameters, decomposing power fluctuation signals according to frequency and distributing them to different types of energy storage units and main power sources for execution. The present application can identify power quality exceeding limit risks in advance and avoid hysteresis; the hierarchical management preferentially uses energy storage adjustment to reduce the probability of load shedding, thereby ensuring the continuous power consumption experience of users and reducing operation and maintenance costs.

Description

Technical Field

[0001] This invention relates to the field of microgrid power quality management technology, and in particular to a method, system, equipment and medium for microgrid power quality management based on time-series prediction and source-load-storage synergy. Background Technology

[0002] With the large-scale integration of distributed energy resources into microgrid systems, power quality issues are becoming increasingly apparent. To address problems such as voltage fluctuations, frequency deviations, and harmonic interference, current technologies mainly focus on two approaches: one is demand-side management-based governance, which monitors key electrical parameters and uses predictive algorithms to identify over-limit risks, thereby adjusting load operation plans to maintain power quality; the other relies on hybrid energy storage systems, which use filtering algorithms to decompose power fluctuations and distribute them among different energy storage media, while simultaneously employing optimization algorithms to collaboratively design energy storage capacity and energy management strategies to smooth out system fluctuations.

[0003] However, most of the aforementioned methods rely solely on load adjustment, which can easily lead to a decrease in power supply continuity, affecting users' normal electricity experience, and is difficult to respond to transient disturbances. Relying solely on energy storage for mitigation, on the other hand, lacks prediction of future operating conditions, often requiring large capacities to cope with extreme fluctuations, resulting in high system investment costs. Furthermore, frequent charging and discharging of energy storage units accelerates their aging. In addition, existing governance methods typically cannot feed forecast information forward to the energy storage control stage, lacking a dynamic coordination mechanism between source, storage, and load, leading to delayed governance response and limited overall effectiveness. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a microgrid power quality management method and system based on time-series prediction and source-load-storage coordination to solve the problems that the current method of maintaining power quality by simply shedding loads reduces power supply reliability, has limited response speed to millisecond-level instantaneous fluctuations, accelerates battery aging due to frequent unnecessary charging and discharging, and lacks a coordination mechanism.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a microgrid power quality management method based on time-series prediction and source-load-storage coordination, comprising: Acquire meteorological and electrical data; The acquired data is input into the time series prediction model to obtain the predicted power quality values ​​for future times; With the main power output power, system investment cost, equipment life loss and power quality indicators as optimization objectives, a multi-objective optimization algorithm is used to coordinately optimize the capacity configuration parameters and power distribution control parameters of the hybrid energy storage system, and obtain a set of optimal benchmark configuration parameters for system configuration and operation. Based on whether the predicted power quality value exceeds the limit, and combined with the real-time status of the hybrid energy storage system, a hierarchical collaborative governance and control strategy is executed to generate corresponding control commands for dynamic adjustment. Based on the dynamically adjusted power distribution control parameters, the power fluctuation signals that the system needs to respond to are decomposed by frequency and distributed to different types of energy storage units and the main power supply in the hybrid energy storage system.

[0007] As a preferred embodiment of the microgrid power quality management method based on time-series forecasting and source-load-storage coordination described in this invention, the method involves: inputting the acquired data into a time-series forecasting model to obtain predicted power quality values ​​for future times, including: Input meteorological and electrical data into the time-series forecasting model; The time series prediction model uses a multi-layer feedforward neural network trained with the backpropagation algorithm for prediction; Output Future Moments The power quality parameters, including frequency deviation. Total harmonic distortion of voltage and long-term flicker index .

[0008] As a preferred embodiment of the microgrid power quality management method based on time-series prediction and source-load-storage coordination described in this invention, the method includes: using a multi-objective optimization algorithm to coordinately optimize the capacity configuration parameters and power allocation control parameters of the hybrid energy storage system, including: Establish a multi-objective optimization model that includes the aforementioned optimization objective and system operation constraints; The system operation constraints include: power balance constraints, state of charge constraints, and power limitation constraints. The multi-objective optimization algorithm jointly optimizes the rated capacity of different energy storage media and the filtering parameters in the power distribution control of the hybrid energy storage system.

[0009] As a preferred embodiment of the microgrid power quality management method based on time-series prediction and source-load-storage coordination described in this invention, the method includes: executing a hierarchical collaborative management control strategy based on whether the predicted power quality value exceeds the limit, and in conjunction with the real-time status of the hybrid energy storage system, generating corresponding control commands for dynamic adjustment, including: If the predicted power quality value does not exceed the limit, the system will continue to operate according to the baseline configuration parameter set.

[0010] As a preferred embodiment of the microgrid power quality management method based on time-series prediction and source-load-storage coordination described in this invention, the method includes: executing a hierarchical collaborative management control strategy based on whether the predicted power quality value exceeds the limit, and in conjunction with the real-time status of the hybrid energy storage system, generating corresponding control commands for dynamic adjustment, including: If the predicted power quality exceeds the limit and the state of the hybrid energy storage system meets the first preset condition, it enters the first-level governance state. The power distribution control parameters are dynamically adjusted, and the hybrid energy storage system is controlled to fully compensate for power fluctuations. The first preset condition is that the state of charge of the hybrid energy storage system is within a safe range.

[0011] As a preferred embodiment of the microgrid power quality management method based on time-series prediction and source-load-storage coordination described in this invention, the method includes: executing a hierarchical collaborative management control strategy based on whether the predicted power quality value exceeds the limit, and in conjunction with the real-time status of the hybrid energy storage system, generating corresponding control commands for dynamic adjustment, including: If the predicted power quality exceeds the limit and the state of the hybrid energy storage system meets the second preset condition, it enters the secondary governance state; The hybrid energy storage system is controlled to output at maximum capacity, and load-side management operations are performed on the remaining power gap; the load-side management operations include cutting off or shifting the corresponding secondary loads according to preset load priorities.

[0012] The second preset condition is that the state of charge of the hybrid energy storage system exceeds the safe range or its maximum output power is insufficient to compensate for the power fluctuation.

[0013] As a preferred embodiment of the microgrid power quality management method based on time-series prediction and source-load-storage coordination described in this invention, wherein: the power fluctuation signal that the system needs to respond to is decomposed by frequency based on dynamically adjusted power allocation control parameters, specifically: A multi-stage filtering structure is used to sequentially separate the power fluctuation signal into high-frequency components, mid-low frequency components, and fundamental smoothing components; The filtering structure includes at least one filtering parameter, which can be dynamically adjusted according to the disturbance characteristics indicated by the power quality prediction value to change the distribution ratio of different frequency components.

[0014] Secondly, the present invention provides a microgrid power quality management system based on time-series prediction and source-load-storage coordination, comprising: The data acquisition module is used to acquire meteorological and electrical data; The prediction module is used to input the acquired data into the time series prediction model to obtain the predicted power quality values ​​for future times. The collaborative optimization module is used to perform collaborative optimization of the capacity configuration parameters and power distribution control parameters of the hybrid energy storage system with the main power output power, system investment cost, equipment life loss and power quality indicators as optimization objectives. It uses a multi-objective optimization algorithm to obtain a set of optimal benchmark configuration parameters for system configuration and operation. The decision module is used to execute a hierarchical collaborative governance control strategy and generate corresponding control commands for dynamic adjustment based on whether the predicted power quality value exceeds the limit and in combination with the real-time status of the hybrid energy storage system. The control module is used to decompose the power fluctuation signal that the system needs to respond to by frequency based on the dynamically adjusted power distribution control parameters, and distribute it to different types of energy storage units and the main power supply in the hybrid energy storage system for execution.

[0015] Thirdly, the present invention provides a computer device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of a microgrid power quality management method based on time-series prediction and source-load-storage coordination.

[0016] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the microgrid power quality management method based on time-series prediction and source-load-storage coordination.

[0017] Compared with existing technologies, the beneficial effects of this invention are as follows: By introducing time-series prediction, this invention can identify the risk of power quality exceeding limits in advance, allowing for proactive mitigation actions and avoiding the lag of traditional feedback control, thus effectively protecting sensitive electrical equipment; by combining the use of the NSGA-II algorithm to optimize the objective function of investment cost and battery life loss, it can reduce the capacity configuration cost and operation and maintenance cost of the energy storage system while achieving the same mitigation effect; finally, by using a second-order filtering strategy to finely allocate power, allowing the supercapacitor to withstand high-frequency impacts and protecting the lithium battery; and by employing a tiered mitigation strategy to prioritize the use of energy storage regulation, thereby reducing the probability of load shedding and ensuring a continuous power supply experience for users. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the overall process of a microgrid power quality management method based on time-series prediction and source-load-storage coordination, as described in one embodiment of the present invention.

[0020] Figure 2 This is a control flow diagram of the active power quality classification management method for microgrids, which is described in an embodiment of the present invention, based on time-series prediction and source-load-storage coordination.

[0021] Figure 3 This is a schematic diagram of the principle of a second-order filtering power allocation strategy based on dynamic parameter adjustment of ANN in a microgrid power quality management method based on time-series prediction and source-load-storage coordination, as described in an embodiment of the present invention.

[0022] Figure 4 This is a schematic diagram of the system architecture of a microgrid power quality management method based on time-series prediction and source-load-storage coordination, as described in one embodiment of the present invention. Detailed Implementation

[0023] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0024] Example 1, referring to Figure 1 As an embodiment of the present invention, a microgrid power quality management method based on time-series prediction and source-load-storage coordination is provided, comprising: S100: Acquire meteorological and electrical data; S200: Input the acquired data into the time series prediction model to obtain the predicted power quality values ​​for future times; S300: Taking the main power output power, system investment cost, equipment life loss and power quality indicators as optimization objectives, it uses a multi-objective optimization algorithm to coordinately optimize the capacity configuration parameters and power distribution control parameters of the hybrid energy storage system, obtains a set of optimal benchmark configuration parameters, and performs system configuration and operation. S400: Based on whether the predicted power quality value exceeds the limit, and combined with the real-time status of the hybrid energy storage system, execute the hierarchical collaborative governance control strategy, generate corresponding control commands for dynamic adjustment; S500: Based on dynamically adjusted power distribution control parameters, the power fluctuation signal that the system needs to respond to is decomposed by frequency and distributed to different types of energy storage units and main power supply in the hybrid energy storage system.

[0025] Specifically, in the present invention S100-S500, the problems of frequent load shedding by single demand-side management (ADSM) affecting user experience and the lack of operational condition prediction leading to capacity redundancy and lagging governance in single hybrid energy storage systems (HESS) in existing microgrid power quality management are addressed by using an ANN model to predict future power quality risks, utilizing the NSGA-II algorithm to collaboratively optimize energy storage capacity and filtering parameters, and employing a hierarchical control strategy to minimize system investment costs and maximize power supply continuity while ensuring that power quality meets standards.

[0026] Example 2, refer to Figures 1-3 As an embodiment of the present invention, based on the above embodiment, a microgrid power quality management method based on time-series prediction and source-load-storage coordination is provided. The method includes: S100: Acquire meteorological and electrical data; Specifically, the meteorological data acquired may include, for example, light intensity. Ambient temperature Wind speed Electrical data must include key parameters reflecting the real-time operating status, load characteristics, and power quality of the microgrid, such as: total load power, active and reactive power of each branch or key load, load type and switching status, etc.; and, not limited to, system frequency, voltage amplitude of each node, total harmonic distortion (THD), etc.

[0027] In one optional implementation, the data acquisition method in S100 can be achieved by an energy management platform deployed in the central control room of the microgrid, which can simultaneously collect data from various monitoring points. Specifically, meteorological data can be uploaded in real time by micro weather stations deployed near photovoltaic arrays and wind turbines via wireless communication networks; electrical data is collected by intelligent measurement and control devices installed on the busbar, critical load circuits, energy storage converter ports, and main power output side.

[0028] In another optional implementation, in S100, data can also be collected by deploying a smart gateway with edge computing capabilities near the data source. The gateway can not only collect local meteorological or electrical raw data, but also perform data preprocessing.

[0029] S200: Input the acquired data into the time series prediction model to obtain the predicted power quality values ​​for future times; In this embodiment of the application, step S200 involves inputting the acquired data into a time-series prediction model to obtain predicted power quality values ​​for future times, including the following steps A1-A3: A1: Input meteorological and electrical data into the time-series forecasting model; Specifically, refer to Figure 2 The time-series forecasting model can be an ANN model. After receiving the data from S100, its input module first performs time alignment, missing value imputation, and outlier processing to ensure data continuity. Subsequently, the multi-source heterogeneous data is normalized or standardized to construct an input feature vector. This vector can contain meteorological data, load data, current power quality index values, etc., from the current and past time series, forming the complete input of the model at a certain moment.

[0030] A2: The time series prediction model uses a multi-layer feedforward neural network trained with the backpropagation algorithm for prediction; Specifically, the ANN time series prediction model includes an input layer, a hidden layer, and an output layer; The input layer has a number of neurons that match the dimension of the preprocessed input feature vector and is responsible for receiving data. The hidden layers can be one or more, each containing several neurons and employing a non-linear activation function. The hidden layers progressively perform high-dimensional transformations and non-linear combinations on the input data, automatically extracting deep temporal features and complex patterns that influence power quality changes. The number of hidden layers and neurons can be determined through training based on the scale of historical data and the complexity of the prediction.

[0031] A3: Output Future Moments The power quality parameters, including frequency deviation. Total harmonic distortion of voltage and long-term flicker index .

[0032] Specifically, the number of neurons in the output layer is consistent with the number of power quality parameters to be predicted.

[0033] For example, the output layer can be set to three neurons, each corresponding to a future neuron. Three key prediction targets for time: frequency deviation Total harmonic distortion of voltage and long-term flicker index Use a linear activation function and directly output the specific numerical value of the predicted value.

[0034] It should be noted that the S200 uses the future power quality indicators predicted by the ANN model, especially the high-frequency voltage flicker value, as feedforward control variables. The purpose is to dynamically adjust the two time constants of the second-order low-pass filter in the hybrid energy storage system in real time during subsequent steps. This allows for dynamic adjustment of the power distribution ratio between the supercapacitor and the lithium battery based on the type of disturbance.

[0035] In another alternative implementation, in addition to ANN, the time series prediction model can also use Long Short-Term Memory Network (LSTM) or Gated Recurrent Unit (GRU) as alternatives; both networks can be used for time series data, both are explicit models, the existing model structure can directly handle the time series dimension and capture the time dependencies, periodicity and trends of the data; the model interface and functions are consistent with ANN.

[0036] S300: Reference Figure 2 With the main power output power, system investment cost, equipment life loss and power quality indicators as optimization objectives, a multi-objective optimization algorithm is used to coordinately optimize the capacity configuration parameters and power distribution control parameters of the hybrid energy storage system, and obtain a set of optimal benchmark configuration parameters for system configuration and operation. It should be noted that, in order to determine the optimal capacity configuration and optimal filtering parameters of the hybrid energy storage system (HESS), this invention establishes a multi-objective collaborative optimization model and uses a non-dominated sorting genetic algorithm (NSGA-II) with an elitist strategy to solve it.

[0037] Specifically, the objective function for main power supply output power This refers to minimizing the output power fluctuations of the main power source (diesel engine / photovoltaic) to smooth the source-end output, thereby reducing mechanical wear or impact on the power grid, and can be expressed as: In the formula, for The output power of the main power supply (diesel engine) at all times; This represents the total number of sampling periods.

[0038] Specifically, minimizing system investment costs aims to avoid over-provisioning of capacity; the objective function is... It can be represented as: In the formula, The unit capacity cost of lithium batteries (RMB / kWh); The unit capacity cost of supercapacitors (RMB / kWh).

[0039] Specifically, minimizing lithium battery life loss considers the impact of depth of discharge and cycle count on lifespan, with the objective function being... It can be represented as: In the formula, To the depth of discharge The cycle life under the given conditions is typically fitted as follows: ( (These are the fitting coefficients). This refers to the depth of discharge of the lithium battery. For the charging and discharging efficiency of lithium batteries; This refers to the discharge power of the lithium battery. This represents the discharge duration.

[0040] Specifically, minimizing DC bus voltage fluctuations directly reflects the effectiveness of power quality management; the objective function is... It can be represented as: In the formula, for The voltage value of the DC bus at any given time.

[0041] In this embodiment of the application, step S300 utilizes a multi-objective optimization algorithm to collaboratively optimize the capacity configuration parameters and power allocation control parameters of the hybrid energy storage system, including the following steps B1-B2: B1: Establish a multi-objective optimization model that includes the aforementioned optimization objective and system operation constraints; The system operation constraints include: power balance constraints, state of charge constraints, and power limitation constraints. Specifically, the power balance constraint can be expressed as: State of charge (SOC) constraints can be expressed as: The power limitation constraint can be expressed as: B2: The multi-objective optimization algorithm jointly optimizes the rated capacity of different energy storage media and the filtering parameters in the power distribution control of the hybrid energy storage system.

[0042] Specifically, the rated capacity of different energy storage media and the filtering parameters in power distribution control, i.e., the decision variable vector of the optimization process. , represented as: In the formula, The rated capacity (kWh) of the lithium battery. The rated capacity (kWh) of the supercapacitor; The time constant (s) of the first-stage low-pass filter; is the time constant (s) of the second-stage low-pass filter.

[0043] It should be noted that the S300 constructs a multi-objective optimization model by minimizing four objective functions and combining three constraints to balance governance effectiveness and economy. The model is solved using the NSGA-II multi-objective optimization algorithm, which outputs one or more Pareto optimal solutions. Each solution includes: baseline configuration parameters of the energy storage system hardware, such as the rated capacity of lithium batteries and supercapacitors; and baseline values ​​of soft parameters of the control system, such as the filtering time constant. This output provides the system with an optimal initial operating point that balances economy and performance, achieving global optimization of system investment cost, battery life loss, and voltage governance effectiveness.

[0044] S400: Based on whether the predicted power quality value exceeds the limit, and combined with the real-time status of the hybrid energy storage system, execute the hierarchical collaborative governance control strategy, generate corresponding control commands for dynamic adjustment; In this embodiment of the application, step S400, based on whether the predicted power quality value exceeds the limit and in conjunction with the real-time status of the hybrid energy storage system, executes a hierarchical collaborative governance control strategy to generate corresponding control commands for dynamic adjustment, including: If the predicted power quality value When the limits are not exceeded, the system will continue to operate according to the aforementioned baseline configuration parameter set.

[0045] It should be noted that this is the normal operating state, and the system can run according to the baseline parameters optimized by NSGA-II in step S300.

[0046] In this embodiment of the application, step S400, based on whether the predicted power quality value exceeds the limit and in conjunction with the real-time status of the hybrid energy storage system, executes a hierarchical collaborative governance control strategy to generate corresponding control commands for dynamic adjustment, including: If the predicted power quality exceeds the limit and the state of the hybrid energy storage system meets the first preset condition, it enters the first-level governance state. The power distribution control parameters are dynamically adjusted, and the hybrid energy storage system is controlled to fully compensate for power fluctuations. The first preset condition is that the state of charge of the hybrid energy storage system is within a safe range.

[0047] Specifically, if Exceeding the limit, and HESS's SOC is at... The range; then adjust. Parameters, fully compensated for power deficit through HESS During this phase, no load shedding is performed; energy storage is prioritized.

[0048] In this embodiment of the application, step S400, based on whether the predicted power quality value exceeds the limit and in conjunction with the real-time status of the hybrid energy storage system, executes a hierarchical collaborative governance control strategy to generate corresponding control commands for dynamic adjustment, including: If the predicted power quality exceeds the limit and the state of the hybrid energy storage system meets the second preset condition, it enters the secondary governance state; The hybrid energy storage system is controlled to output at maximum capacity, and load-side management operations are performed on the remaining power gap; the load-side management operations include cutting off or shifting the corresponding secondary loads according to preset load priorities.

[0049] The second preset condition is that the state of charge of the hybrid energy storage system exceeds the safe range or its maximum output power is insufficient to compensate for the power fluctuation.

[0050] Specifically, Exceeding limits, and the HESS's SOC exceeds the safe range or the required power. Then HESS will first use the maximum allowable power. Output; and calculate the remaining uncompensated power. The ADSM module cuts off total power according to a preset priority list. Secondary loads (i.e., controllable secondary loads).

[0051] It should be noted that the S400 as a whole constructs a hierarchical closed-loop control logic: Level 1 governance: When the predicted index exceeds the limit, the energy storage status is checked first, and the hybrid energy storage system is controlled to fully compensate for the fluctuation by adjusting the filter parameters, without cutting off the load; Level 2 governance: Active demand-side management (ADSM) is only activated when the energy storage system's SOC exceeds the limit or its power is insufficient, and secondary loads are cut off or shifted according to priority.

[0052] S500: Based on dynamically adjusted power distribution control parameters, the power fluctuation signal that the system needs to respond to is decomposed by frequency and distributed to different types of energy storage units and main power supply in the hybrid energy storage system.

[0053] In this embodiment of the application, the step S500, which involves decomposing the power fluctuation signal that the system needs to respond to according to frequency based on the dynamically adjusted power distribution control parameters, specifically includes: A multi-stage filtering structure is used to sequentially separate the power fluctuation signal into high-frequency components, mid-low frequency components, and fundamental smoothing components; The filtering structure includes at least one filtering parameter, which can be dynamically adjusted according to the disturbance characteristics indicated by the power quality prediction value to change the distribution ratio of different frequency components.

[0054] Specifically, the S500 employs a two-stage low-pass filter structure in series to filter system net load fluctuations. It is decomposed into high-frequency, mid-frequency and low-frequency components.

[0055] Power allocation mathematical model based on Figure 3 Based on the control principle, the power distribution calculation for each part can be performed as follows: First-stage separation (extraction of high-frequency components): utilizing a time constant of... First-order low-pass filter handles the net load high-frequency components were separated. Powered by supercapacitors: The remaining power is : In the formula, For the Laplace operator; The time constant for the first-stage filter is dynamically corrected based on the ANN prediction results.

[0056] Second-stage separation (extraction of intermediate frequency components): utilizing a time constant of... First-order low-pass filter for processing residual power Separate the intermediate frequency component Powered by lithium batteries: Low-frequency components (main power supply): final smoothed power after two stages of filtering. Powered by the main power supply: It should be noted that in this invention and Not a fixed value; when the ANN prediction model predicts future power quality indicators When high-frequency, drastic fluctuations occur, the control system will automatically reduce... ,make It contains more frequency components and utilizes the fast response characteristics of supercapacitors to forcefully smooth out fluctuations.

[0057] Example 3 illustrates a schematic scheme for a microgrid power quality management method based on time-series forecasting and source-load-storage synergy. It should be noted that the technical solution of this microgrid power quality management system based on time-series forecasting and source-load-storage synergy is based on the same concept as the aforementioned microgrid power quality management method based on time-series forecasting and source-load-storage synergy. Details not described in detail in this example of the microgrid power quality management system based on time-series forecasting and source-load-storage synergy can be found in the description of the aforementioned microgrid power quality management method based on time-series forecasting and source-load-storage synergy.

[0058] refer to Figure 4 This embodiment also provides a microgrid power quality management system based on time-series prediction and source-load-storage coordination, including: The data acquisition module is used to acquire meteorological and electrical data; The prediction module is used to input the acquired data into the time series prediction model to obtain the predicted power quality values ​​for future times. The collaborative optimization module is used to perform collaborative optimization of the capacity configuration parameters and power distribution control parameters of the hybrid energy storage system with the main power output power, system investment cost, equipment life loss and power quality indicators as optimization objectives. It uses a multi-objective optimization algorithm to obtain a set of optimal benchmark configuration parameters for system configuration and operation. The decision module is used to execute a hierarchical collaborative governance control strategy and generate corresponding control commands for dynamic adjustment based on whether the predicted power quality value exceeds the limit and in combination with the real-time status of the hybrid energy storage system. The control module is used to decompose the power fluctuation signal that the system needs to respond to by frequency based on the dynamically adjusted power distribution control parameters, and distribute it to different types of energy storage units and the main power supply in the hybrid energy storage system for execution.

[0059] This embodiment also provides a computer device applicable to a microgrid power quality management method based on time-series prediction and source-load-storage coordination, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the microgrid power quality management method based on time-series prediction and source-load-storage coordination proposed in the above embodiment.

[0060] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements a microgrid power quality management method based on time-series prediction and source-load-storage coordination, as proposed in the above embodiments.

[0061] The storage medium proposed in this embodiment belongs to the same inventive concept as the microgrid power quality management method based on time-series prediction and source-load-storage coordination proposed in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0062] Based on the above description of the implementation methods, those skilled in the art will clearly understand that the present invention can be implemented using software and necessary general-purpose hardware. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0063] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A microgrid power quality management method based on time-series prediction and source-load-storage coordination, characterized in that, include: Acquire meteorological and electrical data; The acquired data is input into the time series prediction model to obtain the predicted power quality values ​​for future times; With the main power output power, system investment cost, equipment life loss and power quality indicators as optimization objectives, a multi-objective optimization algorithm is used to coordinately optimize the capacity configuration parameters and power distribution control parameters of the hybrid energy storage system, and obtain a set of optimal benchmark configuration parameters for system configuration and operation. Based on whether the predicted power quality value exceeds the limit, and combined with the real-time status of the hybrid energy storage system, a hierarchical collaborative governance and control strategy is executed to generate corresponding control commands for dynamic adjustment. Based on the dynamically adjusted power distribution control parameters, the power fluctuation signals that the system needs to respond to are decomposed by frequency and distributed to different types of energy storage units and the main power supply in the hybrid energy storage system.

2. The microgrid power quality management method based on time-series prediction and source-load-storage coordination as described in claim 1, characterized in that, The acquired data is input into the time-series prediction model to obtain predicted power quality values ​​for future times, including: Input meteorological and electrical data into the time-series forecasting model; The time series prediction model uses a multi-layer feedforward neural network trained with the backpropagation algorithm for prediction; Output Future Moments The power quality parameters, including frequency deviation. Total harmonic distortion of voltage and long-term flicker index .

3. The microgrid power quality management method based on time-series prediction and source-load-storage coordination as described in claim 2, characterized in that, A multi-objective optimization algorithm is used to collaboratively optimize the capacity configuration parameters and power allocation control parameters of a hybrid energy storage system, including: Establish a multi-objective optimization model that includes the aforementioned optimization objective and system operation constraints; The system operation constraints include: power balance constraints, state of charge constraints, and power limitation constraints. The multi-objective optimization algorithm jointly optimizes the rated capacity of different energy storage media and the filtering parameters in the power distribution control of the hybrid energy storage system.

4. The microgrid power quality management method based on time-series prediction and source-load-storage coordination as described in claim 3, characterized in that, Based on whether the predicted power quality value exceeds the limit, and in conjunction with the real-time status of the hybrid energy storage system, a hierarchical collaborative governance control strategy is executed to generate corresponding control commands for dynamic adjustment, including: If the predicted power quality value does not exceed the limit, the system will continue to operate according to the baseline configuration parameter set.

5. A microgrid power quality management method based on time-series prediction and source-load-storage coordination as described in claim 4, characterized in that, Based on whether the predicted power quality value exceeds the limit, and in conjunction with the real-time status of the hybrid energy storage system, a hierarchical collaborative governance control strategy is executed to generate corresponding control commands for dynamic adjustment, including: If the predicted power quality exceeds the limit and the state of the hybrid energy storage system meets the first preset condition, it enters the first-level governance state. The power distribution control parameters are dynamically adjusted, and the hybrid energy storage system is controlled to fully compensate for power fluctuations. The first preset condition is that the state of charge of the hybrid energy storage system is within a safe range.

6. The microgrid power quality management method based on time-series prediction and source-load-storage coordination as described in claim 5, characterized in that, Based on whether the predicted power quality value exceeds the limit, and in conjunction with the real-time status of the hybrid energy storage system, a hierarchical collaborative governance control strategy is executed to generate corresponding control commands for dynamic adjustment, including: If the predicted power quality exceeds the limit and the state of the hybrid energy storage system meets the second preset condition, it enters the secondary governance state; The hybrid energy storage system is controlled to output at maximum capacity, and load-side management operations are performed on the remaining power gap; the load-side management operations include cutting off or shifting the corresponding secondary loads according to preset load priorities; The second preset condition is that the state of charge of the hybrid energy storage system exceeds the safe range or its maximum output power is insufficient to compensate for the power fluctuation.

7. A microgrid power quality management method based on time-series prediction and source-load-storage coordination as described in claim 1 or 6, characterized in that, The power fluctuation signal that the system needs to respond to is decomposed by frequency based on the dynamically adjusted power distribution control parameters, specifically as follows: A multi-stage filtering structure is used to sequentially separate the power fluctuation signal into high-frequency components, mid-low frequency components, and fundamental smoothing components; The filtering structure includes at least one filtering parameter, which can be dynamically adjusted according to the disturbance characteristics indicated by the power quality prediction value to change the distribution ratio of different frequency components.

8. A microgrid power quality management system based on time-series prediction and source-load-storage coordination, employing the method described in any one of claims 1-7, characterized in that, include: The data acquisition module is used to acquire meteorological and electrical data; The prediction module is used to input the acquired data into the time series prediction model to obtain the predicted power quality values ​​for future times. The collaborative optimization module is used to perform collaborative optimization of the capacity configuration parameters and power distribution control parameters of the hybrid energy storage system with the main power output power, system investment cost, equipment life loss and power quality indicators as optimization objectives. It uses a multi-objective optimization algorithm to obtain a set of optimal benchmark configuration parameters for system configuration and operation. The decision module is used to execute a hierarchical collaborative governance control strategy and generate corresponding control commands for dynamic adjustment based on whether the predicted power quality value exceeds the limit and in combination with the real-time status of the hybrid energy storage system. The control module is used to decompose the power fluctuation signal that the system needs to respond to by frequency based on the dynamically adjusted power distribution control parameters, and distribute it to different types of energy storage units and the main power supply in the hybrid energy storage system for execution.

9. A computer device, characterized in that, include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the microgrid power quality management method based on time-series prediction and source-load-storage coordination as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores computer-executable instructions, which, when executed by a processor, implement the steps of the microgrid power quality management method based on time-series prediction and source-load-storage coordination as described in any one of claims 1 to 7.

Images