Intelligent energy storage control method, device and equipment based on bidirectional energy management

Abstract

The present invention relates to the technical field of intelligent energy storage control, and discloses an intelligent energy storage control method, device and equipment based on bidirectional energy management. The method includes: performing real-time acquisition and power grid state analysis on power grid parameters, energy storage module parameters, load demand and photovoltaic power generation data to obtain power grid state evaluation indexes and system operation mode division results; executing a multi-objective optimization algorithm to obtain an energy scheduling plan including charge and discharge power instructions; converting the energy scheduling plan into charge and discharge current control parameters and inputting them into a control structure composed of a prediction control layer and a real-time response control layer in a three-phase hybrid inverter to obtain power output data; uploading the power output data of multiple three-phase hybrid inverters to a smart management cloud platform and performing multi-machine parallel coordinated control to obtain a distributed energy network management scheme. The present invention predicts the system dynamic characteristics under different power flow directions, and enhances the stability and adaptability of the distributed energy network.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent energy storage control, and particularly to an intelligent energy storage control method, device and equipment based on bidirectional energy management. Background Art

[0002] A distributed energy network composed of a solar power generation system and an intelligent energy storage system has become one of the ideal topological structures to meet the electricity demand of modern households and businesses. However, this photovoltaic-grid-energy storage hybrid architecture faces many technical challenges in practical applications, including power supply instability caused by the mismatch between grid fluctuations and user electricity demand, power fluctuation management during peak and off-peak electricity consumption periods, and how to efficiently coordinate the mutual conversion and scheduling between multiple energy forms, which seriously affect the overall performance of the system and the user experience.

[0003] The rapid growth of modern household and commercial electricity consumption has led to continuous increases in electricity bills and peak electricity demand. Traditional energy management systems lack effective grid state perception and prediction capabilities and cannot flexibly adjust the charge and discharge strategies according to grid states and electricity price changes. At the same time, existing energy storage control methods often adopt simplified system models, ignoring the dynamic characteristics of the power flow direction and the complex interaction relationships between components of the system, and it is difficult to achieve precise power distribution and smooth energy conversion, especially in the case of large grid disturbances or rapid load changes. Summary of the Invention

[0004] The present invention provides an intelligent energy storage control method, device and equipment based on bidirectional energy management. The present invention predicts the system dynamic characteristics under different power flow directions and enhances the stability and adaptability of the distributed energy network.

[0005] In a first aspect, the present invention provides an intelligent energy storage control method based on bidirectional energy management. The intelligent energy storage control method based on bidirectional energy management includes:

[0006] Collect grid parameters, energy storage module parameters, load demands and photovoltaic power generation data in real time and analyze the grid state to obtain grid state evaluation indicators and system operation mode division results;

[0007] Based on the grid state evaluation indicators and the system operation mode division results, execute a multi-objective optimization algorithm to obtain an energy scheduling plan including charge and discharge power commands;

[0008] Convert the energy scheduling plan into charge and discharge current control parameters and input them into a control structure composed of a predictive control layer and a real-time response control layer in a three-phase hybrid inverter to obtain power output data;

[0009] Upload the power output data of multiple three-phase hybrid inverters to the intelligent management cloud platform, perform multi-machine parallel coordinated control, and obtain a distributed energy network management solution.

[0010] In a second aspect, the present invention provides an intelligent energy storage control device based on bidirectional energy management. The intelligent energy storage control device based on bidirectional energy management includes:

[0011] A real-time acquisition module, configured to perform real-time acquisition of grid parameters, energy storage module parameters, load demands, and photovoltaic power generation data, and analyze the grid state, so as to obtain grid state evaluation indicators and a system operation mode division result;

[0012] A multi-objective optimization module, configured to execute a multi-objective optimization algorithm based on the grid state evaluation indicators and the system operation mode division result, so as to obtain an energy scheduling plan including charge and discharge power instructions;

[0013] A predictive control module, configured to convert the energy scheduling plan into charge and discharge current control parameters, and input them into a control structure composed of a predictive control layer and a real-time response control layer in a three-phase hybrid inverter, so as to obtain power output data;

[0014] A parallel coordinated control module, configured to upload the power output data of multiple three-phase hybrid inverters to the intelligent management cloud platform, perform multi-machine parallel coordinated control, and obtain a distributed energy network management solution.

[0015] In a third aspect of the present invention, there is provided an intelligent energy storage control device based on bidirectional energy management, including: a memory and at least one processor, wherein instructions are stored in the memory; the at least one processor calls the instructions in the memory, so that the intelligent energy storage control device based on bidirectional energy management executes the above-mentioned intelligent energy storage control method based on bidirectional energy management.

[0016] In the technical solution provided by the present invention, through a high-precision and multi-frequency parameter real-time acquisition system, comprehensive monitoring of the power grid status, energy storage status, load demand, and photovoltaic power generation is achieved, providing a reliable data basis for system operation and making the identification of energy flow more accurate. Based on the power grid status evaluation mechanism of power grid harmonic content analysis and weighted average composite function, combined with the electricity price interval division technology of fuzzy clustering algorithm, the system can intelligently perceive the changes in the power grid status and automatically adjust the operation mode according to the electricity price characteristics. By introducing a parametric representation method of power flow, expressing the system matrix and input matrix as functions of three states: charging, discharging, and standby, the controller design is greatly simplified, and at the same time, the system dynamic characteristics under different power flows are accurately described. The multi-objective optimization algorithm is used for energy scheduling, comprehensively considering multiple objectives such as electricity cost, battery life, self-use rate of spontaneous power, and power grid interaction support degree, and dynamically adjusting the weight coefficients according to the system operation mode, realizing the optimal allocation of resources. A two-level control structure combining a predictive control layer and a real-time response control layer is designed, cooperating with a smooth transition strategy and a power smoothing algorithm, effectively suppressing system oscillations and power grid interaction power fluctuations, and ensuring the stable operation of the three-phase hybrid inverter under various working conditions. Through the intelligent management cloud platform, remote monitoring of system operation data and multi-machine parallel coordinated control are realized. By using the master-slave droop control algorithm and virtual synchronous machine technology, the stability and adaptability of the distributed energy network are enhanced, especially the autonomous operation ability during communication interruption. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0018] Figure 1 It is a schematic flowchart of an intelligent energy storage control method based on bidirectional energy management provided by an embodiment of the present application;

[0019] Figure 2 It is a schematic block diagram of the structure of an intelligent energy storage control device based on bidirectional energy management provided by an embodiment of the present application;

[0020] Figure 3 It is a schematic block diagram of the structure of an intelligent energy storage control device based on bidirectional energy management provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0022] The flowcharts shown in the accompanying drawings are only illustrative examples, and do not necessarily include all the contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged, so the actual execution order may change based on the actual situation.

[0023] It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification of this application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0024] It should be further understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0025] Next, some embodiments of this application will be described in detail in conjunction with the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0026] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of the intelligent energy storage control method based on bidirectional energy management provided by the embodiments of this application. As Figure 1 shown, the intelligent energy storage control method based on bidirectional energy management provided by the embodiments of this application includes steps S100 to S400.

[0027] Step S100: Real-time collect grid parameters, energy storage module parameters, load demands, and photovoltaic power generation data, and perform grid state analysis to obtain grid state evaluation indicators and system operation mode division results;

[0028] It can be understood that the execution subject of the present invention can be an intelligent energy storage control device based on bidirectional energy management, or a terminal or a server. Specifically, it is not limited here. The embodiments of the present invention will be described by taking the server as the execution subject as an example.

[0029] Specifically, high-precision sampling is carried out on the voltage, frequency, phase and electricity price information of the three-phase power grid to ensure that the measurement results of grid parameters have sufficient accuracy and real-time performance. The sampling process uses a high-frequency data acquisition module, and the sampling frequency is set to 10 kHz to capture the instantaneous changes of the power grid and transmit the obtained grid parameter data to the data processing unit for storage and subsequent analysis. At the same time, the state of charge of the battery pack, DC bus voltage, charge and discharge current, and battery temperature are continuously monitored. Among them, the state of charge SOC of the battery is an important parameter to measure the remaining capacity of the battery, while the DC bus voltage is used to judge the energy exchange situation between the battery and the system. The measurement of the charge and discharge current helps to calculate the power input and output of the battery, and the monitoring of the battery temperature can effectively prevent potential safety hazards caused by overheating. The power consumption of the user's load is continuously monitored to obtain complete load demand information. In this process, a power analyzer is used to measure the power consumption of the user's three-phase or single-phase load, identify the peak periods of the load and their change patterns, and the sampling frequency is set to once per minute to ensure the continuity and accuracy of the data. At the same time, the photovoltaic power generation monitoring module synchronously measures the electrical parameters such as the output voltage, current, and power of the photovoltaic array, as well as external influencing factors such as environmental irradiance and temperature, and obtains high-precision photovoltaic power generation data at a sampling frequency of 100 Hz. These data can reflect the real-time power output of photovoltaic power generation and, combined with environmental factors, are used to evaluate future power generation capabilities. All the collected grid parameters, energy storage module parameters, load demand data, and photovoltaic power generation data are uniformly transmitted to the data processing unit, which relies on the ARM Cortex-A53 processor to perform preprocessing tasks such as denoising, outlier detection, and missing value imputation on the data. In the denoising process, a weighted moving average filtering method is used to remove high-frequency noise interference, and at the same time, a median filtering algorithm is used to eliminate sudden outliers. In the outlier detection process, a threshold judgment model is constructed based on the historical data distribution. If the measured value exceeds the set range, it is corrected through an interpolation algorithm to ensure the continuity and accuracy of the data. For the missing values that appear, linear regression and Kalman filtering methods are used to complete them to ensure the integrity of the data. The preprocessed data will be stored in the local cache and archived in a unified data format, and a timestamp is marked for subsequent analysis. Based on the preprocessed data, by comparing the real-time values of photovoltaic power generation power, load demand power, battery charge and discharge power, and grid exchange power, the power flow direction is identified, and a system parameter data set is formed. In this process, a power flow direction identification model is established, and the power flow direction is divided into five basic modes, namely photovoltaic direct power supply mode, photovoltaic charging the battery mode, battery supplying power to the load mode, grid charging the battery mode, and battery feeding power to the grid mode.Calculate based on the real-time measured photovoltaic power generation, user load power, battery charge and discharge power, and grid exchange power, and judge the current power flow direction through the power balance relationship. If the photovoltaic power generation is greater than the load demand power and the remaining part is used to charge the battery, it is determined that the current is in the photovoltaic-to-battery charging mode; if the battery power supply is greater than the load demand power, it is determined as the battery-to-grid power transmission mode. Through real-time analysis, dynamically update the power flow information and form a system parameter data set. Analyze the grid state based on the system parameter data set to obtain the grid state evaluation index and the system operation mode division result.

[0030] Continuously monitor the three-phase voltage amplitude, phase difference, frequency and their volatility in the system parameter dataset to reflect the dynamic changes in the grid operation status. The data acquisition module collects the basic grid parameters in real time with high precision and high sampling rate, and obtains the monitoring results of the basic grid parameters by calculating the voltage amplitude change rate, phase deviation and frequency fluctuation between adjacent sampling points. Perform Fourier transform on the monitoring results of the basic grid parameters, extract the harmonic components in the grid signal, and calculate the amplitude of each order harmonic and the total harmonic distortion rate THD to obtain the analysis result of the grid harmonic content. Based on the analysis result of the grid harmonic content, use the weighted average composite function calculation method to comprehensively evaluate the grid status and determine the grid status evaluation index. This calculation method constructs a grid status evaluation model by performing weighted summation on multiple key factors such as grid frequency stability, phase consistency, voltage volatility and harmonic distortion. In this model, the weight coefficient of each parameter is obtained through training based on historical operation data to ensure that the evaluation index can accurately reflect the actual situation of the grid status. The numerical range of the grid status evaluation index calculated by the system is set between 0 and 100. When the index value is higher than 85, it means the grid is in a stable state; when the index value is between 60 and 85, it indicates that the grid is in a fluctuating state; and when the index value is lower than 60, the grid status is determined to be abnormal. Through this calculation process, accurately evaluate the grid status, and determine the stability level of the grid based on this evaluation index to obtain the grid status determination result. At the same time, combine the electricity price information to ensure that the division of the operation mode optimizes the energy management while reducing the economic cost. After obtaining the real-time electricity price data in the system parameter dataset, use the fuzzy clustering algorithm to intelligently divide the electricity price and obtain the classification results of different electricity price intervals. The fuzzy clustering algorithm dynamically adjusts the clustering center by analyzing the time series change characteristics of the electricity price and combining the local electricity price policy to ensure the rationality of the electricity price division. Set three main electricity price intervals, where the electricity price in the peak interval is higher than 130% of the average daily electricity price, the electricity price in the valley interval is lower than 80% of the average daily electricity price, and the interval between the two is classified as the flat peak interval. Through this process, identify the high and low electricity price periods and adapt to the electricity price structure in different regions. Divide the system operation mode according to the grid status determination result and the electricity price interval division result, and determine multiple operation modes including charging priority mode, discharging priority mode, self-consumption priority mode, grid support mode, off-grid standby mode and emergency protection mode. When the grid status is in a stable state and the electricity price is in the valley interval, automatically enter the charging priority mode. In this mode, the battery energy storage system uses low-cost electricity for charging to reduce the subsequent electricity consumption cost. When the grid status remains stable but the electricity price enters the peak interval, switch to the discharging priority mode, so that the energy storage battery supplies power to the load to reduce the grid power purchase volume during high electricity price periods.If the photovoltaic power generation is high and can meet the load demand, it enters the self-consumption priority mode, where photovoltaic power generation supplies the load first and charges the battery when there is surplus power, so as to increase the self-use rate of photovoltaic power generation. When the grid state is fluctuating, it enters the grid support mode, and the energy storage system supports the grid through the two-way power regulation function to alleviate the grid fluctuation problem and enhance the system stability. If the grid state further deteriorates and enters the abnormal state, it automatically switches to the off-grid standby mode to ensure the uninterrupted power supply of critical loads. In this mode, the energy storage system relies on its own battery reserve to provide continuous power supply for important loads to avoid the abnormal operation of the power consumption terminal due to grid faults. When the system detects abnormalities in the energy storage device itself, such as too high battery temperature, abnormal charge and discharge current or communication failure, it immediately enters the emergency protection mode and executes a series of safety protection measures, such as disconnecting the charge and discharge circuit, reducing the output power or completely stopping the system operation, to prevent equipment damage or safety accidents.

[0031] Step S200: Based on the grid state evaluation index and the system operation mode division result, execute the multi-objective optimization algorithm to obtain an energy scheduling plan including charge and discharge power instructions;

[0032] Specifically, the three-phase hybrid inverter system is structurally simplified and divided into an interconnected system on the grid side, DC bus side, and load side to establish a mathematical model. In this system, the grid side is connected to the DC bus through a bidirectional AC / DC converter, and the DC bus is simultaneously connected to the energy storage unit and the photovoltaic input terminal, thus forming an energy interaction framework. The load side is connected to the DC bus through a DC / AC converter to ensure that the load can obtain stable AC electrical energy. To quantify the operating state of the system, a system state vector is defined, which includes the DC bus voltage, state of charge of the battery, grid exchange power, load power, and photovoltaic power generation. These variables can comprehensively describe the energy flow of the system and form a simplified model of the system. On this basis, a control input vector is defined, which includes a charging current command and a discharging current command. These two variables determine the energy inflow and outflow of the battery and are therefore the core control quantities for the energy storage system scheduling. Combining the system state vector and the control input vector, a system control model is constructed, and based on this, a discrete-time state equation of the system is established to form a discrete-time mathematical model of the system suitable for digital control and predictive optimization. Since the energy management of the energy storage system involves three operating states: charging, discharging, and standby, an electric energy flow parameter is introduced into the mathematical model to enable it to reflect the system dynamic characteristics in different modes. The electric energy flow parameter is defined, which consists of the activation degrees of the charging, discharging, and standby states. The activation degree of each state varies between 0 and 1 and satisfies the constraint relationship that their sum is 1 to ensure the uniqueness and identifiability of the system state. To accurately describe the operating characteristics of the energy storage system in different electric energy flow modes, a corresponding sub-model parameter matrix is established for each electric energy flow state to obtain a discrete-time system model. In the charging mode, the parameter matrix of the system needs to include a charging efficiency coefficient to ensure accurate modeling of the battery energy absorption process. In the discharging mode, the discharging efficiency coefficient is introduced into the system parameter matrix to reflect the energy loss when the battery releases energy to the load or the grid. In the standby mode, considering the self-discharge characteristics of the battery, the corresponding parameter matrix should include an equivalent coefficient that can describe the static loss of the battery to ensure accurate description of the standby state in the mathematical model. The recursive least squares method is used to update the parameters of the discrete-time system model to dynamically adjust the model parameters so that they can adapt to the effects of factors such as battery aging, grid fluctuations, and environmental changes. Historical data is used to train the initial parameters, and the model is gradually corrected based on real-time measurement data to ensure that the system model can maintain a high prediction accuracy under different operating conditions. Since the change of the DC bus voltage and the dynamic change of the state of charge of the battery will affect the non-linear characteristics of the charging and discharging processes, these non-linear factors are considered in the model update process, and a battery equivalent internal resistance model is introduced to correct the charging and discharging power calculation formula of the system to ensure the accuracy of the optimization calculation. Through the model update process, the electric energy flow parameters accurately representing the charging, discharging, and standby states are obtained.According to the power flow parameters, power grid state evaluation indicators, and the division results of the system operation mode, execute a multi-objective optimization algorithm to calculate the optimal energy scheduling plan including charge and discharge power instructions.

[0033] Define the optimization objective function based on the power flow parameters and multi-objective optimization algorithm. This objective function comprehensively considers four core objectives: minimizing electricity cost, maximizing battery service life, maximizing the self-use rate, and maximizing the grid interaction support degree. At the same time, dynamically adjust the weight coefficients in the optimization objective function according to the division result of the system operation mode to ensure that the optimization objectives can be adaptively adjusted under different operation modes. Calculate the dynamic weight coefficients in real time according to the current grid state and operation mode, and train the optimization weight adjustment strategy through historical data. For example, in the charging priority mode, the weight coefficient of minimizing electricity cost increases, while in the discharging priority mode, the weight coefficient of optimizing battery life increases. In the self-consumption priority mode, the weight coefficient of the self-use rate dominates, and in the grid support mode, the weight coefficient of the grid interaction support degree will be greatly improved. The optimization algorithm reasonably allocates weights in the objective function according to the priorities of different modes to ensure that the scheduling strategy meets the current operation requirements of the system. After determining the optimization objective function, set the optimization constraint conditions based on the dynamic weight coefficients to ensure that the optimized scheduling results can operate within the physical and technical limits. The optimization constraint conditions mainly include battery state of charge limit, charge and discharge power limit, grid exchange power limit, and power balance constraint. Among them, the battery state of charge limit ensures that the working range of the battery does not exceed the minimum and maximum values of SOC to prevent overcharging or over-discharging; the charge and discharge power limit ensures that the charge and discharge rate of the battery does not exceed the allowed safety range to protect the battery health; the grid exchange power limit controls the power exchange volume between the system and the grid to ensure that no unnecessary impact is imposed on the grid; the power balance constraint ensures the energy conservation among the photovoltaic power generation, load power, battery charge and discharge power, and grid exchange power, thus maintaining the system stability. After determining the constraint conditions, predict the grid electricity price, load demand, and photovoltaic power generation based on the system parameter dataset to obtain the prediction results of the system future state. This process uses time series prediction methods. Among them, the grid electricity price prediction is modeled based on historical electricity price data and market trends, and the long short-term memory network (LSTM) or autoregressive integrated moving average model (ARIMA) is used to predict the electricity price fluctuation trend in the next 24 hours; the load demand prediction analyzes the historical load curve, time characteristics, and weather factors, and uses a hybrid prediction method based on regression analysis and neural network to obtain accurate load demand prediction values; the photovoltaic power generation prediction is modeled using irradiance, temperature, and historical power generation data, and the recurrent neural network (RNN) or support vector regression (SVR) algorithm is used to predict the future power generation power distribution. Through these prediction models, obtain the future grid electricity price changes, user load demands, and photovoltaic power generation capabilities in advance. Based on the prediction results of the system future state and the optimization constraint conditions, transform the optimization problem into a quadratic programming form and solve it through the interior point method to obtain the preliminary optimization results.The core of the quadratic programming optimization method lies in minimizing the objective function while satisfying all constraint conditions, so that the finally obtained charge and discharge strategy realizes optimal energy management under different operating modes. In this process, based on the electricity price, load demand and photovoltaic power generation prediction data for the next 24 hours, the optimal charge and discharge power distribution at different time steps is calculated, and an optimization problem is constructed through a quadratic programming model, where the objective function contains multiple optimization sub-objectives and is adjusted using dynamic weight coefficients. The interior point method is used for solution, which can efficiently solve large-scale optimization problems and ensure the global optimality of the optimization results while guaranteeing computational stability. Through this optimization process, a preliminary optimization result that conforms to the grid state, energy storage requirements and economic objectives is calculated to ensure that the charge and discharge scheduling strategy can be reasonably adjusted under different working conditions. The rolling horizon processing is performed on the preliminary optimization result to generate a final energy scheduling plan containing charge and discharge power commands. The rolling horizon processing is to execute only the result of the first time step obtained by the optimization calculation within a certain optimization window each time, and slide the window to recalculate during the next optimization, so as to achieve continuous dynamic optimization. An optimization window of 6 hours is adopted, and the optimization is updated every 15 minutes to ensure that the optimized scheduling can continuously adapt to the changes in the real-time operating environment. At the same time, in order to reduce the computational complexity, only the charge and discharge power of the most recent time step is adjusted during each rolling optimization, and the control variables of the remaining time steps are provided as a reference by the previous optimization result. The energy scheduling plan after the rolling optimization processing contains charge and discharge power commands within the next 24 hours and is dynamically adjusted every 15 minutes to ensure that the energy storage system can achieve optimal scheduling under a complex grid environment and fluctuating load demands.

[0034] Step S300: Convert the energy scheduling plan into charge and discharge current control parameters and input them into the control structure composed of a predictive control layer and a real-time response control layer in a three-phase hybrid inverter to obtain power output data;

[0035] Specifically, the charge and discharge power commands in the energy scheduling plan are converted to obtain the charge and discharge current control parameters. Since the relationship between the power and current of battery charging and discharging is affected by the DC bus voltage, the calculation of charging current and discharging current needs to consider the change of instantaneous bus voltage to ensure the accuracy of current calculation. The charging current is obtained by the ratio of the power command to the real-time bus voltage, while the discharging current also depends on the current bus voltage and is corrected by combining the equivalent internal resistance of the battery, so as to generate accurate charge and discharge current control parameters. The charge and discharge current control parameters are input into the control structure of the three-phase hybrid inverter, which consists of a predictive control layer and a real-time response control layer, to ensure that the control system can not only predict the system state in advance but also quickly respond to the changes of the power grid and load. Among them, the predictive control layer uses a bidirectional long short-term memory network, which uses historical data to predict future charge and discharge current requirements and obtains the dynamic characteristics of the system through time series modeling, so as to calculate a reasonable current reference value. This current reference value is transmitted to the real-time response control layer, which adopts a double closed-loop control structure. The inner loop is the current loop, which is responsible for the precise regulation of current, and the outer loop is the power loop, which is used to maintain the system power balance and optimize the power output characteristics. Through the double-layer control method, accurate charge and discharge control can be achieved under different operating modes, and at the same time, it has strong dynamic adaptability. In the predictive control layer, the bidirectional long short-term memory network is trained by historical data of grid state, load demand, photovoltaic power generation, and battery state of charge, and combined with the current system state for predictive calculation to obtain the future current reference value. Since the bidirectional LSTM network considers both past and future time series characteristics, it can accurately predict the current change trend in a complex energy storage system environment and effectively reduce the impact of external disturbances on current control. After the predictive calculation is completed, the current reference value is input into the real-time response control layer. In this control layer, the current loop is optimized offline using a proportional-integral controller and adaptively adjusted online in combination with real-time data during system operation to compensate for errors caused by grid fluctuations, load changes, and environmental impacts, and obtain a more stable current control signal. Based on the current control signal, power tracking control is performed through the power loop, where the power loop compares the reference power with the actual power and dynamically adjusts the current command according to the power error to ensure that the system output power meets the requirements of the optimal scheduling plan. To improve the anti-disturbance ability of power tracking, a feed-forward compensation mechanism is introduced, which adjusts the current command in advance according to the changes in the load power and photovoltaic power generation power monitored in real time to compensate for the power fluctuations caused by external condition changes, thereby improving the dynamic response ability of the system. Under the control of the power flow parameters, a seamless switching mechanism is designed to ensure a smooth transition between different operating modes and avoid current shocks or power fluctuations caused by mode switching. In the implementation process of the seamless switching mechanism, an exponential decay function is used as the smooth transition strategy of the power command to ensure the smoothness of the power adjustment process.The exponential decay function sets the rate of power adjustment according to the time constant, enabling the system to gradually adjust to the new operating state during the charge-discharge mode switch without sudden impact. When the system switches from the charging mode to the discharging mode, or from the discharging mode to the standby mode, the exponential decay function gradually reduces or increases the power command to ensure a smooth transition of power output during the system switch. The time constant of the exponential decay function is adaptively adjusted according to the battery type. For example, the time constant of the lithium iron phosphate battery is set to 200 ms, while that of the ternary lithium battery is set to 150 ms to match the charge-discharge characteristics of different types of batteries. To improve the grid adaptability of the system, the control signal of smooth switching is combined with the virtual impedance drop control strategy to optimize the regulation ability of the grid exchange power. The virtual impedance drop control strategy enables the system to better respond to the fluctuations of the grid voltage by simulating the equivalent impedance characteristics of the energy storage system and optimizes the support effect of the system on the grid by dynamically adjusting the impedance parameters. At the same time, for the grid exchange power, a power smoothing algorithm based on moving average is applied. This algorithm stabilizes the grid power output and adaptively adjusts the smoothing window size according to the grid state. For example, when the grid is in a stable state, the power smoothing window is set to 5 minutes, while when the grid is in a fluctuating state, the smoothing window is reduced to 2 minutes to improve the response speed of the system to grid fluctuations. After the calculations and optimizations of all control links, the finally calculated power control signal is converted into actual power output data through the IGBT power module. During this process, the IGBT module accurately adjusts the switching frequency and pulse width according to the system control instructions to ensure that the quality of the inverter output power meets the requirements of the grid and the load. During the entire power conversion process, the system continuously monitors the real-time data of the output power and compares it with the reference power to ensure that the final output power meets the requirements of the dispatching plan, thus realizing the efficient and stable operation of the energy storage system.

[0036] Step S400: Upload the power output data of multiple three-phase hybrid inverters to the intelligent management cloud platform, perform multi-machine parallel coordinated control, and obtain a distributed energy network management solution.

[0037] Specifically, collect the system parameter datasets, power flow parameters, and power output data of multiple three-phase hybrid inverters respectively, and upload them to the intelligent management cloud platform through a secure encrypted transmission protocol to ensure that the data will not be maliciously tampered with or leaked during the transmission process. The data upload frequency is classified according to the importance of the parameters. Among them, the upload period of key status parameters is set to 10 seconds to ensure real-time performance, while general operation parameters are uploaded once a minute, and historical statistical data is stored at 15-minute intervals for subsequent analysis. In terms of data storage, a distributed database is used for management, and combined with time series database technology, high-frequency collected time series data is efficiently processed to form structured storage data. Based on the structured storage data, a remote monitoring and control architecture is established, which includes a data display layer, an analysis and decision-making layer, and a remote control layer to ensure that the cloud platform can provide complete visualization, intelligent analysis, and remote regulation functions. In the data display layer, real-time monitoring functions are provided through a Web interface and a mobile application, enabling users to view the operating status of the energy storage system at any time, including important information such as the system topology diagram, power flow diagram, energy storage status indication, and grid interaction situation, and through dynamic data visualization technology, the interface can update the system operating conditions in real time. In the analysis and decision-making layer, big data technology is used to analyze the power consumption pattern, combined with historical data, to identify the periodic change trend of the user load, and at the same time predict the future energy demand and photovoltaic power generation, and optimize the energy management strategy based on machine learning algorithms. In the remote control layer, the system allows authorized users to send control commands through the cloud platform, including adjusting the battery charge and discharge strategy, setting the power distribution ratio, switching the operating mode, etc., and provides a remote access mechanism based on permission management to ensure the security and reliability of control permissions. Through the construction of the remote monitoring and control architecture, centralized management of multiple inverters is realized. With the support of the remote monitoring and control architecture, multiple parallel three-phase hybrid inverters are divided, and one is set as the master inverter, which is responsible for global resource scheduling, and the rest of the inverters are used as slave inverters, receiving the instructions sent by the master inverter and performing corresponding operations. The master inverter obtains global data through the cloud platform, and calculates a reasonable power sharing ratio according to the capacity, load conditions, and energy storage status of each inverter, thus forming an efficient master-slave control structure. In this structure, the master inverter is responsible for global energy optimization scheduling, while monitoring the operating status of the slave inverters, and adjusting the power distribution strategy when necessary to ensure the stability and efficiency of the entire system. The slave inverters execute the corresponding charge and discharge tasks according to the instructions of the master inverter, and feedback their operating status to the master inverter so that the master inverter can adjust the control strategy in real time to achieve dynamic optimization. Based on the master-slave control structure, a master-slave droop control algorithm is adopted to ensure the balanced distribution of power in the multi-machine parallel system.The droop control algorithm enables each inverter to automatically allocate power according to its own capacity and load conditions by adjusting the frequency and voltage output characteristics of the inverter, without the need for complex centralized control. The system dynamically adjusts the droop characteristic curve based on the rated power of each inverter to ensure that power can be reasonably distributed among multiple inverters when the load changes, while avoiding the failure of a certain inverter due to overload. In practical applications, the master inverter continuously monitors the load changes of the entire system and adjusts the droop control parameters to optimize the power distribution effect. When the load suddenly changes, the system quickly adjusts the droop curve to ensure the stable operation of the entire parallel system, while reducing the impact of power fluctuations on the power grid, thereby improving the overall reliability of the system. Based on the multi-machine power equalization distribution scheme, the virtual synchronous machine technology is introduced to enhance the power grid adaptability of the parallel inverter cluster. The virtual synchronous machine technology simulates the inertia characteristics of traditional synchronous generators, enabling the energy storage system to provide a response ability similar to physical rotational inertia when operating in parallel with the grid, thereby improving the system's adaptability to grid frequency fluctuations. A synchronous inertia model is introduced into the controller of each inverter, and active frequency control is achieved through power regulation between inverters, enabling the system to automatically adjust the output power when the grid is disturbed to mitigate the impact of grid fluctuations on the energy storage system. The system uses the CAN bus for multi-machine communication to ensure that the information exchange between the master inverter and slave inverters has sufficient real-time performance and reliability. The communication cycle of the CAN bus is set to 10 milliseconds to ensure that all inverters can quickly share the operating status and control instructions and respond within milliseconds, thereby achieving precise multi-machine coordinated control. In the distributed energy network management scheme, the operation safety in case of communication interruption is considered. When a communication failure occurs on the CAN bus, the system automatically switches to the independent operation mode, that is, each inverter operates independently according to local measurement data and preset strategies to ensure that the entire energy storage system can still operate normally even in the case of communication failure. When the master inverter detects communication anomalies, it will trigger the local control mode. Each slave inverter will continue to operate according to the latest power distribution instructions and dynamically adjust the charge and discharge strategies according to the locally measured load conditions to minimize the impact of communication interruption on the system operation. At the same time, the system attempts to re-establish the communication connection and re-enter the master-slave control mode after the communication is restored to ensure that the system can quickly resume the normal operation state.

[0038] In the embodiments of the present invention, through a high-precision and multi-frequency parameter real-time acquisition system, comprehensive monitoring of the power grid state, energy storage state, load demand, and photovoltaic power generation is realized, providing a reliable data basis for system operation and making the identification of energy flow direction more accurate. Based on the power grid state evaluation mechanism of power grid harmonic content analysis and weighted average composite function, combined with the electricity price interval division technology of fuzzy clustering algorithm, the system can intelligently perceive the changes in the power grid state and automatically adjust the operation mode according to the electricity price characteristics. The parametric representation method of power flow is introduced, and the system matrix and input matrix are expressed as functions of three states: charging, discharging, and standby, greatly simplifying the controller design and accurately describing the system dynamic characteristics under different power flow directions. The multi-objective optimization algorithm is used for energy scheduling, comprehensively considering multiple objectives such as electricity cost, battery life, self-use rate of spontaneous power generation, and power grid interaction support degree, and dynamically adjusting the weight coefficients according to the system operation mode, realizing the optimal allocation of resources. A two-level control structure combining a predictive control layer and a real-time response control layer is designed, cooperating with a smooth transition strategy and a power smoothing algorithm, effectively suppressing system oscillation and power grid interaction power fluctuation, and ensuring the stable operation of the three-phase hybrid inverter under various working conditions. Through the intelligent management cloud platform, remote monitoring of system operation data and multi-machine parallel coordinated control are realized. The master-slave droop control algorithm and virtual synchronous machine technology are adopted to enhance the stability and adaptability of the distributed energy network, especially the autonomous operation ability during communication interruption.

[0039] In a specific embodiment, the process of executing step S100 may specifically include the following steps:

[0040] Sample the voltage, frequency, phase, and electricity price information of the three-phase power grid to obtain the measurement results of power grid parameters; monitor the state of charge of the battery pack, the DC bus voltage, the charge and discharge current, and the battery temperature to obtain the measurement results of energy storage module parameters; collect the power consumption of the user's three-phase or single-phase load to obtain the load demand monitoring results; measure the output voltage, current, power, environmental irradiance, and temperature of the photovoltaic array to obtain the photovoltaic power generation monitoring results;

[0041] Transmit the measurement results of power grid parameters, energy storage module parameters, load demand monitoring results, and photovoltaic power generation monitoring results to the data processing unit, and perform preprocessing such as denoising, outlier detection, and missing value interpolation to obtain preprocessed data;

[0042] Based on the preprocessed data, identify the power flow direction by comparing the real-time values of photovoltaic power generation power, load demand power, battery charge and discharge power, and grid exchange power to obtain a system parameter data set;

[0043] Analyze the power grid state according to the system parameter data set to obtain the power grid state evaluation index and the system operation mode division result.

[0044] Specifically, sensors installed on the grid side capture three-phase voltage, frequency, and phase information at a high sampling rate, and combine with smart meters to obtain real-time electricity price information. The update frequency of these data is usually in the millisecond level to ensure that the system accurately reflects the changes in the grid state. At the same time, current, voltage, and temperature sensors inside the energy storage module continuously collect the state of charge of the battery, and calculate the state of health of the battery through the built-in management system to predict the available capacity and performance degradation of the battery. The power consumption of the user load is accurately monitored to grasp the real-time demand of the load. The load measurement module records the power consumption of three-phase or single-phase loads and identifies the peak power consumption periods of the load to form the load change pattern of the user. At the same time, to ensure the application effect of the system in the photovoltaic power generation system, the output voltage, current, power, and environmental irradiance and temperature of the photovoltaic array are measured to obtain the real-time state of photovoltaic power generation. The photovoltaic monitoring module can record the working state of photovoltaic modules at a high frequency and analyze the influence of environmental factors in combination with meteorological sensors. For example, on cloudy or rainy days, the output power of the photovoltaic array drops significantly, while on sunny days, more electrical energy can be generated. These data can help the system optimize the utilization strategy of photovoltaic electrical energy and improve the self-use rate. Transmit the grid parameter measurement, energy storage module parameter measurement, load demand monitoring, and photovoltaic power generation monitoring data to the data processing unit, and perform a series of preprocessing on the original data to improve the accuracy and reliability of the data. In this process, denoising technology is used to smooth the data to eliminate abnormal fluctuations caused by sensor noise or environmental interference. To prevent the influence of outliers caused by measurement errors, threshold detection and statistical methods are used to detect outliers in the data, and interpolation technology is used to fill in the missing data caused by signal loss. After the data is preprocessed, electricity flow identification is performed based on these data to analyze the energy distribution of the current energy storage system. The core of electricity flow identification is to compare the real-time values of photovoltaic power generation power, load demand power, battery charge and discharge power, and grid exchange power, and judge the current energy flow pattern. The determination of the electricity flow can help the system optimize the energy storage management strategy and provide alarm information when necessary. For example, if the system detects that the battery charging current is too large while the photovoltaic power generation power is insufficient, it means that there is an abnormality in the system and inspection is required. After completing the electricity flow identification, analyze the grid state and calculate the grid state evaluation index to determine the operating condition of the grid. For example, by calculating the stability of the three-phase grid voltage, phase consistency, frequency volatility, and harmonic content, a comprehensive score of the grid state is formed, which can reflect the health status of the grid. In some scenarios, when the grid frequency fluctuates greatly or the harmonic content exceeds the set threshold, it is determined that the grid is in a fluctuating state, and corresponding measures are taken, such as restricting the power of the grid to charge the battery, or reducing the rate of the battery discharging to the grid, to reduce the impact on the grid.Meanwhile, combined with real-time electricity price information, an economic analysis of the power grid status is carried out. For example, when the power grid electricity price is at a low valley, even if the power grid status evaluation index is low, it is preferred to purchase electricity from the power grid for charging to reduce the overall operating cost. Based on these data, the division of the system operation mode is completed. For example, when the power grid status is good and the electricity price is at a low valley, it enters the charging priority mode, and when the power grid status is poor and the battery is fully charged, it enters the discharging priority mode, so as to achieve optimal energy storage management.

[0045] In a specific embodiment, the process of performing the step of analyzing the power grid status according to the system parameter data set to obtain the power grid status evaluation index and the system operation mode division result may specifically include the following steps:

[0046] Continuously monitor the three-phase voltage amplitude, phase difference, frequency and their volatility of the power grid in the system parameter data set to obtain the power grid basic parameter monitoring result, and perform Fourier transform on the power grid basic parameter monitoring result to obtain the power grid harmonic content analysis result;

[0047] Perform a weighted average composite function calculation based on the power grid harmonic content analysis result to obtain the power grid status evaluation index;

[0048] Divide the power grid status into a stable state, a fluctuating state and an abnormal state according to the power grid status evaluation index to obtain the power grid status determination result;

[0049] Perform fuzzy clustering on the real-time electricity price data in the system parameter data set to obtain the electricity price interval division result;

[0050] Divide the system operation mode according to the power grid status determination result and the electricity price interval division result to obtain the system operation mode division result including a charging priority mode, a discharging priority mode, a self-consumption priority mode, a power grid support mode, an off-grid standby mode and an emergency protection mode.

[0051] Specifically, high-precision sensors are used to collect key parameters on the grid side in real time and continuously record them through a data acquisition unit to ensure that the system can accurately reflect the operating state of the grid. A high-sampling-rate data acquisition module is adopted to capture the instantaneous changes in voltage, phase, and frequency at a millisecond-level sampling frequency, and the short-time sliding window technique is used to calculate the volatility to measure the dynamic stability of the grid. Fourier transform is performed on the monitoring results of the grid's basic parameters to extract the harmonic content of the grid and analyze the impact of high-order harmonics on the grid stability. The collected grid signals are transformed from the time domain to the frequency domain, and the amplitude distribution of each harmonic is calculated to identify the harmonic distortion of the grid. The harmonic characteristics of the grid are analyzed through Fourier transform to identify whether the grid is interfered by nonlinear loads and corresponding optimization measures are taken. Based on the analysis results of the grid harmonic content, a weighted average composite function calculation is performed to comprehensively measure the grid state and determine the grid state evaluation index. According to the three-phase voltage stability, phase consistency, frequency volatility, and harmonic distortion degree, the scores of each sub-index are calculated respectively, and these sub-indices are synthesized into a unified grid state evaluation value through the weighted average method. The operating state of the grid is divided based on the grid state evaluation index to determine whether the grid is currently in a stable state, a fluctuating state, or an abnormal state. When the grid state evaluation index is in a higher range, it is considered that the grid operates stably. At this time, the energy storage system normally performs charge and discharge operations according to the dispatching plan without affecting the safety of the grid. If the grid state evaluation index is in a medium range, it indicates that there is a certain degree of fluctuation in the grid, and the energy dispatching strategy needs to be adjusted to reduce the impact on the grid. For example, when the grid state is in a fluctuating state, the energy storage system reduces the rate of injecting power into the grid to prevent further unstable effects on the grid caused by power changes. When the grid state evaluation index drops to a lower range, indicating that the grid is in an abnormal state, the system takes emergency measures, such as switching to the off-grid mode, to ensure the stable power supply of important loads and avoid the unstable operation of the energy storage system caused by grid faults. After the grid state is determined, the electricity price information is analyzed to optimize the economic operation strategy of the energy storage system. Fuzzy clustering is performed on the real-time electricity price data in the system parameter dataset to divide the electricity price intervals and provide a basis for subsequent energy dispatching. Using historical electricity price data and current market electricity price information, the change trend of the electricity price is identified, and the electricity price is divided into three intervals: peak, flat, and valley through the fuzzy clustering algorithm. According to the grid state determination result and the electricity price interval division result, the operating mode of the energy storage system is determined to ensure that the system can not only meet the stability requirements of the grid operation but also optimize the economic benefits of the energy storage system. The system operating modes include charge priority mode, discharge priority mode, self-consumption priority mode, grid support mode, off-grid standby mode, and emergency protection mode. When the grid state is stable and the electricity price is in the valley interval, the system enters the charge priority mode and preferentially uses low-cost electricity to charge the battery to reduce the electricity purchase cost during future high-electricity-price periods.When the power grid is stable and the electricity price is in the peak range, the system enters the discharge priority mode, and preferentially releases the electric energy of the energy storage battery to the load to reduce the electricity purchase volume during high electricity price periods. When the photovoltaic power generation is sufficient and the power grid is stable, the system enters the self-consumption priority mode, enabling the photovoltaic electric energy to be preferentially supplied to the load and charging the energy storage to reduce the electricity purchase volume from the power grid and improve the utilization rate of renewable energy. When the power grid state is in a fluctuating state, the system switches to the power grid support mode. In this mode, the energy storage system adjusts the charge and discharge power to reduce the impact of power grid fluctuations on the load. In the event of an abnormal power grid state, the system automatically enters the off-grid standby mode to ensure uninterrupted power supply to critical loads. When the system detects an abnormality in the energy storage device itself, such as too high battery temperature or abnormal charge and discharge current, the system enters the emergency protection mode and takes a series of safety measures, such as disconnecting the charge and discharge circuits or reducing the power output, to prevent equipment damage or safety accidents.

[0052] In a specific embodiment, the process of executing step S200 may specifically include the following steps:

[0053] Simplify the three-phase hybrid inverter system into an interconnected system of the grid side, DC bus side, and load side, define the system state vector, and obtain the system simplified model;

[0054] Based on the system simplified model, define the control input vector including the charge current command and discharge current command to obtain the system control model;

[0055] Establish the system discrete-time state equation according to the system control model to obtain the system discrete-time mathematical model, and introduce the power flow direction into the system discrete-time mathematical model to obtain the parameterized system model. The power flow directions include charging, discharging, and standby;

[0056] For each power flow direction in the parameterized system model, establish the corresponding sub-model parameter matrix to obtain the discrete-time system model, where the charging state includes the charging efficiency coefficient, the discharging state includes the discharging efficiency coefficient, and the standby state reflects the self-discharge characteristics;

[0057] Perform parameter update of the recursive least squares method on the discrete-time system model, and consider the non-linear relationship between the DC bus voltage change and the state of charge of the battery to obtain the power flow parameters characterizing the charging, discharging, and standby states;

[0058] According to the power flow parameters, the power grid state evaluation index, and the system operation mode division result, execute the multi-objective optimization algorithm to obtain the energy scheduling plan including the charge and discharge power commands.

[0059] Specifically, the three-phase hybrid inverter system is simplified to describe the energy flow and control logic of the system in a more intuitive way. The system is divided into three main parts: the grid side, the DC bus side, and the load side. The grid side is connected to the DC bus through a bidirectional AC / DC converter. The DC bus side is connected to the energy storage battery and the PV input. The load side is connected to the DC bus through a DC / AC converter, enabling the entire system to flexibly switch the power flow under different operating conditions. Under this framework, the core variables of the system include the DC bus voltage, the state of charge of the battery, the grid exchange power, the load power, and the PV power generation power. These variables together constitute the system state vector, thereby establishing a simplified model of the system for subsequent control and optimization calculations. Based on the simplified model, control input variables are defined to determine the regulation strategy of the system. Since the main control objective of the energy storage system is to manage the charge and discharge process, the control input vector includes the charge current command and the discharge current command. These two variables directly determine the charge and discharge rate of the battery and simultaneously affect the change of the DC bus voltage. To describe the dynamic behavior of the system, a control model of the system is established based on the control input vector and the state variables, and a discrete-time state equation of the system is constructed to obtain a complete mathematical description. In this process, considering the energy exchange relationship between the grid side, the DC bus side, and the load side, the discrete-time mathematical model of the system needs to comprehensively consider the battery charge and discharge characteristics, the grid interaction power, and the load dynamic demand, and incorporate these factors into the state update equation to ensure that the model can accurately describe the system characteristics under different operating modes. An electric energy flow parameter is introduced into the discrete-time mathematical model of the system, enabling the system to dynamically adjust according to different operating modes. The electric energy flow parameters include three states: charge, discharge, and standby. The activation degree of each state is represented by a normalized parameter, and the sum of these parameters is always 1 to ensure that the system is only in one of these three states at any time. For example, in the charging mode, the charge current flow parameter is close to 1, while the discharge current flow parameter and the standby current flow parameter are close to 0. In the discharge mode, the discharge current flow parameter dominates, while the charge current flow parameter and the standby current flow parameter are small. In the standby state, all current flow parameters are evenly distributed to reflect that the system is in a static equilibrium state. By introducing the electric energy flow parameter, the system state equation can flexibly adapt to different operating modes, thereby improving the adaptability of the control strategy. On this basis, corresponding sub-model parameter matrices are established for different electric energy flow states to construct a discrete-time system model. In the charging state, the parameter matrix of the system needs to include a charge efficiency coefficient to describe the conversion loss during the battery energy absorption process. In the discharge state, the parameter matrix of the system needs to consider the discharge efficiency to accurately calculate the proportion of energy released by the battery to the load or the grid. For the standby state, since there is still a certain self-discharge loss in the battery, the parameter matrix needs to include the self-discharge characteristics to ensure that the actual available energy of the battery can be accurately estimated during the long-term operation of the system.To ensure the long-term accuracy of the discrete-time system model, its parameters are updated online. Therefore, the recursive least squares method is adopted to dynamically adjust the model parameters to adapt to environmental changes. During the calculation process of the recursive least squares method, based on real-time data, the correlation coefficients of the charging, discharging, and standby states in the parameter matrix are adjusted, enabling the model to maintain a high prediction accuracy during long-term operation. Due to the non-linear relationship between the DC bus voltage and the state of charge of the battery, a non-linear correction term needs to be introduced during parameter update to ensure the accuracy of the optimization calculation. For example, under high load conditions, the non-linear effect of the battery discharge rate causes large fluctuations in the bus voltage. Therefore, an additional compensation term needs to be introduced during the parameter update process to correct the impact of the change in the battery equivalent internal resistance on the dynamic characteristics of the system. After obtaining accurate power flow parameters, combined with the grid state evaluation index and the operation mode division result, a multi-objective optimization algorithm is executed to calculate the optimal charge and discharge power commands. The core of this optimization algorithm lies in comprehensively considering multiple objectives, including minimizing the electricity cost, maximizing the battery life, maximizing the self-use rate of self-generated electricity, and maximizing the grid interaction support degree, and by dynamically adjusting the weight coefficients, the optimization objectives can adapt to different operation modes. During the optimization calculation process, based on the grid electricity price, load demand, and photovoltaic power generation prediction data for the next 24 hours, the optimal charge and discharge power at different time steps is calculated, and the quadratic programming method is used to solve the optimization problem. Through multi-objective optimization calculation, an energy scheduling plan containing the charge and discharge power commands for the next 24 hours is generated, and in the actual operation process, it is dynamically adjusted in combination with the rolling optimization strategy to ensure that the energy storage system can achieve optimal energy management under different working conditions.

[0060] In a specific embodiment, the process of executing the multi-objective optimization algorithm according to the power flow parameters, grid state evaluation index, and system operation mode division result to obtain an energy scheduling plan containing charge and discharge power commands may specifically include the following steps:

[0061] Define an optimization objective function based on the power flow parameters and the multi-objective optimization algorithm, and dynamically adjust the weight coefficients in the optimization objective function according to the system operation mode division result to obtain dynamic weight coefficients;

[0062] Set optimization constraint conditions based on the dynamic weight coefficients. The optimization constraint conditions include the state of charge limit of the battery, charge and discharge power limit, grid exchange power limit, and power balance constraint;

[0063] Perform grid electricity price, load demand, and photovoltaic power generation predictions based on the system parameter dataset to obtain the system future state prediction results;

[0064] Based on the system future state prediction results and the optimization constraint conditions, transform the optimization problem into a quadratic programming form and solve it using the interior point method to obtain the preliminary optimization results;

[0065] Perform a rolling horizon processing on the preliminary optimization results to generate an energy scheduling plan including charge and discharge power commands.

[0066] Specifically, clarify the core optimization objectives of the energy storage system, including minimizing electricity cost, maximizing battery life, maximizing the self-consumption rate of photovoltaic power, and maximizing grid interaction support. The priorities of these objectives vary in different operating modes. During the optimization calculation process, the weight coefficients in the optimization objective function are dynamically adjusted according to the classification results of the system operating modes, so as to ensure that the optimization strategy adapts to different working conditions. For example, in the charging priority mode, priority is given to using low electricity price periods for battery charging to reduce the overall electricity cost, so the weight of minimizing electricity cost needs to be increased accordingly; in the discharging priority mode, ensure that the battery supplies power to the load during high electricity price periods to reduce the electricity purchase from the grid, so the weight of improving the battery discharging strategy is increased. In the self-consumption priority mode, the optimization objective focuses on the self-consumption rate of photovoltaic power to minimize the dependence on the grid as much as possible, while in the grid support mode, the system needs to optimize the grid interaction support so that the energy storage system can provide effective frequency and voltage regulation capabilities during grid fluctuations, so the weight of grid interaction support will be increased in this mode. Through the dynamic weight adjustment mechanism, the optimization algorithm can adapt to different system requirements and achieve the best energy management effect under various operating conditions. Set optimization constraints based on the dynamic weight coefficients to ensure that the calculated scheduling strategy not only meets the safe operation requirements of physical equipment but also can satisfy the energy balance relationship. The optimization constraints include the limitation of the state of charge of the battery to ensure that the battery will not be overcharged or discharged excessively, thus protecting the long-term service life of the battery; the limitation of the charge and discharge power to ensure that the battery will not experience too high a charge and discharge rate in a short period of time, thus avoiding overheating or overload damage; the limitation of the grid exchange power to prevent the system from injecting or drawing too much power from the grid and avoid affecting the stability of the grid; the power balance constraint to ensure that the system can achieve energy conservation at any time, thus ensuring that the load demand can be reasonably distributed by photovoltaic power generation, battery discharge, and grid power supply. Predict the future system state based on historical data to obtain future grid electricity prices, load demands, and photovoltaic power generation. The grid electricity price prediction uses time series analysis methods. By analyzing the electricity price data over a past period of time and combining with the market trend model, predict the electricity price fluctuations within the next 24 hours. The load demand prediction is based on historical electricity consumption data, weather data, and user behavior patterns, and uses machine learning algorithms for prediction. The photovoltaic power generation prediction uses environmental sensor data, including factors such as solar irradiance, temperature, weather conditions, etc., and combines with the characteristic curve of the photovoltaic module, and uses neural network or support vector regression algorithms to predict the future photovoltaic power generation capacity. Through these prediction methods, accurately obtain the electricity price, load demand, and photovoltaic power generation information for the next 24 hours. Based on the prediction results of the future system state and the optimization constraints, transform the optimization problem into a quadratic programming form and solve it by the interior point method.The quadratic programming method is applicable to solving optimization problems with a quadratic objective function and linear constraints, which can ensure that the calculated scheduling result is globally optimal and satisfies all constraint conditions. In this process, the inputs for the optimization calculation include the electricity price forecast, load demand forecast, photovoltaic power generation forecast for the next 24 hours, as well as the power flow parameters and optimization constraint conditions of the system. Using these data, a quadratic programming problem is constructed and solved using the interior point method. The calculated optimization result provides reasonable charge and discharge power commands for the energy storage system, enabling it to operate according to the optimal strategy within the next 24 hours to maximize economic benefits and system stability. The preliminary optimization result is only the optimal solution calculated based on static data. During the actual operation process, the grid state, load demand, and photovoltaic power generation will change dynamically. Therefore, the rolling horizon approach is used to process the preliminary optimization result to generate the final charge and discharge power commands. In the rolling optimization process, a 6-hour optimization window is adopted, and optimization updates are performed every 15 minutes. That is, in each calculation, only the charge and discharge power commands for the current time step are executed, while the optimization results for subsequent time steps will be used as a reference for the next optimization to ensure that the system can adjust the scheduling strategy in real time. Through the rolling optimization method, the optimal scheduling effect is maintained in an uncertain operating environment, and the intelligent management of the energy storage system is realized.

[0067] In this embodiment, the process of executing the multi-objective optimization algorithm according to the power flow parameters, the power grid state evaluation index, and the electricity price interval division result to obtain an energy scheduling plan including charge and discharge power commands further includes the steps of applying a two-layer deep reinforcement learning agent model, including: constructing a reinforcement learning environment model based on the system parameter data set, defining the state space as the state of the battery charge, the state of the power grid, the electricity price level, the load demand, and the photovoltaic power generation power, setting the charge and discharge power as the action space, and constructing a reward function based on the electricity cost savings, the battery life impact, the power grid stability, and the self-use rate of self-generated electricity to obtain the basis for environmental interaction; designing a high-level policy network for the environmental interaction basis, using a deep recurrent neural network architecture, inputting a 24-hour prediction data sequence, and outputting a long-term decision sequence with a time scale of hours to obtain a long-term planning strategy; designing a low-level execution network based on the long-term planning strategy, using a deep convolutional neural network architecture, inputting a sliding time window containing the real-time data of the last 30 minutes, and outputting a short-term control action with a time scale of minutes to obtain a short-term execution strategy; implementing a priority-based experience replay training mechanism for the high-level policy network and the low-level execution network, assigning a higher replay probability to samples with a larger temporal difference error, and using the target network fixation technique to reduce training instability to obtain network optimization parameters; applying a hierarchical time abstraction method to the network optimization parameters, triggering the high-level network once every 4 hours and the low-level network once every 5 minutes, constructing a hierarchical decision tree structure, and connecting the high-level and low-level network communications through an option framework to obtain a time series coordination model; introducing a multi-agent collaborative decision-making mechanism into the time series coordination model, treating each three-phase hybrid inverter as an independent agent, and applying a graph neural network based on the attention mechanism to establish a communication channel between agents to obtain a group collaborative optimization structure; developing an environment dynamic adaptation mechanism based on the group collaborative optimization structure, comparing the deviation between the predicted value and the actual environmental change, dynamically adjusting the weight of the power grid state evaluation accuracy, and quickly adapting to the new environment through a meta-learning method to obtain an adaptive learning model; integrating the decision result output by the adaptive learning model with the quadratic programming optimization result, using a weighted fusion mechanism to generate a more accurate charge and discharge power command, and obtaining an energy scheduling plan optimized by deep reinforcement learning.

[0068] In a specific embodiment, the process of executing step S300 may specifically include the following steps:

[0069] Convert the charge and discharge power command in the energy scheduling plan into charge and discharge current control parameters;

[0070] Input the charge and discharge current control parameters into the control structure composed of a prediction control layer and a real-time response control layer in the three-phase hybrid inverter. The prediction control layer is a bidirectional long short-term memory network, and the real-time response control layer is a double closed-loop control structure, with the inner loop being the current loop and the outer loop being the power loop;

[0071] In the predictive control layer, the current prediction calculation of the bidirectional long short-term memory network is performed to obtain the current reference value, and the current reference value is input into the real-time response control layer. Through the current loop, offline optimization and online adaptive adjustment are carried out to obtain the current control signal;

[0072] Based on the current control signal, power tracking is performed through the power loop. The actual power is compared with the reference power and the current command is dynamically adjusted. At the same time, a feed-forward compensation mechanism is introduced according to the changes in load and photovoltaic power to obtain a disturbance-resistant power command;

[0073] A seamless switching mechanism is designed based on the numerical value of the power flow direction parameter, and an exponential decay function is used as the smooth transition strategy corresponding to the disturbance-resistant power command to obtain a smoothly switched control signal;

[0074] The smoothly switched control signal is combined with the virtual impedance drop control strategy. For the grid exchange power, a power smoothing algorithm based on moving average is applied, and the power output data is output through the IGBT power module.

[0075] Specifically, calculate the current values required for charging and discharging based on the real-time DC bus voltage. Since the relationship between the charge and discharge power of the energy storage battery and the current is affected by the bus voltage fluctuation, the current calculation method is dynamically adjusted to ensure accurate energy conversion. By real-time monitoring the DC bus voltage and combining with the internal equivalent resistance of the battery, calculate the charge and discharge current control parameters that are more in line with the actual situation, and input them into the control structure of the three-phase hybrid inverter. This control structure consists of a predictive control layer and a real-time response control layer. Among them, the predictive control layer uses a bidirectional long short-term memory network for current prediction calculation, while the real-time response control layer uses a double closed-loop control structure, including a current loop in the inner loop and a power loop in the outer loop, to ensure the accuracy and dynamic adaptability of power control. In the predictive control layer, the bidirectional long short-term memory network analyzes the past and future grid states, load demands, and photovoltaic power generation data to predict the current reference value required at future moments. Input the current reference value into the real-time response control layer. In this layer, the current loop uses a proportional-integral controller for offline optimization and combines real-time data for online adaptive adjustment to compensate for the deviations caused by grid fluctuations, load changes, and environmental impacts, thereby generating an accurate current control signal. In this way, the system flexibly adjusts the charge and discharge strategies under different operating modes to ensure the safety and energy conversion efficiency of the battery. After obtaining the current control signal, perform power tracking control through the power loop to ensure that the actual power output is consistent with the reference power. The power loop compares the measured power with the reference power in real time and adjusts the current command based on the error, enabling the system to accurately control the output power and reduce the power deviation caused by load changes or photovoltaic power generation fluctuations. To improve the anti-disturbance ability of the system, a feed-forward compensation mechanism is introduced into the power loop. This mechanism adjusts the current command in advance according to the change trends of the load power and photovoltaic power generation power to compensate for the power fluctuations that occur. For example, when the system detects an increase in photovoltaic power generation power, the feed-forward compensation mechanism will appropriately reduce the grid power purchase or reduce the battery discharge power to optimize the energy utilization efficiency and thus enhance the dynamic adaptability of the system. At the same time, to ensure the smooth and reliable switching process between the charging, discharging, and standby modes, a seamless switching mechanism is designed based on the numerical values of the power flow parameters, and an exponential decay function is used as the smooth transition strategy corresponding to the anti-disturbance power command to ensure the stability of the current change. In this mechanism, the time constant of the exponential decay function is dynamically adjusted according to the current power flow state to adapt to different switching requirements. For example, when the system switches from the charging mode to the discharging mode, the exponential decay function can gradually adjust the power command to prevent the unstable state of the battery or load caused by sudden current changes. The smooth transition strategy can effectively reduce the power impact and avoid system oscillation caused by mode switching, thereby improving the reliability of the overall system. Combine the smooth switching control signal with the virtual impedance drop control strategy to optimize the regulation ability of the grid exchange power.The virtual impedance droop control strategy enables the system to better respond to the fluctuations of the grid voltage by simulating the equivalent impedance characteristics of the energy storage system, and optimizes the support effect of the system on the grid by dynamically adjusting the impedance parameters. Meanwhile, for the grid exchange power, a power smoothing algorithm based on moving average is applied to reduce the impact on the grid caused by the power fluctuations during the charge and discharge process. This power smoothing algorithm adaptively adjusts the smoothing window size according to the grid state. For example, in the stable grid state, the power smoothing window is set to a longer time interval to ensure the stability of the system operation, while in the grid fluctuation state, the system shortens the smoothing window to improve the response speed to the grid changes. After the calculations and optimizations of all control links, the finally calculated power control signal is converted into actual power output data through the IGBT power module, ensuring that the inverter can operate according to the optimal control strategy and maintain the best energy management effect under different operating modes.

[0076] In a specific embodiment, the process of executing step S400 may specifically include the following steps:

[0077] Upload the system parameter datasets, power flow parameters, and power output data of multiple three-phase hybrid inverters to the intelligent management cloud platform respectively, and perform distributed data storage using an encrypted transmission protocol to obtain structured storage data;

[0078] Based on the structured storage data, establish a data display layer including real-time monitoring functions provided through a Web interface and a mobile application, an analysis and decision-making layer for analyzing the power consumption pattern using big data technology, and a remote control layer that allows authorized users to send control commands, to obtain a remote monitoring and control architecture;

[0079] Adopt the remote monitoring and control architecture to divide multiple parallel three-phase hybrid inverters, set one as the master inverter responsible for global resource scheduling, and the rest as slave inverters to receive and execute commands, and calculate the power sharing ratio according to the capacity, load condition, and energy storage state of each three-phase hybrid inverter, to obtain a master-slave control structure;

[0080] Execute the master-slave droop control algorithm based on the master-slave control structure, and dynamically adjust the droop characteristic curve according to the inverter capacity to obtain a multi-machine balanced power distribution scheme;

[0081] Introduce the virtual synchronous machine technology into the multi-machine balanced power distribution scheme, and implement multi-machine communication through the CAN bus. When the communication is interrupted, automatically switch to the independent operation mode to obtain a distributed energy network management scheme.

[0082] Specifically, the system parameter datasets, power flow parameters, and power output data of each inverter are uploaded to the intelligent management cloud platform to achieve global coordinated control. To ensure the security and reliability of data transmission, an encrypted transmission protocol is adopted. After all parameters are signed and encrypted at the data acquisition end, they are distributed through a secure communication protocol and stored as structured data in the cloud. This storage method combines a time series database with distributed file storage to ensure the high efficiency of data query and provide high fault tolerance, enabling the system to still operate normally even in the case of partial server failures. Since these data include real-time power exchange information, power grid status monitoring results, charge and discharge states of energy storage systems, and changes in load demands, the storage structure needs to have high throughput capabilities and support historical data backtracking for subsequent energy optimization calculations and anomaly analysis. After data upload and storage are completed, a remote monitoring and control architecture is established based on the structured storage data to provide data visualization, intelligent analysis, and remote control functions. The remote monitoring and control architecture includes a data display layer, an analysis and decision-making layer, and a remote control layer. The data display layer provides real-time monitoring functions through a Web interface and a mobile application, enabling users to view the operating status of the system at any location, including power flow, energy storage system status, grid interaction power, and load conditions, and also providing historical data query and trend analysis functions. The analysis and decision-making layer uses big data technology to analyze the operating mode of the system, identifies the power consumption pattern through machine learning algorithms, and combines the grid price fluctuations, photovoltaic power generation capabilities, and load demand prediction results to provide the optimal energy management strategy for the energy storage system. The remote control layer allows authorized users to send control instructions, including adjusting charge and discharge strategies, setting the power distribution ratio of inverters, and switching operating modes, and ensures the legality and security of remote instructions through a security mechanism based on permission management. The establishment of this architecture enables the system to perform remote monitoring and scheduling in a highly intelligent manner and achieve optimal energy storage management under different operating conditions. With the support of the remote monitoring and control architecture, multiple parallel three-phase hybrid inverters are partitioned to establish a master-slave control structure. To achieve efficient energy scheduling, one inverter is set as the master inverter, responsible for the scheduling of global resources, while the remaining inverters act as slave devices, receiving instructions from the master inverter and performing corresponding operations. The master inverter calculates the power sharing ratio of all inverters based on the global data obtained from the cloud platform and dynamically adjusts the power distribution strategy according to the capacity of each inverter, the current load condition, and the energy storage state to ensure the stable operation of the system. For example, when the state of charge of the battery of one inverter is relatively high, while the battery of another inverter has a low power level, the master inverter assigns the inverter with a higher power level to undertake more discharge tasks to balance the overall state of charge of the system. At the same time, the slave inverters output power according to the scheduling instructions of the master inverter and feedback their operating status in real time so that the master inverter can adjust the scheduling strategy when necessary.The master-slave control structure ensures the coordination of the multi-inverter parallel system and improves the energy management efficiency of the overall system. Based on the master-slave control structure, the master-slave droop control algorithm is adopted to achieve the balanced power distribution of multiple inverters. The droop control algorithm adjusts the voltage-power and frequency-power characteristic curves of the inverters, enabling each inverter to dynamically adjust its power output according to its own capacity without centralized control. When the system load increases, the frequency drops, and the inverter automatically increases its power output according to the droop control strategy. When the load decreases, the frequency rises, and the inverter correspondingly reduces its power output. Through this mechanism, the system realizes automatic load distribution without relying on centralized scheduling and improves the stability of the overall system. To optimize the multi-inverter balanced power distribution scheme, the virtual synchronous machine technology is introduced to enhance the adaptability of the inverter to grid fluctuations. The virtual synchronous machine technology simulates the inertia and damping characteristics of a synchronous generator in the inverter control strategy, enabling the inverter to provide a response similar to physical rotational inertia when the grid frequency fluctuates, thereby improving the dynamic stability of the system. For example, when there is an instantaneous load change in the grid, the inverter temporarily stores or releases energy to reduce the amplitude of the grid frequency fluctuation and enhance the anti-interference ability of the system. At the same time, to ensure sufficient real-time performance and reliability of the information exchange between the master inverter and the slave inverters, the CAN bus is used for multi-inverter communication, and the communication cycle is set to 10 milliseconds to ensure that all inverters can quickly share the operating status and control instructions and respond within milliseconds. In actual operation, the system needs to handle communication interruption problems. When the CAN bus fails, the system automatically switches to the independent operation mode to obtain the distributed energy network management scheme. In the independent operation mode, each inverter operates independently according to the local measurement data and preset strategies to ensure that the energy storage system can still operate normally in the event of communication failure. For example, when the master inverter detects communication anomalies, it triggers the local control mode, enabling each slave inverter to continue operating according to the latest power distribution instructions and dynamically adjusting the charge-discharge strategy according to its own load conditions to reduce the impact of communication interruption on the system operation. At the same time, the system attempts to re-establish the communication connection and re-enters the master-slave control mode after the communication is restored to ensure that the system can quickly resume the normal operation state.

[0083] Please refer to Figure 2 , Figure 2 which is a schematic block diagram of the structure of the intelligent energy storage control device 200 based on bidirectional energy management provided by an embodiment of the present application. As Figure 2 shown, the intelligent energy storage control device 200 based on bidirectional energy management includes:

[0084] The real-time acquisition module 210 is used to perform real-time acquisition and power grid state analysis on power grid parameters, energy storage module parameters, load demands, and photovoltaic power generation data, and obtain power grid state evaluation indicators and system operation mode division results;

[0085] The multi-objective optimization module 220 is used to execute a multi-objective optimization algorithm based on the power grid state evaluation indicators and system operation mode division results, and obtain an energy scheduling plan including charge and discharge power instructions;

[0086] The predictive control module 230 is used to convert the energy scheduling plan into charge and discharge current control parameters, and input them into the control structure composed of a predictive control layer and a real-time response control layer in a three-phase hybrid inverter to obtain power output data;

[0087] The parallel coordination control module 240 is used to upload the power output data of multiple three-phase hybrid inverters to the intelligent management cloud platform, execute multi-machine parallel coordination control, and obtain a distributed energy network management solution.

[0088] Through the collaborative cooperation of the above-mentioned various components, through a high-precision and multi-frequency parameter real-time acquisition system, the comprehensive monitoring of the power grid state, energy storage state, load demand, and photovoltaic power generation is realized, providing a reliable data basis for system operation and making the identification of energy flow more accurate. The power grid state evaluation mechanism based on power grid harmonic content analysis and weighted average composite function, combined with the electricity price interval division technology of the fuzzy clustering algorithm, enables the system to intelligently perceive the changes in the power grid state and automatically adjust the operation mode according to the electricity price characteristics. The parametric representation method of the electric energy flow direction is introduced, and the system matrix and input matrix are expressed as functions of three states: charging, discharging, and standby, which greatly simplifies the controller design and accurately describes the system dynamic characteristics under different electric energy flow directions. The multi-objective optimization algorithm is used for energy scheduling, comprehensively considering multiple objectives such as electricity cost, battery life, self-use rate of spontaneous power, and power grid interaction support degree, and dynamically adjusting the weight coefficient according to the system operation mode, realizing the optimal allocation of resources. A two-level control structure combining a predictive control layer and a real-time response control layer is designed, and together with a smooth transition strategy and a power smoothing algorithm, effectively suppresses system oscillation and power grid interaction power fluctuation, ensuring the stable operation of the three-phase hybrid inverter under various working conditions. Through the intelligent management cloud platform, the remote monitoring of system operation data and multi-machine parallel coordination control are realized. The master-slave droop control algorithm and virtual synchronous machine technology are adopted to enhance the stability and adaptability of the distributed energy network, especially the autonomous operation ability during communication interruption.

[0089] Please refer to Figure 3 , Figure 3Schematic block diagram of the intelligent energy storage control device 300 based on bidirectional energy management provided by an embodiment of the present application. The intelligent energy storage control device 300 based on bidirectional energy management includes a processor 301 and a memory 302, and the processor 301 and the memory 302 are connected through a device bus 303. Among them, the memory 302 may include a non-volatile storage medium and an internal memory.

[0090] The non-volatile storage medium can store a computer program. The computer program includes program instructions. When the program instructions are executed by the processor 301, the processor 301 can be enabled to execute any of the above-mentioned intelligent energy storage control methods based on bidirectional energy management.

[0091] The processor 301 is used to provide computing and control capabilities to support the operation of the entire intelligent energy storage control device 300 based on bidirectional energy management.

[0092] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor 301, the processor 301 can be enabled to execute any of the above-mentioned intelligent energy storage control methods based on bidirectional energy management.

[0093] Those skilled in the art can understand that Figure 3 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the intelligent energy storage control device 300 based on bidirectional energy management involved in the solution of the present application. Specifically, the intelligent energy storage control device 300 based on bidirectional energy management may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0094] It should be understood that the processor 301 may be a central processing unit (CPU), and the processor 301 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0095] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the intelligent energy storage control device 300 based on bidirectional energy management described above can refer to the corresponding process of the aforementioned intelligent energy storage control method based on bidirectional energy management, and will not be elaborated here.

[0096] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, systems and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated here.

[0097] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0098] The above is the case. The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. An intelligent energy storage control method based on bidirectional energy management, characterized in that: include: Real-time collection and grid status analysis of grid parameters, energy storage module parameters, load demand and photovoltaic power generation data are carried out to obtain grid status evaluation indicators and system operation mode classification results; Based on the grid state evaluation index and the system operation mode division result, a multi-objective optimization algorithm is executed to obtain an energy scheduling plan including charging and discharging power instructions; Specifically, the method comprises: simplifying the three-phase hybrid inverter system into an interconnected system of a grid side, a DC bus side and a load side, and defining a system state vector to obtain a simplified system model; defining a control input vector including a charging current instruction and a discharging current instruction based on the simplified system model to obtain a system control model; establishing a system discrete time state equation according to the system control model to obtain a system discrete time mathematical model, and introducing electric energy flow direction into the system discrete time mathematical model to obtain a parameterized system model, wherein the electric energy flow direction includes charging, discharging and standby; for each electric energy flow direction in the parameterized system model, Establish a corresponding sub-model parameter matrix to obtain a discrete-time system model, wherein the charging state includes a charging efficiency coefficient, the discharging state includes a discharging efficiency coefficient, and the standby state reflects the self-discharge characteristics; perform recursive least squares parameter update on the discrete-time system model, and consider the nonlinear relationship between the DC bus voltage change and the battery charge state to obtain the power flow parameters characterizing the charging, discharging and standby states; perform a multi-objective optimization algorithm based on the power flow parameters, the grid state evaluation index and the system operation mode division results to obtain an energy scheduling plan including charging and discharging power instructions; The energy scheduling plan is converted into charge and discharge current control parameters, and input into a control structure composed of a prediction control layer and a real-time response control layer in a three-phase hybrid inverter to obtain power output data; The power output data of multiple three-phase hybrid inverters are uploaded to the intelligent management cloud platform, and multi-machine parallel coordinated control is performed to obtain a distributed energy network management solution.

2. The intelligent energy storage control method based on bidirectional energy management according to claim 1 is characterized in that: The real-time collection of grid parameters, energy storage module parameters, load demand and photovoltaic power generation data and grid status analysis are performed to obtain grid status evaluation indicators and system operation mode classification results, including: The voltage, frequency, phase and electricity price information of the three-phase power grid are sampled to obtain the power grid parameter measurement results; the state of charge, DC bus voltage, charge and discharge current and battery temperature of the battery pack are monitored to obtain the energy storage module parameter measurement results; the power consumption of the user's three-phase or single-phase load is collected to obtain the load demand monitoring results; the output voltage, current, power and environmental irradiance and temperature of the photovoltaic array are measured to obtain the photovoltaic power generation monitoring results; The grid parameter measurement results, the energy storage module parameter measurement results, the load demand monitoring results and the photovoltaic power generation monitoring results are transmitted to a data processing unit, and preprocessed by denoising, outlier detection and missing value interpolation to obtain preprocessed data; Based on the preprocessed data, the power flow direction is identified by comparing the real-time values ​​of photovoltaic power generation power, load demand power, battery charging and discharging power, and grid exchange power to obtain a system parameter data set; The power grid state is analyzed according to the system parameter data set to obtain power grid state evaluation indicators and system operation mode classification results.

3. The intelligent energy storage control method based on bidirectional energy management according to claim 2 is characterized in that: The analyzing the power grid state according to the system parameter data set to obtain the power grid state evaluation index and the system operation mode division result includes: Continuously monitoring the three-phase voltage amplitude, phase difference, frequency and fluctuation rate of the power grid in the system parameter data set to obtain the basic parameter monitoring results of the power grid, and performing Fourier transform on the basic parameter monitoring results of the power grid to obtain the harmonic content analysis results of the power grid; Performing a weighted average composite function calculation based on the power grid harmonic content analysis result to obtain a power grid state evaluation index; According to the power grid state evaluation index, the power grid state is divided into a stable state, a fluctuating state and an abnormal state, and a power grid state determination result is obtained; Performing fuzzy clustering on the real-time electricity price data in the system parameter data set to obtain an electricity price interval division result; The system operation mode is divided according to the grid state determination result and the electricity price range division result, and the system operation mode division results including charging priority mode, discharging priority mode, self-consumption priority mode, grid support mode, off-grid standby mode and emergency protection mode are obtained.

4. The intelligent energy storage control method based on bidirectional energy management according to claim 3 is characterized in that: The multi-objective optimization algorithm is executed according to the electric energy flow direction parameter, the grid state evaluation index and the system operation mode division result to obtain an energy scheduling plan including charging and discharging power instructions, including: Defining an optimization objective function based on the electric energy flow direction parameter and the multi-objective optimization algorithm, and dynamically adjusting a weight coefficient in the optimization objective function according to the system operation mode division result to obtain a dynamic weight coefficient; Setting optimization constraints based on the dynamic weight coefficients, the optimization constraints including battery state of charge restriction, charge and discharge power restriction, grid exchange power restriction and power balance restriction; Based on the system parameter data set, grid electricity price, load demand and photovoltaic power generation are predicted to obtain a prediction result of the future state of the system; Based on the prediction result of the future state of the system and the optimization constraints, the optimization problem is converted into a quadratic programming form and solved by an interior point method to obtain a preliminary optimization result; The preliminary optimization results are processed in the rolling time domain to generate an energy scheduling plan including charging and discharging power instructions.

5. The intelligent energy storage control method based on bidirectional energy management according to claim 4 is characterized in that: The energy scheduling plan is converted into a charge and discharge current control parameter and input into a control structure composed of a prediction control layer and a real-time response control layer in a three-phase hybrid inverter to obtain power output data, including: Performing charge and discharge current conversion on the charge and discharge power instructions in the energy scheduling plan to obtain charge and discharge current control parameters; Inputting the charge and discharge current control parameters into a control structure composed of a prediction control layer and a real-time response control layer in a three-phase hybrid inverter, wherein the prediction control layer is a bidirectional long short-term memory network, and the real-time response control layer is a double closed-loop control structure, wherein the inner loop is a current loop and the outer loop is a power loop; In the prediction control layer, a current prediction calculation of a bidirectional long short-term memory network is performed to obtain a current reference value, and the current reference value is input into the real-time response control layer, and an offline optimization and online adaptive adjustment are performed through the current loop to obtain a current control signal; Based on the current control signal, power tracking is performed through the power loop, actual power is compared with reference power and current instructions are dynamically adjusted, and a feedforward compensation mechanism is introduced according to load and photovoltaic power changes to obtain an anti-disturbance power instruction; A seamless switching mechanism is designed based on the numerical value of the electric energy flow direction parameter, and an exponential decay function is used as a smooth transition strategy corresponding to the anti-disturbance power instruction to obtain a control signal for smooth switching; The control signal of the smooth switching is combined with the virtual impedance drop control strategy, a power smoothing algorithm based on sliding average is applied to the grid exchange power, and power output data is output through the IGBT power module.

6. The intelligent energy storage control method based on bidirectional energy management according to claim 5 is characterized in that: The power output data of multiple three-phase hybrid inverters are uploaded to the smart management cloud platform, and multi-machine parallel coordinated control is performed to obtain a distributed energy network management solution, including: The system parameter data sets, power flow parameters and power output data of multiple three-phase hybrid inverters are uploaded to the smart management cloud platform respectively, and the encrypted transmission protocol is used for distributed data storage to obtain structured storage data; Based on the structured storage data, a data display layer is established, which includes providing real-time monitoring functions through a Web interface and a mobile application, an analysis and decision-making layer that uses big data technology to analyze power consumption patterns, and a remote control layer that allows authorized users to send control instructions, thereby obtaining a remote monitoring control architecture; The remote monitoring control architecture is adopted to divide multiple three-phase hybrid inverters in parallel, and one is set as the master inverter responsible for global resource scheduling, and the rest are slave inverters that receive and execute instructions, and the power sharing ratio is calculated according to the capacity, load condition and energy storage state of each three-phase hybrid inverter, so as to obtain a master-slave control structure; Based on the master-slave control structure, a master-slave droop control algorithm is executed, and the droop characteristic curve is dynamically adjusted according to the inverter capacity to obtain a multi-machine balanced power distribution scheme; The virtual synchronous machine technology is introduced into the multi-machine balanced power distribution scheme, and multi-machine communication is realized through the CAN bus. When the communication is interrupted, it automatically switches to the independent operation mode to obtain a distributed energy network management solution.

7. An intelligent energy storage control device based on bidirectional energy management, characterized in that: Used to execute the intelligent energy storage control method based on bidirectional energy management as described in any one of claims 1 to 6, the intelligent energy storage control device based on bidirectional energy management comprises: Real-time acquisition module, used for real-time acquisition of grid parameters, energy storage module parameters, load demand and photovoltaic power generation data and grid status analysis, to obtain grid status evaluation indicators and system operation mode classification results; A multi-objective optimization module, used to execute a multi-objective optimization algorithm based on the grid state evaluation index and the system operation mode division result to obtain an energy scheduling plan including charging and discharging power instructions; A prediction control module, used for converting the energy scheduling plan into charge and discharge current control parameters, and inputting the parameters into a control structure composed of a prediction control layer and a real-time response control layer in a three-phase hybrid inverter to obtain power output data; The parallel coordination control module is used to upload the power output data of multiple three-phase hybrid inverters to the intelligent management cloud platform, perform multi-machine parallel coordination control, and obtain a distributed energy network management solution.

8. An intelligent energy storage control device based on bidirectional energy management, characterized in that: The intelligent energy storage control device based on bidirectional energy management comprises: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instruction in the memory so that the intelligent energy storage control device based on bidirectional energy management executes the intelligent energy storage control method based on bidirectional energy management as described in any one of claims 1-6.

Images