Wind-light-storage integrated multi-energy coordination control method

Abstract

The invention relates to a wind-light-storage integrated multi-energy coordination control method. The method comprises the following steps: predicting future wind-light power generation power; determining a charging and discharging plan of an energy storage unit based on the wind-solar power generation power prediction value and the power grid load demand data; based on the charging and discharging plan, a wind-solar power generation power prediction value and real-time operation data of an energy system; constructing a multi-energy cooperative control mathematical model; wherein the real-time operation data of the energy system comprises real-time operation data of a wind turbine generator, a photovoltaic array, an energy storage unit and a load; and generating a coordination control instruction based on the multi-energy coordination control mathematical model. According to the invention, efficient cooperative operation of new energy, energy storage and a traditional power grid can be realized, and powerful support is provided for large-scale application of an intelligent power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of multi - energy scheduling, and particularly to a multi - energy coordinated control method integrating wind - solar - energy storage Background Art

[0002] The wind - solar - energy storage integrated multi - energy system faces many technical problems in actual operation. First of all, both wind energy and solar energy are intermittent and fluctuating energy sources, and their output is greatly affected by meteorological conditions. It is difficult to accurately predict the power generation of wind turbines and photovoltaic arrays, which brings challenges to the grid dispatching operation. Secondly, although the energy storage unit can smooth the fluctuations of wind - solar power generation to a certain extent, it has problems such as limited capacity and charge - discharge losses, and it is difficult to completely absorb the excess power of wind - solar power generation. In addition, how to achieve optimal coordinated control among multiple subsystems such as wind turbines, photovoltaics, energy storage, and loads is also a major problem. The operating characteristics of each subsystem vary greatly. How to balance the output of each energy source to maximize the overall benefit is a complex optimization problem involving multiple objectives such as power balance, economic operation, and equipment losses. The coordinated controller needs to perform real - time processing and analysis on a large amount of heterogeneous data, and optimize the scheduling of the system with a control period of milliseconds, which poses high requirements for its computing power and algorithms. In short, the multi - time - scale, strong - coupling, and non - linear characteristics of the wind - solar - energy storage system bring many challenges to coordinated control, and breakthroughs in these technical bottlenecks require in - depth research. Summary of the Invention

[0003] The purpose of the present invention is to propose a multi - energy coordinated control method integrating wind - solar - energy storage to solve the problems existing in the above - mentioned prior art.

[0004] To achieve the above purpose, the present invention provides the following solutions:

[0005] A multi - energy coordinated control method integrating wind - solar - energy storage, comprising:

[0006] Predict the future wind - solar power generation;

[0007] Based on the predicted values of wind - solar power generation and the grid load demand data, determine the charge - discharge plan of the energy storage unit;

[0008] Based on the charge - discharge plan, the predicted values of wind - solar power generation, and the real - time operation data of the energy system; construct a multi - energy coordinated control mathematical model; wherein, the real - time operation data of the energy system includes: the real - time operation data of wind turbines, photovoltaic arrays, energy storage units, and loads;

[0009] Based on the multi - energy coordinated control mathematical model, generate a coordinated control instruction.

[0010] Optionally, predicting the future wind - solar power generation includes:

[0011] Obtain the historical power generation data of wind turbines and photovoltaic arrays;

[0012] Obtain the historical meteorological data corresponding to the geographical locations of wind turbines and photovoltaic arrays; wherein, the historical meteorological data includes: wind speed, wind direction, and radiation;

[0013] Align the historical power generation data and historical meteorological data in terms of time to construct a data set;

[0014] Extract preset features from the data set, and use machine learning algorithms for training to construct a wind-solar power generation prediction model; wherein, the preset features include: average wind speed, maximum wind speed, and total radiation;

[0015] Use the wind-solar power generation prediction model to predict the future wind-solar power generation.

[0016] Optionally, determining the charge-discharge plan of the energy storage unit includes:

[0017] Based on the predicted wind-solar power generation value and the grid load demand data, calculate the power difference between wind-solar power generation and load demand, and determine the charge-discharge demand of the energy storage unit;

[0018] Based on the charge-discharge demand, considering the energy storage capacity limit and charge-discharge losses, construct an optimization model for the charge-discharge of the energy storage unit;

[0019] Based on the charge-discharge optimization model, obtain the charge-discharge plan of the energy storage unit.

[0020] Optionally, determining the charge-discharge demand of the energy storage unit includes:

[0021] Calculate the difference between the predicted wind-solar power generation value and the grid load demand data, and obtain the power deficit or surplus at the corresponding time point;

[0022] Based on the power deficit or surplus situation at the time point, judge the working state of the energy storage unit at the time point. If it is positive, the energy storage unit discharges; if it is negative, the energy storage unit charges;

[0023] Adopt the method of a sliding time window to cumulatively calculate the power deficit or surplus data over a period of time, and obtain the cumulative charge-discharge demand of the energy storage unit within the corresponding time window.

[0024] Optionally, constructing the charge-discharge optimization model of the energy storage unit includes:

[0025] Obtain the predicted curve of the charge-discharge demand of the energy storage unit over a future period of time;

[0026] Obtain the initial state information of the energy storage unit; wherein the initial state information includes the current energy storage capacity and the charge-discharge power limit;

[0027] Taking the initial state information and the charge-discharge loss as constraint conditions, based on the constraint conditions and the charge-discharge demand prediction curve, a charge-discharge optimization model is constructed.

[0028] Optionally, obtaining the charge-discharge plan of the energy storage unit based on the charge-discharge optimization model includes:

[0029] Using the dynamic programming algorithm to solve the charge-discharge optimization model, and obtaining the optimal charge-discharge power of the energy storage unit at each moment during the prediction period;

[0030] Based on the optimal charge-discharge power, generating a charge-discharge plan for the energy storage unit; wherein, the charge-discharge plan includes: the charge-discharge state and the charge-discharge amount at each moment.

[0031] Optionally, the multi-energy collaborative control mathematical model includes: the operation constraints of the equipment;

[0032] The operation constraints of the equipment include: the cut-in and cut-out wind speed limits of the wind turbine, the maximum power generation limit of the photovoltaic array, and the charge-discharge power and capacity limits of the energy storage unit.

[0033] Optionally, generating a coordinated control instruction based on the multi-energy collaborative control mathematical model includes:

[0034] Substituting the predicted values of wind and solar power generation, the charge-discharge plan of the energy storage unit, and the predicted load value into the multi-energy collaborative control mathematical model, and using the particle swarm optimization algorithm to solve the multi-energy collaborative control problem to obtain the optimal output scheduling plan of each device;

[0035] Based on the optimal output scheduling plan of each device, generating power control instructions for the wind turbine, the photovoltaic array, and the energy storage unit.

[0036] The beneficial effects of the present invention are:

[0037] The present invention discloses a multi-energy coordinated control method integrating wind-solar-storage. This method realizes precise prediction and optimal control of a complex power grid system by integrating wind power, photovoltaic power, energy storage, and load data. First, a wind-solar power generation prediction model is established using historical data and meteorological forecasts, and the charge-discharge demand of the energy storage is calculated in combination with the load demand. Then, a charge-discharge optimization model is constructed considering the energy storage limitations to formulate an energy storage plan. On this basis, a multi-energy collaborative control mathematical model is established to generate and issue coordinated control instructions. The present invention realizes the efficient coordinated operation of new energy, energy storage, and the traditional power grid, providing strong support for the large-scale application of smart grids. Description of the Drawings

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only 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.

[0039] Figure 1 It is a schematic flow diagram of a multi - energy coordinated control method integrating wind - light - storage in an embodiment of the present invention. Detailed implementation manners

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0041] To make the above - mentioned objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the drawings and specific implementation manners.

[0042] As Figure 1 shown, this embodiment proposes a multi - energy coordinated control method integrating wind - light - storage, including:

[0043] Predict the future wind and solar power generation;

[0044] Based on the predicted values of wind and solar power generation and the grid load demand data, determine the charge - discharge plan of the energy storage unit;

[0045] Based on the charge - discharge plan, the predicted values of wind and solar power generation, and the real - time operation data of the energy system; construct a multi - energy collaborative control mathematical model; wherein, the real - time operation data of the energy system includes: the real - time operation data of wind turbines, photovoltaic arrays, energy storage units, and loads;

[0046] Based on the multi - energy collaborative control mathematical model, generate a coordinated control instruction.

[0047] Specifically, in this embodiment, by integrating wind power, photovoltaic, energy storage, and load data, accurate prediction and optimal control of complex power grid systems are achieved. First, a prediction model for wind and photovoltaic power generation is established using historical data and weather forecasts, and the energy storage charge and discharge requirements are calculated in combination with load demands. Then, an optimization model for charge and discharge is constructed considering energy storage limitations to formulate an energy storage plan. On this basis, a mathematical model for multi-energy collaborative control is established to generate and issue coordinated control instructions. The present invention also has functions of real-time monitoring and dynamic adjustment. When the system operating state exceeds the threshold, it can quickly recalculate and update the control strategy. This closed-loop feedback mechanism significantly improves the stability and reliability of the power grid, realizes the efficient collaborative operation of new energy, energy storage, and traditional power grids, and provides strong support for the large-scale application of smart grids.

[0048] Further, predicting the future wind and photovoltaic power generation includes:

[0049] Obtain the historical power generation data of wind turbines and photovoltaic arrays;

[0050] Obtain the historical meteorological data corresponding to the geographical locations of the wind turbines and photovoltaic arrays; wherein, the historical meteorological data includes: wind speed, wind direction, and radiation;

[0051] Align the historical power generation data and historical meteorological data in time to construct a data set;

[0052] Extract preset features from the data set, and use machine learning algorithms for training to construct a prediction model for wind and photovoltaic power generation; wherein, the preset features include: average wind speed, maximum wind speed, and total radiation;

[0053] Use the prediction model for wind and photovoltaic power generation to predict the future wind and photovoltaic power generation.

[0054] Specifically, in this embodiment, historical power generation data of a wind turbine and a photovoltaic array are obtained, and data cleaning and preprocessing are performed to eliminate outliers and missing values, resulting in a normalized historical power generation dataset. Historical meteorological data corresponding to the geographical locations of the wind turbine and the photovoltaic array are obtained, including wind speed, wind direction, radiation intensity, etc., and time alignment is performed with the historical power generation data to construct a dataset of influencing factors for wind-solar power generation. According to meteorological forecast information, forecast data such as wind speed, wind direction, and radiation intensity for the next 24 hours are obtained as input features for wind-solar power generation prediction. Feature engineering techniques are used to extract key features from historical power generation data and meteorological data, such as average wind speed, maximum wind speed, total radiation amount, etc., to construct an input feature vector for the wind-solar power generation prediction model. A suitable machine learning algorithm is selected, such as support vector machine, random forest, or neural network, and the wind-solar power generation prediction model is trained using historical power generation data and meteorological data, and the model parameters are optimized through methods such as cross-validation to improve the prediction accuracy. The meteorological forecast data for the next 24 hours are input into the trained wind-solar power generation prediction model to obtain the predicted power generation values of the wind turbine and the photovoltaic array for the next 24 hours. The prediction accuracy of the wind-solar power generation prediction model is evaluated, and error metrics such as mean absolute error and root mean square error between the predicted values and the actual power generation are calculated, and the prediction model is continuously iteratively optimized to improve the prediction accuracy, providing a reliable decision-making basis for the scheduling and operation and maintenance of wind-solar power generation.

[0055] Further, determining the charge-discharge plan of the energy storage unit includes:

[0056] Based on the predicted wind-solar power generation values and the grid load demand data, calculate the power difference between wind-solar power generation and load demand, and determine the charge-discharge demand of the energy storage unit;

[0057] Based on the charge-discharge demand, considering the energy storage capacity limit and charge-discharge losses, construct an optimization model for the charge-discharge of the energy storage unit;

[0058] Based on the charge-discharge optimization model, obtain the charge-discharge plan of the energy storage unit.

[0059] Further, determining the charge-discharge demand of the energy storage unit includes:

[0060] Calculate the difference between the predicted wind-solar power generation value and the grid load demand data, and obtain the power deficit or surplus at the corresponding time point;

[0061] Based on the power deficit or surplus situation at the time point, judge the working state of the energy storage unit at the time point. If it is positive, the energy storage unit discharges; if it is negative, the energy storage unit charges;

[0062] Adopt the method of sliding time window to cumulatively calculate the power deficit or surplus data within a period of time, and obtain the cumulative charge and discharge requirements of the energy storage unit within the corresponding time window.

[0063] Specifically, in this embodiment, determining the charge and discharge requirements of the energy storage unit specifically includes: obtaining the predicted values of wind and solar power generation and the grid load demand data, aligning the two sets of data along the time axis to form time series data. For each time point, calculate the difference between the predicted value of wind and solar power generation and the grid load demand data to obtain the power deficit or surplus at this time point. According to the positive or negative situation of the power deficit or surplus, judge the working state of the energy storage unit at this time point. If it is positive, the energy storage unit discharges; if it is negative, the energy storage unit charges. Adopt the sliding time window method to cumulatively calculate the power deficit or surplus data within a period of time to obtain the cumulative charge and discharge requirements of the energy storage unit within this time window.

[0064] Furthermore, constructing the charge and discharge optimization model of the energy storage unit includes:

[0065] Obtain the predicted curve of the charge and discharge requirements of the energy storage unit within a future period of time;

[0066] Obtain the initial state information of the energy storage unit; where the initial state information includes the current energy storage capacity and the charge and discharge power limit;

[0067] Take the initial state information and the charge and discharge losses as constraint conditions, and construct a charge and discharge optimization model based on the constraint conditions and the charge and discharge requirement prediction curve.

[0068] Specifically, in this embodiment, constructing the charge and discharge optimization model of the energy storage unit specifically includes: obtaining the initial state information of the energy storage unit, including parameters such as the current energy storage capacity and the charge and discharge power limit, as the constraint conditions of the optimization model. According to historical data and prediction algorithms, obtain the predicted curve of the charge and discharge requirements of the energy storage unit within a future period of time. Take factors such as the energy storage capacity limit, the charge and discharge power limit, and the charge and discharge losses as constraint conditions to establish a charge and discharge optimization model for the energy storage unit.

[0069] Furthermore, based on the charge and discharge optimization model, obtaining the charge and discharge plan of the energy storage unit includes:

[0070] Use the dynamic programming algorithm to solve the charge and discharge optimization model to obtain the optimal charge and discharge power of the energy storage unit at each moment during the prediction period;

[0071] Based on the optimal charge and discharge power, generate the charge and discharge plan of the energy storage unit; where the charge and discharge plan includes: the charge and discharge state and the charge and discharge amount at each moment.

[0072] Specifically, in this embodiment, a dynamic programming algorithm is used to solve the optimization model, and the optimal charging and discharging power of the energy storage unit at each moment within the prediction period is obtained. According to the optimal charging and discharging power, a detailed charging and discharging plan for the energy storage unit is generated, including the charging and discharging states and amounts at each moment. If there is a large deviation between the actual operating conditions and the prediction, the optimization model is triggered to recalculate and adjust the charging and discharging plan for the subsequent period. Continuously monitor the actual operating state of the energy storage unit, and feedback the measured data to the optimization model to continuously correct and improve the charging and discharging optimization strategy.

[0073] Further, the multi - energy collaborative control mathematical model includes: the operation constraints of the equipment;

[0074] The operation constraints of the equipment include: the cut - in and cut - out wind speed limits of the wind turbine, the maximum power generation limit of the photovoltaic array, and the charging and discharging power and capacity limits of the energy storage unit.

[0075] Further, based on the multi - energy collaborative control mathematical model, generating the coordinated control instructions includes:

[0076] Substitute the predicted values of wind and photovoltaic power generation, the charging and discharging plan of the energy storage unit, and the predicted load value into the multi - energy collaborative control mathematical model, and use the particle swarm optimization algorithm to solve the multi - energy collaborative control problem to obtain the optimal output scheduling plan for each device;

[0077] Based on the optimal output scheduling plan of each device, generate the power control instructions for the wind turbine, photovoltaic array, and energy storage unit.

[0078] Specifically, in this embodiment, a multi - energy system mathematical model including a wind turbine, a photovoltaic array, an energy storage unit, and a load is established, which includes the power balance constraints and operation constraints of each device, such as the cut - in and cut - out wind speed limits of the wind turbine, the maximum power generation limit of the photovoltaic array, and the charging and discharging power and capacity limits of the energy storage unit. Substitute the predicted values of wind and photovoltaic power generation, the charging and discharging plan of the energy storage unit, and the predicted load value into the multi - energy system mathematical model, and use an intelligent optimization algorithm, such as the particle swarm optimization algorithm or genetic algorithm, to solve the multi - energy collaborative control problem to obtain the optimal output scheduling plan for each device. According to the optimization results of the multi - energy collaborative control, generate the power control instructions for the wind turbine, photovoltaic array, and energy storage unit, and send them to the control systems of each device through a communication protocol to achieve real - time scheduling control of each device. Continuously monitor the real - time operating conditions of the wind turbine, photovoltaic array, energy storage unit, and load, and determine whether there is a large deviation. If there is a large deviation, trigger the re - solution of the multi - energy collaborative control model to generate updated device control instructions to ensure the stable operation of the multi - energy system.

[0079] This embodiment also collects the operation status data of each subsystem in real time, compares it with the output scheme, and determines whether the system operation status exceeds a preset threshold. If the system operation status exceeds the preset threshold, the predicted values of wind and photovoltaic power generation are recalculated, the charge and discharge requirements of the energy storage unit are updated, the multi-energy collaborative control mathematical model is solved again, new coordinated control instructions are generated, and are sent to each subsystem for execution through the communication network.

[0080] The operation status data of each subsystem is obtained in real time through sensors and data acquisition devices, including real-time power, voltage, current and other parameters of wind turbine generators, photovoltaic power generation systems, energy storage units, etc. The collected real-time operation status data is compared with the preset output scheme to determine whether the system operation status exceeds the preset threshold range. The threshold can be set according to historical operation data and expert experience. If it is determined that the system operation status exceeds the preset threshold, the wind and photovoltaic power generation prediction model is triggered to recalculate the short-term power prediction values of wind and photovoltaic power generation, considering influencing factors such as weather and temperature. According to the updated predicted values of wind and photovoltaic power generation, combined with the load demand prediction, the charge and discharge requirements of the energy storage unit are re-determined, including charge and discharge power and time periods, etc. Using the predicted values of wind and photovoltaic power generation, the charge and discharge requirements of the energy storage unit, etc. as inputs, a multi-objective optimization algorithm is used to solve the multi-energy collaborative control mathematical model again, generating a new coordinated control strategy and instruction set. The newly generated coordinated control instructions are sent to the controllers of each subsystem such as wind power, photovoltaic, and energy storage through the communication network. The controller analyzes the instructions and executes the corresponding control actions to adjust the operation conditions of the equipment. Continuously monitor the operation status feedback of each subsystem after executing the control instructions, and determine whether the system operation has returned to the normal range. If not, return to step 3 to continue iterative optimization until the requirements are met.

[0081] The embodiments described above are only descriptions of the preferred embodiments of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of the present invention shall fall within the protection scope determined by the claims of the present invention.

Claims

1. A wind-solar-storage integrated multi-energy coordinated control method, characterized in that: include: Predict future wind and solar power generation; Determine the charging and discharging plan of the energy storage unit based on the predicted wind and solar power generation power and grid load demand data; Based on the charging and discharging plan, the wind and solar power generation power forecast value and the real-time operation data of the energy system; Construct a multi-energy coordinated control mathematical model; wherein the real-time operation data of the energy system includes: real-time operation data of wind turbines, photovoltaic arrays, energy storage units, and loads; Based on the multi-energy collaborative control mathematical model, a coordinated control instruction is generated.

2. The integrated wind-solar-storage multi-energy coordinated control method according to claim 1 is characterized in that: The forecast of future wind and solar power generation capacity includes: Obtain historical power generation data of wind turbines and photovoltaic arrays; Acquire historical meteorological data corresponding to the geographical location of the wind turbine and the photovoltaic array; wherein the historical meteorological data includes: wind speed, wind direction and radiation; Aligning the historical power generation data and the historical meteorological data in time to construct a data set; Extracting preset features from the data set, and using a machine learning algorithm to train and construct a wind and solar power generation prediction model; wherein the preset features include: average wind speed, maximum wind speed, and total radiation; The wind-solar power generation prediction model is used to predict future wind-solar power generation.

3. The integrated wind-solar-storage multi-energy coordinated control method according to claim 1 is characterized in that: Determining the charging and discharging plan of the energy storage unit includes: Based on the wind and solar power generation power forecast value and the grid load demand data, the power difference between wind and solar power generation and load demand is calculated to determine the charging and discharging requirements of the energy storage unit; Based on the charging and discharging requirements, a charging and discharging optimization model of the energy storage unit is constructed taking into account the energy storage capacity limitation and the charging and discharging losses; Based on the charging and discharging optimization model, a charging and discharging plan of the energy storage unit is obtained.

4. The integrated wind-solar-storage multi-energy coordinated control method according to claim 3 is characterized in that: Determining the charging and discharging requirements of the energy storage unit includes: Calculate the difference between the wind and solar power generation forecast value and the grid load demand data to obtain the power deficit or surplus at the corresponding time point; Based on the power shortage or surplus at a time point, determine the working state of the energy storage unit at the time point, if it is a positive value, the energy storage unit is discharged, if it is a negative value, the energy storage unit is charged; The sliding time window method is used to accumulate and calculate the power shortage or surplus data within a period of time to obtain the cumulative charging and discharging requirements of the energy storage unit in the corresponding time window.

5. The integrated wind-solar-storage multi-energy coordinated control method according to claim 3 is characterized in that: Building a charging and discharging optimization model for energy storage units includes: Obtain the charging and discharging demand forecast curve of the energy storage unit in the future; Acquire initial state information of the energy storage unit; wherein the initial state information includes current energy storage capacity and charge and discharge power limits; The initial state information and charge and discharge loss are used as constraint conditions, and a charge and discharge optimization model is constructed based on the constraint conditions and the charge and discharge demand prediction curve.

6. The wind-solar-storage integrated multi-energy coordinated control method according to claim 3 is characterized in that: Based on the charging and discharging optimization model, obtaining a charging and discharging plan of the energy storage unit includes: A dynamic programming algorithm is used to solve the charging and discharging optimization model to obtain the optimal charging and discharging power of the energy storage unit at each moment in the prediction period; Based on the optimal charging and discharging power, a charging and discharging plan of the energy storage unit is generated; wherein the charging and discharging plan includes: the charging and discharging state and the charging and discharging amount at each moment.

7. The integrated wind-solar-storage multi-energy coordinated control method according to claim 1 is characterized in that: The multi-energy coordinated control mathematical model includes: equipment operation constraints; The operation constraints of the equipment include: wind speed limits for cutting in and out of wind turbines, maximum power generation limits for photovoltaic arrays, and charging and discharging power and capacity limits for energy storage units.

8. The wind-solar-storage integrated multi-energy coordinated control method according to claim 1 is characterized in that: Based on the multi-energy coordinated control mathematical model, generating coordinated control instructions includes: Substitute the wind and solar power generation power forecast value, the energy storage unit charging and discharging plan, and the load forecast value into the multi-energy coordinated control mathematical model, use the particle swarm optimization algorithm to solve the multi-energy coordinated control problem, and obtain the optimal output dispatch plan for each device; Based on the optimal output dispatch plan of each device, power control instructions for wind turbines, photovoltaic arrays and energy storage units are generated.

Images