Optical storage system cooperative control method and device, terminal and medium

Abstract

The invention relates to the field of optical storage, and particularly discloses an optical storage system cooperative control method and device, a terminal and a medium, and the method comprises the steps: collecting multi-dimensional data in real time, including photovoltaic array data, user side load data, power grid side information data, meteorological data and weather forecast information; generating a photovoltaic power generation power prediction curve, a user load demand prediction curve and a power grid electricity price prediction curve by using the multi-dimensional data through a machine learning model; and taking the current state of the optical storage system and each prediction curve as input parameters, carrying out optimization problem solving based on a multi-objective optimization function and constraint conditions through a model prediction control algorithm, generating an optimal control sequence in a period of time in the future, and controlling corresponding equipment through the optimal control sequence. According to the method, the response speed to uncertainties such as illumination abrupt change and load fluctuation is increased, source-storage-load-network coordination is realized, the sub-optimal problem of independent control of each unit is avoided, the operation cost is reduced, and renewable energy consumption is improved.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic storage, and in particular to a method, device, terminal and medium for collaborative control of a photovoltaic storage system. Background Art

[0002] Current PV-storage systems primarily rely on relatively simple and decentralized control strategies at the control method and device level. Common control strategies include rule-based control, maximum power point tracking (MPPT), and basic battery management systems. These control strategies suffer from the following drawbacks: Traditional control logic is typically based on fixed rules or thresholds, making it difficult to adapt to rapidly changing operating conditions in real time and lacking real-time adaptability and dynamic optimization capabilities. Furthermore, there is a lack of efficient coordinated control between PV generation, energy storage systems, user loads, and their interaction with the grid, preventing them from forming an integrated whole for global energy optimization and scheduling, resulting in insufficient coordinated control capabilities. This results in suboptimal system operation, preventing the full potential of PV-storage systems from being realized, potentially leading to unnecessary energy losses and increased system operating costs. Summary of the Invention

[0003] To solve the above problems, the present invention provides a method, device, terminal and medium for collaborative control of a photovoltaic storage system, which improves the response speed to uncertainties such as sudden changes in sunlight and load fluctuations, realizes the coordination of source-storage-load-grid, avoids the suboptimal problem of independent control of each unit, maximizes peak-valley arbitrage and ancillary service benefits, reduces operating costs, and improves the absorption of renewable energy.

[0004] In a first aspect, the technical solution of the present invention provides a method for collaborative control of a photovoltaic storage system, comprising the following steps: Real-time collection of multi-dimensional data, including photovoltaic array data, user-side load data, grid-side information data, meteorological data and weather forecast information; Constructing photovoltaic array data, meteorological data, and weather forecast information as first input data, and using a first machine learning model to process the first input data to output a photovoltaic power generation prediction curve; Constructing user-side load data as second input data, and using a second machine learning model to process the second input data to output a user load demand prediction curve; Constructing the grid-side information data as third input data, and using a third machine learning model to process the third input data to output a grid electricity price prediction curve; Construct a multi-objective optimization function with the goals of optimizing economic efficiency, maximizing renewable energy consumption, optimizing grid friendliness, maximizing energy storage life, and optimizing user energy experience, and configure constraints; The current state of the photovoltaic storage system is obtained, and the current state of the photovoltaic storage system, the photovoltaic power generation power forecast curve, the user load demand forecast curve, and the grid electricity price forecast curve are used as input parameters. The optimization problem is solved based on the multi-objective optimization function and constraint conditions through the model predictive control algorithm, and the optimal control sequence for a period of time in the future is generated. The corresponding equipment is controlled by the optimal control sequence.

[0005] In an optional embodiment, the multi-objective optimization function is expressed as,

[0006] Where, 、 、 、 、 are weight coefficients, is the economic sub-objective function, is the renewable energy consumption sub-objective function, is the grid-friendliness sub-objective function, is the energy storage life sub-objective function, Sub-objective function for user experience.

[0007] In an optional embodiment, the constraints include the upper and lower limits of the SoC of the energy storage battery, the maximum charge and discharge power, the charge and discharge efficiency, the output power limit of the photovoltaic inverter, the power purchase and sales power limit of the power grid, the voltage and current constraints, the start and stop time of the controllable load, and the operating power range.

[0008] In an optional embodiment, the optimal control sequence includes the charging and discharging power of the energy storage converter, the output power limit value of the photovoltaic inverter, the power of the grid-connected interface device purchased from the grid and the power of the grid sold to the grid, and the start and stop status and set parameters of the intelligent controllable load.

[0009] In an optional embodiment, a model predictive control algorithm is used to solve the optimization problem based on the multi-objective optimization function and the constraints, and an optimal control sequence for a period of time in the future is generated. The corresponding device is controlled by the optimal control sequence, specifically including: Step 1: Set the scenario parameters, including optimization frequency, prediction time domain, and control time domain; Step 2: Obtain the current state of the photovoltaic storage system, collect the photovoltaic power generation prediction curve, the user load demand prediction curve, and the grid electricity price prediction curve, and construct the current photovoltaic storage system state, photovoltaic power generation prediction curve, user load demand prediction curve, and grid electricity price prediction curve as input parameters; Step 3: Based on the scenario parameters and input parameters, the optimization problem is solved by using a model predictive control algorithm based on the multi-objective optimization function and constraints to generate an optimal control sequence for a period of time in the future; Step 4: Control the corresponding device through the optimal control sequence of the first time step, and return to step 2 after waiting for the length of one time step.

[0010] In an optional embodiment, controlling the corresponding device through the optimal control sequence specifically includes: The optimal control sequence is converted into control instructions for the corresponding equipment, and the control instructions are sent to the corresponding equipment.

[0011] In an optional embodiment, the photovoltaic array data includes historical power generation data and the current operating status of the photovoltaic array; the user-side load data includes historical electricity consumption data, user behavior pattern analysis data, time factor data, and potential adjustment space parameters of controllable loads; the grid-side information data includes historical electricity price data, historical load data, power generation side data, and grid status data.

[0012] In a second aspect, the technical solution of the present invention provides a photovoltaic storage system collaborative control device, comprising: Real-time data acquisition module, used to collect multi-dimensional data in real time, including photovoltaic array data, user-side load data, grid-side information data, meteorological data and weather forecast information; A first prediction module is configured to construct photovoltaic array data, meteorological data, and weather forecast information as first input data, and use a first machine learning model to process the first input data to output a photovoltaic power generation prediction curve; A second prediction module is configured to construct user-side load data as second input data, and use a second machine learning model to process the second input data to output a user load demand prediction curve; A third prediction module is configured to construct the grid-side information data as third input data, process the third input data using a third machine learning model, and output a grid electricity price prediction curve; The objective optimization function construction module is used to construct a multi-objective optimization function with the goals of optimizing economic efficiency, maximizing renewable energy consumption, optimizing grid friendliness, maximizing energy storage life, and optimizing user energy experience, and configure constraints; The optimal control sequence generation and execution module is used to obtain the current state of the photovoltaic storage system, take the current state of the photovoltaic storage system, the photovoltaic power generation power prediction curve, the user load demand prediction curve, and the grid electricity price prediction curve as input parameters, solve the optimization problem based on the multi-objective optimization function and constraints through the model predictive control algorithm, generate the optimal control sequence for a period of time in the future, and control the corresponding equipment through the optimal control sequence.

[0013] In a third aspect, the technical solution of the present invention provides a terminal, including: A memory, used for storing a cooperative control program of the optical storage system; A processor is used to implement the steps of the photovoltaic storage system collaborative control method as described in any one of the above items when executing the photovoltaic storage system collaborative control program.

[0014] In a fourth aspect, the technical solution of the present invention provides a computer-readable storage medium, on which a photovoltaic storage system collaborative control program is stored. When the photovoltaic storage system collaborative control program is executed by a processor, the steps of the photovoltaic storage system collaborative control method as described in any one of the above items are implemented.

[0015] It can be seen from the above technical solutions that this application has the following advantages: 1. This application dynamically generates high-precision forecast curves for photovoltaic power generation, load demand, and electricity prices by collecting multi-dimensional data such as photovoltaic, load, power grid, and meteorological data in real time, combined with machine learning prediction models, thus overcoming the lag of traditional fixed rule control. Furthermore, the model predictive control will be based on a rolling optimization mechanism, adjusting the control strategy based on the latest forecast and system status every certain period of time, improving the response speed to uncertainties such as sudden changes in sunlight and load fluctuations, and ensuring that the system always operates in the optimal state. 2. This application achieves source-storage-load-grid synergy by constructing a weighted objective function of economic efficiency, renewable energy absorption, grid friendliness, energy storage lifespan, and user experience. This avoids the suboptimal problem of independent control of each unit and extends the lifespan of the energy storage system. Furthermore, it intelligently regulates controllable loads such as air conditioners and EV charging stations, ensuring user comfort while participating in demand response and further reducing peak-valley differences. 3. This application can maximize peak-valley arbitrage and ancillary service revenue, reduce operating costs, increase the self-use rate of photovoltaic power generation, reduce the abandonment rate, increase the absorption of renewable energy, and reduce energy waste through electricity price forecasting and energy storage optimization scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 A schematic flow chart of a method for collaborative control of a photovoltaic storage system provided by an embodiment of the present invention.

[0018] Figure 2 A schematic block diagram of the structure of a photovoltaic storage system collaborative control device provided in an embodiment of the present invention.

[0019] Figure 3 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the application objectives, features, and advantages of this application more obvious and easy to understand, the technical solutions protected by this application will be clearly and completely described below using specific embodiments and drawings. Obviously, the embodiments described below are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0021] Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as those commonly understood by those skilled in the art to which the present invention pertains. The terms used in this application and in the specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention.

[0022] Figure 1 A schematic flow chart of a method for cooperative control of a photovoltaic storage system provided by an embodiment of the present invention. Figure 1 The execution entity may be a photovoltaic-storage system collaborative control device. The photovoltaic-storage system collaborative control method provided in the embodiments of the present invention is executed by a computer device. Accordingly, the photovoltaic-storage system collaborative control device runs on the computer device. Depending on different needs, the order of the steps in this flowchart may be changed, and some steps may be omitted.

[0023] like Figure 1 As shown, the method includes the following steps.

[0024] S1 collects multi-dimensional data in real time, including photovoltaic array data, user-side load data, grid-side information data, meteorological data, and weather forecast information.

[0025] Real-time collection of photovoltaic array data, user-side load data, grid-side information data, as well as local high-precision meteorological data (irradiance, temperature, wind speed, etc.) and weather forecast information obtained through external interfaces (such as API).

[0026] PV array data includes historical power generation data and the current operating status of the PV array. Specifically, historical power generation data includes actual power generation every 15 minutes over the past 24 hours. The current operating status of the PV array includes the tilt and azimuth of the modules, module cleanliness or contamination, system health (for example, whether there are any faulty or degraded modules), and grid connection status.

[0027] User-side load data includes historical electricity usage data, user behavior pattern analysis data, time factor data, and potential adjustment space parameters for controllable loads. Specifically, historical electricity usage data represents actual hourly electricity usage over the past 15 days. User behavior pattern analysis data includes load characteristics (statistical features extracted from historical data to describe user electricity usage habits), peak load (the highest daily electricity usage), valley load (the lowest daily electricity usage), peak-valley difference (the difference between peak and valley), and load factor (the ratio of average load to peak load). Time factor data includes calendar characteristics and seasonal characteristics. Calendar characteristics include time of day (specific time of day, 0 to 23:00), day of the week (Monday to Sunday, represented by numbers 1-7), and whether it is a weekday, weekend, or holiday (1 represents a holiday, 0 represents a non-holiday). Seasonal characteristics include season (spring, summer, autumn, and winter, coded 1-4) and special period identifiers (whether it is the heating or cooling season). The potential adjustment parameters for controllable loads include device rated power (the maximum operating power of each controllable device), device operating status (whether it is currently on or off), device adjustable range, and response willingness / priority (the user-defined priority or willingness of the device to participate in demand response). For air conditioners, the adjustable range is the upper and lower acceptable temperature settings. For charging stations, the adjustable range is the expected charging completion time and the current state of charge (SoC). For water heaters, the adjustable range is the acceptable water temperature range.

[0028] Grid-side information data includes historical electricity price data, historical load data, power generation data, and grid status data. Specifically, historical electricity price data includes historical price series from the day-ahead market, intraday market, and real-time market. Historical load data includes the total power load data of the grid over the past period of time. Power generation data includes renewable energy forecasts (wind and solar power generation forecasts) and unit status (available capacity and maintenance plans for traditional power generation units (thermal power, nuclear power)). Grid status data includes historical frequency data (minute-level historical records of grid frequency), historical frequency regulation / peak regulation data (actual calls and prices for peak and frequency regulation services in the past), tie line power (planned and actual power for cross-regional power transmission), and time characteristic data (hour, day of the week, whether it is a holiday, etc.).

[0029] Meteorological data include total solar radiation, diffuse radiation, direct radiation, ambient temperature, wind speed, wind direction, relative humidity, and cloud cover.

[0030] Weather forecast information includes the predicted radiation values ​​for the next 24, 48, and 72 hours, the predicted temperature values ​​for the next 24, 48, and 72 hours, and the predicted weather conditions for the next 24, 48, and 72 hours (such as sunny, cloudy, rainy, snowy, etc.).

[0031] After the data is collected, the collected raw data is cleaned, verified, format converted and time synchronized to build a unified multi-dimensional time series database, providing a high-quality data foundation for subsequent prediction and optimization.

[0032] S2: PV array data, meteorological data, and weather forecast information are constructed as first input data, and a first machine learning model is used to process the first input data to output a PV power generation prediction curve.

[0033] This step combines photovoltaic array data, meteorological data, and weather forecast information, and uses the first machine learning model to predict the power generation of the photovoltaic system. It can make high-precision predictions of the power generation at multiple time scales in the future (for example, the next 15 minutes, 1 hour, and 24 hours).

[0034] In some optional embodiments, the first machine learning model is a long short-term memory network (LSTM) + attention mechanism (Attention) architecture, which includes an input layer, an LSTM layer (64 units), an LSTM layer (32 units), an Attention layer, a fully connected layer (ReLU), and an output layer (linear).

[0035] Its objective function minimizes the mean square error (MSE) of the prediction error and controls the model complexity, which is expressed as,

[0036] Where, is the time period t i The predicted value of photovoltaic power generation is is the time period t i The actual value of photovoltaic power generation, is the sample size, is the regularization coefficient, are the model parameters (weights and biases to be optimized), is the L2 regularization term.

[0037] S3: Construct the user-side load data as the second input data, and use the second machine learning model to process the second input data to output a user load demand prediction curve.

[0038] This step uses the second machine learning model to predict the user's total load curve for multiple future time scales (e.g., the next 15 minutes, 1 hour, and 24 hours) based on the user-side load data.

[0039] In some optional embodiments, the second machine learning model is a gradient boosting tree (XGBoost) + time feature engineering architecture, which includes an input layer, a feature engineering (one-hot encoding weekdays / holidays) layer, an XGBoost (100 trees, max_depth=6), and an output layer.

[0040] Its objective function minimizes the weighted square error of load forecast error while limiting the model complexity, which is expressed as,

[0041] Where, is the time period t i The load demand forecast value, is the time period t i The true value of the load demand, is the regularization coefficient, is the complexity penalty term of the j-th tree, is the total number of trees.

[0042] S4, constructing the grid-side information data as third input data, and using a third machine learning model to process the third input data to output a grid electricity price prediction curve.

[0043] This step uses the third machine learning model to predict the fluctuation trend of grid electricity prices based on grid-side information data and predict electricity prices at multiple time scales in the future (e.g., the next 24 hours, 48 ​​hours).

[0044] In some optional embodiments, the third machine learning model is a Transformer + convolutional neural network (CNN) architecture, which includes an input layer, a CNN (extracting local fluctuation features) layer, a Transformer encoder (capturing long-term dependencies) layer, a fully connected layer, and an output layer.

[0045] Its objective function minimizes the mean absolute error (MAE) of electricity price forecast and gives priority to peak period forecast accuracy, which is expressed as,

[0046] Where, is the time period t i The electricity price forecast value, is the time period t i The real value of electricity price, is the mean absolute error during peak hours, is the peak period error weight coefficient.

[0047] S5 constructs a multi-objective optimization function with the goals of optimizing economic efficiency, maximizing renewable energy consumption, optimizing grid friendliness, maximizing energy storage life, and optimizing user energy experience, and configures constraints.

[0048] A multi-objective optimization function is formed by comprehensively considering multiple interrelated and even conflicting objectives. These objectives include: Economic optimization: Maximizing the net benefits of system operation, including minimizing electricity purchase costs, maximizing electricity sales revenue, and participating in ancillary service benefits.

[0049] Maximize renewable energy consumption: prioritize the use of local photovoltaic power generation and reduce abandoned solar power; Grid-friendly: Reduce impact on the grid, smooth the load curve, and provide grid support on demand (such as peak shaving, frequency regulation, and voltage support); Maximizing energy storage life: Extending the service life of energy storage batteries by optimizing charge and discharge strategies (such as controlling charge and discharge rate, depth, and frequency to avoid overcharge and overdischarge); User energy experience: Ensure reliable power supply to critical loads, and dispatch controllable loads within the range of comfort or convenience acceptable to users.

[0050] The multi-objective optimization function is expressed as,

[0051] Where, 、 、 、 、 are weight coefficients respectively, and the sum of the weight coefficients is 1; is the economic sub-objective function, is the renewable energy consumption sub-objective function, is the grid-friendliness sub-objective function, is the energy storage life sub-objective function, Sub-objective function for user experience.

[0052] In some optional embodiments, the economic sub-objective function The goal is to minimize the total system operating cost, including electricity purchase cost, electricity sales revenue, battery loss and ancillary service revenue, which can be expressed as,

[0053] Among them, the items in the brackets on the right side of the equation are, from left to right, the electricity purchase cost item, the electricity sales revenue item, the battery loss item, and the ancillary service revenue item.

[0054] is the electricity purchase price in period t, is the power purchased from the grid during period t, is the electricity price in period t, is the power sold to the grid during period t, is the loss cost coefficient of the battery per unit charge and discharge power, is the battery charging and discharging power (charging is negative, discharging is positive), is the income from participating in grid ancillary services in period t.

[0055] In some optional implementations, the renewable energy consumption sub-objective function The goal is to maximize the self-use rate of photovoltaic power generation and minimize the abandonment of light, which can be expressed as,

[0056] Where, is the photovoltaic power generation power in period t, is the load power during time period t. If the PV output exceeds the local load, energy storage charging, and electricity sales requirements, the excess is considered abandoned and needs to be minimized.

[0057] In some optional embodiments, the grid-friendliness sub-goal The goal is to smooth the interaction power with the grid, reduce the peak-valley difference, and provide auxiliary services (such as frequency regulation), which is expressed as,

[0058] Where, is the rate of change of grid interaction power, is the smoothness weight coefficient. The first term in the formula penalizes high-power interactions, and the second term penalizes power fluctuations.

[0059] In some optional embodiments, the energy storage life sub-objective function The goal is to extend battery life and reduce deep charge and discharge and high rate charge and discharge, expressed as,

[0060] Where, is the battery state of charge at time period t (0~1), For the ideal SOC, are weight coefficients, which penalize SOC deviation and charge and discharge power respectively.

[0061] In some optional implementations, the user experience sub-objective function The goal is to ensure user comfort and reduce the frequent adjustment of controllable loads, which can be expressed as,

[0062] Where, is the actual indoor temperature, Set the temperature for the user, is the controllable load power variation, are weight coefficients, which penalize temperature deviation and load fluctuation respectively.

[0063] In some optional embodiments, the constraints include the upper and lower limits of the SoC of the energy storage battery, the maximum charge and discharge power, the charge and discharge efficiency, the output power limit of the photovoltaic inverter, the power purchase and sales power limit of the power grid, the voltage and current constraints, the start and stop time of the controllable load, and the operating power range.

[0064] S6, obtain the current state of the photovoltaic storage system, use the current state of the photovoltaic storage system, the photovoltaic power generation power prediction curve, the user load demand prediction curve, and the grid electricity price prediction curve as input parameters, solve the optimization problem based on the multi-objective optimization function and constraints through the model predictive control algorithm, generate the optimal control sequence for a period of time in the future, and control the corresponding equipment through the optimal control sequence.

[0065] This step uses an optimization algorithm to generate the optimal control sequence based on the current photovoltaic storage system status, photovoltaic power generation power forecast curve, user load demand forecast curve, and grid electricity price forecast curve.

[0066] The optimization algorithm employed is model predictive control (MPC), whose core principle is "look ahead and take one step forward." It performs optimization within a limited timeframe (called the "prediction horizon"), executing only the first step based on the optimization results. This process is then repeated at the next time point, based on the latest system status and predictions. The optimization engine in this embodiment performs rolling optimization at a regular frequency (e.g., every 5-15 minutes). Based on the latest prediction results and system status, it generates the optimal control sequence for the next period (e.g., the next 1-24 hours). This process specifically includes the following steps.

[0067] S61, setting scenario parameters, including optimization frequency, prediction time domain, and control time domain.

[0068] Optimization frequency: Optimization is started every 15 minutes.

[0069] Forecast horizon (Np): Look ahead 24 hours (i.e. 96 15-minute time steps).

[0070] Control horizon (Nc): determines the control actions for the next few steps, usually Nc≤Np.

[0071] S62, obtain the current state of the photovoltaic storage system, collect the photovoltaic power generation power prediction curve, the user load demand prediction curve, and the grid electricity price prediction curve, and construct the current state of the photovoltaic storage system, the photovoltaic power generation power prediction curve, the user load demand prediction curve, and the grid electricity price prediction curve as input parameters.

[0072] The current system status includes the energy storage system status, PV power generation status, load status, grid interaction status, environmental and external conditions, and other key conditions. The energy storage system status includes the battery state of charge, battery health status, battery temperature, and charge and discharge power. The PV power generation status includes the PV array output power, PV DC voltage / current, and PV module temperature. The load status includes the total load power and controllable load status. The grid interaction status includes the grid purchased power, the grid sold power, and the grid frequency / voltage. The environmental and external conditions include real-time irradiance and ambient temperature. Other key conditions include the current electricity price signal and the ancillary service demand signal (which determines whether to participate in frequency regulation / peak regulation to obtain additional revenue).

[0073] The photovoltaic power generation power forecast curve, user load demand forecast curve, and grid electricity price forecast curve are forecast data for the next 24 hours.

[0074] S63, according to the scenario parameters and the input parameters, solving the optimization problem based on the multi-objective optimization function and the constraint conditions by using a model predictive control algorithm to generate an optimal control sequence for a period of time in the future.

[0075] Generate the optimal control sequence for the next 24 hours based on the set scenario parameters. S64, controlling the corresponding device through the optimal control sequence of the first time step, and returning to step S62 after waiting for the duration of one time step.

[0076] When executing the optimal control sequence, the optimal control sequence of the first time step of the algorithm is selected to control the corresponding device. For example, according to the set scene parameters, only the control instructions for the next 15 minutes are executed, and then return to step S62 after waiting for 15 minutes.

[0077] The optimal control sequence is a set of target power or state values ​​that change over time. At the beginning of each rolling optimization cycle (for example, 15 minutes), the control sequence for the entire future forecast horizon is calculated, but only the instructions for the first time step in the sequence (the next 15 minutes) are executed. The ICU (Intelligent Control Unit) converts the optimal control sequence into specific, executable control instructions and issues them to the corresponding devices.

[0078] In some optional implementations, the optimal control sequence includes the charge and discharge power of the energy storage converter, the output power limit of the photovoltaic inverter, the power purchased from the grid and sold to the grid by the grid-connected interface device, and the start and stop states and set parameters of the intelligent controllable load. Table 1 below shows the output parameters and corresponding devices included in the optimal control sequence within a time step.

[0079] Table 1: Snapshot of the optimal control sequence within one time step

[0080] An embodiment of a photovoltaic storage system collaborative control method is described in detail above. Based on the photovoltaic storage system collaborative control method described in the above embodiment, an embodiment of the present invention further provides a photovoltaic storage system collaborative control device corresponding to the method.

[0081] Figure 2 This is a schematic block diagram of the structure of a photovoltaic-storage system collaborative control device provided in an embodiment of the present invention. In this embodiment, the photovoltaic-storage system collaborative control device 200 can be divided into multiple functional modules according to the functions they perform. A module, as referred to in this invention, is a series of computer program segments that can be executed by at least one processor and can perform fixed functions, and is stored in a memory.

[0082] The real-time data acquisition module 210 is used to acquire multi-dimensional data in real time, including photovoltaic array data, user-side load data, grid-side information data, meteorological data and weather forecast information.

[0083] The first prediction module 220 is used to construct the photovoltaic array data, meteorological data and weather forecast information as first input data, use the first machine learning model to process the first input data, and output a photovoltaic power generation prediction curve.

[0084] The second prediction module 230 is used to construct the user-side load data as second input data, and use the second machine learning model to process the second input data to output a user load demand prediction curve.

[0085] The third prediction module 240 is used to construct the grid-side information data into third input data, and use the third machine learning model to process the third input data to output a grid electricity price prediction curve.

[0086] The objective optimization function construction module 250 is used to construct a multi-objective optimization function with the goals of optimizing economy, maximizing renewable energy consumption, optimizing grid friendliness, maximizing energy storage life, and optimizing user energy experience, and configure constraints.

[0087] The optimal control sequence generation and execution module 260 is used to obtain the current state of the photovoltaic storage system, take the current state of the photovoltaic storage system, the photovoltaic power generation power prediction curve, the user load demand prediction curve, and the grid electricity price prediction curve as input parameters, solve the optimization problem based on the multi-objective optimization function and constraint conditions through the model predictive control algorithm, generate the optimal control sequence for a period of time in the future, and control the corresponding equipment through the optimal control sequence.

[0088] The photovoltaic storage system collaborative control device of this embodiment is used to implement the aforementioned photovoltaic storage system collaborative control method. Therefore, the specific implementation method of the device can be seen in the embodiment part of the photovoltaic storage system collaborative control method in the previous text. Therefore, its specific implementation method can refer to the description of the corresponding embodiments of each part and will not be elaborated here.

[0089] In addition, since the photovoltaic storage system collaborative control device of this embodiment is used to implement the aforementioned photovoltaic storage system collaborative control method, its function corresponds to that of the aforementioned method and will not be described in detail here.

[0090] Figure 3 A schematic diagram of the structure of a terminal 300 provided in an embodiment of the present invention includes: a processor 310, a memory 320, and a communication unit 330. The processor 310 is configured to implement the steps of the embodiment of the photovoltaic-storage system collaborative control method when executing the photovoltaic-storage system collaborative control program stored in the memory 320.

[0091] The terminal 300 includes a processor 310, a memory 320, and a communication unit 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention; it may be a bus structure or a star structure, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0092] Memory 320 can be used to store execution instructions of processor 310. Memory 320 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk. When the execution instructions in memory 320 are executed by processor 310, terminal 300 can perform some or all of the steps in the above-described method embodiments.

[0093] The processor 310 is the control center of the storage terminal. It uses various interfaces and lines to connect various parts of the entire electronic terminal. It executes various functions of the electronic terminal and / or processes data by running or executing software programs and / or modules stored in the memory 320, and calling data stored in the memory. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 310 can only include a central processing unit (CPU). In the embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0094] The communication unit 330 is configured to establish a communication channel so that the storage terminal can communicate with other terminals, receive user data sent by other terminals, or send user data to other terminals.

[0095] The present invention also provides a computer storage medium, wherein the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0096] The present invention also provides a computer storage medium, wherein the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0097] The computer storage medium stores a photovoltaic storage system collaborative control program, and when the photovoltaic storage system collaborative control program is executed by the processor, the steps of the above-mentioned photovoltaic storage system collaborative control method embodiment are implemented.

[0098] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus a necessary general-purpose hardware platform. Based on this understanding, the technical solutions in the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, among other media capable of storing program code, and includes instructions for causing a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention.

[0099] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0100] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0101] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0102] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein, but is intended to be construed in the widest manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for collaborative control of a photovoltaic storage system, characterized in that: The following steps are involved: Real-time collection of multi-dimensional data, including photovoltaic array data, user-side load data, grid-side information data, meteorological data and weather forecast information; Constructing photovoltaic array data, meteorological data, and weather forecast information as first input data, and using a first machine learning model to process the first input data to output a photovoltaic power generation prediction curve; Constructing user-side load data as second input data, and using a second machine learning model to process the second input data to output a user load demand prediction curve; Constructing the grid-side information data as third input data, and using a third machine learning model to process the third input data to output a grid electricity price prediction curve; Construct a multi-objective optimization function with the goals of optimizing economic efficiency, maximizing renewable energy consumption, optimizing grid friendliness, maximizing energy storage life, and optimizing user energy experience, and configure constraints; The current state of the photovoltaic storage system is obtained, and the current state of the photovoltaic storage system, the photovoltaic power generation power forecast curve, the user load demand forecast curve, and the grid electricity price forecast curve are used as input parameters. The optimization problem is solved based on the multi-objective optimization function and constraint conditions through the model predictive control algorithm, and the optimal control sequence for a period of time in the future is generated. The corresponding equipment is controlled by the optimal control sequence.

2. The method for cooperative control of a photovoltaic storage system according to claim 1, characterized in that: The multi-objective optimization function is expressed as, Where, 、 、 、 、 are weight coefficients, is the economic sub-objective function, is the renewable energy consumption sub-objective function, is the grid-friendliness sub-objective function, is the energy storage life sub-objective function, Sub-objective function for user experience.

3. The method for controlling a photovoltaic storage system according to claim 1, wherein: The constraints include the upper and lower limits of the SoC of the energy storage battery, the maximum charge and discharge power, the charge and discharge efficiency, the output power limit of the photovoltaic inverter, the power purchase and sales power limit of the power grid, the voltage and current constraints, the start and stop time of the controllable load, and the operating power range.

4. The method for controlling a photovoltaic storage system according to claim 1, wherein: The optimal control sequence includes the charging and discharging power of the energy storage converter, the output power limit value of the photovoltaic inverter, the power of the grid-connected interface device to purchase electricity from the grid and the power of electricity sold to the grid, and the start and stop status and setting parameters of the intelligent controllable load.

5. The method for controlling a photovoltaic storage system according to claim 1, wherein: Solving the optimization problem based on the multi-objective optimization function and constraints using a model predictive control algorithm, generating an optimal control sequence for a period of time in the future, and controlling the corresponding equipment using the optimal control sequence, specifically including: Step 1: Set the scenario parameters, including optimization frequency, prediction time domain, and control time domain; Step 2: Obtain the current state of the photovoltaic storage system, collect the photovoltaic power generation prediction curve, the user load demand prediction curve, and the grid electricity price prediction curve, and construct the current photovoltaic storage system state, photovoltaic power generation prediction curve, user load demand prediction curve, and grid electricity price prediction curve as input parameters; Step 3: Based on the scenario parameters and input parameters, the optimization problem is solved by using a model predictive control algorithm based on the multi-objective optimization function and constraints to generate an optimal control sequence for a period of time in the future; Step 4: Control the corresponding device through the optimal control sequence of the first time step, and return to step 2 after waiting for the length of one time step.

6. The method for controlling a photovoltaic storage system according to claim 1, wherein: Controlling the corresponding equipment through the optimal control sequence specifically includes: The optimal control sequence is converted into control instructions for the corresponding equipment, and the control instructions are sent to the corresponding equipment.

7. The method for cooperative control of a photovoltaic storage system according to claim 1, characterized in that: Photovoltaic array data includes historical power generation data and the current operating status of the photovoltaic array; user-side load data includes historical electricity consumption data, user behavior pattern analysis data, time factor data, and potential adjustment space parameters of controllable loads; grid-side information data includes historical electricity price data, historical load data, power generation side data, and grid status data.

8. A photovoltaic storage system collaborative control device, characterized in that: include: Real-time data acquisition module, used to collect multi-dimensional data in real time, including photovoltaic array data, user-side load data, grid-side information data, meteorological data and weather forecast information; A first prediction module is configured to construct photovoltaic array data, meteorological data, and weather forecast information as first input data, and use a first machine learning model to process the first input data to output a photovoltaic power generation prediction curve; A second prediction module is configured to construct user-side load data as second input data, and use a second machine learning model to process the second input data to output a user load demand prediction curve; A third prediction module is configured to construct the grid-side information data as third input data, process the third input data using a third machine learning model, and output a grid electricity price prediction curve; The objective optimization function construction module is used to construct a multi-objective optimization function with the goals of optimizing economic efficiency, maximizing renewable energy consumption, optimizing grid friendliness, maximizing energy storage life, and optimizing user energy experience, and configure constraints; The optimal control sequence generation and execution module is used to obtain the current state of the photovoltaic storage system, take the current state of the photovoltaic storage system, the photovoltaic power generation power prediction curve, the user load demand prediction curve, and the grid electricity price prediction curve as input parameters, solve the optimization problem based on the multi-objective optimization function and constraints through the model predictive control algorithm, generate the optimal control sequence for a period of time in the future, and control the corresponding equipment through the optimal control sequence.

9. A terminal, characterized in that: include: A memory, used for storing a cooperative control program of the optical storage system; A processor is configured to implement the steps of the photovoltaic-storage system collaborative control method according to any one of claims 1 to 7 when executing the photovoltaic-storage system collaborative control program.

10. A computer-readable storage medium, characterized in that The readable storage medium stores a photovoltaic storage system collaborative control program, which, when executed by a processor, implements the steps of the photovoltaic storage system collaborative control method according to any one of claims 1 to 7.

Images