Control method and system of car light storage and charging system and electronic equipment

Abstract

The invention relates to a control method and system of a car home light storage and charging system and electronic equipment, and is applied to the technical field of vehicles, and the method comprises the steps that comprehensive energy data of the car home light storage and charging system are acquired, the car home light storage and charging system comprises multiple pieces of power equipment, and the power equipment comprises an inverter and a vehicle; according to the comprehensive energy data, determining an energy management strategy of the vehicle home light storage and charging system, wherein the energy management strategy is used for indicating the adjustment condition of the charging and discharging power of each device in the vehicle home light storage and charging system; obtaining an electric power planning strategy sent by the vehicle, wherein the electric power planning strategy is used for indicating the power utilization planning condition of each device in the vehicle home light storage and charging system; and based on the energy management strategy and the power planning strategy, controlling each power device in the car home light storage and charging system.

Description

Technical Field

[0001] This application relates to the technical field of vehicles, and in particular, to a control method, system, and electronic device for a vehicle-home photovoltaic energy storage charging system. Background Art

[0002] With the growth of global energy demand and the enhancement of environmental awareness, distributed energy systems (such as photovoltaic power generation, energy storage systems, and automobiles) have gradually become an important part of the energy Internet.

[0003] Traditional energy management systems usually rely on fixed rule logics or simple optimization algorithms. For example, they control the charging and discharging power of home photovoltaic energy storage charging according to pre-set charging and discharging parameters. This method is difficult to cope with complex dynamic environments and lacks self-adaptive capabilities. Summary of the Invention

[0004] This application provides a control method, system, and electronic device for a vehicle-home photovoltaic energy storage charging system to solve the problem in the prior art that controlling the charging and discharging power of home photovoltaic energy storage charging with fixed charging and discharging parameters is not self-adaptive.

[0005] According to the first aspect of the embodiments of this application, a control method for a vehicle-home photovoltaic energy storage charging system is provided, which is applied to an inverter. The method includes:

[0006] Obtain comprehensive energy data of the vehicle-home photovoltaic energy storage charging system. The vehicle-home photovoltaic energy storage charging system includes multiple power devices, and the power devices include an inverter and a vehicle;

[0007] Determine an energy management strategy for the vehicle-home photovoltaic energy storage charging system according to the comprehensive energy data. The energy management strategy is used to indicate the adjustment of the charging and discharging power of each device in the vehicle-home photovoltaic energy storage charging system;

[0008] Obtain a power planning strategy sent by the vehicle. The power planning strategy is used to indicate the power consumption planning of each device in the vehicle-home photovoltaic energy storage charging system;

[0009] Based on the energy management strategy and the power planning strategy, control each of the power devices in the vehicle-home photovoltaic energy storage charging system.

[0010] Optionally, determining the energy management strategy for the vehicle-home photovoltaic energy storage charging system according to the comprehensive energy data includes:

[0011] Input the comprehensive energy data into a pre-trained reinforcement learning model, and predict the comprehensive energy data through the reinforcement learning model to obtain the energy management strategy.

[0012] Optionally, the training process of the reinforcement learning model includes:

[0013] Obtain a training sample set, where the training sample set includes multiple integrated energy data samples,

[0014] Initialize the Q-network parameters and target network parameters in the original reinforcement learning model;

[0015] Select the current execution action according to the integrated energy data sample, where the current execution action can represent an energy management strategy;

[0016] Execute according to the current execution action to obtain the current integrated energy data and execution reward value;

[0017] Update the Q-network parameters to minimize the loss function.

[0018] Optionally, the execution reward value is obtained by the following method:

[0019]

[0020] where R represents the execution reward value, C represents the electricity price cost coefficient, represents the power supplied from the power grid to the household load, t represents the power consumption duration, represents the power supplied from the vehicle to the household load, represents the power supplied from the energy storage device to the household load, represents the battery charge rate change, represents the battery health rate change, P {imbalance} represents the system power imbalance, and R1, R2, and R3 all represent weight coefficients.

[0021] Optionally, the current execution actions include: vehicle charging / discharging power adjustment, energy storage device charging / discharging power adjustment, and household load power distribution.

[0022] Optionally, the loss function is:

[0023]

[0024] where L(θ) represents the loss function, R t represents the execution reward value obtained at time step t, represents the expectation with respect to the integrated energy data sample S t 、the current execution action A t 、the execution reward value R t and the current integrated energy data S t+1 ,Q(S t ,A t ;θ) represents the action value function with Q-network parameters θ when taking A t under S t ,γ represents the discount factor, represents under St+1 Under the following conditions, for all possible actions a, it is the maximum value of the action value function with the target network parameter θ'.

[0025] According to the second aspect of the embodiments of the present application, a control method for a vehicle-home photovoltaic-storage-charging system is provided, which is applied to a vehicle. The method includes:

[0026] Obtain the comprehensive energy data of the vehicle-home photovoltaic-storage-charging system. The vehicle-home photovoltaic-storage-charging system includes multiple power devices, and the power devices include an inverter and a vehicle;

[0027] Determine the smart grid mode of the vehicle-home photovoltaic-storage-charging system;

[0028] Based on the smart grid mode and the comprehensive energy data, determine the power planning strategy of the vehicle-home photovoltaic-storage-charging system;

[0029] Send the power planning strategy to the inverter, so that the inverter controls each power device in the vehicle-home photovoltaic-storage-charging system based on the energy management strategy determined by itself and the power planning strategy.

[0030] Optionally, based on the smart grid mode and the comprehensive energy data, determining the power planning strategy of the vehicle-home photovoltaic-storage-charging system includes:

[0031] Determine the power consumption behavior data of the vehicle-home photovoltaic-storage-charging system from a pre-constructed knowledge base;

[0032] Based on the thought chain constructed in the planning model, reason about the power consumption behavior data, the smart grid mode, and the comprehensive energy data to obtain the power planning strategy.

[0033] According to the third aspect of the embodiments of the present application, a control system for a vehicle-home photovoltaic-storage-charging system is provided, including: the inverter described in the first aspect, the vehicle described in the second aspect, and a household load.

[0034] According to the fourth aspect of the embodiments of the present application, a control device for a vehicle-home photovoltaic-storage-charging system is provided, including:

[0035] A first acquisition unit for acquiring the comprehensive energy data of the vehicle-home photovoltaic-storage-charging system. The vehicle-home photovoltaic-storage-charging system includes multiple power devices, and the power devices include an inverter and a vehicle;

[0036] A first determination unit for determining the energy management strategy of the vehicle-home photovoltaic-storage-charging system according to the comprehensive energy data. The energy management strategy is used to indicate the adjustment situation of the charging and discharging power of each device in the vehicle-home photovoltaic-storage-charging system;

[0037] A second acquisition unit, configured to acquire the power planning strategy sent by the vehicle, where the power planning strategy is used to indicate the power usage planning conditions of each device in the vehicle-home photovoltaic-storage-charging system;

[0038] A control unit, configured to control each of the power devices in the vehicle-home photovoltaic-storage-charging system based on the energy management strategy and the power planning strategy.

[0039] According to a fifth aspect of the embodiments of the present application, there is provided a control device for a vehicle-home photovoltaic-storage-charging system, including:

[0040] A third acquisition unit, configured to acquire the integrated energy data of the vehicle-home photovoltaic-storage-charging system. The vehicle-home photovoltaic-storage-charging system includes a plurality of power devices, and the power devices include an inverter and a vehicle;

[0041] A second determination unit, configured to determine the smart grid mode of the vehicle-home photovoltaic-storage-charging system;

[0042] A third determination unit, configured to determine the power planning strategy of the vehicle-home photovoltaic-storage-charging system based on the smart grid mode and the integrated energy data;

[0043] A sending unit, configured to send the power planning strategy to the inverter, so that the inverter controls each of the power devices in the vehicle-home photovoltaic-storage-charging system based on the energy management strategy determined by itself and the power planning strategy.

[0044] According to a sixth aspect of the embodiments of the present application, there is provided an electronic device, including a memory and a processor;

[0045] The memory is connected to the processor and is used to store a program;

[0046] The processor is configured to implement the control method of the vehicle-home photovoltaic-storage-charging system as described in the first aspect or the second aspect by running the program in the memory.

[0047] According to a seventh aspect of the embodiments of the present application, there is provided a storage medium, on which a computer program is stored. When the computer program is run by a processor, the control method of the vehicle-home photovoltaic-storage-charging system as described in the first aspect or the second aspect is implemented.

[0048] According to an eighth aspect of the embodiments of the present application, there is provided a computer program product, including computer program instructions. When the computer program instructions are run by a processor, the processor is caused to execute the control method of the vehicle-home photovoltaic-storage-charging system as described in the first aspect or the second aspect.

[0049] The above technical solution provided by the embodiments of the present application has the following advantages compared with the prior art: In the method provided by the embodiments of the present application, by obtaining the comprehensive energy data of the vehicle-home photovoltaic-storage-charging system, the vehicle-home photovoltaic-storage-charging system includes a plurality of power devices, and the power devices include an inverter and a vehicle; determining an energy management strategy for the vehicle-home photovoltaic-storage-charging system according to the comprehensive energy data, where the energy management strategy is used to indicate the adjustment of the charging and discharging power of each device in the vehicle-home photovoltaic-storage-charging system; obtaining a power planning strategy sent by the vehicle; and controlling each of the power devices in the vehicle-home photovoltaic-storage-charging system based on the energy management strategy and the power planning strategy. In this way, it is possible to utilize the obtained total energy data in real time to perform real-time regulation and planning on the power situation of the vehicle-home photovoltaic-storage-charging system, and it can also be adaptively adjusted in the face of a complex environment. Moreover, the vehicle can be fully integrated into the home energy management terminal intelligently, realizing intelligent and real-time energy management decision-making for the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0051] Figure 1 Structural schematic diagram of a vehicle-home photovoltaic-storage-charging system provided by an embodiment of the present application;

[0052] Figure 2 Flowchart of the control method of the vehicle-home photovoltaic-storage-charging system provided by an embodiment of the present application;

[0053] Figure 3 Flowchart of the control method of the vehicle-home photovoltaic-storage-charging system provided by another embodiment of the present application;

[0054] Figure 4 Structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0056] EXEMPLARY IMPLEMENTATION ENVIRONMENT

[0057] The control method of the vehicle-home photovoltaic-storage-charging system according to the embodiments of the present application can be executed by power equipment such as an inverter and a vehicle in the vehicle-home photovoltaic-storage-charging system (hereinafter referred to as the system). Among them, the vehicle-home photovoltaic-storage-charging system includes an inverter, a vehicle, a home load, a energy storage device, a photovoltaic device, a power grid, etc.

[0058] Among them, the inverter obtains the comprehensive energy data of the vehicle-home photovoltaic-storage-charging system. The vehicle-home photovoltaic-storage-charging system includes multiple power equipment, and the power equipment includes an inverter and a vehicle; determine the energy management strategy of the vehicle-home photovoltaic-storage-charging system according to the comprehensive energy data, and the energy management strategy is used to indicate the adjustment of the charging and discharging power of each device in the vehicle-home photovoltaic-storage-charging system; obtain the power planning strategy sent by the vehicle, and the power planning strategy is used to indicate the electricity consumption planning of each device in the vehicle-home photovoltaic-storage-charging system; based on the energy management strategy and the power planning strategy, control each power device in the vehicle-home photovoltaic-storage-charging system.

[0059] The vehicle obtains the comprehensive energy data of the vehicle-home photovoltaic-storage-charging system. The vehicle-home photovoltaic-storage-charging system includes multiple power equipment, and the power equipment includes an inverter and a vehicle; determine the smart grid mode of the vehicle-home photovoltaic-storage-charging system; based on the smart grid mode and the comprehensive energy data, determine the power planning strategy of the vehicle-home photovoltaic-storage-charging system; send the power planning strategy to the inverter so that the inverter controls each power device in the vehicle-home photovoltaic-storage-charging system based on the energy management strategy and the power planning strategy determined by itself.

[0060] The vehicle-home photovoltaic-storage-charging system of the present application is a real-time energy distribution system based on reinforcement learning, which can make decisions in real time and adjust the energy flow direction (such as charging / discharging) in real time according to information such as vehicle status (battery level, location), home electricity demand, photovoltaic power generation, and energy storage status. The system finds the optimal balance point among multiple objectives such as reducing electricity costs, increasing energy self-sufficiency rate, and extending battery life by continuously iterating and optimizing strategies, and adapts to uncertain factors such as changes in driver behavior and weather fluctuations. Its advantages are strong real-time performance and high self-adaptability. The personalized energy management strategy driven by the vehicle large model uses the large model to analyze the user's driving habits (such as charging time, driving route), home electricity consumption patterns (such as peak electricity consumption periods), and the change rules of photovoltaic power generation (such as power generation efficiency under different weather conditions), and generates personalized charging / discharging plans and energy-saving suggestions. For example, "It is recommended to charge during the low electricity price period to reduce costs". The system explains the decision-making basis to the user in the form of natural language generation, and can predict future energy demands and adjust strategies in advance. Its advantages are data-driven, strong context understanding ability, and interpretability.

[0061] Moreover, this system is a long-term planning system that combines the historical electricity consumption trends of the household and the long-term planning capabilities of the large model to formulate flexible and sustainable energy management strategies. For example, adjust the charging / discharging strategy according to the user's driving plan and historical trends; formulate a flexible scheduling plan according to the changes in household electricity demand (such as seasonal changes). This system analyzes the historical electricity consumption of the household and the electricity consumption trends of the vehicle through the large model, predicts future electricity consumption, and plans long-term charging and discharging plans. Its advantages lie in being user-friendly, highly flexible, and having a long-term perspective.

[0062] The intelligent center with the vehicle as the core node is the central node of the entire "vehicle-home PV-storage-charging" system. It works in coordination with the inverter power management system, can operate independently offline, and is responsible for data analysis, recommendation generation, and long-term planning. The status of the vehicle (battery level, location, driving plan, etc.) is always used as the dynamic input of the entire system. Its advantage lies in highlighting the importance of the vehicle and being able to complete complex data analysis and decision support tasks even in offline / off-grid environments.

[0063] It can provide a user-friendly interface with natural language interaction, parse the user's voice or text instructions through natural language processing technology, and convert them into specific scheduling instructions. For example, "I prefer to give priority to using photovoltaic power generation". This system can dynamically adjust the scheduling strategy according to the user's feedback and explain the decision-making basis to the user in the form of natural language generation. Its advantage lies in enhancing the friendliness of the user experience and making it easier for users to understand and participate in the energy management process.

[0064] Exemplary method

[0065] Please refer to Figure 2 , in an exemplary embodiment, a control method for a vehicle-home PV-storage-charging system is provided. This method is applied to an inverter or the server of the inverter. The method includes:

[0066] Step 201, obtain the comprehensive energy data of the vehicle-home PV-storage-charging system. The vehicle-home PV-storage-charging system includes multiple power devices, and the power devices include an inverter and a vehicle.

[0067] In some embodiments, the comprehensive energy data can be sent by the vehicle, or directly sent to the inverter by the relevant power devices, or the power devices first send it to the vehicle, and then the vehicle sends it to the inverter.

[0068] The comprehensive energy data includes the energy data of each power device. For example, the comprehensive energy data includes vehicle status data, household load data, photovoltaic device power generation data, and energy storage device status data.

[0069] The vehicle status data includes parameters such as the remaining battery charge (State of Charge, SOC), geographical location, driving status (such as charging / discharging status), battery health (State of Health, SOH), and estimated driving range; the home load data

[0070] The home load data includes the real-time load power (such as the electricity demand of household appliances), historical electricity consumption patterns (predicting future electricity demand through a time series prediction model), and adjustable loads (such as the controllable power of devices like air conditioners and water heaters).

[0071] The photovoltaic power generation data includes predicting the real-time photovoltaic power generation according to weather forecasts (such as light intensity, cloud cover) and the efficiency characteristics of photovoltaic panels (such as the impact of temperature on power generation efficiency).

[0072] The energy storage device status data includes parameters such as the remaining capacity of the energy storage device, charge / discharge power limits (such as the maximum charging power and maximum discharging power), charge / discharge efficiency, and the health of the energy storage device.

[0073] Furthermore, during the collection or transmission of the above data, there may be interferences such as noise. Therefore, the above comprehensive energy data can also be preprocessed to obtain cleaner data.

[0074] Among them, the preprocessing process includes data standardization (normalizing data with different dimensions to the same range), denoising (removing outliers or noise data), and feature extraction (extracting key features for state representation). The preprocessed data is used to construct the state vector of the system.

[0075] Step 202, determining the energy management strategy of the vehicle-home-photovoltaic-energy storage-charging system according to the comprehensive energy data, where the energy management strategy is used to indicate the adjustment of the charge / discharge power of each device in the vehicle-home-photovoltaic-energy storage-charging system.

[0076] In some embodiments, after obtaining the above comprehensive energy data, the energy management strategy of the current system can be determined by analyzing and processing the comprehensive energy data.

[0077] Among them, the energy management strategy can include, but is not limited to, adjusting the vehicle charging / discharging power, adjusting the charge / discharge power of the energy storage device, and distributing the home load power.

[0078] In an alternative embodiment, determining the energy management strategy of the vehicle-home-photovoltaic-energy storage-charging system according to the comprehensive energy data includes:

[0079] Inputting the comprehensive energy data into a pre-trained reinforcement learning model, and predicting the comprehensive energy data through the reinforcement learning model to obtain the energy management strategy.

[0080] In some embodiments, the pre-trained reinforcement learning model can be, but is not limited to, trained from an initial model based on a Deep Q-Network (DQN) combined with a Double DQN structure.

[0081] Furthermore, the process of determining an energy management strategy using the reinforcement learning model includes:

[0082] Real-time data collection: Information such as vehicle status, household electricity demand, photovoltaic power generation, and energy storage status is collected in real time through sensors and intelligent terminals.

[0083] Data preprocessing: The collected data is standardized, denoised, and feature-extracted.

[0084] State update: The preprocessed data is constructed into a current state vector.

[0085] Action selection: The optimal action is selected based on the current state vector and the output of the Q-network.

[0086] Policy optimization: The Q-network parameters are continuously updated through an online learning mechanism to adapt to environmental changes.

[0087] In an alternative embodiment, the training process of the reinforcement learning model includes:

[0088] Obtain a training sample set, where the training sample set includes multiple integrated energy data samples,

[0089] Initialize the Q-network parameters and target network parameters in the original reinforcement learning model;

[0090] Select a current execution action according to the integrated energy data sample, where the current execution action can represent an energy management strategy;

[0091] Execute according to the current execution action to obtain the current integrated energy data and an execution reward value;

[0092] Update the Q-network parameters to minimize the loss function.

[0093] In some embodiments, the initialization of the Q-network parameters θ and the target network parameters θ' can be generated according to certain rules or randomly generated. During the training process, θ is continuously optimized, and every certain number of training rounds, θ' is assigned the value of θ.

[0094] Among them, the integrated energy data samples in the training sample set can include, but are not limited to, the state of charge (SOC) of the vehicle battery, the position information (Position) of the vehicle, the household electricity demand (Load) at present and for a period of time in the future {current} and Load {future}, current and predicted photovoltaic power generation PV {current} and PV {forecast} as well as the remaining capacity and available charge-discharge power of the energy storage device Storage {SOC} and Storage {Power} .

[0095] The above data can be represented as a high-dimensional vector S, [S = [SOC, Position, Load {current} , Load {future} , PV {current} , PV {forecast} , Storage {SOC} , Storage {Power} .

[0096] Among them, the execution reward value is obtained in the following way:

[0097]

[0098] Among them, R represents the execution reward value, C represents the electricity price cost coefficient, represents the power supplied from the power grid to the household load, t represents the power consumption duration, represents the power supplied from the vehicle to the household load, represents the power supplied from the energy storage device to the household load, represents the battery charge change rate, represents the battery health change rate, P {imbalance} represents the system power imbalance, and R1, R2, and R3 all represent weight coefficients.

[0099] In some embodiments, the execution reward value is used to measure the effect of each decision and guide the system to approach the optimal goal. The reward function comprehensively considers the following multi-objective optimization indicators:

[0100] Minimization of electricity cost: where C is the electricity price cost coefficient;

[0101] Maximization of the energy self-sufficiency rate:

[0102] Battery life: -R2·(|dSOC / dt| + |dSOH / dt|), where dSOC / dt and dSOH / dt represent the battery charge change rate and the health change rate respectively;

[0103] System stability: -R3·(|P {imbalance} |), where P_{imbalance represents the system power imbalance.

[0104] The original reinforcement learning model makes predictions based on the integrated energy data samples to obtain the current execution action, and the system executes according to this current execution action. The current integrated energy data S at the subsequent moment of the execution time point of the integrated energy data sample t+1 , and the immediate reward R is obtained through the above execution reward function t .

[0105] Among them, the current execution actions include: vehicle charging / discharging power adjustment, energy storage device charging / discharging power adjustment, and household load power distribution.

[0106] In an alternative embodiment, the loss function is as follows:

[0107]

[0108] Among them, L(θ) represents the loss function, R t represents the execution reward value obtained at time step t, represents the expectation with respect to the integrated energy data sample S t , the current execution action A t , the execution reward value R t and the current integrated energy data S t+1 . Q(S t ,A t ; θ) represents the action value function with Q network parameters θ when taking A t under S t , γ represents the discount factor, represents the maximum value of the action value function with target network parameters θ' for all possible actions a under S t+1 .

[0109] Among them, represents the expectation with respect to the state S t , the action A t , the reward R t and the next state S t+1 . The expectation is the weighted average of all possible values of these random variables according to their probability distributions.

[0110] Q(S t ,A t ; θ) is the action value function with parameters θ when taking the action A t under the state S t , and it estimates the future cumulative reward for this state-action pair.

[0111] R t is the immediate reward obtained at time step t.

[0112] γ is the discount factor, and its value range is usually between [0, 1]. It is used to measure the importance of future rewards. The closer γ is to 0, the more it emphasizes immediate rewards; the closer γ is to 1, the more it emphasizes future rewards.

[0113] Denotes the maximum value of the action-value function with parameter θ′ for all possible actions a in state S. Here, θ′ is usually a set of parameters related to but possibly different from θ. t+1

[0114] is in the form of mean squared error, which is used to quantify the difference between Q(S t , A t ; θ) and the target value.

[0115] Furthermore, in order to adapt to the behavior changes of drivers (such as changes in travel patterns) and weather fluctuations (such as changes in light intensity), the system introduces an online learning mechanism. Specifically, it includes:

[0116] Real-time update of the state space: Dynamically adjust the state vector S according to new input data; Dynamically adjust the weights of the reward function: Automatically optimize the weight coefficients R1, R2, R3 in the reward function according to the actual operation situation; Continuously optimize the policy: Adapt to environmental changes by online sampling new data and updating the Q-network parameters.

[0117] Step 203, obtain the power planning strategy sent by the vehicle, where the power planning strategy is used to indicate the power usage planning of each device in the vehicle-home photovoltaic energy storage charging system.

[0118] In some embodiments, a planning large model is set inside the vehicle, which can perform reasoning and decision-making based on the relevant data of each power device in the system, so as to obtain the power planning strategy of the system.

[0119] Among them, the power planning strategy may include the priority of the energy flow direction (such as preferentially charging from the power grid or discharging to the power grid), the charge and discharge priority of the energy storage device (such as preferentially charging the vehicle or preferentially meeting the household electricity demand), the charge and discharge plan within a certain period in the future, etc.

[0120] In an alternative embodiment, obtain the comprehensive energy data of the vehicle-home photovoltaic energy storage charging system. The vehicle-home photovoltaic energy storage charging system includes multiple power devices, and the power devices include inverters and vehicles;

[0121] Determine the smart grid mode of the vehicle-home photovoltaic energy storage charging system;

[0122] Based on the smart grid mode and the comprehensive energy data, determine the power planning strategy of the vehicle-home photovoltaic energy storage charging system;​

[0123] Send the power planning strategy to the inverter so that the inverter controls each power device in the vehicle-home photovoltaic energy storage charging system based on the energy management strategy determined by itself and the power planning strategy.

[0124] In some embodiments, the intelligent grid mode of the system can be distinguished by whether the system is connected to the public grid and whether the system is connected to the Internet. This intelligent grid mode mainly includes four types: online grid-connected mode, online off-grid mode, offline grid-connected mode, and offline off-grid mode. Among them, online means that the system is connected to the Internet, grid-connected means that the system is connected to the public grid, offline means that the system is not connected to the Internet, and off-grid means that the system is not connected to the public grid.

[0125] Among them, when the system is connected to the public grid, the vehicle can charge from the grid or discharge to the grid through the charging pile. When the system disconnects from the public grid, it completely depends on the home energy storage system and photovoltaic power generation. When the system is connected to the Internet, it can obtain external data (such as weather forecasts, electricity price policies) in real time and communicate with the cloud server. When the system disconnects from the Internet, it completely depends on local data and algorithms for decision-making.

[0126] Based on this, the intelligent grid mode can be determined according to the connection status of the system to the public grid and the Internet.

[0127] In an alternative embodiment, determining the power planning strategy of the vehicle-home photovoltaic energy storage charging system based on the intelligent grid mode and the integrated energy data includes:

[0128] Determine the power consumption behavior data of the vehicle-home photovoltaic energy storage charging system from a pre-constructed knowledge base;

[0129] Based on the thought chain constructed in the planning model, reason about the power consumption behavior data, the intelligent grid mode, and the integrated energy data to obtain the power planning strategy.

[0130] In some embodiments, after the vehicle is activated, the initial knowledge base is loaded into the vehicle. After the vehicle runs for a period of time, the knowledge base is updated according to the system data obtained.

[0131] Among them, the knowledge content in the knowledge base can include but is not limited to: professional knowledge in the field of energy management (such as battery charge and discharge characteristics, photovoltaic panel efficiency curve); user behavior patterns (such as driving habits, electricity consumption preferences, driving mileage); real-time dynamic information (such as weather forecasts, electricity price fluctuations); historical power consumption and discharge curves of the vehicle, home, photovoltaic, and energy storage.

[0132] The knowledge base has the capabilities of storage and retrieval. It can use a vector database (such as FAISS or Milvus) to store the content of the knowledge base and provide an efficient retrieval interface (such as retrieval based on keywords or semantic similarity).

[0133] The content of the knowledge base can also be updated regularly to reflect the latest environmental changes (such as adjustments to electricity price policies or updates to weather forecasts).

[0134] Furthermore, the planning model can be obtained by fine-tuning a large model based on the specific requirements of the energy management field.

[0135] The training process of the planning model can include:

[0136] Training data preparation: Collect text data related to energy management (such as academic papers, industry reports, user manuals, etc.) and annotate key information (such as electricity price policies, PV efficiency curves, etc.).

[0137] Fine-tuning the objective function: Add domain-specific task objectives (such as predicting the SOC change rate or optimizing the charging plan) on the basis of the standard language modeling objective.

[0138] Domain adaptation layer: Add a lightweight adapter layer on top of the large model to capture the specific patterns in the energy management field.

[0139] Among them, in order to enable the large model to have stronger reasoning ability, the chain-of-thought method is adopted when generating decisions.

[0140] Specifically, before generating the final decision, the model first analyzes the problem step by step and records the intermediate reasoning process. For example, analyze the current SOC and future trip requirements; predict future PV power generation; formulate a charging plan in combination with electricity price fluctuations; adjust the charge and discharge power of the energy storage device to balance the system.

[0141] In order to guide the large model to generate high-quality outputs (such as personalized charging plans and energy-saving suggestions), the following prompt engineering strategies are adopted:

[0142] Multi-round conversational prompt: Design a multi-round conversation template to gradually guide the model to deeply analyze the problem and generate detailed suggestions.

[0143] Context-enhanced prompt: Incorporate historical data and domain knowledge (such as electricity price policies, PV efficiency curves) into the prompt to help the model make more accurate decisions.

[0144] Result verification prompt: After generating the final suggestion, ensure its rationality through reverse verification.

[0145] Step 204: Control each of the power devices in the vehicle-home PV-storage-charging system based on the energy management strategy and the power planning strategy.

[0146] In some embodiments, the charging and discharging of each power device in the system is controlled according to the energy management strategy and the power planning strategy.

[0147] Exemplarily, in the grid-connected mode of the system, the planning model of the vehicle analyzes the household electricity demand, the vehicle's SOC (State of Charge), the driving plan, and the external environment (such as electricity price policy, weather forecast). According to the analysis results, a long-term plan (such as the charging / discharging plan for the next few days) is generated. The vehicle sends instructions to the inverter to optimize the energy flow direction (such as preferentially charging from the grid or discharging to the grid). The inverter adjusts the energy distribution strategy in real time under the reinforcement learning framework (such as power distribution ratio, charging and discharging priority). According to the long-term plan of the vehicle, in the grid-connected mode, it maximizes the use of low-valley electricity prices for charging or discharges to the grid during the peak electricity price period.

[0148] In the off-grid mode of the system, the vehicle analyzes the household electricity demand, the vehicle's SOC, and the remaining capacity of the energy storage system. According to the vehicle's driving plan (such as whether a long-distance trip is needed), a dynamic energy management strategy is generated. The vehicle sends instructions to the inverter to optimize the charging and discharging sequence of the energy storage system (such as preferentially charging the vehicle or preferentially meeting the household electricity demand). The inverter adjusts the charging and discharging power of the energy storage system in real time under the reinforcement learning framework. According to the instructions of the vehicle, in the off-grid mode, it preferentially meets the household electricity demand or charges the vehicle.

[0149] In the online mode of the system, the vehicle receives the updated information from the cloud server in real time (such as changes in electricity price policy, weather forecast updates), and uploads the real-time status information (such as the vehicle's SOC, household electricity demand) to the cloud for optimization calculation. According to the feedback from the cloud, a more accurate long-term plan is generated, and optimization instructions are sent to the inverter. The inverter adjusts the energy distribution strategy in real time under the reinforcement learning framework in combination with the cloud feedback. According to the instructions of the vehicle, in the online mode, it maximizes the use of external information to optimize energy management.

[0150] In the offline mode of the system, the vehicle generates an energy management strategy according to the locally stored historical data and preset rules, monitors the vehicle's SOC and household electricity demand, and dynamically adjusts the long-term plan. The vehicle sends instructions to the inverter to optimize the charging and discharging sequence of the energy storage system. The inverter adjusts the energy distribution strategy in real time only relying on local data under the reinforcement learning framework. According to the instructions of the vehicle, in the offline mode, it ensures that the system can still operate stably without external information.

[0151] It is understandable that, in order to achieve flexible and efficient energy management, multi-mode collaborative control and dynamic adjustment based on vehicle status can also be adopted. The vehicle status (such as SOC, location, driving plan) is always used as the dynamic input of the entire system. The large model of the vehicle generates personalized energy management strategies based on these dynamic inputs and sends instructions to the inverter to optimize energy distribution.

[0152] The control method of the vehicle-home photovoltaic-storage-charging system of the present application takes the vehicle as the central node of the "vehicle-home photovoltaic-storage-charging" system and works in coordination with the inverter power management system. The vehicle is equipped with a personalized energy management strategy and long-term planning system driven by a large model, while the inverter is equipped with a real-time energy distribution system based on reinforcement learning (RL). In this way, the vehicle can operate independently and complete complex data analysis and decision support tasks in an offline / stand-alone environment. It can improve the real-time performance and dynamic adaptability of the system; enhance the global collaborative optimization ability of the system; realize the intelligent interaction and distribution of energy between the vehicle and the home end; achieve efficient energy management in an offline / stand-alone environment; by introducing reinforcement learning agents and in-vehicle large model technologies, the present application can realize intelligent and real-time energy management decisions in complex dynamic environments and offline environments, and effectively improve the stability and efficiency of the system.

[0153] Correspondingly, the embodiment of the present application also provides another control method for the vehicle-home photovoltaic-storage-charging system. This method is applied to the vehicle or the server of the vehicle. See Figure 3 , and this method includes:

[0154] Step 301: Obtain the comprehensive energy data of the vehicle-home photovoltaic-storage-charging system. There are multiple power devices in the vehicle-home photovoltaic-storage-charging system, and the power devices include an inverter and a vehicle;

[0155] Step 302: Determine the smart grid mode of the vehicle-home photovoltaic-storage-charging system;

[0156] Step 303: Based on the smart grid mode and the comprehensive energy data, determine the power planning strategy of the vehicle-home photovoltaic-storage-charging system;

[0157] Step 304: Send the power planning strategy to the inverter so that the inverter controls each power device in the vehicle-home photovoltaic-storage-charging system based on the energy management strategy determined by itself and the power planning strategy.

[0158] Further, determining the power planning strategy of the vehicle-home photovoltaic-storage-charging system based on the smart grid mode and the comprehensive energy data includes:

[0159] Determine the power consumption behavior data of the vehicle-home photovoltaic-storage-charging system from the pre-constructed knowledge base;

[0160] Based on the thought chain constructed in the planning model, reason about the electricity consumption behavior data, the smart grid mode, and the integrated energy data to obtain the power planning strategy.

[0161] Among them, the specific implementation process of this method can be referred to the above related embodiments and will not be elaborated here.

[0162] The control method of the vehicle-home photovoltaic energy storage charging system of the present application takes the vehicle as the core node of the energy platform, can sense and analyze the vehicle state in real time (such as battery level, location, driving plan), and realizes dynamic energy distribution and multi-objective optimization; through the local analysis ability of the vehicle large model, reduces the dependence on the cloud, and improves the system operation efficiency and privacy protection ability; the vehicle, as a mobile energy hub, can work in coordination with systems such as home energy storage and photovoltaic power generation to optimize the overall energy use efficiency; the vehicle has an independent operation ability and can still complete data analysis and decision support tasks in an offline or weak network environment; the vehicle state is always used as a dynamic input and output to participate in the decision-making process, improving the accuracy of the energy management strategy and the level of personalized service; improves the overall intelligence level of the system by jointly optimizing the long-term plan through reinforcement learning and the large model.

[0163] Exemplary device

[0164] Correspondingly, the embodiment of the present application also provides a control device for a vehicle-home photovoltaic energy storage charging system, including:

[0165] The first acquisition unit is used to acquire the integrated energy data of the vehicle-home photovoltaic energy storage charging system. The vehicle-home photovoltaic energy storage charging system includes multiple power devices, and the power devices include an inverter and a vehicle;

[0166] The first determination unit is used to determine the energy management strategy of the vehicle-home photovoltaic energy storage charging system according to the integrated energy data, and the energy management strategy is used to indicate the adjustment situation of the charging and discharging power of each device in the vehicle-home photovoltaic energy storage charging system;

[0167] The second acquisition unit is used to acquire the power planning strategy sent by the vehicle, and the power planning strategy is used to indicate the electricity consumption planning situation of each device in the vehicle-home photovoltaic energy storage charging system;

[0168] The control unit is used to control each power device in the vehicle-home photovoltaic energy storage charging system based on the energy management strategy and the power planning strategy.

[0169] Correspondingly, the embodiment of the present application also provides another control device for a vehicle-home photovoltaic energy storage charging system, including:

[0170] The third acquisition unit is used to acquire the integrated energy data of the vehicle-home photovoltaic energy storage charging system. The vehicle-home photovoltaic energy storage charging system includes multiple power devices, and the power devices include an inverter and a vehicle;

[0171] A second determination unit, configured to determine an intelligent power grid mode of the vehicle-home photovoltaic-storage-charging system;

[0172] A third determination unit, configured to determine a power planning strategy of the vehicle-home photovoltaic-storage-charging system based on the intelligent power grid mode and the integrated energy data;

[0173] A sending unit, configured to send the power planning strategy to the inverter, so that the inverter controls each power device in the vehicle-home photovoltaic-storage-charging system based on the energy management strategy determined by itself and the power planning strategy.

[0174] The control device of the vehicle-home photovoltaic-storage-charging system provided in this embodiment belongs to the same inventive concept as the control method of the vehicle-home photovoltaic-storage-charging system provided in the foregoing embodiments of the present application, can execute the methods provided in any of the foregoing embodiments of the present application, and has corresponding functional modules and beneficial effects for executing the methods. Technical details not described in detail in this embodiment can be found in the specific processing content of the control method of the vehicle-home photovoltaic-storage-charging system provided in the foregoing embodiments of the present application, and will not be elaborated herein.

[0175] The functions implemented by each unit in the above control device of the vehicle-home photovoltaic-storage-charging system can be implemented by the same or different processors respectively, and the embodiments of the present application do not make limitations.

[0176] It should be understood that each functional unit in the above device can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, instructions are stored in the memory, and the processor calls the instructions stored in the memory to implement any of the above methods or implement the functions of each unit of the device. The processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory inside the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of a hardware circuit. By designing the hardware circuit, part or all of the functions of the units can be implemented. The hardware circuit can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and by designing the logical relationship of the components in the circuit, part or all of the functions of the above units are implemented; again, in another implementation, the hardware circuit can be implemented by a PLD. Taking an FPGA as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured through a configuration file to implement part or all of the functions of the above units. All units of the above device can be all implemented in the form of a processor calling software, or all implemented in the form of a hardware circuit, or part implemented in the form of a processor calling software, and the remaining part implemented in the form of a hardware circuit.

[0177] In an embodiment of the present application, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and running capabilities, such as a CPU, microprocessor, GPU, or DSP, etc.; in another implementation, the processor can implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of this hardware circuit is fixed or can be reconfigured. For example, the processor is a hardware circuit implemented by an ASIC or PLD, such as an FPGA, etc. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as a type of ASIC, such as an NPU, TPU, DPU, etc.

[0178] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0179] In addition, each unit in the above device can be integrated in whole or in part, or can be independently implemented. In one implementation, these units are integrated together and implemented in the form of an SOC. The SOC can include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The types of the at least one processor can be different, such as including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0180] Exemplary electronic device

[0181] Another embodiment of the present application also proposes an electronic device. Refer to Figure 4 As shown, the device includes:

[0182] A memory 400 and a processor 410;

[0183] Among them, the memory 400 is connected to the processor 410 and is used to store programs;

[0184] The processor 410 is used to implement the control method of the vehicle-home photovoltaic-storage-charging system disclosed in any of the above embodiments by running the program stored in the memory 400.

[0185] Specifically, the control device of the above vehicle-home photovoltaic-storage-charging system may further include: a bus, a communication interface 420, an input device 430, and an output device 440.

[0186] The processor 410, the memory 400, the communication interface 420, the input device 430, and the output device 440 are interconnected via a bus. Among them:

[0187] The bus may include a path for transmitting information between various components of the computer system.

[0188] The processor 410 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present invention solution. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0189] The processor 410 may include a main processor, and may also include a baseband chip, a modem, etc.

[0190] The memory 400 stores the program for implementing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include program code, and the program code includes computer operation instructions. More specifically, the memory 400 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk memory, a flash memory, etc.

[0191] The input device 440 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor, etc.

[0192] The output device 440 may include a device for allowing information to be output to a user, such as a display screen, a printer, a speaker, etc.

[0193] The communication interface 420 may include a device of any transceiver type for communicating with other devices or communication networks, such as Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0194] The processor 410 executes the program stored in the memory 400 and calls other devices, which can be used to implement each step of any one of the control methods of the vehicle-home optical storage charging system provided in the above embodiments of the present application.

[0195] Exemplary computer program product and storage medium

[0196] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions that, when run by a processor, cause the processor to execute the steps in the control method of the vehicle-home photovoltaic-storage-charging system according to various embodiments of the present application described in any of the above embodiments of this specification.

[0197] The computer program product may be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present application. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The programming code may be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0198] Furthermore, an embodiment of the present application may also be a storage medium on which a computer program is stored. The computer program is executed by a processor to perform the steps in the control method of the vehicle-home photovoltaic-storage-charging system according to various embodiments of the present application described in any of the above embodiments of this specification. Specifically, the following steps may be implemented:

[0199] Obtain the comprehensive energy data of the vehicle-home photovoltaic-storage-charging system. The vehicle-home photovoltaic-storage-charging system includes a plurality of power devices, and the power devices include an inverter and a vehicle;

[0200] Determine the energy management strategy of the vehicle-home photovoltaic-storage-charging system according to the comprehensive energy data. The energy management strategy is used to indicate the adjustment of the charging and discharging power of each device in the vehicle-home photovoltaic-storage-charging system;

[0201] Obtain the power planning strategy sent by the vehicle. The power planning strategy is used to indicate the power usage planning of each device in the vehicle-home photovoltaic-storage-charging system;

[0202] Based on the energy management strategy and the power planning strategy, control each of the power devices in the vehicle-home photovoltaic-storage-charging system. Or,

[0203] Obtain the comprehensive energy data of the vehicle-home photovoltaic-storage-charging system. The vehicle-home photovoltaic-storage-charging system includes a plurality of power devices, and the power devices include an inverter and a vehicle;

[0204] Determine the smart grid mode of the vehicle-home photovoltaic-storage-charging system;

[0205] Based on the smart grid mode and the comprehensive energy data, determine the power planning strategy of the vehicle-home photovoltaic-storage-charging system;

[0206] Send the power planning strategy to the inverter, so that the inverter controls each power device in the vehicle-home PV energy storage charging system based on the energy management strategy determined by itself and the power planning strategy.

[0207] For each of the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be adopted in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0208] It should be noted that each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other. For device embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0209] The steps in the methods of the embodiments of this application can be adjusted, combined, and deleted according to actual needs. The technical features recorded in each embodiment can be replaced or combined.

[0210] The modules and sub-modules in the devices and terminals in the embodiments of this application can be combined, divided, and deleted according to actual needs.

[0211] In several embodiments provided by this application, it should be understood that the disclosed terminals, devices, and methods can be implemented in other ways. For example, the terminal embodiments described above are only illustrative. For example, the division of modules or sub-modules is only a logical function division. In actual implementation, there can be other division methods. For example, multiple sub-modules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be in electrical, mechanical, or other forms.

[0212] The modules or sub-modules described as separate components may or may not be physically separated. The components as modules or sub-modules may or may not be physical modules or sub-modules, that is, they can be located in one place, or they can be distributed to multiple network modules or sub-modules. Some or all of the modules or sub-modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0213] In addition, in each embodiment of the present application, each functional module or sub-module can be integrated into one processing module, or each module or sub-module can exist physically alone, or two or more modules or sub-modules can be integrated into one module. The above integrated module or sub-module can be implemented in the form of hardware, or in the form of a software functional module or sub-module.

[0214] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0215] The steps of the method or algorithm described in combination with the embodiments disclosed in this article can be directly implemented by hardware, a software unit executed by a processor, or a combination of the two. The software unit can be placed in a random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0216] Finally, it should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0217] The foregoing description of the disclosed embodiments enables those skilled in the art to practice or use the present application. 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 application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A control method for a car-home solar storage and charging system, characterized in that: Applied to an inverter, the method comprises: Obtaining comprehensive energy data of a vehicle-based solar-storage-charging system, where the vehicle-based solar-storage-charging system includes multiple power devices, including an inverter and a vehicle; Determine the energy management strategy of the car home solar storage and charging system according to the comprehensive energy data, wherein the energy management strategy is used to indicate the adjustment of the charging and discharging power of each device in the car home solar storage and charging system; Obtaining a power planning strategy sent by the vehicle, wherein the power planning strategy is used to indicate the power planning of each device in the vehicle-home solar storage and charging system; Based on the energy management strategy and the power planning strategy, each power device in the car-home solar storage and charging system is controlled.

2. The method according to claim 1, characterized in that Determining the energy management strategy of the vehicle-home solar storage and charging system according to the comprehensive energy data includes: The comprehensive energy data is input into a pre-trained reinforcement learning model, and the comprehensive energy data is predicted by the reinforcement learning model to obtain the energy management strategy.

3. The method according to claim 2, characterized in that The training process of the reinforcement learning model includes: Acquire a training sample set, wherein the training sample set includes a plurality of comprehensive energy data samples, Initialize the Q network parameters and target network parameters in the original reinforcement learning model; Selecting a current execution action according to the comprehensive energy data sample, wherein the current execution action can represent an energy management strategy; Execute according to the current execution action to obtain the current comprehensive energy data and execution reward value; The Q network parameters are updated to minimize the loss function.

4. The method according to claim 3, characterized in that: The execution reward value is obtained in the following way: Among them, R represents the execution reward value, C represents the electricity price cost coefficient, represents the power supplied from the grid to the household load, t represents the duration of electricity consumption, Indicates the power supplied by the vehicle to the household loads, Indicates the power supplied by the energy storage device to the household load. Indicates the battery charge change rate. Indicates the battery health change rate, P {imbalance} Indicates the system power imbalance, and R1, R2, and R3 all represent weight coefficients.

5. The method according to claim 3, characterized in that: The currently executed actions include: vehicle charging / discharging power adjustment, energy storage device charging / discharging power adjustment, and household load power allocation.

6. The method according to claim 3, characterized in that The loss function is: Among them, L(θ) represents the loss function, R t represents the execution reward value obtained at time step t, Represents the comprehensive energy data sample S t 、Currently executing action A t , Execution reward value R t and current comprehensive energy data S t+1 Expectation, Q(S t ,A t ; θ) represents the t Next take A t When , the Q network parameter is the action value function of θ, γ represents the discount factor, Indicates that in S t+1 Under this condition, for all possible actions a, the target network parameter is the maximum value of the action-value function θ'.

7. A control method for a car-home solar storage and charging system, characterized in that: Applied to a vehicle, the method comprises: Obtaining comprehensive energy data of a vehicle-based solar-storage-charging system, where the vehicle-based solar-storage-charging system includes multiple power devices, including an inverter and a vehicle; Determine the smart grid mode of the vehicle-home solar storage and charging system; Determine the power planning strategy of the car-home solar storage and charging system based on the smart grid model and the comprehensive energy data; The power planning strategy is sent to the inverter so that the inverter controls each power device in the car-home solar-storage-charging system based on the energy management strategy determined by itself and the power planning strategy.

8. The method according to claim 7, characterized in that Based on the smart grid model and the comprehensive energy data, a power planning strategy of the car-home solar storage and charging system is determined, including: Determine the power consumption behavior data of the vehicle-home solar-storage-charging system from a pre-built knowledge base; Based on the thinking chain constructed in the planning model, the electricity consumption behavior data, the smart grid model and the comprehensive energy data are inferred to obtain the power planning strategy.

9. A car-home solar storage and charging system, characterized in that: include: The inverter according to any one of claims 1 to 6, the vehicle according to any one of claims 7 to 8, and a household load.

10. An electronic device, characterized in that: including memory and processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the control method of the car-home solar storage and charging system as described in any one of claims 1 to 8 by running the program in the memory.

Images