Method and system for regulating power of intelligent light, storage and charging integrated microgrid system

Abstract

The embodiment of the application relates to the field of electric energy regulation, and discloses an electric energy regulation method and system of a smart light, storage and charging integrated microgrid system. The system method comprises: acquiring real-time data of each module of the microgrid system; acquiring a current time and a current execution scheme of the microgrid system; substituting the real-time data of each module of the microgrid system, the current time and the current execution scheme of the microgrid system into an electric energy regulation model, so that the current execution scheme is selectively adjusted or selectively predicted and adjusted according to the real-time data of each module of the microgrid system and the current time of the microgrid system, to obtain an adjustment scheme and an adjustment time corresponding to the current execution scheme; and based on the real-time adjustment scheme or the predicted adjustment scheme, the current execution scheme is adjusted at the adjustment time, and each module of the microgrid system is accurately controlled, so that intelligent management of the microgrid system is realized, and intelligent regulation level is improved.

Description

Technical Field

[0001] This application relates to the field of power regulation technology, and in particular to a power regulation method and system for an integrated smart photovoltaic, energy storage and charging microgrid system. Background Technology

[0002] With the technological advancements and industry development in photovoltaics, energy storage, and new energy vehicles, the "photovoltaic + energy storage + charging" combination is being increasingly applied in various scenarios, giving rise to integrated photovoltaic, energy storage, and charging systems. However, existing technologies generally employ unified control of each module within the integrated photovoltaic, energy storage, and charging system, which limits its operation and hinders precise control of the photovoltaic, energy storage, and charging modules.

[0003] Accordingly, there is a need in this field for a new power regulation scheme for an integrated smart solar, energy storage, and charging microgrid system to address the above problems. Summary of the Invention

[0004] One objective of this application is to provide a power regulation method and system for an integrated photovoltaic, energy storage, and charging microgrid system, at least to solve the technical problem that the existing regulation methods generally adopt unified regulation of each module of the system, which results in limitations in the operation of the integrated photovoltaic, energy storage, and charging system and is not conducive to the precise control of photovoltaic, energy storage, and charging modules in the integrated photovoltaic, energy storage, and charging system.

[0005] To achieve the above objectives, some embodiments of this application provide the following aspects:

[0006] In a first aspect, some embodiments of this application provide a power regulation method for a smart integrated photovoltaic, energy storage, and charging microgrid system. The method is applied to a power regulation system, which interacts with the smart integrated photovoltaic, energy storage, and charging microgrid system. The smart integrated photovoltaic, energy storage, and charging microgrid system includes at least a photovoltaic module, an energy storage module, and a charging module. The method includes the following steps:

[0007] Obtain real-time data from each module of the microgrid system;

[0008] Obtain the current time and current execution plan of the microgrid system;

[0009] The real-time data of each module of the microgrid system, the current time of the microgrid system, and the current execution plan are substituted into the power control model. Based on the real-time data of each module of the microgrid system and the current time of the microgrid system, the current execution plan is selectively adjusted, or the current execution plan is selectively predicted and adjusted, to obtain an adjustment plan and adjustment time corresponding to the current execution plan. The adjustment plan includes an immediate adjustment plan or a predictive adjustment plan.

[0010] Based on the real-time adjustment scheme or the predictive adjustment scheme, the current execution scheme is adjusted at the adjustment time to achieve targeted control of each module of the microgrid system.

[0011] Furthermore, the power control system also interacts with the management terminal. Before acquiring real-time data from each module of the microgrid system, the method further includes:

[0012] In response to control commands or emergency commands received by the power regulation system, corresponding operations are selectively performed on one or more modules within the power regulation system or the microgrid system.

[0013] Furthermore, the step of selectively performing corresponding operations on one or more modules within the power regulation system or the microgrid system in response to control commands or emergency commands received by the power regulation system includes:

[0014] In response to a control command issued by a management terminal received by the power regulation system, the system executes a grid connection or off-grid operation matching the control command, wherein the control command is a grid connection command or an off-grid command;

[0015] or,

[0016] In response to an emergency command issued by the microgrid system received by the power control system, the module type corresponding to the emergency command is obtained;

[0017] Based on the emergency instruction, emergency operations are performed on the module corresponding to the emergency instruction.

[0018] Furthermore, the acquisition of real-time data from each module of the microgrid system includes:

[0019] Determine the current state of the microgrid system, wherein the current state is one of grid-connected state and grid-connected ratio, or off-grid state;

[0020] The current module status and real-time information of each module in the microgrid system are obtained, and the real-time data of each module in the microgrid system is constructed based on the current module status and real-time information of each module in the microgrid system.

[0021] Furthermore, the step of substituting the real-time data of each module of the microgrid system, the current time of the microgrid system, and the current execution plan into the power control model, so that the current execution plan is selectively adjusted based on the real-time data of each module of the microgrid system and the current time of the microgrid system, or, selectively, the current execution plan is predictively adjusted, to obtain an adjustment plan and adjustment time corresponding to the current execution plan, includes:

[0022] Based on the current time of the microgrid system, the current mode of the microgrid system is determined, wherein the current mode includes daytime mode or nighttime mode;

[0023] Based on the current mode of the microgrid system, determine the corresponding configuration scheme for the microgrid system;

[0024] If the setting scheme corresponding to the microgrid system is inconsistent with the current execution scheme of the microgrid system, it is determined that the current execution scheme of the microgrid system needs to be adjusted.

[0025] Otherwise, based on the real-time data of each module of the microgrid system and the current state of the microgrid system, it is determined whether the current execution plan of the microgrid system needs to be adjusted.

[0026] Based on the judgment result, an adjustment plan and adjustment time corresponding to the current execution plan are selectively generated.

[0027] Furthermore, the power regulation model stores a preset system setting scheme database. This database includes various microgrid systems, at least one daytime mode setting scheme and at least one nighttime mode setting scheme for each microgrid system, and the construction time of each setting scheme. Determining the setting scheme corresponding to the microgrid system based on its current mode includes:

[0028] If the current mode of the microgrid system is daytime mode, retrieve the latest version of the daytime mode setting scheme that matches the microgrid system from the preset system setting scheme database;

[0029] or,

[0030] If the current mode of the microgrid system is night mode, retrieve the latest night mode setting scheme that matches the microgrid system from the preset system setting scheme database.

[0031] Furthermore, determining whether the current execution plan of the microgrid system needs adjustment based on real-time data from each module of the microgrid system and the current state of the microgrid system includes:

[0032] If the current module status of each module in the real-time data of each module of the microgrid system is inconsistent with the current execution plan of the microgrid system, then it is determined that the current execution plan of the microgrid system needs to be adjusted.

[0033] or,

[0034] If the current state of the microgrid system is inconsistent with the current execution plan of the microgrid system, then it is determined that the current execution plan of the microgrid system needs to be adjusted.

[0035] Otherwise, it is determined that the current execution scheme of the microgrid system does not need to be adjusted.

[0036] Furthermore, the step of selectively generating an adjustment plan and adjustment time corresponding to the current execution plan based on the judgment result includes:

[0037] If it is determined that the current execution plan of the microgrid system needs to be adjusted, an adjustment plan matching the microgrid system and the adjustment time of the adjustment plan are generated based on the current state of the microgrid system, the current module state of each module of the microgrid system and real-time information, as well as the control instructions or emergency instructions received by the power regulation system.

[0038] If it is determined that the current execution plan of the microgrid system does not need to be adjusted, then the environmental data of the microgrid system is obtained, wherein the environmental data includes current environmental data and predicted environmental data;

[0039] Based on the environmental data of the microgrid system and the real-time data of each module of the microgrid system, an adjustment scheme corresponding to the current execution scheme is selectively generated.

[0040] Furthermore, the step of generating an adjustment scheme matching the microgrid system based on the current state of the microgrid system, the current module state and real-time information of each module of the microgrid system, and the control commands or emergency commands received by the power regulation system, and the adjustment time of the adjustment scheme, includes:

[0041] Based on the current state of the microgrid system, the current module state of each module of the microgrid system, and real-time information, an adjustment scheme matching the microgrid system is generated.

[0042] Based on the control commands or emergency commands received by the power regulation system, the adjustment time of the adjustment scheme is determined;

[0043] Based on the adjustment time of the adjustment plan, the type of the adjustment plan is determined, which is either an immediate adjustment plan or a predictive adjustment plan.

[0044] On the other hand, this application also provides a power regulation system, which interacts with a smart photovoltaic, energy storage, and charging integrated microgrid system and with a management terminal. The smart photovoltaic, energy storage, and charging integrated microgrid system includes at least a photovoltaic module, an energy storage module, and a charging module. The power regulation system includes a power regulation model and a control device. The power regulation model stores a preset current mode lookup table and a preset system setting scheme database. The control device includes a processor and a memory. The memory is adapted to store multiple program codes, which are adapted to be loaded and run by the processor to execute the power regulation method of the smart photovoltaic, energy storage, and charging integrated microgrid system described in any of the above technical solutions.

[0045] Compared with existing technologies, the beneficial effects of this application are as follows: by collecting real-time data of each module of the microgrid system, as well as the current time and current execution plan, and substituting the acquired data into the power regulation model, the current execution model can be selectively adjusted based on the real-time data of each module of the microgrid system and the current time, or the current execution plan can be selectively predicted and adjusted to obtain the adjustment plan and adjustment time corresponding to the current execution plan, thereby optimizing energy configuration. Then, according to the adjustment plan, the current execution plan is adjusted at the corresponding adjustment time to achieve targeted control of each module of the microgrid system. This realizes the intelligent management of the smart photovoltaic, energy storage, and charging integrated microgrid system by the power regulation system, avoiding the technical problem that the existing technology generally adopts unified control of each module of the system, which makes the photovoltaic, energy storage, and charging integrated system limited in operation and not conducive to the precise control of photovoltaic, energy storage, and charging modules in the photovoltaic, energy storage, and charging integrated system.

[0046] In implementing the technical solution of this application, during model processing, the current mode of the microgrid system is determined based on the current time of the microgrid system, and then the setting scheme of the microgrid system is determined. If the setting scheme is inconsistent with the current execution scheme of the microgrid system, it is determined that the current execution scheme of the microgrid system needs to be adjusted; otherwise, it is determined whether the current execution scheme of the microgrid system needs to be adjusted based on the real-time data and current status of each module of the microgrid system. Based on the judgment result, an adjustment scheme and adjustment time corresponding to the current execution scheme are selectively generated, thereby realizing the selective adjustment of the current execution scheme of the microgrid system and thus realizing targeted control of each module of the microgrid system, improving the intelligent data processing level of the power regulation model. Attached Figure Description

[0047] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0048] Figure 1 This is a schematic flowchart of the main steps of a power regulation method for an integrated smart photovoltaic, energy storage, and charging microgrid system according to an embodiment of this application.

[0049] Figure 2 This is a schematic diagram of the main steps in data processing of the power regulation model of a power regulation method for a smart integrated photovoltaic, energy storage, and charging microgrid system according to an embodiment of this application.

[0050] Figure 3 This is a schematic diagram of the main structure of an energy control system according to an embodiment of this application.

[0051] Explanation of reference numerals in the attached figures:

[0052] 300: Power control system; 301: Control device; 3011: Processor; 3012: Memory; 3013: Program code; 302: Power control model; 3021: Current mode comparison table; 3022: System setting scheme database. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0054] First Embodiment

[0055] See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of a power regulation method for an integrated smart photovoltaic, energy storage, and charging microgrid system according to an embodiment of this application. Figure 1 As shown, the power regulation method of the smart photovoltaic, energy storage and charging integrated microgrid system in this application embodiment is applied to the power regulation system. The power regulation system interacts with the smart photovoltaic, energy storage and charging integrated microgrid system. The smart photovoltaic, energy storage and charging integrated microgrid system includes at least a photovoltaic module, an energy storage module and a charging module. The method mainly includes the following steps S101-S104.

[0056] Step S101: Obtain real-time data from each module of the microgrid system;

[0057] Furthermore, in some embodiments, the power control system also interacts with a management terminal, and before acquiring real-time data from each module of the microgrid system, the method further includes:

[0058] In response to control commands or emergency commands received by the power regulation system, corresponding operations are selectively performed on one or more modules within the power regulation system or the microgrid system.

[0059] Specifically, in some embodiments, the step of selectively performing corresponding operations on one or more modules within the power regulation system or the microgrid system in response to control commands or emergency commands received by the power regulation system includes:

[0060] In response to a control command issued by a management terminal received by the power regulation system, the system executes a grid connection or off-grid operation matching the control command, wherein the control command is a grid connection command or an off-grid command;

[0061] or,

[0062] In response to an emergency command issued by the microgrid system received by the power control system, the module type corresponding to the emergency command is obtained;

[0063] Based on the emergency instruction, emergency operations are performed on the module corresponding to the emergency instruction.

[0064] Specifically, in some embodiments, acquiring real-time data from each module of the microgrid system includes:

[0065] Determine the current state of the microgrid system, wherein the current state is one of grid-connected state and grid-connected ratio, or off-grid state;

[0066] The current module status and real-time information of each module in the microgrid system are obtained, and the real-time data of each module in the microgrid system is constructed based on the current module status and real-time information of each module in the microgrid system.

[0067] Step S102: Obtain the current time and current execution plan of the microgrid system;

[0068] Step S103: Substitute the real-time data of each module of the microgrid system, the current time of the microgrid system, and the current execution plan into the power control model, so that the current execution plan can be selectively adjusted or the current execution plan can be selectively predicted and adjusted according to the real-time data of each module of the microgrid system and the current time of the microgrid system, so as to obtain the adjustment plan and adjustment time corresponding to the current execution plan, wherein the adjustment plan includes an immediate adjustment plan or a predictive adjustment plan;

[0069] like Figure 2 As shown, specifically, in some embodiments, substituting the real-time data of each module of the microgrid system, the current time of the microgrid system, and the current execution plan into the power regulation model, so that the current execution plan is selectively adjusted based on the real-time data of each module of the microgrid system and the current time of the microgrid system, or, selectively, the current execution plan is predictively adjusted, to obtain an adjustment plan and adjustment time corresponding to the current execution plan, including:

[0070] Based on the current time of the microgrid system, the current mode of the microgrid system is determined, wherein the current mode includes daytime mode or nighttime mode;

[0071] Based on the current mode of the microgrid system, determine the corresponding configuration scheme for the microgrid system;

[0072] If the setting scheme corresponding to the microgrid system is inconsistent with the current execution scheme of the microgrid system, it is determined that the current execution scheme of the microgrid system needs to be adjusted.

[0073] Otherwise, based on the real-time data of each module of the microgrid system and the current state of the microgrid system, it is determined whether the current execution plan of the microgrid system needs to be adjusted.

[0074] Based on the judgment result, an adjustment plan and adjustment time corresponding to the current execution plan are selectively generated.

[0075] Specifically, the power regulation model stores a preset current mode lookup table, which stores various modes and their corresponding time ranges. Based on the current time of the microgrid system, the current mode of the microgrid system is determined. The current mode includes either a daytime mode or a nighttime mode.

[0076] The current mode of the microgrid system is determined based on the current time of the microgrid system and a preset current mode lookup table.

[0077] Specifically, based on the current time of the microgrid system and a preset current mode lookup table, determining the current mode of the microgrid system includes:

[0078] If the current time of the microgrid system falls within the time range corresponding to the daytime mode in the preset current mode lookup table, then the current mode of the microgrid system is determined to be the daytime mode.

[0079] If the current time of the microgrid system falls within the time range corresponding to the night mode in the preset current mode lookup table, then the current mode of the microgrid system is determined to be the night mode.

[0080] Specifically, in some embodiments, the power regulation model stores a preset system setting scheme database. This database includes various microgrid systems, at least one daytime mode setting scheme and at least one nighttime mode setting scheme for each microgrid system, and the construction time of each setting scheme. Determining the setting scheme corresponding to the microgrid system based on its current mode includes:

[0081] If the current mode of the microgrid system is daytime mode, retrieve the latest version of the daytime mode setting scheme that matches the microgrid system from the preset system setting scheme database;

[0082] or,

[0083] If the current mode of the microgrid system is night mode, retrieve the latest night mode setting scheme that matches the microgrid system from the preset system setting scheme database.

[0084] Specifically, in some embodiments, determining whether the current execution plan of the microgrid system needs adjustment based on real-time data from each module of the microgrid system and the current state of the microgrid system includes:

[0085] If the current module status of each module in the real-time data of each module of the microgrid system is inconsistent with the current execution plan of the microgrid system, then it is determined that the current execution plan of the microgrid system needs to be adjusted.

[0086] or,

[0087] If the current state of the microgrid system is inconsistent with the current execution plan of the microgrid system, then it is determined that the current execution plan of the microgrid system needs to be adjusted.

[0088] Otherwise, it is determined that the current execution scheme of the microgrid system does not need to be adjusted.

[0089] Specifically, in some embodiments, the step of selectively generating an adjustment plan and adjustment time corresponding to the current execution plan based on the judgment result includes:

[0090] If it is determined that the current execution plan of the microgrid system needs to be adjusted, an adjustment plan matching the microgrid system and the adjustment time of the adjustment plan are generated based on the current state of the microgrid system, the current module state of each module of the microgrid system and real-time information, as well as the control instructions or emergency instructions received by the power regulation system.

[0091] If it is determined that the current execution plan of the microgrid system does not need to be adjusted, then the environmental data of the microgrid system is obtained, wherein the environmental data includes current environmental data and predicted environmental data;

[0092] Based on the environmental data of the microgrid system and the real-time data of each module of the microgrid system, an adjustment scheme corresponding to the current execution scheme is selectively generated.

[0093] Specifically, the selective generation of an adjustment scheme corresponding to the current execution scheme based on the environmental data of the microgrid system and the real-time data of each module of the microgrid system includes:

[0094] Based on the environmental data of the microgrid system and the real-time data of each module of the microgrid system, the microgrid system is simulated to obtain the simulation data of the microgrid system.

[0095] Based on the simulation data, the adjustment time for the current execution plan of the microgrid system is determined;

[0096] Based on the adjustment time of the current execution plan of the microgrid system, an adjustment plan matching the adjustment time is generated.

[0097] Specifically, determining the adjustment time for the current execution plan of the microgrid system based on the simulation data includes:

[0098] Based on the simulation data, determine the time when the simulation data of each module of the microgrid system becomes abnormal;

[0099] Based on the time of the anomaly, the adjustment time for the current execution plan of the microgrid system is determined.

[0100] Specifically, the adjustment time is the average of (the time when the simulated data of any module becomes abnormal * the preset weight value corresponding to the module).

[0101] Specifically, the simulation technology used to simulate the microgrid system can be any existing simulation technology. The choice of simulation technology here is only an example. In actual testing, those skilled in the art can choose according to their actual needs. As long as the microgrid system can be simulated based on the environmental data of the microgrid system and the real-time data of each module of the microgrid system to obtain the simulation data of the microgrid system, it will not be elaborated here.

[0102] Specifically, in some embodiments, the step of generating an adjustment scheme matching the microgrid system and the adjustment time of the adjustment scheme based on the current state of the microgrid system, the current module state and real-time information of each module of the microgrid system, and the control commands or emergency commands received by the power regulation system includes:

[0103] Based on the current state of the microgrid system, the current module state of each module of the microgrid system, and real-time information, an adjustment scheme matching the microgrid system is generated.

[0104] Based on the control commands or emergency commands received by the power regulation system, the adjustment time of the adjustment scheme is determined;

[0105] Based on the adjustment time of the adjustment plan, the type of the adjustment plan is determined, which is either an immediate adjustment plan or a predictive adjustment plan.

[0106] Specifically, determining the adjustment time of the adjustment scheme based on the control commands or emergency commands received by the power regulation system includes:

[0107] If the power regulation system receives a control command, it will simulate the execution of the microgrid system based on the adjustment scheme that matches the microgrid system to obtain simulation data.

[0108] Based on the simulation data, the adjustment time for the adjustment plan is determined;

[0109] If the power regulation system receives an emergency command, it determines that the adjustment time of the adjustment scheme is a preset immediate adjustment time value.

[0110] Specifically, the simulation technology used to simulate the execution of the microgrid system can be a simulation model in the prior art. The selection of simulation technology here is only an example. In actual testing, those skilled in the art can make the selection according to actual needs, as long as the microgrid system can be simulated and the simulation data can be obtained according to the adjustment scheme that matches the microgrid system. Further details are not provided here.

[0111] Specifically, the preset immediate adjustment time value can be 0 seconds or 1 minute. The setting of the preset immediate adjustment time value here is only an example. In actual testing, those skilled in the art can set it according to actual needs, which will not be elaborated here.

[0112] Specifically, determining the adjustment time of the adjustment plan based on the simulation data includes:

[0113] Based on the simulation data, determine the time when the simulation data of each module of the microgrid system returns to normal;

[0114] Based on the normal time, the adjustment time of the adjustment plan is determined.

[0115] Specifically, the adjustment time of the adjustment scheme is the average of (the time it takes for the simulated data of any module to return to normal * the preset weight value corresponding to the module).

[0116] Specifically, the method for generating an adjustment scheme that matches the microgrid system can be a trained deep learning neural network or an intelligent learning model that has undergone machine learning. The choice of the method for generating an adjustment scheme that matches the microgrid system is only an example. In actual testing, those skilled in the art can choose according to actual needs, as long as the adjustment scheme that matches the microgrid system can be generated based on the current state of the microgrid system, the current module state of each module of the microgrid system, and real-time information. Further details are omitted here.

[0117] In the above embodiments, during model processing, the current mode of the microgrid system is determined based on the current time of the microgrid system, and then the setting scheme of the microgrid system is determined. If the setting scheme is inconsistent with the current execution scheme of the microgrid system, it is determined that the current execution scheme of the microgrid system needs to be adjusted; otherwise, it is determined whether the current execution scheme of the microgrid system needs to be adjusted based on the real-time data and current status of each module of the microgrid system. Based on the judgment result, an adjustment scheme and adjustment time corresponding to the current execution scheme are selectively generated, thereby realizing the selective adjustment of the current execution scheme of the microgrid system and thus realizing targeted control of each module of the microgrid system, improving the intelligent data processing level of the power regulation model.

[0118] Preferably, the power regulation model in the embodiments of the present invention embeds a deep reinforcement learning (DRL) module and employs a deep Q-network (DQN) algorithm to construct an interaction mechanism between the agent and the environment (microgrid system). Through real-time reward functions (such as energy utilization, cost savings, and stability), the control strategies of each module are dynamically optimized. Specifically, this includes:

[0119] (1) Set up the DQN network structure, including the input layer, hidden layer and output layer.

[0120] The input layer has the following number of nodes, determined by the dimension of the state space (S). The state space s... t If there are 6 variables, then the input layer has 6 nodes. That is, the input data is a variable in the state space corresponding to each node, namely, real-time photovoltaic output, state of charge of energy storage system, total power demand of charging pile, real-time electricity price, current time period type, and grid connection status.

[0121] Hidden Layers: Number of Layers and Nodes: Not explicitly stated in the invention, but DQN typically includes multiple fully connected hidden layers to extract state features. For example, two hidden layers can be used, each containing a number of nodes (e.g., 64 nodes), the specific number to be determined based on the actual situation. Activation Function: Hidden layers usually use non-linear activation functions, such as ReLU (Rectified Linear Unit), to introduce non-linearity and enhance the network's expressive power.

[0122] Output layer: Number of nodes: Determined based on the dimension of the action space (A). Action space a t It comprises three actions, meaning the output layer has three nodes. The output data is one action in the action space corresponding to each node, namely the proportion of photovoltaic power charging the energy storage, the proportion of energy storage discharging to the total load, and grid interaction commands. Activation function: The output layer typically uses a linear activation function because the Q value can be any real number.

[0123] (2) Parameter definition:

[0124] Input parameters (state space S):

[0125] s t =[P pv SOC ess ,P load C g [T,M]

[0126] Among them, P pv Real-time power output (kW) for photovoltaics; SOC ess State of charge (%) of the energy storage system; P load C represents the total power demand of the charging pile (kW). gThe real-time electricity price is (RMB / kWh); T represents the current time period type (daytime / nighttime); M represents the grid connection status (0: off-grid, 1: grid-connected).

[0127] Output parameters (motion space A):

[0128] a t =[ɑ charge ,β discharge ,γ g ]

[0129] Where, α charge The proportion of photovoltaic power charging energy storage, and α charge ∈[0,1], representing the proportion of photovoltaic power generation used to charge energy storage; β discharge The proportion of energy storage discharge to the total load, and β discharge ∈[0,1], representing the proportion of energy storage discharge used to meet load demand; γ g This indicates the power grid interaction command (-1: purchase electricity, 0: disconnect, 1: sell electricity), γ g ∈{-1,0,1}.

[0130] Reward function (R):

[0131] R t =w1·U renew +w2·(C saved -C cost )+w3·exp(-ΔSOC)

[0132] Among them, U renew For renewable energy utilization rate, P pv-used For the effective utilization rate of photovoltaic power, P pv-max C represents the nominal maximum power (kW) of the photovoltaic module. saved To save costs on energy storage and discharge and C saved =∑P ess-discharge ·C g-peak P ess-discharge For the actual discharge power of energy storage, C g-peak Peak electricity price (yuan / kWh); C cost For grid interaction costs, and C cost =P g ·C g P g For grid interaction power; ΔSOC represents the energy storage state deviation, and ΔSOC=|SOC t -SOC target |, SOC t ∈[0,1] represents the state of charge (SOC) of the energy storage system at time t. target∈[0,1] represents the target state of charge of the energy storage system; w1, w2, w3 are weighting coefficients, which are determined by Pareto optimization.

[0133] (3) Historical data training: Use historical photovoltaic power output, load demand and electricity price information to train Q-learning or deep reinforcement learning models and generate an initial policy library.

[0134] During training, the Q-value update formula is as follows:

[0135]

[0136] The loss function L is:

[0137]

[0138] Where Q(s,a) is the state-action value function, representing the expected long-term reward that the agent can obtain after taking action a in state s. By continuously updating Q(s,a), the algorithm approximates the optimal policy; α is the learning rate; r is the immediate reward, the direct feedback that the agent receives from the environment after performing action a; γ is the discount factor, 0≤γ≤1, which represents the degree of decay of future rewards and balances the importance of immediate rewards and future rewards. This represents the maximum Q-value among all possible actions a' in the next state s', signifying the expected reward of the agent taking the optimal action in s'. The loss function L is used to measure the predicted Q-value Q(s). i ,a i ) and the target Q value y i Mean squared error (MSE) between samples; N is the sample size; target Q value y i This means that for each sample i, based on the immediate reward r... i The “true” Q value is calculated from the maximum Q value of the next state s'.

[0139] The training process includes: (a) Action selection: An ε-greedy policy is used to balance exploration and exploitation, with an initial high exploration rate of 1.0, which gradually decreases. (b) Experience collection: The experience (state transition) of each interaction is stored in the replay buffer. (c) Network update: Batch data is randomly sampled from the buffer, and the current Q-value and target Q-value are calculated. The target Q-value is calculated through the target network to ensure stability. The mean squared error (MSE) loss is used to update the online network. (d) Target network synchronization: The target network parameters are kept in lag mode through soft updates (tau controls the update ratio) or periodic hard updates. (e) Exploration rate decay: The probability of random exploration is gradually reduced, so that the policy tends to utilize the learned knowledge.

[0140] (4) Online adaptive adjustment: Real-time data acquisition is input into the model, and combined with the current grid status (grid-connected / off-grid), the photovoltaic power output allocation, energy storage charging and discharging thresholds and charging pile power are dynamically adjusted to maximize the consumption of renewable energy.

[0141] (4) Predictive strategy generation: Based on weather forecasts and load forecasts, generate optimization strategies for future periods in advance (such as pre-charging energy storage to cope with cloudy days) as a predictive adjustment scheme.

[0142] In the prediction and adjustment phase, a Long Short-Term Memory (LSTM) network is introduced for multi-step prediction:

[0143]

[0144] Among them W p W l The weight matrix obtained from training is used to predict the results and input them into the model to generate the optimal policy sequence for the next k steps.

[0145] For example, in a certain scenario, there is a sudden change in photovoltaic (PV) output. State detection: At 14:00 during daytime mode, PV output suddenly drops by 30% (due to cloud cover). DRL response: The real-time state input to the DRL model yields the action vector: a t =[0.2,0.8,-1], Execution strategy: 20% of the remaining photovoltaic power is used to charge the energy storage, 80% of the energy storage is used to discharge and support the load, while electricity is purchased at the real-time electricity price to supplement the load. Ultimately, compared with traditional threshold control, it can effectively reduce the load interruption time.

[0146] By embedding a deep reinforcement learning (DRL) module into the power regulation model, a multi-objective dynamic trade-off is achieved, which optimizes energy utilization, economy and stability in real time. Compared with traditional optimization algorithms, the calculation speed is greatly improved, and the risk of over-discharge of energy storage can be predicted in advance.

[0147] Step S104: Based on the real-time adjustment scheme or the predictive adjustment scheme, at the adjustment time, adjust the current execution scheme to achieve targeted control of each module of the microgrid system.

[0148] Based on steps S101-S104 above, by collecting real-time data, current time, and current execution plan of each module of the microgrid system, and substituting the acquired data into the power regulation model, the current execution model can be selectively adjusted according to the real-time data and current time of each module of the microgrid system, or the current execution plan can be selectively predicted and adjusted to obtain the adjustment plan and adjustment time corresponding to the current execution plan, so as to optimize energy configuration. Then, according to the adjustment plan, the current execution plan is adjusted at the corresponding adjustment time to achieve targeted control of each module of the microgrid system. This realizes the intelligent management of the smart photovoltaic, energy storage, and charging integrated microgrid system by the power regulation system, avoiding the technical problem that the existing regulation method generally adopts unified regulation of each module of the system, which makes the photovoltaic, energy storage, and charging integrated system limited in operation and not conducive to the precise control of photovoltaic, energy storage, and charging modules in the photovoltaic, energy storage, and charging integrated system.

[0149] The steps of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but without changing the core design of the algorithm and process, are also within the scope of protection of this patent.

[0150] Second Embodiment

[0151] See appendix Figure 3 , Figure 3 This is a main structural block diagram of an energy control system 300 according to an embodiment of this application. Figure 3As shown, the power regulation system 300 in this embodiment interacts with the smart photovoltaic, energy storage, and charging integrated microgrid system. The power regulation system 300 also interacts with the management terminal. The smart photovoltaic, energy storage, and charging integrated microgrid system includes at least a photovoltaic module, an energy storage module, and a charging module. The power regulation system 300 mainly includes a power regulation model 302 and a control device 301. The power regulation model 302 stores a preset current mode comparison table 3021 and a preset system setting scheme database 3022. The control device 301 includes a processor 3011 and a memory 3012. The memory 3012 can be configured to store program code 3013 for executing the power regulation method of the smart photovoltaic, energy storage, and charging integrated microgrid system in the above method embodiment. The processor 3011 can be configured to execute the program code 3013 in the memory 3012. The program code 3013 includes, but is not limited to, the program code 3013 for executing the power regulation method of the smart photovoltaic, energy storage, and charging integrated microgrid system in the above method embodiment. For ease of explanation, only the parts relevant to the embodiments of this application are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of this application. The control device 301 may be a control device 301 device comprising various electronic devices.

[0152] Specifically, the preset current mode lookup table 3021 stores various modes and the time range corresponding to each mode, and the preset system setting scheme database 3022 includes each microgrid system, at least one daytime mode setting scheme and at least one nighttime mode setting scheme for each microgrid system, and the construction time of each setting scheme.

[0153] In one implementation, the specific function can be described in steps S101-S104.

[0154] The aforementioned power control system 300 is used to perform Figure 3 The power regulation method embodiment of the integrated smart photovoltaic, energy storage and charging microgrid system shown is similar in technical principle, technical problem solved and technical effect produced. Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the power regulation system 300 can be referred to the content described in the embodiment of the power regulation method of the integrated smart photovoltaic, energy storage and charging microgrid system, and will not be repeated here.

[0155] It is not difficult to see that this embodiment is a system implementation corresponding to the first embodiment, and this embodiment can be implemented in conjunction with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment, and will not be repeated here to reduce repetition. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the first embodiment.

[0156] It is worth noting that all modules involved in this embodiment are logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this application, this embodiment does not introduce units that are not closely related to solving the technical problem proposed in this application; however, this does not mean that other units are absent from this embodiment.

[0157] The scope of this application is defined by the appended claims rather than the foregoing description, and is therefore intended to encompass all variations falling within the meaning and scope of equivalents of the claims. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a device claim may also be implemented by a single unit or device in software or hardware. Terms such as "first," "second," etc., are used only for distinguishing descriptions and do not indicate any particular order, nor should they be construed as indicating or implying relative importance.

[0158] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily made by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims, and the above embodiments should be regarded as exemplary and non-limiting.

Claims

1. A power regulation method for a smart integrated photovoltaic, energy storage, and charging microgrid system, characterized in that, The method is applied to a power regulation system, which interacts with a smart integrated photovoltaic, energy storage, and charging microgrid system. The smart integrated photovoltaic, energy storage, and charging microgrid system includes at least a photovoltaic module, an energy storage module, and a charging module. The method includes the following steps: Obtain real-time data from each module of the microgrid system; Obtain the current time and current execution plan of the microgrid system; The real-time data of each module of the microgrid system, the current time of the microgrid system, and the current execution plan are substituted into the power control model. Based on the real-time data of each module of the microgrid system and the current time of the microgrid system, the current execution plan is selectively adjusted, or the current execution plan is selectively predicted and adjusted, to obtain an adjustment plan and adjustment time corresponding to the current execution plan. The adjustment plan includes an immediate adjustment plan or a predictive adjustment plan. Based on the real-time adjustment scheme or the predictive adjustment scheme, the current execution scheme is adjusted at the adjustment time to achieve targeted control of each module of the microgrid system; Determine the current state of the microgrid system, wherein the current state is one of grid-connected state and grid-connected ratio, or off-grid state; The current module status and real-time information of each module of the microgrid system are obtained, and the current module status and real-time information of each module of the microgrid system are used to construct the real-time data of each module of the microgrid system. Based on the current time of the microgrid system, the current mode of the microgrid system is determined, wherein the current mode includes daytime mode or nighttime mode; Based on the current mode of the microgrid system, determine the corresponding configuration scheme for the microgrid system; If the setting scheme corresponding to the microgrid system is inconsistent with the current execution scheme of the microgrid system, it is determined that the current execution scheme of the microgrid system needs to be adjusted. Otherwise, based on the real-time data of each module of the microgrid system and the current state of the microgrid system, it is determined whether the current execution plan of the microgrid system needs to be adjusted. Based on the judgment result, an adjustment plan and adjustment time corresponding to the current execution plan are selectively generated; If it is determined that the current execution plan of the microgrid system needs to be adjusted, an adjustment plan matching the microgrid system and the adjustment time of the adjustment plan are generated based on the current state of the microgrid system, the current module state of each module of the microgrid system and real-time information, as well as the control instructions or emergency instructions received by the power regulation system. If it is determined that the current execution plan of the microgrid system does not need to be adjusted, then the environmental data of the microgrid system is obtained, wherein the environmental data includes current environmental data and predicted environmental data; Based on the environmental data of the microgrid system and the real-time data of each module of the microgrid system, an adjustment scheme corresponding to the current execution scheme is selectively generated.

2. The power regulation method for a smart integrated photovoltaic, energy storage, and charging microgrid system according to claim 1, characterized in that, The power control system also interacts with the management terminal. Before acquiring real-time data from each module of the microgrid system, the method further includes: In response to control commands or emergency commands received by the power regulation system, the system selectively performs corresponding operations on one or more modules within the power regulation system or the microgrid system.

3. The power regulation method for a smart integrated photovoltaic, energy storage, and charging microgrid system according to claim 2, characterized in that, The selective execution of corresponding operations on one or more modules within the power regulation system or the microgrid system in response to control commands or emergency commands received by the power regulation system includes: In response to a control command issued by a management terminal received by the power regulation system, the system performs a grid connection or off-grid operation that matches the control command, wherein the control command is a grid connection command or an off-grid command; or, In response to an emergency command issued by the microgrid system received by the power control system, the module type corresponding to the emergency command is obtained; Based on the emergency instruction, emergency operations are performed on the module corresponding to the emergency instruction.

4. The power regulation method for a smart integrated photovoltaic, energy storage, and charging microgrid system according to claim 3, characterized in that, The power regulation model stores a preset system setting scheme database. This database includes various microgrid systems, at least one daytime mode setting scheme and at least one nighttime mode setting scheme for each microgrid system, and the construction time of each setting scheme. Determining the setting scheme corresponding to the microgrid system based on its current mode includes: If the current mode of the microgrid system is daytime mode, retrieve the latest version of the daytime mode setting scheme that matches the microgrid system from the preset system setting scheme database; or, If the current mode of the microgrid system is night mode, retrieve the latest night mode setting scheme that matches the microgrid system from the preset system setting scheme database.

5. The power regulation method for a smart integrated photovoltaic, energy storage, and charging microgrid system according to claim 4, characterized in that, The determination of whether the current execution plan of the microgrid system needs to be adjusted based on the real-time data of each module of the microgrid system and the current state of the microgrid system includes: If the current module status of each module in the real-time data of each module of the microgrid system is inconsistent with the current execution plan of the microgrid system, then it is determined that the current execution plan of the microgrid system needs to be adjusted. or, If the current state of the microgrid system is inconsistent with the current execution plan of the microgrid system, then it is determined that the current execution plan of the microgrid system needs to be adjusted. Otherwise, it is determined that the current execution scheme of the microgrid system does not need to be adjusted.

6. The power regulation method for a smart integrated photovoltaic, energy storage, and charging microgrid system according to claim 5, characterized in that, The process of generating an adjustment scheme matching the microgrid system based on the current state of the microgrid system, the current module state and real-time information of each module of the microgrid system, and the control commands or emergency commands received by the power regulation system, and the adjustment time of the adjustment scheme, includes: Based on the current state of the microgrid system, the current module state of each module of the microgrid system, and real-time information, an adjustment scheme matching the microgrid system is generated. Based on the control commands or emergency commands received by the power regulation system, the adjustment time of the adjustment scheme is determined; Based on the adjustment time of the adjustment plan, the type of the adjustment plan is determined, which is either an immediate adjustment plan or a predictive adjustment plan.

7. An electrical energy control system, characterized in that, The power regulation system interacts with the smart photovoltaic, energy storage, and charging integrated microgrid system, and also interacts with the management terminal. The smart photovoltaic, energy storage, and charging integrated microgrid system includes at least a photovoltaic module, an energy storage module, and a charging module. The power regulation system includes a power regulation model and a control device. The power regulation model stores a preset current mode lookup table and a preset system setting scheme database. The control device includes a processor and a memory. The memory is adapted to store multiple program codes, which are adapted to be loaded and run by the processor to execute the power regulation method of the smart photovoltaic, energy storage, and charging integrated microgrid system as described in any one of claims 1 to 6.

Images