Virtual power plant cloud-edge operation control method and system

Abstract

The present invention discloses a cloud-edge operation control method and system for a virtual power plant, which belongs to the field of cloud-edge operation control methods, wherein the method includes the following steps: Step 1: Data acquisition and preprocessing; Step 2: Edge computing and rapid response, aggregating charging pile operation data in each region at the edge node, and performing local optimization and rapid response; Step 3: Cloud-based global optimization and scheduling, the cloud platform predicts the charging demand for the next 24 hours based on the long-short term memory model, and solves the multi-objective optimization model to generate a scheduling plan; Step 4: Instruction issuance and execution; Step 5: Dynamic feedback and closed-loop optimization. The present invention, through a cloud-edge collaborative architecture and a multi-level optimization strategy, solves the problems of response delay, lack of local optimization, and poor multi-objective coordination of existing virtual power plant technologies in large-scale charging pile scenarios, and provides an innovative solution for the efficient operation of smart grids and the two-way interaction of user needs.

Description

Technical Field

[0001] The present invention relates to the field of cloud-edge operation control methods, and specifically to a virtual power plant cloud-edge operation control method and system. Background Art

[0002] Virtual power plants (VPPs) have become an important means of improving grid flexibility and stability by integrating distributed energy resources (such as renewable energy, energy storage systems, and electric vehicle charging stations) and leveraging information and communication technologies to achieve efficient resource coordination. However, existing technologies for real-time scheduling and optimization of large-scale electric vehicle charging stations still face the following challenges:

[0003] 1. Insufficient response speed: Traditional virtual power plants rely on centralized cloud scheduling, with long data processing links, making it difficult to meet the demand for rapid power adjustment of charging piles (such as response in seconds), resulting in delayed adjustment when the grid's dynamic load fluctuates.

[0004] 2. Lack of local optimization: Existing solutions mostly adopt global optimization strategies, but lack real-time data analysis and rapid decision-making capabilities on the edge side, and cannot effectively deal with problems such as overloaded transformers in local distribution networks or sudden increases in charging demand.

[0005] 3. Poor multi-objective coordination: Existing optimization models lack coordination for multiple objectives such as grid power purchase costs, peak power suppression, and user charging demand satisfaction. In addition, the comprehensiveness of constraints (such as charging completion time deviation, energy storage SOC range, and voltage stability) needs to be improved.

[0006] Therefore, those skilled in the art have provided a virtual power plant cloud-edge operation control method and system to solve the problems raised in the above background technology. Summary of the Invention

[0007] The purpose of the present invention is to provide a cloud-edge operation control method and system for a virtual power plant. Through a cloud-edge collaborative architecture and a multi-level optimization strategy, it solves the problems of response delay, lack of local optimization, and poor multi-objective coordination in existing virtual power plant technologies in large-scale charging pile scenarios, and provides an innovative solution for the efficient operation of smart grids and the two-way interaction of user needs, so as to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] The virtual power plant cloud-edge operation control method includes the following steps:

[0010] Step 1: Data collection and preprocessing;

[0011] Sensors deployed at charging pile terminals collect real-time data on charging power, battery state of charge (SOC), user reservation information, and distribution network node voltage. Edge gateways filter outliers and perform protocol conversion on the raw data.

[0012] Step 2: Edge computing and rapid response;

[0013] Aggregate charging pile operation data in various regions at edge nodes and perform local optimization and rapid response;

[0014] Step 3: Global optimization and scheduling in the cloud;

[0015] The cloud platform uses a long short-term memory (LSTM) model to predict charging demand for the next 24 hours and solves a multi-objective optimization model to generate a scheduling plan;

[0016] Step 4: Instruction issuance and execution;

[0017] The cloud-generated scheduling plan is broken down into power instructions at 15-minute intervals, which are then sent to the charging pile terminal via the 5G Ultra-Reliable Low-Latency Communication (URLLC) channel. The charging power is then adjusted in real time using pulse-width modulation (PWM) signals, with a response time of ≤1 second.

[0018] Step 5: Dynamic feedback and closed-loop optimization;

[0019] The deviation between the actual power of the charging pile and the command is monitored in real time. If the mean absolute percentage error (MAPE) is greater than 8%, the adjustment mechanism is triggered.

[0020] As a further solution of the present invention: the local optimization in step 2 includes the following sub-steps:

[0021] S1: Collect the current total load of the distribution network transformers in the target area and compare it with the load value of the previous 15 minutes;

[0022] S2: Based on the comparison results, vehicles waiting to be charged in the target area but without confirmed reservations are directed to the highest priority charging station;

[0023] S3: Extract the charging station that the target vehicle intends to go to from the user's reservation information and obtain the current distribution network transformer load of the charging station;

[0024] S4: Allocate a charging pile to the user's vehicle according to the preset allocation rules, and send the allocation result to the user's vehicle;

[0025] S5: If the total load in the current target area exceeds the preset threshold, the charging pile power is reduced according to the preset priority.

[0026] As a further solution of the present invention: the specific process of charging station diversion in step S2 is:

[0027] Extract the distribution network transformer loads of each charging station in the target area and generate a first list by sorting the loads from smallest to largest;

[0028] Extract the distance between each charging station and the target vehicle, and sort them in ascending order to generate a second list;

[0029] According to the current load change range, dynamic weight factors a and b are assigned to the first list and the second list respectively;

[0030] Calculate the priority parameter S of each charging station = list ranking weight * a + distance ranking weight * b, and select the charging station with the smallest S as the highest priority charging station;

[0031] The location of the highest priority charging station is sent to the target vehicle, guiding it to the destination.

[0032] As a further solution of the present invention: the assignment rule of the dynamic weight factors a and b is:

[0033] If the current total load increases by ≥5% compared to the previous 15 minutes, then a=3, b=1;

[0034] If the increase is less than 5%, then a=3, b=2;

[0035] If the decrease is less than 5%, then a=2, b=3;

[0036] If the decrease is ≥5%, then a=1, b=3.

[0037] As a further solution of the present invention: if the target vehicle accepts guidance and arrives at the highest priority charging station, contribution points are accumulated for it according to the mileage.

[0038] As a further solution of the present invention: the preset allocation rule in step S4 is:

[0039] Calculate the decentralized weight value V of each idle charging pile according to the load status of the target charging station;

[0040] If the load is within the preset range, V is the number of idle charging piles within a radius of 5 meters;

[0041] If the load exceeds the limit, V is the number of idle charging piles within a radius of 3 meters;

[0042] If the load is insufficient, V is the number of idle charging piles within a radius of 10 meters;

[0043] Select the charging pile corresponding to the maximum V value and assign it to the user's vehicle.

[0044] As a further solution of the present invention: in step S5, the specific process of reducing the power of the charging pile according to the preset priority is:

[0045] Reduce the power of non-public transportation charging stations in the current target area by 50%;

[0046] Collect the distribution network transformer load after power reduction in the target area and mark it as C;

[0047] Under the premise of ensuring that the bus charging pile operates at full power, calculate the load idle value Q = (c1-C) / c2, where c1 and c2 are both preset values;

[0048] Extract the integer of the load idle value Q, marked as q;

[0049] Extract the contribution points of the remaining charging vehicles in the target area and sort them from largest to smallest according to the contribution points to obtain a third list;

[0050] Send an offer to the first q charging vehicles in the third list, with the offer content being "Do you want to consume ten contribution points to increase the current charging power?"

[0051] If the charging vehicle agrees to the offer, the contribution points corresponding to the charging vehicle will be deducted, and the charging pile corresponding to the charging vehicle will be adjusted to full power operation;

[0052] If the charging vehicle does not agree to the offer, the offer is sent to the charging vehicles in the next lower part of the third list.

[0053] As a further solution of the present invention: in step 3, the model expression of the multi-objective optimization model is:

[0054] ;

[0055] in, Refers to the cost of electricity purchased from the power grid during time period t, Refers to the total charging power of all charging piles during time period t. Refers to the weight parameter for peak power, Refers to the maximum value of charging power during the optimization period, and T refers to the total time period of the optimization period;

[0056] The constraints of the multi-objective optimization model include: the user charging completion time deviation is ≤10%, the energy storage SOC is maintained in the range of 20%-90%, and the distribution network node voltage deviation does not exceed ±7%.

[0057] As a further solution of the present invention: the adjustment mechanism includes:

[0058] (1) Enable the backup energy storage system to compensate for the power gap;

[0059] (2) Update the LSTM model weights through the federated learning framework and optimize the subsequent scheduling plan every 15 minutes.

[0060] This application also discloses a virtual power plant cloud-edge operation control system, which adopts a virtual power plant cloud-edge operation control method, including:

[0061] Data acquisition module, used to perform data acquisition and preprocessing;

[0062] Edge computing module, used to perform edge computing and rapid response;

[0063] Cloud decision module, used to perform global optimization and scheduling in the cloud;

[0064] Instruction execution module, used to issue and execute power instructions;

[0065] Dynamic feedback module, used to perform dynamic feedback and closed-loop optimization.

[0066] Compared with the prior art, the present invention has the following beneficial effects:

[0067] 1. This application uses edge computing to achieve real-time monitoring and rapid drainage of local loads, alleviating the risk of overload of distribution network transformers.

[0068] 2. This application uses cloud-based intelligent prediction (such as LSTM model) to generate multi-objective optimized scheduling plans to balance economic efficiency and grid stability.

[0069] 3. This application designs a dynamic feedback mechanism, combining the backup energy storage system with rolling updates of model parameters to improve system robustness.

[0070] 4. This application introduces incentive mechanisms such as user contribution points to optimize the charging pile allocation strategy and improve user participation and resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 Flowchart of the cloud-edge operation control method for a virtual power plant;

[0072] Figure 2 This is the structural block diagram of the cloud-edge operation control system of the virtual power plant. DETAILED DESCRIPTION

[0073] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0074] As mentioned in the background technology of this application, research has found that the existing technology still has certain defects in the real-time scheduling and optimization of large-scale electric vehicle charging piles, such as insufficient response speed, lack of local optimization, and poor multi-objective coordination.

[0075] In order to solve the above-mentioned defects, this application discloses a cloud-edge operation control method and system for a virtual power plant. Through a cloud-edge collaborative architecture and a multi-level optimization strategy, it solves the problems of response delay, lack of local optimization, and poor multi-objective coordination in existing virtual power plant technologies in large-scale charging pile scenarios, and provides an innovative solution for the efficient operation of smart grids and the two-way interaction of user needs.

[0076] The following will describe in detail how the solution of this application solves the above technical problems with reference to the accompanying drawings.

[0077] See also Figure 1 In an embodiment of the present invention, a virtual power plant cloud-edge operation control method includes the following steps: Step 1: Data acquisition and preprocessing: Charging power, battery state of charge (SOC), user reservation information, and distribution network node voltage data are collected in real time through sensors deployed on charging pile terminals, and outlier filtering and protocol conversion are performed on the original data through the edge gateway; Step 2: Edge computing and rapid response: Charging pile operation data in various regions are aggregated at the edge nodes, and local optimization and rapid response are performed; Step 3: Cloud-based global optimization and scheduling: The cloud platform predicts charging demand for the next 24 hours based on a long short-term memory (LSTM) model, and solves a multi-objective optimization model to generate a scheduling plan; Step 4: Instruction issuance and execution: The scheduling plan generated on the cloud is decomposed into power instructions at 15-minute intervals, which are issued to the charging pile terminals through a 5G ultra-reliable low-latency communication (URLLC) channel and transmitted to the charging pile terminals through pulse width modulation (Pulse Width Modulation). The system uses a PWM (power-pulse width modulation) signal to adjust charging power in real time, with a response time of ≤1 second. Step 5: Dynamic feedback and closed-loop optimization: The system monitors the deviation between the actual charging pile power and the commanded power in real time. If the mean absolute percentage error (MAPE) exceeds 8%, an adjustment mechanism is triggered. This layered architecture (rapid response at the edge and global optimization in the cloud) enables real-time scheduling and closed-loop control, addressing the response delay issues of traditional solutions and improving the grid's dynamic regulation capabilities.

[0078] In this embodiment, the local optimization in step 2 includes the following sub-steps: S1: Collect the current total load of the distribution network transformers in the target area and compare it with the load value of the previous 15 minutes; S2: Based on the comparison results, direct vehicles in the target area that are waiting to charge but have not confirmed their reservations to the highest priority charging station; S3: Extract the charging station that the target vehicle intends to visit from the user's reservation information and obtain the current distribution network transformer load at that charging station; S4: Assign a charging pile to the user's vehicle according to the preset allocation rules and send the allocation result to the user's vehicle; S5: If the current total load in the target area exceeds a preset threshold, reduce the power of the charging pile according to the preset priority. Based on the real-time data from the edge nodes, the charging strategy is quickly adjusted to prioritize mitigating the risk of overload in local areas and ensure the stable operation of the distribution network.

[0079] In this embodiment, the specific process of charging station diversion in step S2 is as follows: extract the distribution network transformer load of each charging station in the target area and sort it by load in ascending order to generate a first list; extract the distance between each charging station and the target vehicle and sort it by distance in ascending order to generate a second list; assign dynamic weight factors a and b to the first and second lists, respectively, based on the current load fluctuation; calculate each charging station's priority parameter S = list ranking weight * a + distance ranking weight * b, and select the charging station with the smallest S as the highest priority charging station; and send the location of the highest priority charging station to the target vehicle, guiding it there. This dynamically balances charging station load and user convenience, optimizes resource allocation, reduces local grid pressure, and improves user charging efficiency.

[0080] In this embodiment, the dynamic weighting factors a and b are assigned as follows: if the current total load increases by ≥5% compared to the previous 15 minutes, a = 3 and b = 1; if the increase is <5%, a = 3 and b = 2; if the decrease is <5%, a = 2 and b = 3; if the decrease is ≥5%, a = 1 and b = 3. This setting flexibly responds to grid load fluctuations, prioritizing grid stability in high-load scenarios while also balancing user charging convenience.

[0081] In this embodiment, if the target vehicle accepts guidance and arrives at the highest-priority charging station, it will be awarded contribution points based on its mileage. This setting encourages users to cooperate with the scheduling strategy, promotes a balanced distribution of charging demand in time and space, and improves resource utilization and user engagement.

[0082] In this embodiment, the preset allocation rule in step S4 is as follows: based on the load status of the target charging station, a distributed weight value V is calculated for each idle charging pile. If the load is within a preset range, V is the number of idle charging piles within a 5-meter radius; if the load exceeds the limit, V is the number of idle charging piles within a 3-meter radius; if the load is insufficient, V is the number of idle charging piles within a 10-meter radius. The charging pile with the largest V value is selected and allocated to the user's vehicle. This configuration optimizes the spatial distribution of charging piles, avoids local congestion, improves charging station efficiency, and extends equipment life.

[0083] In this embodiment, in step S5, the specific process of reducing charging pile power according to preset priorities is as follows: reducing the power of non-bus charging piles within the current target area by 50%; collecting the distribution network transformer load after the power reduction in the target area and marking it as C; calculating the load idle value Q = (c1-C) / c2, where c1 and c2 are both preset values, while ensuring that the bus charging piles operate at full power; extracting the integer of the load idle value Q, marked as q; extracting the contribution points of the remaining charging vehicles in the target area and sorting them from highest to lowest according to contribution points to obtain a third list; sending an offer to the first q charging vehicles in the third list, the offer content being "whether to consume ten contribution points to increase the current charging power?"; if the charging vehicle agrees to the offer, the corresponding contribution points are deducted and the corresponding charging pile is adjusted to full power; if the charging vehicle disagrees, the offer is sent to the charging vehicles further down in the third list. This configuration allows for rapid load reduction in the event of an emergency load limit exceeding the limit, while also enabling user autonomy through a points mechanism, balancing grid stability and user experience.

[0084] In this embodiment, in step 3, the model expression of the multi-objective optimization model is:

[0085] ;

[0086] in, Refers to the cost of electricity purchased from the power grid during time period t, Refers to the total charging power of all charging piles during time period t. Refers to the weight parameter for peak power, The maximum charging power within the optimization cycle is T, and the total time period is T. The constraints of the multi-objective optimization model include: user charging completion time deviation ≤ 10%, energy storage SOC maintained between 20% and 90%, and distribution network node voltage deviation no more than ±7%. Mathematical modeling enables multi-objective coordinated optimization of economic efficiency and grid security, ensuring that the dispatch plan addresses both user needs and grid constraints.

[0087] In this embodiment, the adjustment mechanism includes: (1) enabling the backup energy storage system to compensate for the power gap; (2) updating the LSTM model weights through the federated learning framework and optimizing the subsequent scheduling plan every 15 minutes. This setting continuously improves prediction accuracy by dynamically compensating for operational deviations and combining data-driven optimization to enhance the robustness and adaptability of the system.

[0088] See also Figure 2 This application also discloses a virtual power plant cloud-edge operation control system, which adopts a virtual power plant cloud-edge operation control method, including: a data acquisition module for performing data acquisition and preprocessing; an edge computing module for performing edge computing and rapid response; a cloud decision module for performing cloud global optimization and scheduling; an instruction execution module for issuing and executing power instructions; and a dynamic feedback module for performing dynamic feedback and closed-loop optimization.

[0089] In order to further illustrate the present invention, the virtual power plant cloud-edge operation control method and system provided by the present invention are described in detail below in combination with embodiments.

[0090] Example 1: Charging Station Traffic Diversion and Power Regulation

[0091] The edge node collects charging pile data in the target area and calculates the load change rate of the distribution network transformer;

[0092] Dynamically adjust the priority weights (a, b) of charging stations based on the load change rate to generate a list of charging stations with the highest priority;

[0093] Send guidance information to the target vehicle and allocate charging piles based on user response;

[0094] If the total load in the area exceeds the limit, the power of non-public transportation charging piles will be reduced according to preset rules, and the user charging priority will be dynamically adjusted through the contribution points mechanism.

[0095] Example 2: Cloud-based multi-objective optimization

[0096] The cloud predicts charging demand for the next 24 hours based on the LSTM model;

[0097] Solve the objective function to minimize the weighted sum of the grid's electricity purchase cost and peak power, while satisfying user charging time, energy storage SOC, and voltage stability constraints;

[0098] Model parameters are updated through federated learning every 15 minutes, and subsequent scheduling plans are continuously optimized.

[0099] This invention uses edge computing to enable real-time monitoring and rapid power diversion of local loads, mitigating the risk of transformer overload in the distribution network. Cloud-based intelligent prediction (such as LSTM models) is also used to generate multi-objective optimized scheduling plans, balancing economic efficiency and grid stability. A dynamic feedback mechanism, combined with a backup energy storage system and rolling updates of model parameters, enhances system robustness. Furthermore, incentive mechanisms such as user contribution points are introduced to optimize charging station allocation strategies, increasing user engagement and resource utilization.

[0100] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

[0101] The above is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solutions and inventive concepts of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A virtual power plant cloud-edge operation control method, characterized in that: The following steps are involved: Step 1: Data collection and preprocessing; Sensors deployed at charging pile terminals collect charging power, battery state of charge, user reservation information, and distribution network node voltage data in real time. Edge gateways filter outliers and perform protocol conversion on the raw data. Step 2: Edge computing and rapid response; Aggregate charging pile operation data in various regions at edge nodes and perform local optimization and rapid response; Step 3: Global optimization and scheduling in the cloud; The cloud platform predicts charging demand for the next 24 hours based on the long-short-term memory model and solves the multi-objective optimization model to generate a scheduling plan; Step 4: Instruction issuance and execution; The scheduling plan generated in the cloud is broken down into power instructions at 15-minute intervals, which are sent to the charging pile terminal via the 5G communication channel. The charging power is adjusted in real time through pulse width modulation signals, with a response time of ≤1 second. Step 5: Dynamic feedback and closed-loop optimization; Real-time monitoring of the deviation between the actual power of the charging pile and the command. If the average absolute percentage error is greater than 8%, the adjustment mechanism is triggered; The local optimization in step 2 includes the following sub-steps: S1: Collect the current total load of the distribution network transformers in the target area and compare it with the load value of the previous 15 minutes; S2: Based on the comparison results, vehicles waiting to be charged in the target area but without confirmed reservations are directed to the highest priority charging station; S3: Extract the charging station that the target vehicle intends to go to from the user's reservation information and obtain the current distribution network transformer load of the charging station; S4: Allocate a charging pile to the user's vehicle according to the preset allocation rules, and send the allocation result to the user's vehicle; S5: If the total load in the current target area exceeds the preset threshold, the charging pile power is reduced according to the preset priority; The specific process of charging station drainage in step S2 is as follows: Extract the distribution network transformer loads of each charging station in the target area and generate a first list by sorting the loads from smallest to largest; Extract the distance between each charging station and the target vehicle, and sort them in ascending order to generate a second list; According to the current load change range, dynamic weight factors a and b are assigned to the first list and the second list respectively; Calculate the priority parameter S of each charging station = list ranking weight * a + distance ranking weight * b, and select the charging station with the smallest S as the highest priority charging station; Send the location of the highest priority charging station to the target vehicle and guide it there; The assignment rules of the dynamic weight factors a and b are as follows: If the current total load increases by ≥5% compared to the previous 15 minutes, then a = 3, b = 1; If the increase is less than 5%, then a = 3, b = 2; If the decrease is less than 5%, then a = 2, b = 3; If the decrease is ≥5%, then a=1, b=3; If the target vehicle accepts guidance and arrives at the highest priority charging station, it will accumulate contribution points based on the mileage; The preset allocation rule in step S4 is: Calculate the decentralized weight value V of each idle charging pile according to the load status of the target charging station; If the load is within the preset range, V is the number of idle charging piles within a radius of 5 meters; If the load exceeds the limit, V is the number of idle charging piles within a radius of 3 meters; If the load is insufficient, V is the number of idle charging piles within a radius of 10 meters; Select the charging pile corresponding to the maximum V value and assign it to the user's vehicle.

2. The virtual power plant cloud-edge operation control method according to claim 1 is characterized in that: In step S5, the specific process of reducing the power of the charging pile according to the preset priority is as follows: Reduce the power of non-public transportation charging stations in the current target area by 50%; Collect the distribution network transformer load after power reduction in the target area and mark it as C; Under the premise of ensuring that the bus charging pile operates at full power, calculate the load idle value Q = (c1-C) / c2, where c1 and c2 are both preset values; Extract the integer of the load idle value Q, marked as q; Extract the contribution points of the remaining charging vehicles in the target area and sort them from largest to smallest according to the contribution points to obtain a third list; Send an offer to the first q charging vehicles in the third list, with the offer content being "Do you want to consume ten contribution points to increase the current charging power?" If the charging vehicle agrees to the offer, the contribution points corresponding to the charging vehicle will be deducted, and the charging pile corresponding to the charging vehicle will be adjusted to full power operation; If the charging vehicle does not agree to the offer, the offer is sent to the charging vehicles in the next lower part of the third list.

3. The virtual power plant cloud-edge operation control method according to claim 2 is characterized in that: In step 3, the model expression of the multi-objective optimization model is: Among them, C grid (t) refers to the power purchase cost of the power grid during time period t, P charge (t) refers to the total charging power of all charging piles in the time period t, λ refers to the weight parameter for peak power, max t (P charge (t)) refers to the maximum value of charging power during the optimization period, and T refers to the total time period of the optimization period; The constraints of the multi-objective optimization model include: the user charging completion time deviation is ≤10%, the energy storage SOC is maintained in the range of 20%-90%, and the distribution network node voltage deviation does not exceed ±7%.

4. The virtual power plant cloud-edge operation control method according to claim 3 is characterized in that: The adjustment mechanism includes: (1) Enable the backup energy storage system to compensate for the power gap; (2) Update the LSTM model weights through the federated learning framework and optimize the subsequent scheduling plan every 15 minutes.

5. The virtual power plant cloud-edge operation control system is characterized by: The method for controlling cloud-edge operation of a virtual power plant according to any one of claims 1 to 4 is adopted, comprising: Data acquisition module, used to perform data acquisition and preprocessing; Edge computing module, used to perform edge computing and rapid response; Cloud decision module, used to perform global optimization and scheduling in the cloud; Instruction execution module, used to issue and execute power instructions; Dynamic feedback module, used to perform dynamic feedback and closed-loop optimization.

Images