Optical storage and charging micro-grid coordination control system based on multi-source feature fusion

Abstract

The invention discloses an optical storage and charging micro-grid coordination control system based on multi-source feature fusion, and relates to the technical field of optical storage and charging grid coordination control. Comprising a power coupling degree acquisition module, a transmission delay acquisition module, a coupling compactness acquisition module, a coupling node relation judgment module, a pilot candidate pool establishment module, a fault node judgment module, a temporary pilot node calibration module, a cooperative adjustment module and a feedback module. Marking a node exceeding an early warning threshold value as a fault node, outputting positioning information of the fault node, and selecting a non-fault node closest to the fault node from the navigation candidate pool through a temporary navigation node calibration module as a temporary navigation node; the primary slave node accurately executes the optimal control quantity issued by the temporary pilot node to quickly recover the stability of the system, and the secondary slave node randomly adjusts the output power in a set control interval as auxiliary support.

Description

Technical Field

[0001] This invention belongs to the field of photovoltaic-storage-charging network coordination control technology, specifically a photovoltaic-storage-charging microgrid coordination control system based on multi-source feature fusion. Background Technology

[0002] A microgrid is a power system capable of achieving local energy self-sufficiency, integrating renewable energy sources, energy storage devices, and electrical loads. With the increasing prevalence of renewable energy, microgrids are gaining more attention as a flexible and efficient energy management method. A photovoltaic-storage-charging microgrid includes photovoltaic power generation systems, energy storage systems, and charging piles as loads. Complex energy flows and interactions exist among these components, requiring effective coordination and control strategies to ensure stable system operation and efficient utilization. During the operation of a microgrid, there are numerous power flow interactions between control nodes, such as photovoltaic power charging energy storage, energy storage discharging to loads, or reverse regulation. Simultaneously, the nodes are distributed in different physical locations and rely on wireless or industrial communication networks for coordination. Therefore, the nodes not only have interactive coupling relationships with all candidate node rates but are also affected by communication delays caused by differences in communication distance and bandwidth.

[0003] However, in the control of photovoltaic-storage-charging microgrids, the control and scheduling are based only on power or energy flow, ignoring the impact of communication delay on real-time coordination. At the same time, the master control node is fixed or statically set and cannot be dynamically adjusted according to the node's computing power and resource status. It lacks a hierarchical master-slave collaborative control mechanism based on node capabilities and coupling relationships. Based on this, a photovoltaic-storage-charging microgrid coordinated control system based on multi-source feature fusion is proposed. Summary of the Invention

[0004] The purpose of this invention is to provide a coordinated control system for photovoltaic, energy storage, and charging microgrids based on multi-source feature fusion, so as to solve the problems mentioned in the background art.

[0005] A coordinated control system for photovoltaic-storage-charging microgrids based on multi-source feature fusion includes: The power coupling degree acquisition module obtains the power coupling degree between any two control nodes based on the transmission power and output power between any two control nodes in the energy storage and charging microgrid. The transmission delay acquisition module obtains the transmission delay between any two control nodes in the photovoltaic-storage-charging microgrid by measuring the communication distance and link bandwidth between them. The coupling tightness acquisition module obtains the coupling tightness between any two control nodes based on the power coupling degree and transmission delay between any two control nodes. The coupling node relationship determination module obtains the strongly correlated and weakly correlated coupling nodes of each control node based on the coupling tightness between any two control nodes. The navigation candidate pool establishment module normalizes the CPU computing power, remaining memory and communication bandwidth of each control node to obtain the node capabilities of each control node, and establishes the navigation candidate pool based on the node capabilities. The fault node determination module determines the fault node based on the real-time output power and early warning threshold of each control node, and outputs the location of the fault node. The temporary navigation node calibration module calibrates the temporary navigation node of the faulty node based on the node distance between each non-faulty node in the navigation candidate pool and the faulty node. The collaborative adjustment module designates strongly correlated nodes of the temporary navigation node as primary slave nodes and weakly correlated nodes as secondary slave nodes. Based on the real-time output power and target output power of each primary and secondary slave node, it obtains and issues the optimal control quantity for each primary slave node and the control range for each secondary slave node. The primary slave node adjusts according to the issued optimal control quantity, and the secondary slave node selects an adjustment value within the control range for adjustment.

[0006] As a further aspect of the present invention, the specific method for obtaining the power coupling degree between any two control nodes is as follows: The ratio between the absolute value of the transmission power between any two control nodes during the monitoring period and the sum of the output power of the two control nodes is taken as the power coupling degree between any two control nodes.

[0007] As a further aspect of the present invention, the specific method for obtaining the transmission delay between any two control nodes is as follows: Calculate the physical distance between any two control nodes, and use the ratio between the physical distance between any two control nodes and the bandwidth of their corresponding links as the transmission delay between the two control nodes.

[0008] As a further aspect of the present invention, the specific method for obtaining the coupling tightness between any two control nodes is as follows: After normalizing all power coupling degrees Rd and transmission delays Dd, normalized values ​​Rd′ and Dd′ of all power coupling degrees Rd and transmission delays Dd are obtained. The sum of the products of the normalized values ​​Rd′ and Dd′ with preset parameter factors w1 and w2 respectively is taken as the coupling tightness Jd between any two control nodes, where d refers to the node pair formed by any two control nodes.

[0009] As a further aspect of the present invention, the specific method for obtaining the strongly correlated and weakly correlated coupling nodes of each control node is as follows: The coupling tightness between a single control node and other control nodes is obtained. Control nodes with coupling tightness greater than the coupling tightness threshold are designated as strongly correlated coupled nodes of the corresponding control node, and control nodes with coupling tightness less than or equal to the coupling tightness threshold are designated as weakly correlated coupled nodes of the corresponding control node. Both strongly correlated and weakly correlated coupled nodes are bound to the corresponding control node.

[0010] As a further aspect of the present invention, the specific method for establishing the leader candidate pool is as follows: After normalizing the CPU computing power, remaining memory, and communication bandwidth of each control node, normalized values ​​EAi, EBi, and ECi are obtained. Then, the node capability Ji of each control node is obtained by using Ji = 0.5×EAi + 0.3×EBi + 0.2×ECi. The mean of the maximum and minimum values ​​of the node capabilities Ji of all control nodes, as well as the absolute value of the difference between the maximum and minimum values, are obtained. The sum of the mean and the absolute value of the difference is used as the screening threshold. Control nodes whose node capabilities are greater than or equal to the screening threshold are selected as candidate nodes. A navigation candidate pool is established through all candidate nodes.

[0011] As a further aspect of the present invention, the specific method for determining the faulty node is as follows: Obtain the rated output power of each control node, and use 1.25 times the rated output power as the warning threshold for each control node. Mark the control node whose real-time output power is greater than the corresponding warning threshold as a fault node.

[0012] As a further aspect of the present invention, the specific method for calibrating the temporary navigation node of the faulty node is as follows: Obtain fault location and the physical location of each candidate node in the pilot candidate pool in the photovoltaic-storage-charging microgrid. Obtain the node distance between each non-faulty node in the pilot candidate pool and the faulty node. Mark the candidate node with the smallest node distance as the temporary pilot node.

[0013] As a further aspect of the present invention: if multiple nodes are at completely equal distances, then according to the additional rule: the candidate node with the highest node capability is selected first as the temporary navigation node; if the node capabilities are still the same, then one of them is randomly selected as the temporary navigation node.

[0014] As a further aspect of the present invention, the specific method for obtaining the optimal control quantity of each primary subordinate node and the control range of each secondary subordinate node is as follows: Obtain the difference ΔFa between the target output power and the real-time output power of each primary slave node. Multiply the difference between the target output power and the real-time output power of the primary slave node by the preset adjustment factor K. Use this product as the optimal control quantity Za for each primary slave node, where a represents different primary slave nodes. When the optimal control quantity Za is positive, the output power of the primary slave node is increased according to the value of the optimal control quantity Za. When the optimal control quantity Za is negative, the output power of the primary slave node is decreased according to the value of the optimal control quantity Za. The specific method for obtaining the control range of each secondary slave node is △Fb, and the control range Zb of each secondary slave node is obtained as [△Fb×(1-2θ), △Fb×(1-0.5×θ)], where θ is a preset scaling factor, and the preset scaling factor θ takes a value range of 0.1-0.2. When the secondary slave node randomly selects a positive adjustment value within the control range, the output power of the secondary slave node is increased according to the selected adjustment value. When the slave node randomly selects a negative adjustment value within the control range, the output power of the primary slave node is decreased according to the selected adjustment value.

[0015] Compared with the prior art, the beneficial effects of the present invention are: (1) In this invention, the physical distance between any two control nodes is calculated by physical positioning, and the transmission delay is calculated by combining the link bandwidth. The transmission delay is the ratio of physical distance to link bandwidth, which is used to quantify the data interaction capability between the two nodes. A high transmission delay indicates that the link may become a bottleneck for real-time control and needs to be avoided when allocating master and slave nodes, so as to provide a basis for prioritizing the selection of nodes with better communication conditions when selecting temporary navigation nodes in the future; (2) In this invention, by using coupling tightness, the strongly correlated and weakly correlated coupled nodes of each control node are identified, and a list of coupling relationships is generated. The coupling tightness threshold is the average of the maximum and minimum values, which clearly distinguishes between strongly correlated nodes that require precise coordination and weakly correlated nodes that can be roughly adjusted, providing a basis for subsequent differentiated control strategies; (3) In this invention, the CPU computing power, remaining memory and communication bandwidth of the control node are normalized and weighted and summed to obtain the node capability. Nodes with node capabilities greater than the screening threshold are entered into the navigation candidate pool. When a fault occurs, a temporary navigation node is selected from the high-capability node pool to ensure the rapid calculation and issuance of control commands. (4) In this invention, when a node fails, a temporary navigation node is selected based on the physical distance between the failed node and the candidate node and the node's capabilities. Non-faulty nodes are then activated as primary and secondary slave nodes. The primary slave node precisely executes the optimal control quantity issued by the temporary navigation node to quickly restore system stability. The secondary slave node randomly adjusts its output power within a set control range as an auxiliary support. By dynamically adjusting the primary control node and the temporary navigation node, the system can flexibly balance the load of each node during the adjustment process, thus avoiding the risk of overload. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the system framework structure of the present invention. Detailed Implementation

[0017] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1: Please refer to Figure 1 This application provides a coordinated control system for photovoltaic-storage-charging microgrids based on multi-source feature fusion, including: The power coupling degree acquisition module obtains all controllers with computing capabilities in the photovoltaic-storage-charging microgrid and treats them as control nodes in the microgrid. It obtains the power transmission relationship between any two control nodes within the monitoring time and obtains the power coupling degree between each control node through the power transmission relationship between each control node. The power transmission relationship refers to the transmission power between two control nodes and the output power of the two control nodes within the monitoring time. The specific monitoring time is 5 minutes. Each controller is assigned a unique control node number i, i = 1, 2, ..., n, where n is the total number of control nodes and is a positive integer greater than or equal to 2. For example, in a 10MW photovoltaic-storage-charging microgrid, 18 controllers that meet the criteria are found, so the control node numbers are 1 to 18. At the same time, the physical location (xi, yi) of each control node in the photovoltaic-storage-charging microgrid is obtained. The ratio between the absolute value of the transmission power between any two control nodes during the monitoring period and the sum of the output power of the two control nodes is taken as the power coupling degree Rd between any two control nodes, where d refers to the node pair formed by any two control nodes. For example: Assume there are three control nodes in a photovoltaic-storage-charging microgrid: a photovoltaic inverter, an energy storage device, and a load controller. The power transfer relationship between them is as follows: the photovoltaic inverter transfers 10kW of power to the energy storage device, the photovoltaic inverter outputs 20kW, and the energy storage device outputs 15kW; the energy storage device transfers 5kW of power to the load controller, the energy storage device outputs 15kW, and the load controller's output is assumed to be 10kW. The power coupling degree between the photovoltaic inverter and the energy storage device is: |10| / (20+15)≈0.2857; the power coupling degree between the photovoltaic inverter and the energy storage device is 0.2857, which means that the power transmission dependence between them is 28.57%. This power coupling degree value is relatively high, indicating that there is a tight power coupling relationship between them. The power coupling degree between the energy storage device and the load controller is: |5| / (15+10)=0.2. The power coupling degree between the energy storage device and the load controller is 0.2, which means that the power transmission dependence between them is 20%. This power coupling degree value is low, indicating that the power transmission relationship between the energy storage device and the load controller is not as tight as that between the photovoltaic inverter and the energy storage device. By acquiring all control nodes with computing capabilities as control nodes, the power coupling degree between any two control nodes is calculated. The power coupling degree is obtained as the ratio of the absolute value of the power transmitted between two control nodes during the monitoring period to the sum of the output power of the two nodes. The power coupling degree reveals the degree of power transmission dependence between nodes; a high power coupling degree indicates a close energy interaction between nodes, and these nodes should be prioritized in coordinated control. The power coupling degree is the core basis for subsequent classification of strongly / weakly coupled nodes, ensuring that the control strategy conforms to the physical energy flow characteristics.

[0019] The transmission delay acquisition module obtains and analyzes the communication distance and link bandwidth between any two control nodes in the photovoltaic-storage-charging microgrid to obtain the transmission delay between any two control nodes. The physical distance between any two control nodes can be directly calculated by physical location. For example, if the physical locations of dummy node 1 and node 2 are (x1, y1) and (x2, y2) respectively, the physical distance between them can be calculated using the Euclidean distance formula. The link bandwidth between any two control nodes can be obtained. The ratio between the physical distance between any two control nodes and its corresponding link bandwidth is taken as the transmission delay Dd between any two control nodes. The physical distance between two control nodes and its corresponding link bandwidth refer to the amount of data that can be transmitted per unit time in the communication link established between the two control nodes. It is a link-level parameter describing the communication capability between the two control nodes and is independent of the local hardware bandwidth of a single control node. It is the available bandwidth measured or preset based on the actual communication medium, physical link, routing path and protocol limitations between the two control nodes, and is used to quantify the data interaction capability between the two nodes. Transmission delay Dd is a dimensionless metric used to measure the difficulty of communication transmission between any two control nodes. It is obtained by comparing the physical distance between the two nodes with the communication bandwidth between the two nodes, and is used to describe the relative communication delay rather than the actual time delay in a physical sense.

[0020] The physical distance between any two control nodes is calculated using physical location, and the transmission delay is calculated in conjunction with the link bandwidth. The transmission delay, which is the ratio of physical distance to link bandwidth, is used to quantify the data interaction capability between the two nodes. A high transmission delay indicates that the link may become a bottleneck for real-time control and needs to be avoided when allocating master and slave nodes. This provides a basis for prioritizing nodes with better communication conditions when selecting temporary lead nodes.

[0021] The coupling tightness acquisition module obtains the coupling tightness between any two control nodes based on the power coupling degree and transmission delay between any two control nodes in the photovoltaic-storage-charging microgrid. After normalizing all power coupling degrees Rd and transmission delays Dd, normalized values ​​Rd′ and Dd′ of all power coupling degrees Rd and transmission delays Dd are obtained. The sum of the products of the normalized values ​​Rd′ and Dd′ with preset parameter factors w1 and w2 respectively is taken as the coupling tightness Jd between any two control nodes, i.e., Jd = Rd′ × w1 + Dd′ × w2. The specific values ​​of the preset parameter factors w1 and w2 are: w1 = 0.7 power coupling priority, w2 = 0.3 communication delay second priority. The normalization process is as follows: extract the maximum value Rmax from all power coupling degrees Rd, and at the same time obtain the ratio Rd′ between each power coupling degree Rd and the maximum value Rmax; extract the maximum value Dmax from all transmission delays Dd, and at the same time obtain the ratio Dd′ between each transmission delay Dd and the maximum value Dmax. By combining power coupling degree and transmission delay, the coupling tightness between any two control nodes is calculated through normalization and weighted summation. Nodes with high coupling tightness correspond to strong physical coupling and low communication delay. In coordinated control, a master-slave relationship is established to ensure that commands are transmitted quickly and accurately.

[0022] The coupling node relationship determination module obtains the strongly related and weakly related coupling nodes corresponding to each control node based on the coupling tightness between any two control nodes, and binds them to the corresponding control nodes to generate a coupling relationship list corresponding to each control node. The coupling tightness between a single control node and other control nodes is obtained. Control nodes with coupling tightness greater than the coupling tightness threshold are designated as strongly correlated coupled nodes, while those with coupling tightness less than or equal to the coupling tightness threshold are designated as weakly correlated coupled nodes. Both strongly correlated and weakly correlated coupled nodes are bound to their respective control nodes, generating a coupling relationship list for each control node. The remaining control nodes are analyzed one by one to generate a coupling relationship list for each control node. The specific value of the coupling tightness threshold is the average of the maximum and minimum values ​​of the coupling tightness between a single control node and other control nodes. This avoids misjudgment that may be caused by a fixed threshold and ensures that the classification results conform to the actual coupling status of each node. Based on the coupling tightness, strongly correlated and weakly correlated nodes of each control node are identified, and a list of coupling relationships is generated. The coupling tightness threshold is the average of the maximum and minimum values, clearly distinguishing between strongly correlated nodes that require precise coordination and weakly correlated nodes that can be coarsely adjusted, providing a basis for subsequent differentiated control strategies.

[0023] The candidate pool establishment module obtains the CPU computing power, remaining memory and communication bandwidth corresponding to each control node. After normalizing the CPU computing power, remaining memory and communication bandwidth, it analyzes them to obtain the node capabilities corresponding to each control node. Based on the node capabilities corresponding to each control node, the candidate pool is established. The communication bandwidth of a control node refers to the maximum data throughput capacity that the communication interface configured by the control node itself can support per unit time. It is a node-level parameter that describes the communication processing capacity of a single control node and is independent of the link bandwidth between the control node and other nodes. It is used to characterize the control node's ability to undertake scheduling communication tasks. After normalizing the CPU computing power, remaining memory, and communication bandwidth of each control node, normalized values ​​EAi, EBi, and ECi are obtained. Then, the node capability Ji corresponding to each control node is obtained by calculating Ji = 0.5×EAi + 0.3×EBi + 0.2×ECi. The normalization process for the CPU computing power, remaining memory, communication bandwidth, and distance from the electrical center point of the microgrid for each control node is as follows: extract the maximum values ​​of CPU computing power, remaining memory, and communication bandwidth to obtain the ratio EAi between the CPU computing power of each control node and its corresponding maximum value; obtain the ratio EBi between the remaining memory of each control node and its corresponding maximum value; and obtain the ratio ECi between the communication bandwidth of each control node and its corresponding maximum value. The mean of the maximum and minimum values ​​of the node capabilities Ji of all control nodes, as well as the absolute value of the difference between the maximum and minimum values, are obtained. The sum of the mean and the absolute value of the difference is used as the screening threshold. Control nodes whose node capabilities are greater than or equal to the screening threshold are selected as candidate nodes. A leader candidate pool is established through all candidate nodes. No processing is performed on control nodes whose node capabilities are less than the screening threshold. When the maximum and minimum values ​​of node capability Ji are Jmax and Jmin respectively, the mean JA of Jmax and Jmin is obtained by (Jmax+Jmin) / 2, the absolute value JD of the difference between Jmax and Jmin is obtained by |Jmax-Jmin|, and the screening threshold YJ is obtained by JA+0.3JD. Control nodes that satisfy Ji≥YJ are selected as candidate nodes, and a navigation candidate pool is established for all candidate nodes. No processing is performed on control nodes that Ji<YJ. The node capability is obtained by normalizing and weighting the CPU computing power, remaining memory, and communication bandwidth of the control node. Nodes with capabilities greater than the screening threshold are entered into the navigation candidate pool. When a fault occurs, a temporary navigation node is selected from the high-capability node pool to ensure the rapid calculation and issuance of control commands.

[0024] The fault node determination module obtains the rated output power of each control node and sets 1.25 times the rated output power as the warning threshold for each control node. Using 1.25 times the rated value as the threshold, it can identify when the equipment is overloaded but has not completely failed, thus avoiding cascading failures. Control nodes whose real-time output power is greater than the corresponding warning threshold are marked as fault nodes. That is, when the real-time output power of a control node is greater than its corresponding warning threshold, the control node is marked as a fault node. At the same time, the module obtains the location of the fault node from the physical location (xi,yi) of each control node in the photovoltaic-storage-charging microgrid and outputs it, providing accurate information for the subsequent selection of a nearby temporary pilot node.

[0025] The temporary navigation node calibration module calibrates the temporary navigation node corresponding to the faulty node based on the node distance between the non-faulty nodes in each candidate node in the navigation candidate pool and the faulty node. Obtain fault location and the physical location of each candidate node in the pilot candidate pool in the photovoltaic-storage-charging microgrid. Obtain the node distance between each non-faulty node in the pilot candidate pool and the faulty node. Mark the candidate node with the smallest node distance as the temporary pilot node. If multiple nodes are at the same distance, then according to the additional rule: the candidate node with the highest node capability is selected as the temporary leader node. If the node capabilities are still the same, then one of them is randomly selected as the temporary leader node. In the candidate pool of navigation nodes, the non-faulty node that is closest to the faulty node is selected as the temporary navigation node; if the distances are the same, the node with the highest node capability is selected first to ensure that the temporary navigation node has sufficient scheduling capability.

[0026] The collaborative adjustment module activates other non-faulty nodes into slave mode immediately after selecting a temporary navigation node, obtains the strongly correlated and weakly correlated nodes corresponding to the temporary navigation node, and takes the strongly correlated nodes as the primary slave nodes and the weakly correlated nodes as the secondary slave nodes. The system obtains the real-time output power and target output power of each primary and secondary slave node. Based on these values, the temporary navigation node calculates and issues the optimal control values ​​for each primary slave node. The primary slave node executes the control values ​​precisely to ensure the system recovers to a stable state in the shortest possible time. For secondary slave nodes, the temporary navigation node calculates and issues the control range. The control range sets the adjustment range of the node's operable power range, not a precise value. The secondary slave node randomly selects an adjustment value within the control range and does not need to strictly follow the optimal control values. Instead, it plays an auxiliary role in supporting system recovery. The specific method for obtaining the optimal control quantity for each primary subordinate node is as follows: Obtain the difference ΔFa between the target output power and the real-time output power of each primary slave node, i.e., ΔFa = target output power - real-time output power. Multiply the difference between the target output power and the real-time output power of the primary slave node by the preset adjustment factor K, i.e., ΔFa × K, as the optimal control quantity Za for each primary slave node, where a represents different primary slave nodes. The specific value of the preset adjustment factor K is determined by relevant personnel according to actual needs. When the optimal control quantity Za is positive, the output power of the primary slave node is increased according to the value of the optimal control quantity Za. When the optimal control quantity Za is negative, the output power of the primary slave node is decreased according to the value of the optimal control quantity Za. The specific method for obtaining the control interval of each secondary subordinate node is △Fb, where b represents different secondary subordinate nodes. The product of △Fb and (1-2θ) is taken as the minimum value of the control interval, and the product of △Fb and (1-0.5×θ) is taken as the maximum value of the control interval. That is, the control interval Zb of each secondary subordinate node is obtained as [△Fb×(1-2θ), △Fb×(1-0.5×θ)], where θ is a preset scaling factor. The specific value of the preset scaling factor θ is determined by relevant personnel according to actual needs. Here, the preset scaling factor θ ranges from 0.1 to 0.2. When the secondary subordinate node randomly selects a positive adjustment value within the control interval, the output power of the secondary subordinate node is increased according to the selected adjustment value. When the subordinate node randomly selects a negative adjustment value within the control interval, the output power of the primary subordinate node is decreased according to the selected adjustment value. The temporary pilot node activates non-faulty nodes to enter slave mode and issues control commands based on the coupling relationship. Strongly coupled nodes act as primary slave nodes, acquiring the optimal control quantity Za; weakly coupled nodes act as secondary slave nodes, acquiring the control range Zb. Precise control is implemented for strongly coupled nodes to ensure rapid recovery of critical power paths; relaxed control is implemented for weakly coupled nodes to reduce communication burden, avoid using high-precision control for all nodes, reduce computational and communication overhead, improve overall system efficiency, and provide a certain degree of flexibility for the range control of secondary slave nodes. Even if some nodes respond poorly, it will not seriously affect system recovery.

[0027] The system achieves refined management and coordinated control of each control node through multi-source feature fusion. First, it acquires the power transmission relationship and physical location of each control node, calculates the power coupling degree and communication delay between nodes, and obtains the node coupling tightness through normalized weighted summation. This tightness is used to classify each node into strongly correlated and weakly correlated coupled nodes, thereby constructing a coupling relationship list. Simultaneously, it acquires the node's CPU computing power, remaining memory, and communication bandwidth, comprehensively calculates the node's capabilities, and establishes a leader candidate pool. During operation, when a node fails, the system selects a temporary leader node based on the physical distance between the failed node and candidate nodes, as well as the node's capabilities. Non-faulty nodes are then stratified and activated as primary and secondary slave nodes. The primary slave node precisely executes the optimal control input from the temporary leader node to quickly restore system stability, while the secondary slave nodes randomly adjust their output power within a set control range as auxiliary support. By dynamically adjusting the primary and temporary leader nodes, the system's robustness and response speed to faults are improved. This refined slave node management strategy allows the system to flexibly balance the load of each node during adjustments, avoiding overload risks and ensuring the reliable operation of the microgrid. This provides an innovative solution for the efficient utilization of photovoltaic-storage-charging microgrids.

[0028] Example 2: As Example 2 of the present invention, in specific implementation, the technical solution of this example differs from that of Example 1 only in that this example includes a feedback module; The feedback module requires the primary slave node to send back an execution confirmation plus the actual value within 100ms after execution, confirming that the control quantity has been executed according to the issued control quantity and providing the actual power value after execution. This allows the temporary pilot node to understand the execution status of the primary slave node in real time. The secondary slave node only needs to send back a confirmation that it has received the control interval and execute the auxiliary scheduling task. The primary slave node enforces the execution, and the secondary slave node assists in the execution. The primary slave node sends back execution confirmation and actual values ​​within 100ms after execution, while secondary slave nodes send back received confirmation. The primary slave node enforces execution, while secondary slave nodes assist in execution. The rapid feedback from the primary slave node allows the temporary pilot node to immediately grasp the execution status, forming a closed-loop adjustment. Secondary slave nodes only need simple confirmation, avoiding the consumption of communication resources by large amounts of low-value data. The execution confirmation mechanism promptly detects execution deviations or communication failures, triggering compensation measures. Based on actual feedback values, the temporary pilot node can dynamically adjust subsequent control strategies, improving system adaptability. According to the instructions of the temporary pilot node, strongly correlated nodes are designated as primary slave nodes to issue precise control quantities, while weakly correlated nodes are designated as secondary slave nodes to issue control ranges, achieving hierarchical collaborative adjustment. Finally, the feedback mechanism module ensures the effective execution of system instructions and auxiliary adjustment through the execution feedback from the primary slave node and the received confirmation from the secondary slave node.

[0029] Example 3: As Example 3 of the present invention, in specific implementation, compared with Example 1 and Example 2, the technical solution of this example is to combine the solutions of Example 1 and Example 2.

[0030] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0031] 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 conceived by those skilled in the art within the technical scope 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.

Claims

1. A light storage and charging micro-grid coordinated control system based on multi-source feature fusion, characterized in that, The method comprises the following steps: a power coupling degree acquisition module, according to the transmission power and the output power between any two control nodes in the storage and charging micro-grid, obtains the power coupling degree between any two control nodes; a transmission delay acquisition module, by the communication distance and the link bandwidth between any two control nodes in the optical storage and charging micro-grid, obtains the transmission delay between any two control nodes; a coupling tightness acquisition module, according to the power coupling degree and the transmission delay between any two control nodes, obtains the coupling tightness between any two control nodes; a coupling node relationship judgment module, according to the coupling tightness between any two control nodes, obtains the strongly related coupling nodes and the weakly related coupling nodes of each control node; a navigation candidate pool establishment module, after normalizing the CPU computing power, the remaining memory and the communication bandwidth corresponding to each control node, obtains the node capability of each control node, and establishes a navigation candidate pool according to the node capability; a fault node judgment module, according to the real-time output power of each control node and the early warning threshold, judges the fault node, and outputs the fault node positioning; a temporary navigation node calibration module, according to the node distance between each non-fault node in the navigation candidate pool and the fault node, calibrates the temporary navigation node of the fault node; a cooperative adjustment module, taking the strongly related coupling nodes of the temporary navigation node as the primary subordinate nodes and the weakly related coupling nodes as the secondary subordinate nodes; according to the real-time output power and the target output power corresponding to each primary subordinate node and secondary subordinate node, obtaining the optimal control quantity of each primary subordinate node and the control interval of each secondary subordinate node and issuing, the primary subordinate node adjusts according to the optimal control quantity issued, and the secondary subordinate node selects an adjustment value within the control interval range for adjustment. 2.The multi-source feature fusion based microgrid coordinated control system of claim 1, wherein, The specific way to obtain the power coupling degree between any two control nodes is: the ratio between the transmission power absolute value corresponding to any two control nodes and the sum of the output power of the corresponding two control nodes within the monitoring time is taken as the power coupling degree corresponding to any two control nodes. 3.The multi-source feature fusion based microgrid coordinated control system of claim 2, wherein, The specific way to obtain the transmission delay between any two control nodes is: calculate the physical distance between any two control nodes, and take the ratio between the physical distance and the corresponding link bandwidth as the transmission delay between any two control nodes. 4.The multi-source feature fusion based microgrid coordinated control system of claim 3, characterized in that, The specific way to obtain the coupling tightness between any two control nodes is: after normalizing all power coupling degrees Rd and transmission delays Dd, the normalized values Rd' and Dd' of all power coupling degrees Rd and transmission delays Dd are obtained, and the sum of the product of the normalized values Rd' and Dd' and the preset parameter factors w1 and w2 is taken as the coupling tightness Jd between any two control nodes, d represents the node pair composed of any two control nodes. 5.The multi-source feature fusion based microgrid coordinated control system of claim 4, wherein, The specific way to obtain the strongly related coupling nodes and the weakly related coupling nodes of each control node is: Obtaining coupling tightness between each control node and other control nodes respectively, taking the control node with coupling tightness greater than the coupling tightness threshold value as a strongly related coupling node of the corresponding control node, taking the control node with coupling tightness less than or equal to the coupling tightness threshold value as a weakly related coupling node of the corresponding control node, and binding the strongly related coupling node and the weakly related coupling node to the corresponding control node. 6.The multi-source feature fusion based microgrid coordinated control system of claim 1, wherein, The specific way of establishing the navigation candidate pool is: After normalizing the CPU computing power, the remaining memory and the communication bandwidth corresponding to each control node respectively, obtaining the normalized values EAi, EBi and ECi, and obtaining Ji=0.5×EAi+0.3×EBi+0.2×ECi, obtaining the node capability Ji corresponding to each control node, obtaining the mean value of the maximum value and the minimum value of the node capabilities Ji of all control nodes, and the absolute value of the difference between the maximum value and the minimum value, and taking the sum of the mean value and the absolute value of the difference as a screening threshold, taking the control node with node capability greater than or equal to the screening threshold as a candidate node, and establishing a navigation candidate pool through all candidate nodes, i is the number of different control nodes. 7.The multi-source feature fusion based microgrid coordinated control system of claim 6, wherein, The specific way of determining the fault node is: Obtaining the rated output power corresponding to each control node, taking 1.25 times of each rated output power as the warning threshold of each control node, and marking the control node with real-time output power greater than the corresponding warning threshold as a fault node. 8.The multi-source feature fusion based microgrid coordinated control system of claim 7, wherein, The specific way of marking the temporary navigation node of the fault node is: Obtaining the fault positioning and the physical positioning of each candidate node in the navigation candidate pool in the optical storage and charging micro-grid respectively, obtaining the node distance between each non-fault node in the navigation candidate pool and the fault node, and marking the candidate node with the smallest node distance as the temporary navigation node. 9.The multi-source feature fusion based microgrid coordinated control system of claim 8, wherein, If multiple node distances are completely equal, according to the additional rule: preferentially selecting the candidate node with the highest node capability as the temporary navigation node, if the node capability is still the same, then randomly selecting one as the temporary navigation node. 10.The multi-source feature fusion based microgrid coordinated control system of claim 8, wherein, The specific way of obtaining the optimal control amount of each primary subordinate node and the control interval of each secondary subordinate node is: Obtaining the difference △Fa between the target output power and the real-time output power of each primary subordinate node, and taking the product between the difference between the target output power and the real-time output power of the primary subordinate node and the preset adjustment factor K as the optimal control amount Za of each primary subordinate node, wherein a represents different primary subordinate nodes, when the optimal control amount Za is positive, then increasing the output power of the primary subordinate node according to the value of the optimal control amount Za, when the optimal control amount Za is negative, then decreasing the output power of the primary subordinate node according to the value of the optimal control amount Za; The specific way of obtaining the control interval of each secondary subordinate node is △Fb, the control interval Zb of each secondary subordinate node is [△Fb×(1-2θ), △Fb×(1-0.5×θ)], wherein θ is a preset proportion factor, the preset proportion factor θ is in a range of 0.1-0.2, when the secondary subordinate node randomly selects a positive value in the control interval range, the output power of the secondary subordinate node is increased according to the selected adjustment value, and when the secondary subordinate node randomly selects a negative value in the control interval range, the output power of the primary subordinate node is reduced according to the selected adjustment value.

Images