Distributed power equipment networking based on active registration and control method thereof

Abstract

The invention discloses a distributed power equipment networking based on active registration. Each distributed power equipment sends a registration request and registration information to a main power grid registrar; discovering other distributed power equipment through the main power grid registrar, acquiring data of other equipment and historical data of the main power grid registrar, and receiving request instructions sent by other equipment; predicting an equipment state by adopting a neural network model; formulating an energy scheduling strategy according to the predicted equipment state, the obtained equipment data and the energy demand, optimizing the energy scheduling strategy by adopting a neural network and then executing the energy scheduling strategy, and sending a request instruction for executing the demand to other equipment according to the energy scheduling strategy; or executing the received request instruction. An active registration mechanism is adopted, so that new equipment can be dynamically added into the network, and the system has relatively high flexibility and expansibility; each device is autonomously registered in the network, and no centralized control node exists, so that the system is more decentralized, and the risk of single-point failure is reduced.

Description

Technical Field

[0001] The present invention relates to the networking of a distribution network, and in particular to a distributed power equipment networking based on active registration and a control method thereof. Background Art

[0002] With the development and popularization of renewable energy technology, more and more distributed energy devices (such as solar panels, wind turbines, etc.) are connected to the power system. As the scale and complexity of the power system continue to increase, the traditional centralized management model can no longer meet the needs of the power system. Traditional power equipment networking usually relies on manual configuration and management, which is inefficient and prone to errors. Summary of the invention

[0003] Purpose of the invention: In view of the above shortcomings, the present invention provides a distributed power equipment networking based on active registration to improve the efficiency, reliability and intelligence of the energy system.

[0004] The present invention also provides a control method for microgrid secondary system networking based on elastic matching.

[0005] Technical solution: To solve the above problems, the present invention adopts a distributed power equipment networking based on active registration, including a main power grid registrar, which is used to send a command to activate active registration to the distributed power equipment, and receive the registration request of the distributed power equipment and the registration information of the distributed power equipment itself; and manage the registration information sent by all registered distributed power equipment;

[0006] Each distributed power device is used to send a registration request and its own registration information to the main grid registrar according to an active registration command, obtain the registration information managed by the main grid registrar after registration, obtain the equipment data of other registered distributed power devices according to the obtained registration information managed by the main grid registrar, and use a neural network model to predict its own equipment status according to its own historical data, formulate an energy scheduling strategy according to the distributed power device's own equipment status, the equipment data of other distributed power devices and energy demand, and use a neural network to optimize the energy scheduling strategy, execute the optimized energy scheduling strategy, and send a request instruction to execute the demand to other registered distributed power devices according to the optimized energy scheduling strategy; it is also used to execute the request instruction received from other registered distributed power devices.

[0007] Furthermore, the main power grid registrar is used to determine whether registration information sent by the distributed power equipment is received within a first set time after a command to activate active registration is sent to the distributed power equipment. When no registration information is received, the active registration progress of the distributed power equipment is queried, and corresponding registration operations are performed based on the queried active registration progress of the distributed power equipment.

[0008] Furthermore, the calculation formula of the first set time T is:

[0009] T=T base +ω 1 ×W+ω 2 ×T type +ω 3 ×S+ω 4 ×H

[0010] Among them, T base is the first setting time basic value, ω 1 ,ω 2 ,ω 3 ,ω 4 is the adjustment factor, W is the weight of the distributed power equipment slave node, T is the node type weight, S is the node state parameter, and H is

[0011] type

[0012] Historical registration time decay factor.

[0013] Furthermore, the corresponding registration operation is performed based on the active registration progress of the queried distributed power equipment, including replying to an instruction confirmation frame after receiving an instruction to end the active registration reported by the distributed power equipment, and sending an instruction to terminate the active registration from the node to the distributed power equipment, wherein the instruction confirmation frame includes information confirming that the distributed power equipment has received the termination signal.

[0014] Furthermore, it also includes a network maintenance and update module, which is used to monitor the communication operation status between the main grid registrar and the distributed power equipment, and regularly perform periodic tests and verifications on the communication operation status between the main grid registrar and the distributed power equipment. The test cycle time length T test The calculation formula is:

[0015] T test =[1-(M 1 / M+N 1 / N)×T c / T z ]×T 0

[0016] Among them, M 1 is the number of communication connections; M is the number of communication disconnections; N1 is the total number of registrations; N is the number of registration failures; T c T is the average timeout duration of the actual communication duration relative to the theoretical communication duration among all communication connection times; z is the average duration of a single communication corresponding to all communication connections; T 0 It is the length of the initial cycle time, which is used to measure the communication operation status between the main grid registrar and the distributed power devices in the initial stage.

[0017] Furthermore, it also includes a fault detection module for performing fault detection on the device using a convolutional neural network.

[0018] The present invention also adopts a control method for distributed power equipment networking based on active registration, comprising the following steps:

[0019] The distributed power device sends a registration request and the registration information of the distributed power device itself to the main power grid registrar according to the received active registration command;

[0020] After the distributed power equipment is registered, the registration information managed by the main power grid registrar is obtained, and the equipment data of other registered distributed power equipment is obtained according to the obtained registration information managed by the main power grid registrar; the registration information managed by the main power grid registrar includes the registration information sent by all registered distributed power equipment;

[0021] Distributed power equipment uses a neural network model to predict its own equipment status based on its own historical data, and formulates an energy dispatch strategy based on its own equipment status, equipment data of other distributed power equipment, and energy demand, and uses a neural network to optimize the energy dispatch strategy;

[0022] The distributed power equipment executes the optimized energy dispatching strategy, and sends request instructions to other registered distributed power equipment to execute the requirements according to the optimized energy dispatching strategy; or executes the request instructions received from other registered distributed power equipment.

[0023] The present invention also adopts a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the above method when executing the computer program.

[0024] The present invention also adopts a computer-readable storage medium on which a computer program is stored, characterized in that the computer program implements the steps of the above method when executed by a processor.

[0025] Beneficial effects: Compared with the prior art, the significant advantages of the present invention are that the active registration mechanism is adopted, which can enable new devices to dynamically join the network, making the system more flexible and scalable; each device can register with the network autonomously, and there is no centralized control node, making the system more decentralized and reducing the risk of single point failure; the device can be instantly registered with the network and respond to requests from other devices in real time, making the system highly real-time and responsive; devices can share information through the network and collaborate to complete tasks such as energy management, optimized scheduling, etc., making the system more coordinated and efficient; the network can adopt a secure encryption mechanism to protect the security of communication data and the privacy of users, and ensure the safe operation of the system; the use of neural networks can better realize device status prediction, fault detection and energy scheduling optimization, thereby further improving the intelligence level, operation efficiency and reliability of distributed power equipment self-organizing networks based on the active registration mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a technical flow chart of the self-organizing network of distributed power equipment in the present invention.

[0027] Figure 2 It is a structural diagram of the device registration module in the present invention.

[0028] Figure 3 This is a working principle diagram of the intelligent optimization and prediction in the present invention. DETAILED DESCRIPTION

[0029] Example 1

[0030] like Figure 1As shown, in this embodiment, a distributed power equipment networking based on active registration includes a device registration module, a registrar management module, a device discovery and communication module, a data sharing and collaboration module, and a network maintenance and update module. Each distributed power device sends a registration request to the main grid registrar according to preset rules and conditions, including the unique identification, type, location and other information of the device. The main grid registrar receives and manages these registration requests, maintains the device registration table, and notifies other devices of the addition of new devices. Each device discovers other devices by querying the main grid registrar or monitoring network communications, and exchanges and communicates data through network protocols, shares local data and collaborates to complete tasks such as energy scheduling and load balancing. Each device is regularly maintained and updated through the network to keep the device online and ensure communication security and network stability. Each device introduces an intelligent optimization and prediction module, and uses a variety of neural network algorithms to perform device status prediction, fault detection and energy scheduling optimization, thereby improving the intelligence level of the system. The main grid registrar (master node) is responsible for managing the registration process of the entire network. When a distributed power device completes active registration, it will notify the master node (main grid registrar), and the master node will confirm and send instructions to the slave node to terminate its active registration state. This means that the registration process of the slave node has been completed and the master node has confirmed this. Slave nodes refer to non-master devices in the distributed power device network. They accept and execute instructions from the master node during the active registration process.

[0031] like Figure 2 As shown, the main grid register includes:

[0032] A start module is used to send a command to activate active registration to the distributed power equipment, thereby starting an active registration process of the distributed power equipment;

[0033] The storage and processing module receives registration information from distributed power equipment and stores and processes the registration information; the stored registration information includes: equipment topology relationship, equipment association relationship, equipment registration time, equipment communication key, equipment type, equipment location, equipment status, and other specific information;

[0034] The progress judgment module queries the active registration progress of the distributed power equipment when the main power grid registrar does not receive the registration information reported by the distributed power equipment within the first set time; the calculation formula for the first set time is:

[0035] T=T base +ω 1 ×W+ω 2 ×T type +ω 3 ×S+ω 4 ×H (1)

[0036] Where, T represents the first setting time; T base Indicates the first set time basic value; ω 1 ,ω 2 ,ω 3 and ω 4 is the adjustment factor; W represents the slave node weight; T type represents the node type weight; S represents the node status parameter; H represents the historical registration time decay factor.

[0037] The registration operation module performs corresponding registration operations according to the active registration progress of the queried distributed power equipment. When the main grid registrar receives the instruction of the end of active registration reported by the distributed power equipment, the main grid registrar replies with an instruction confirmation frame and sends an instruction to terminate the active registration to the distributed power equipment. The instruction confirmation frame includes information confirming that the distributed power equipment has received the termination signal. The specific steps include:

[0038] The main grid registrar management module is responsible for managing the registration information of distributed power equipment and maintaining the registration table of each device; the working steps include:

[0039] Step B1, establishing an analog front end in the main grid register;

[0040] Step B2, simulating the front end to receive the request information sent by the distributed power equipment in real time;

[0041] Step B3, parsing the request information to obtain the simulated operation content contained in the request information;

[0042] Step B4, controlling the simulation front end to perform simulation operation on the simulation operation content and obtaining the simulation operation result;

[0043] Step B5, controlling the simulation front end to send the simulation operation result to the distributed power equipment;

[0044] Step B6, after receiving the simulation operation result, the distributed power device returns the simulation operation result to the main grid registrar through the TCP connection. By allowing the distributed power device to return the simulation operation result, the main grid registrar can verify whether the result received by the distributed device is consistent with the result sent, ensure that there is no data loss or tampering during the transmission process, confirm whether the device has performed the simulation operation correctly, and understand the current status of the device.

[0045] Step B7, performing data management on the data generated during the communication process between the main grid registrar and the distributed power equipment;

[0046] The working benefits of the above technical solution are: during the communication process between the main grid registrar and the distributed power equipment, various data will be generated, including requests, responses and possible log data. Data management involves the recording, storage, transmission and processing of data to ensure the integrity of communication and the accuracy of data.

[0047] Distributed power equipment includes:

[0048] The device registration module is used to send a registration request to the main grid registrar according to the preset rules and conditions of the distributed power equipment, including the communication security key, type, location and other information of the equipment; the registration information sent by the device registration module to the main grid registrar includes:

[0049] Device communication key: information used to uniquely identify each device, usually a unique string or number. The secure encryption mechanism ensures that the main grid registrar can accurately and securely identify each distributed power device;

[0050] Device Type: Indicates the kind or type of device, such as solar panel, wind turbine, fuel cell, etc. This helps other devices recognize and understand the functions and features of the new device;

[0051] Device location: indicates the location information of the device, which can be geographic coordinates (latitude and longitude), physical address (street, building, etc.) or other forms of location description;

[0052] Device status: including the device’s operating status, working mode, energy generation, etc. This helps other devices understand the device’s current working status and performance;

[0053] Other specific information: Based on actual needs, other specific equipment information may also be included, such as the equipment manufacturer, model, rated power, voltage, etc.

[0054] The device registration module working steps include:

[0055] Step S1, establishing a communication architecture between the main grid registrar and the distributed power equipment;

[0056] Step S2, establishing a simulation front end in the distributed power equipment and performing simulation operations;

[0057] The working benefits of the above technical solution are: network connection, protocol setting and establishment of communication channels can ensure that distributed power equipment can communicate with the main grid registrar; the establishment of distributed power equipment simulation front end means that the distributed power equipment will simulate the operation of the main grid registrar to achieve simulated access to the main grid registrar. This process may include simulated user input, requests and operations.

[0058] The device discovery and communication module is used to query the main grid registrar or network communication protocol for data exchange and communication, including data query, status update, event notification, etc., so as to discover newly added devices; including: defining the communication protocol between the main grid registrar and the distributed power equipment, and defining the data format between the main grid registrar and the distributed power equipment; using the secure socket layer method to encrypt the communication data between the main grid registrar and the distributed power equipment; the main grid registrar establishes a registration interface for the distributed power equipment to provide registration information; when the distributed power equipment is successfully registered, a long connection is established between the main grid registrar and the distributed power equipment, wherein the long connection between the main grid registrar and the distributed power equipment is used to ensure that only authorized applications can communicate the main grid registrar data; the network communication protocol used is MQTT;

[0059] The working benefits of the above technical solution are: Secure communication: By defining communication protocols, data formats and using encrypted communication, this method ensures the security of communication and prevents unauthorized visitors from accessing communication data.

[0060] The data sharing and collaboration module is used to share distributed power equipment data, such as energy generation, energy consumption, grid load, etc., and coordinate energy scheduling, load balancing and other operations according to the status and needs of other devices in the network, so as to optimize energy utilization efficiency. Including:

[0061] Data sharing and query: The device sends data query requests to other devices through network communication protocols to obtain information such as energy generation and energy consumption of other devices. After receiving the query request, the device sends the corresponding data to the requesting device according to the content and authority of the request;

[0062] Data update and status synchronization: The device regularly updates its own status information such as energy generation and energy consumption, and broadcasts or sends update notifications to other devices; the device that receives the update notification updates its own status information and broadcasts the updated status information to other devices;

[0063] Event notification and collaborative tasks: When a device detects a specific event (such as energy supply alarm, grid load change, etc.), it sends an event notification to other devices; the device that receives the event notification performs corresponding collaborative tasks based on the content and requirements of the notification, such as adjusting energy generation, reducing energy consumption, etc.;

[0064] Data processing and analysis: The data collected by the equipment can be used to analyze the operation of the energy system, identify potential problems and optimization space; the equipment can take corresponding measures based on the analysis results, adjust its own working mode and parameters, and realize intelligent management and optimized scheduling of the energy system.

[0065] Testing and Verification: Testing the normal operation of distributed power equipment to verify whether it functions properly, and also testing abnormal conditions to evaluate the stability and robustness of the main power grid.

[0066] The shared distributed power equipment data includes:

[0067] Total energy production of distributed power equipment E gen :

[0068] E gen =P gen ×T gen (2)

[0069] Where P gen It represents the energy generation power per unit time of distributed power equipment, T gen Indicates the production capacity time;

[0070] Total energy consumption of distributed power equipment E con :

[0071] E con =P con ×T con (3)

[0072] Where P con Represents the energy consumption of distributed power equipment per unit time, T con Indicates energy consumption time;

[0073] Total grid load L grid :

[0074] L grid =E gen -E con (4)

[0075] Energy storage status of distributed power equipment S storage :

[0076] S storage =C storage -E con +E gen (5)

[0077] In the formula, C storage Represents the total energy storage capacity of distributed power equipment.

[0078] The working benefits of the above technical solution are: it can realize data sharing and collaboration of distributed power equipment, intelligent management and optimized scheduling of energy systems, and improve energy utilization efficiency and system reliability.

[0079] The network maintenance and update module is used to regularly check the online status of the equipment, so that the main power grid registrar can update the registration table in time and delete the offline equipment information. The distributed power equipment sends heartbeat signals to the registrar regularly to keep the equipment online. The steps include:

[0080] Step E1, real-time monitoring of the communication operation status between the distributed power equipment and the main grid registrar;

[0081] Step E2, determine whether the communication operation status between the distributed power equipment and the main power grid registrar has any processing connection disconnection, timeout and / or registration failure; when the communication operation status between the distributed power equipment and the main power grid registrar has any processing connection disconnection, timeout and / or registration failure, the processing connection disconnection, timeout and / or registration failure will be recorded in the log.

[0082] Regularly test and verify the distributed power equipment and the main grid register to determine whether the communication operation between the distributed power equipment and the main grid register has good functions and operating status; regularly update and maintain the system embedded in the connection equipment between the distributed power equipment and the main grid register. This can include software updates, firmware upgrades, security maintenance, etc. to ensure the reliability and security of the connection equipment. The formula for obtaining the test cycle time length is:

[0083] T test =[1-(M 1 / M+N 1 / N)×T c / T z ]×T 0 (6)

[0084] Where, T test Indicates the length of the test cycle; M 1 Indicates the number of communication connections; M indicates the number of communication disconnections; N 1 Indicates the total number of registrations; N indicates the number of registration failures; T c Indicates the average timeout duration of the actual communication duration relative to the theoretical communication duration among all communication connection times; T z Represents the average duration of a single communication corresponding to all communication connections, T 0 Refers to the length of the initial cycle time, which is used to measure the communication operation status between the main grid registrar and distributed power devices during the initial stage.

[0085] Based on the communication operation status information in the initial cycle, the system calculates the test cycle time length (T test ), this period is determined based on communication disconnection, registration failure, and communication timeout.

[0086] The effect of the above technical solution is: by calculating the length of the test cycle, the system can adaptively adjust the frequency of the test according to the actual communication situation. If the communication is running normally, the test cycle can be extended to reduce resource overhead. If a problem occurs, the test cycle can be shortened to detect and respond to the problem more quickly.

[0087] like Figure 3 As shown, the intelligent optimization and prediction module is used to apply the neural network model to predict and optimize the equipment status, energy demand and supply, and realize intelligent scheduling and fault detection. Select a suitable neural network model for equipment status prediction, fault detection and energy scheduling optimization; train and update the neural network model, use historical data and real-time data to optimize the model; use the trained neural network model for real-time prediction and optimized scheduling. The neural network model selection module specifically includes:

[0088] The long short-term memory network (LSTM) model is used to predict the time series of equipment status and energy demand; the equipment status prediction formula is as follows:

[0089]

[0090] In the formula, represents the predicted value of the equipment status at time t+1; x t represents the input data at time t; h t and c t Respectively represent the hidden state and unit state at time t; f LSTM Represents an LSTM network function.

[0091] Convolutional neural network (CNN) model for equipment fault detection and image recognition; the equipment fault detection formula is as follows:

[0092]

[0093] In the formula, represents the fault detection result; I represents the input image or information data; f CNN Represents the CNN network function.

[0094] The deep reinforcement learning (DRL) model is used to optimize the energy scheduling strategy. The energy scheduling optimization formula is as follows:

[0095]

[0096] In the formula, a t represents the optimal action at time t; s t represents the state at time t; Q(s t ,a;θ) represents the Q-value function of the DRL model, and θ is the model parameter.

[0097] Example 2

[0098] In this embodiment, a control method for distributed power equipment networking based on active registration includes the following steps:

[0099] Step 1: The main grid registrar sends a command to activate active registration to the distributed power device;

[0100] Step 2: The distributed power device sends a registration request and registration information to the main grid registrar according to the active registration command;

[0101] Step 3: The main grid registrar receives the registration request of the distributed power device and manages the registration information of the distributed power device;

[0102] Step 4: The distributed power equipment discovers other distributed power equipment through the main power grid registrar;

[0103] Step 5: After the distributed power equipment is registered, it obtains the registration information managed by the main grid registrar, and obtains the equipment data of other registered distributed power equipment and its own historical data based on the obtained registration information; the distributed power equipment collects data such as energy generation, consumption, grid load, and environmental parameters (such as weather, temperature); and pre-processes the collected data, including data cleaning, normalization, feature extraction, etc. Through the active registration mechanism, each device registers and shares the pre-processed data to the central server or distributed database. The MQTT secure communication protocol is used to ensure the security and real-time transmission of data between devices.

[0104] Step 6: Distributed power equipment uses a neural network model to predict the equipment status based on its own historical data; select an appropriate neural network model based on specific needs, such as LSTM for time series prediction, CNN for fault detection, and DRL for optimized scheduling; use a shared data set to train the neural network model on a central server or cloud platform, and use historical data for model training and cross-validation; deploy the trained model to distributed power equipment to ensure real-time performance and low latency. Use the LSTM model deployed on distributed power equipment to make real-time predictions of equipment status and energy demand.

[0105] Step 7: Distributed power equipment formulates an energy scheduling strategy based on the predicted equipment status of itself, the equipment data of other distributed power equipment, and the energy demand. Based on the prediction results, the DRL model is used to optimize energy scheduling and allocation, and the equipment operation strategy is adjusted to improve energy utilization efficiency.

[0106] Step 8: The distributed power device executes the optimized energy scheduling strategy, and sends a request instruction to execute the demand to other registered distributed power devices according to the optimized energy scheduling strategy; or executes the request instruction received from other registered distributed power devices.

[0107] Step 9: Anomaly detection and self-healing, using the CNN model to detect abnormal conditions in equipment operation and identify fault signals. The system executes self-healing strategies based on the detection results, such as switching to backup equipment and adjusting operating parameters.

[0108] Step 10: Data analysis and feedback, collect the prediction and optimization results of the neural network model, as well as the feedback data from actual operation. Analyze the performance and effect of the model, update and optimize the model, and improve the intelligence level and operation efficiency of the system.

[0109] The beneficial effects of adopting this technical solution are: by combining the active registration mechanism and neural network technology, the self-organizing network, intelligent management and optimized scheduling of distributed power equipment can be realized, which not only improves the communication efficiency and data sharing capabilities between devices, but also enhances the system's prediction and fault detection capabilities, optimizes energy utilization efficiency, and ensures the stability and reliability of the power grid, thereby greatly improving the intelligence level and operation efficiency of the entire energy system.

[0110] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0111] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0112] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0114] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A distributed power equipment networking based on active registration, characterized in that: include: The main power grid registrar is used to send a command to activate active registration to the distributed power equipment, and receive the registration request of the distributed power equipment and the registration information of the distributed power equipment itself; And manage the registration information sent by all registered distributed power devices; Each distributed power device is used to send a registration request and its own registration information to the main grid registrar according to an active registration command, obtain the registration information managed by the main grid registrar after registration, obtain the equipment data of other registered distributed power devices according to the obtained registration information managed by the main grid registrar, and use a neural network model to predict its own equipment status according to its own historical data, formulate an energy scheduling strategy according to the distributed power device's own equipment status, the equipment data of other distributed power devices and energy demand, and use a neural network to optimize the energy scheduling strategy, execute the optimized energy scheduling strategy, and send a request instruction to execute the demand to other registered distributed power devices according to the optimized energy scheduling strategy; it is also used to execute the request instruction received from other registered distributed power devices.

2. The distributed power equipment networking based on active registration according to claim 1 is characterized in that: The main power grid registrar is used to determine whether registration information sent by the distributed power equipment is received within a first set time after a command to activate active registration is sent to the distributed power equipment. When no registration information is received, the active registration progress of the distributed power equipment is queried, and corresponding registration operations are performed according to the queried active registration progress of the distributed power equipment.

3. The distributed power equipment networking based on active registration according to claim 2 is characterized in that: The calculation formula of the first set time T is: T=T base +ω1×W+ω2×T type +ω3×S+ω4×H Among them, T base is the first set time basic value, ω1, ω2, ω3, ω4 are adjustment factors, W is the weight of the distributed power equipment slave node, T is the node type weight, S is the node state parameter, H is the type Historical registration time decay factor.

4. The distributed power equipment networking based on active registration according to claim 2 is characterized in that: The corresponding registration operation is performed based on the active registration progress of the queried distributed power equipment, including replying to an instruction confirmation frame after receiving an instruction to end the active registration reported by the distributed power equipment, and sending an instruction to terminate the active registration of the slave node to the distributed power equipment, wherein the instruction confirmation frame includes information confirming that the distributed power equipment has received the termination signal.

5. The distributed power equipment networking based on active registration according to claim 1 is characterized in that: It also includes a network maintenance and update module for monitoring the communication operation status between the main grid registrar and the distributed power equipment, and periodically testing and verifying the communication operation status between the main grid registrar and the distributed power equipment. The test cycle time length T test The calculation formula is: T test =[1-(M1 / M+N1 / N)×T c / T z ]×T0 Among them, M1 is the number of communication connections; M is the number of communication disconnections; N1 is the total number of registrations; N is the number of registration failures; T c T is the average timeout duration of the actual communication duration relative to the theoretical communication duration among all communication connection times; z is the average duration of a single communication corresponding to all communication connections; T0 is the length of the initial cycle time.

6. The distributed power equipment networking based on active registration according to claim 1 is characterized in that: It also includes a fault detection module for performing fault detection on the device using a deep reinforcement learning model.

7. A control method for distributed power equipment networking based on active registration, characterized in that: The following steps are involved: The distributed power device sends a registration request and the registration information of the distributed power device itself to the main power grid registrar according to the received active registration command; After the distributed power equipment is registered, the registration information managed by the main power grid registrar is obtained, and the equipment data of other registered distributed power equipment is obtained according to the obtained registration information managed by the main power grid registrar; The registration information managed by the main power grid registrar includes registration information sent by all registered distributed power devices; Distributed power equipment uses a neural network model to predict its own equipment status based on its own historical data, and formulates an energy dispatch strategy based on its own equipment status, equipment data of other distributed power equipment, and energy demand, and uses a neural network to optimize the energy dispatch strategy; The distributed power equipment executes the optimized energy dispatching strategy, and sends request instructions to other registered distributed power equipment to execute the requirements according to the optimized energy dispatching strategy; or executes the request instructions received from other registered distributed power equipment.

8. The control method according to claim 7, characterized in that: The main power grid registrar determines whether the registration information sent by the distributed power device is received within the first set time after sending a command to activate active registration to the distributed power device. When no registration information is received, the main power grid registrar queries the active registration progress of the distributed power device, and performs corresponding registration operations based on the active registration progress of the queried distributed power device.

9. The control method according to claim 8, characterized in that: The calculation formula of the first set time T is: T=T base +ω1×W+ω2×T type +ω3×S+ω4×H Among them, T base is the first set time basic value, ω1, ω2, ω3, ω4 are adjustment factors, W is the weight of the distributed power equipment slave node, T is the node type weight, S is the node state parameter, H is the type Historical registration time decay factor.

10. The control method according to claim 8, characterized in that: The corresponding registration operation is performed based on the active registration progress of the queried distributed power equipment, including replying to an instruction confirmation frame after receiving an instruction to end the active registration reported by the distributed power equipment, and sending an instruction to terminate the active registration of the slave node to the distributed power equipment, wherein the instruction confirmation frame includes information confirming that the distributed power equipment has received the termination signal.

11. The control method according to claim 7, characterized in that: It also includes monitoring the communication operation status between the main grid register and the distributed power equipment, and periodically testing and verifying the communication operation status between the main grid register and the distributed power equipment. The test cycle time length T test The calculation formula is: T test =[1-(M1 / M+N1 / N)×T c / T z ]×T0 Among them, M1 is the number of communication connections; M is the number of communication disconnections; N1 is the total number of registrations; N is the number of registration failures; T c T is the average timeout duration of the actual communication duration relative to the theoretical communication duration among all communication connection times; z is the average duration of a single communication corresponding to all communication connections; T0 is the length of the initial cycle time.

12. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 7 to 11 are implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 7 to 11 are implemented.

Images