Parallel inverter control method and system for adaptively adjusting active droop coefficient

Abstract

The invention discloses a parallel inverter control method for adaptively adjusting an active droop coefficient, and the method comprises the following steps: 1, designing a parallel inverter network through a system architecture: building a plurality of parallel inverters, forming a distributed power generation system, and enabling each inverter to be provided with a controller and a communication module; block chain network establishment: creating a private block chain network, adding all inverters as nodes into a block chain, and configuring the block chain network to support intelligent contract and distributed account book functions; and 2, data acquisition and processing and integration of Internet of Things sensors: deploying the Internet of Things sensors on each inverter, and acquiring voltage, current, power and frequency operation data in real time. According to the invention, the operation state of the system can be monitored in real time, the fault inverter can be detected and isolated in time, the operation parameters of other inverters can be adjusted, the system can still operate continuously and stably under the fault condition, and the optimal operation state can be recovered rapidly after the fault.

Description

Technical Field

[0001] The present invention relates to the technical field of inverter control, and in particular to a parallel inverter control method and system for adaptively adjusting an active power droop coefficient. Background Art

[0002] With the rapid development of renewable energy, distributed power generation systems have become an important part of modern power systems. Parallel inverters are key power conversion devices in distributed power generation systems. They are connected to the power grid in parallel and jointly undertake the task of power supply. However, in practical applications, parallel inverter systems face many challenges, such as system stability, uneven load sharing, and self-healing capabilities in the event of faults.

[0003] Although the traditional droop control method has been widely used in parallel inverter control, its inherent limitations make the system less flexible in dealing with load changes and operating environment changes, which easily leads to voltage and frequency instability problems. In addition, traditional control methods often rely on centralized control, which makes the system more sensitive to single point failures and difficult to meet the needs of distributed and decentralized control in modern power systems.

[0004] In recent years, with the rapid development of the Internet of Things, blockchain and artificial intelligence technologies, control methods based on these emerging technologies have provided new ideas for solving the above problems. For example, by integrating IoT sensors for real-time data collection, using blockchain to achieve data transparency and decentralized control, and combining reinforcement learning algorithms to dynamically adjust control parameters, the stability, reliability and adaptability of the system can be greatly improved. However, how to effectively integrate and apply these emerging technologies to parallel inverter control systems is still a problem that needs to be solved. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the problems existing in the above-mentioned existing parallel inverter control method and system for adaptively adjusting the active power droop coefficient, the present invention is proposed.

[0007] Therefore, the purpose of the present invention is to provide a parallel inverter control method and system for adaptively adjusting the active power droop coefficient, which can monitor the operating status of the system in real time, promptly detect and isolate faulty inverters, and adjust the operating parameters of other inverters to ensure that the system can continue to operate stably in the event of a fault and quickly recover to the optimal operating state after the fault.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: a parallel inverter control method for adaptively adjusting the active droop coefficient, comprising the following steps:

[0009] Step 1: System architecture design

[0010] Parallel inverter network: Establish multiple parallel inverters to form a distributed power generation system, and each inverter is equipped with a controller and communication module;

[0011] Blockchain network establishment: Create a private blockchain network, join all inverters as nodes, and configure the blockchain network to support smart contracts and distributed ledger functions;

[0012] Step 2: Data collection and processing

[0013] IoT sensor integration: IoT sensors are deployed on each inverter to collect voltage, current, power, and frequency operation data in real time. Edge computing devices are used to process sensor data and preliminarily screen and filter noise.

[0014] System performance feedback: Establish a data feedback mechanism to send processed data to the controller and blockchain network;

[0015] Step 3: Reinforcement Learning Model Development

[0016] Model construction: Build a reinforcement learning model with the inverter operation data as input and the adjusted active power droop coefficient as output;

[0017] Reward function design:

[0018] Design a reward function to motivate the model to maintain voltage and frequency stability while achieving load balancing;

[0019] Model training and optimization:

[0020] Use historical operation data and simulation data to train reinforcement learning models and continuously optimize model parameters;

[0021] Regularly retrain models to adapt to new environments and load conditions;

[0022] Step 4: Blockchain Decentralized Control

[0023] Data on-chain:

[0024] The real-time operation data of the inverter is uploaded to the chain through the IoT gateway to ensure the transparency and non-tamperability of the data;

[0025] Each inverter node records and broadcasts its own and other nodes’ operating data;

[0026] Smart Contract Execution:

[0027] Deploy smart contracts to achieve data sharing and control collaboration between inverters; smart contracts dynamically adjust the active droop coefficient of each inverter based on the operating data recorded in the blockchain network and the output of the reinforcement learning model;

[0028] Consensus Algorithm:

[0029] Use consensus algorithms to ensure the consistency of data and control instructions among inverter nodes; consensus algorithms guarantee the decentralization and fault resistance of the control system;

[0030] Step 5: Real-time control and adaptive adjustment

[0031] Control command issuance: Generate real-time control commands based on the output of smart contracts and reinforcement learning models, and send the control commands to each inverter through edge computing devices;

[0032] Adaptive adjustment: Each inverter adaptively adjusts the active power droop coefficient according to the received control instructions to ensure stable operation and load balancing of the system; the inverter feeds back the adjustment results in real time and updates the operation data in the blockchain network;

[0033] Step 6: System Monitoring and Maintenance

[0034] Fault detection and isolation: Implement self-healing algorithms, monitor system operating status in real time, detect and isolate faulty inverters, and ensure continuous operation and performance optimization of the system in the event of a fault.

[0035] As a preferred solution of the parallel inverter control method for adaptively adjusting the active power droop coefficient of the present invention, the reinforcement learning model in step 3 includes:

[0036] Status: The current status of the system, including the inverter’s operating data, voltage, current, frequency, and load;

[0037] Action: The action taken by the system to adjust the active power droop coefficient;

[0038] Reward: The feedback the system gets after taking an action, used to measure the quality of the action;

[0039] Strategy: determines the strategy of the system to choose a certain action in a certain state;

[0040] Value function: evaluates the quality of a state or state-action pair;

[0041] Among them, the status represents:

[0042] Status S t Represented by a vector, including the key operating data of the inverter: St =[V t ,I t ,f t ,L t ],V t Indicates voltage, I t represents the current, f t Indicates frequency, L t Indicates load;

[0043] Action Space: Action A t Is to adjust the value of active power droop coefficient k: A t =Δk, where Δk is the increase or decrease of the active droop coefficient;

[0044] Reward function: Reward function R t Designed for:

[0045] R t =-(w1·Voltage Deviation+w2·Frequency Deviation+w3·Load Imbalance+w4·Power Loss),

[0046] Among them: w1, w2, w3, w4 are weight coefficients, which are adjusted according to actual applications;

[0047] Voltage Deviation means voltage deviation, which is defined as the difference between target voltage and actual voltage.

[0048] Frequency Deviation means frequency deviation, which is defined as the difference between the target frequency and the actual frequency;

[0049] Load Imbalance indicates the load imbalance;

[0050] Strategy and value function: Use the DQN algorithm as the reinforcement learning algorithm. DQN approximates the value function S(s,a;θ) through a deep neural network, where θ is the parameter of the neural network.

[0051] As a preferred solution of the parallel inverter control method for adaptively adjusting the active droop coefficient of the present invention, the DQN algorithm steps include:

[0052] S1. Initialize the experience replay pool D;

[0053] S2, initialize the Q network and the target Q network, with parameters θ and θ' respectively;

[0054] S3. For each round of training:

[0055] Get the current state S t ;

[0056] Select action A according to the ∈-greedy strategy t ;

[0057] Execute action A t , get the next state S t+1 and reward R t ;

[0058] (S t ,A t ,R t ,S t+1 ) is stored in the experience replay pool D;

[0059] Randomly sample a batch of data (S i ,A i ,R i ,S i+1 );

[0060] Calculate the target Q value: y i =R i +γmax a' Q(S i+1 ,a';θ');

[0061] Calculate the loss function:

[0062] Update the Q network parameters θ by gradient descent method;

[0063] The target Q network parameter θ'=θ is updated periodically.

[0064] As a preferred solution of the parallel inverter control method for adaptively adjusting the active droop coefficient of the present invention, the reinforcement learning model training process uses historical operation data and simulation data for model training, continuously optimizes the neural network parameter θ, and in actual operation, inputs the current state S t To the trained DQN model, get the optimal action A t , adjust the control parameters of the inverter in real time.

[0065] As a preferred solution of the parallel inverter control method for adaptively adjusting the active droop coefficient of the present invention, the consensus algorithm in step 4 adopts practical Byzantine fault tolerance, and the specific algorithm steps include:

[0066] A1. System model: Assume there are n nodes, of which f nodes may be malicious, and n≥3f+1 is required; Practical Byzantine Fault Tolerance includes three main stages: pre-prepare, prepare, and commit;

[0067] A2. Phase 1: Pre-preparation. The master node sends a pre-preparation message to all backup nodes. The pre-preparation message includes a proposal m to reach consensus and a sequence number s.

[0068] A3. Phase 2: Preparation. After receiving the pre-prepare message, the backup node verifies the correctness of the message and broadcasts the prepare message to all nodes. The prepare message includes the proposal m and the sequence number s.

[0069] A4. Phase 3: Commit. After receiving at least 2f prepare messages, the backup node broadcasts the commit message to all nodes. The commit message includes the proposal m and the sequence number s.

[0070] A5. Reaching consensus: After all nodes receive at least 2f+1 commit messages, they consider that proposal m has reached consensus and execute the proposal. The message transmission formula is as follows:

[0071] Message total =n·Message prepare +n·Message commit

[0072] Among them, Message prepare and Message commit The number of prepare messages and commit messages, respectively.

[0073] As a preferred solution of the parallel inverter control method for adaptively adjusting the active power droop coefficient of the present invention, the specific steps of the self-healing algorithm in step 6 are as follows:

[0074] B1. Real-time monitoring system operation status:

[0075] Collect the operating data of each inverter in the system, including voltage, current, frequency and temperature, and use the data acquisition module to obtain and update the status information of the inverter in real time;

[0076] Formula: Let S i (t) is the state vector of the i-th inverter at time t:

[0077] S i (t) = [V i (t),I i (t),f i (t),T i (t)]

[0078] Among them, V i (t) represents the voltage of the i-th inverter at time t; I i (t) represents the current of the i-th inverter at time t; f i (t) represents the frequency of the i-th inverter at time t; Ti (t) represents the temperature of the i-th inverter at time t;

[0079] B2. Fault detection:

[0080] Define fault detection thresholds and use anomaly detection algorithms to analyze inverter status data in real time to determine whether a fault has occurred;

[0081] Formula: Let the threshold be {V min ,V max ,I min ,I max ,f min ,f max ,T max}, the fault detection condition is:

[0082]

[0083] B3. Fault isolation:

[0084] When an inverter fault is detected, the faulty inverter is immediately isolated to prevent it from affecting the normal operation of the system; the load is redistributed to ensure stable operation of the system; Formula: Assume that the faulty inverter is the i-th inverter, and its state is S i (t), the isolation operation is: Isolate(S i (t)), the formula for redistributing the load is:

[0085]

[0086] Where: L new (t) is the load of each inverter after redistribution;

[0087] L total (t) is the total system load;

[0088] L i (t) is the load of the faulty inverter;

[0089] n is the total number of inverters in the system.

[0090] As a preferred solution of the parallel inverter control method for adaptively adjusting the active droop coefficient of the present invention, the self-healing algorithm also includes self-healing control, which uses the prediction model and historical data to predict and analyze the system operation status, dynamically adjust the control parameters of the inverter, and optimize the system performance;

[0091] The prediction model is: Predict(S i (t)), the adjustment amount of self-healing control is ΔP(t), and the control formula is:

[0092] ΔP(t)=Predict(S(t))-S(t)

[0093] Update the inverter control parameters according to the adjustment amount:

[0094] P new (t) = P (t) + ΔP (t)

[0095] Where: Predict(S(t)) is the predicted system state;

[0096] ΔP(t) is the difference between the predicted state and the actual state;

[0097] P(t) is the control parameter of the current inverter;

[0098] P new (t) is the updated control parameter.

[0099] As a preferred solution of the parallel inverter control method for adaptively adjusting the active power droop coefficient of the present invention, wherein: the parallel inverter control system for adaptively adjusting the active power droop coefficient includes a parallel inverter system architecture, a data acquisition and processing subsystem, a reinforcement learning control subsystem, a blockchain decentralized control subsystem, a real-time control and adaptive adjustment subsystem and a system monitoring and self-healing maintenance subsystem;

[0100] Wherein, the parallel inverter system architecture includes an inverter unit and a blockchain network;

[0101] The data acquisition and processing subsystem includes an IoT sensor network and an edge computing module. The IoT sensor network is an IoT sensor network integrated on each inverter, which monitors and collects voltage, current, power, and frequency data in real time. The edge computing module is responsible for performing preliminary processing on the collected data, reducing data noise, and providing preliminary system performance feedback. The feedback mechanism transmits the processed data to the controller and blockchain network to provide real-time data support for the reinforcement learning model.

[0102] The reinforcement learning control subsystem includes a reinforcement learning model module: an input port: receiving operation data from the inverter; an output port: providing an adjusted active power droop coefficient for real-time control of the inverter operation; a reward function: motivating the model to maintain the stability of the system voltage and frequency and achieve load balancing; a model training module: training the model using historical data and simulation data, and regularly updating the model parameters to adapt to new conditions of the system;

[0103] The blockchain decentralized control subsystem includes a data management module: data on-chain: the inverter operation data is uploaded to the chain through the IoT gateway to ensure data transparency and non-tamperability; smart contract execution module: based on the on-chain data and the output of the reinforcement learning model, the smart contract is executed to dynamically adjust the active droop coefficient of the inverter; consensus algorithm module: a consensus algorithm is used to ensure the consistency of data and control instructions between inverter nodes;

[0104] The real-time control and adaptive regulation subsystem includes a control instruction generation module and an adaptive regulation module; the control instruction generation module generates and issues real-time control instructions according to the output of the smart contract and the reinforcement learning model; the adaptive regulation module includes an adjustment module: each inverter adaptively adjusts the active droop coefficient according to the received control instruction to ensure system stability and load balance; a feedback module: the inverter feeds back the adjusted operating status to the blockchain network to achieve closed-loop control;

[0105] The system monitoring and self-healing maintenance subsystem includes a real-time monitoring module, a fault isolation module and a maintenance module; the real-time monitoring module implements a self-healing algorithm to monitor and detect faulty inverters in the system in real time; the fault isolation module: when a faulty inverter is detected, the system automatically isolates the faulty inverter and adjusts the operation of other inverters to maintain the continuity and optimized performance of the system; the maintenance module: generates a fault report and shares it through the blockchain network to facilitate system maintenance and optimization.

[0106] As a preferred solution of the parallel inverter control method for adaptively adjusting the active power droop coefficient of the present invention, the inverter unit includes a plurality of parallel inverters, each of which is equipped with the following modules:

[0107] Controller: responsible for executing the control algorithm, adjusting the active power droop coefficient, and executing the received control instructions;

[0108] Communication module: supports communication with other inverters, ensures data sharing and control collaboration, and supports blockchain network communication;

[0109] IoT sensors: including voltage sensors, current sensors, and temperature sensors, used to collect operating data;

[0110] Edge computing devices: process sensor data, perform preliminary data screening and noise filtering, and pass processed data to the controller and blockchain network.

[0111] As a preferred solution of the parallel inverter control method for adaptively adjusting the active power droop coefficient of the present invention, the blockchain network includes:

[0112] Private blockchain: Establish a private blockchain, and all inverters join the blockchain network as nodes;

[0113] Blockchain nodes: The inverter and its controller act as blockchain nodes, responsible for recording, broadcasting and sharing operating data;

[0114] Smart contract module: deployed on the blockchain network to perform data sharing and control collaboration.

[0115] Beneficial effects of the present invention:

[0116] 1. The present invention constructs a reinforcement learning model to adaptively adjust the active droop coefficient according to the real-time operating data of the inverter (such as voltage, frequency, load, etc.). The reinforcement learning model designs a reasonable reward function to encourage the system to achieve uniform load distribution while maintaining voltage and frequency stability, thereby greatly improving the stability and load sharing accuracy of the parallel inverter system;

[0117] 2. The present invention implements a self-healing algorithm, which can monitor the operating status of the system in real time, detect and isolate faulty inverters in a timely manner, and adjust the operating parameters of other inverters to ensure that the system can continue to operate stably in the event of a fault and quickly recover to the optimal operating state after the fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0118] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0119] Figure 1 The figure is an overall schematic diagram of the parallel inverter control method for adaptively adjusting the active power droop coefficient according to the present invention.

[0120] Figure 2 This is a diagram of an embodiment of the self-healing algorithm verification based on simulation data of the parallel inverter control method for adaptively adjusting the active power droop coefficient of the present invention.

[0121] Figure 3 This is a diagram showing an embodiment of a simulation experiment to verify the parallel inverter control method for adaptively adjusting the active power droop coefficient of the present invention. DETAILED DESCRIPTION

[0122] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0123] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0124] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0125] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0126] Reference Figure 1 , a parallel inverter control method for adaptively adjusting active droop coefficient is provided, comprising the following steps:

[0127] Step 1: System architecture design

[0128] Parallel inverter network: Establish multiple parallel inverters to form a distributed power generation system, and each inverter is equipped with a controller and communication module;

[0129] Blockchain network establishment: Create a private blockchain network, join all inverters as nodes, and configure the blockchain network to support smart contracts and distributed ledger functions;

[0130] Step 2: Data collection and processing

[0131] IoT sensor integration: IoT sensors are deployed on each inverter to collect voltage, current, power, and frequency operation data in real time. Edge computing devices are used to process sensor data and preliminarily screen and filter noise.

[0132] System performance feedback: Establish a data feedback mechanism to send processed data to the controller and blockchain network;

[0133] Step 3: Reinforcement Learning Model Development

[0134] Model construction: Build a reinforcement learning model with the inverter operation data as input and the adjusted active power droop coefficient as output;

[0135] Reward function design:

[0136] Design a reward function to motivate the model to maintain voltage and frequency stability while achieving load balancing;

[0137] Model training and optimization:

[0138] Use historical operation data and simulation data to train reinforcement learning models and continuously optimize model parameters;

[0139] Regularly retrain models to adapt to new environments and load conditions;

[0140] Step 4: Blockchain Decentralized Control

[0141] Data on-chain:

[0142] The real-time operation data of the inverter is uploaded to the chain through the IoT gateway to ensure the transparency and non-tamperability of the data;

[0143] Each inverter node records and broadcasts its own and other nodes’ operating data;

[0144] Smart Contract Execution:

[0145] Deploy smart contracts to achieve data sharing and control collaboration between inverters; smart contracts dynamically adjust the active droop coefficient of each inverter based on the operating data recorded in the blockchain network and the output of the reinforcement learning model;

[0146] Consensus Algorithm:

[0147] Use consensus algorithms to ensure the consistency of data and control instructions among inverter nodes; consensus algorithms guarantee the decentralization and fault resistance of the control system;

[0148] Step 5: Real-time control and adaptive adjustment

[0149] Control command issuance: Generate real-time control commands based on the output of smart contracts and reinforcement learning models, and send the control commands to each inverter through edge computing devices;

[0150] Adaptive adjustment: Each inverter adaptively adjusts the active power droop coefficient according to the received control instructions to ensure stable operation and load balancing of the system; the inverter feeds back the adjustment results in real time and updates the operation data in the blockchain network;

[0151] Step 6: System Monitoring and Maintenance

[0152] Fault detection and isolation: Implement self-healing algorithms, monitor system operating status in real time, detect and isolate faulty inverters, and ensure continuous operation and performance optimization of the system in the event of a fault.

[0153] Wherein, the reinforcement learning model in step 3 includes:

[0154] Status: The current status of the system, including the inverter’s operating data, voltage, current, frequency, and load;

[0155] Action: The action taken by the system to adjust the active power droop coefficient;

[0156] Reward: The feedback the system gets after taking an action, used to measure the quality of the action;

[0157] Strategy: determines the strategy of the system to choose a certain action in a certain state;

[0158] Value function: evaluates the quality of a state or state-action pair;

[0159] Among them, the status represents:

[0160] Status S t Represented by a vector, including the key operating data of the inverter: S t =[V t ,I t ,f t ,L t ],V t Indicates voltage, I t represents the current, f t Indicates frequency, L t Indicates load;

[0161] Action Space: Action A t Is to adjust the value of active power droop coefficient k: A t =Δk, where Δk is the increase or decrease of the active droop coefficient;

[0162] Reward function: Reward function R t Designed for:

[0163] R t =-(w1·Voltage Deviation+w2·Frequency Deviation+w3·Load Imbalance+w4·Power Loss),

[0164] Among them: w1, w2, w3, w4 are weight coefficients, which are adjusted according to actual applications;

[0165] Voltage Deviation means voltage deviation, which is defined as the difference between target voltage and actual voltage.

[0166] Frequency Deviation means frequency deviation, which is defined as the difference between the target frequency and the actual frequency;

[0167] Load Imbalance indicates the load imbalance;

[0168] Strategy and value function: Use the DQN algorithm as the reinforcement learning algorithm. DQN approximates the value function S(s,a;θ) through a deep neural network, where θ is the parameter of the neural network.

[0169] Furthermore, the DQN algorithm steps include:

[0170] S1. Initialize the experience replay pool D;

[0171] S2, initialize the Q network and the target Q network, with parameters θ and θ' respectively;

[0172] S3. For each round of training:

[0173] Get the current state S t ;

[0174] Select action A according to the ∈-greedy strategy t ;

[0175] Execute action A t , get the next state S t+1 and reward R t ;

[0176] (S t ,A t ,R t ,S t+1 ) is stored in the experience replay pool D;

[0177] Randomly sample a batch of data (S i ,A i ,R i ,S i+1 );

[0178] Calculate the target Q value: y i =R i +γmax a' Q(S i+1 ,a';θ');

[0179] Calculate the loss function:

[0180] Update the Q network parameters θ by gradient descent method;

[0181] Regularly update the target Q network parameter θ'=θ. Specifically, the reinforcement learning model training process uses historical operation data and simulation data to train the model and continuously optimize the neural network parameter θ. In actual operation, the current state S is input. t To the trained DQN model, get the optimal action A t , adjust the control parameters of the inverter in real time.

[0182] The consensus algorithm in step 4 adopts practical Byzantine fault tolerance, and the specific algorithm steps include:

[0183] A1. System model: Assume there are n nodes, of which f nodes may be malicious, and n≥3f+1 is required; Practical Byzantine Fault Tolerance includes three main stages: pre-prepare, prepare, and commit;

[0184] A2. Phase 1: Pre-preparation. The master node sends a pre-preparation message to all backup nodes. The pre-preparation message includes a proposal m to reach consensus and a sequence number s.

[0185] A3. Phase 2: Preparation. After receiving the pre-prepare message, the backup node verifies the correctness of the message and broadcasts the prepare message to all nodes. The prepare message includes the proposal m and the sequence number s.

[0186] A4. Phase 3: Commit. After receiving at least 2f prepare messages, the backup node broadcasts the commit message to all nodes. The commit message includes the proposal m and the sequence number s.

[0187] A5. Reaching consensus: After all nodes receive at least 2f+1 commit messages, they consider that proposal m has reached consensus and execute the proposal. The message transmission formula is as follows:

[0188] Message total =n·Message prepare +n·Message commit

[0189] Among them, Message prepare and Message commit The number of prepare messages and commit messages, respectively.

[0190] The specific steps of the self-healing algorithm in step 6 are as follows:

[0191] B1. Real-time monitoring system operation status:

[0192] Collect the operating data of each inverter in the system, including voltage, current, frequency and temperature, and use the data acquisition module to obtain and update the status information of the inverter in real time;

[0193] Formula: Let S i (t) is the state vector of the i-th inverter at time t:

[0194] S i (t) = [V i (t),I i (t),f i (t),T i (t)]

[0195] Among them, V i (t) represents the voltage of the i-th inverter at time t; I i (t) represents the current of the i-th inverter at time t; f i (t) represents the frequency of the i-th inverter at time t; T i (t) represents the temperature of the i-th inverter at time t;

[0196] B2. Fault detection:

[0197] Define fault detection thresholds and use anomaly detection algorithms to analyze inverter status data in real time to determine whether a fault has occurred;

[0198] Formula: Let the threshold be {V min ,V max ,I min ,I max ,f min ,f max ,T max}, the fault detection condition is:

[0199]

[0200] B3. Fault isolation:

[0201] When an inverter fault is detected, the faulty inverter is immediately isolated to prevent it from affecting the normal operation of the system; the load is redistributed to ensure stable operation of the system; Formula: Assume that the faulty inverter is the i-th inverter, and its state is S i (t), the isolation operation is: Isolate(S i (t)), the formula for redistributing the load is:

[0202]

[0203] Where: L new (t) is the load of each inverter after redistribution;

[0204] L total (t) is the total system load;

[0205] L i (t) is the load of the faulty inverter;

[0206] n is the total number of inverters in the system.

[0207] Furthermore, the self-healing algorithm also includes self-healing control, which uses prediction models and historical data to predict and analyze the system operation status, dynamically adjust the control parameters of the inverter, and optimize the system performance;

[0208] The prediction model is: Predict(S i (t)), the adjustment amount of self-healing control is ΔP(t), and the control formula is:

[0209] ΔP(t)=Predict(S(t))-S(t)

[0210] Update the inverter control parameters according to the adjustment amount:

[0211] P new (t) = P (t) + ΔP (t)

[0212] Where: Predict(S(t)) is the predicted system state;

[0213] ΔP(t) is the difference between the predicted state and the actual state;

[0214] P(t) is the control parameter of the current inverter;

[0215] P new (t) is the updated control parameter.

[0216] The specific examples are as follows:

[0217] Assume that there are three parallel inverters in the system (NodeA, Node B, Node C), and set the following thresholds:

[0218] Voltage threshold: V min =210V, V max =240V

[0219] Current threshold: I min =0A, I max =10A

[0220] Frequency threshold: f min =49.5Hz, f max =50.5Hz

[0221] Temperature threshold: T max =80℃

[0222] Self-healing process

[0223] 1. Real-time monitoring:

[0224] NodeA status: S A (t) = [230V, 8A, 50Hz, 75°C]

[0225] Node B status: S B (t)=[235V, 7A, 50.2Hz, 78℃]

[0226] Node C status: SC (t) = [220V, 9A, 50Hz, 82°C]

[0227] 2. Fault detection:

[0228] The temperature of Node C exceeds the threshold T max =80°C, fault detected;

[0229] 3. Fault isolation:

[0230] Isolate Node C and perform the following operation: Isolate(S C (t))

[0231] Redistribute the load, assuming that the total system load L total (t) = 24A, the load before the fault is:

[0232] NodeA: 8A; Node B: 7A; Node C: 9A;

[0233] After a failure, redistribute the load:

[0234]

[0235] NodeA: 7.5A; Node B: 7.5A;

[0236] 4. Self-healing control:

[0237] Use the prediction model to predict the system state: Predict(S(t)); dynamically adjust the control parameters to optimize the system performance;

[0238] Through the above steps, the self-healing algorithm can monitor the operating status of the parallel inverter system in real time, detect and isolate faulty inverters, ensure stable system operation and optimize performance.

[0239] Reference Figure 2 , Example 1: Self-healing algorithm verification based on simulation data

[0240] Simulation data generation

[0241] We generate simulation data of the parallel inverter system, including voltage, current, frequency, and temperature parameters, which are used to generate simulation data and verify the effect of the self-healing algorithm;

[0242] Reference Figure 3 , Example 2: Simulation Experiment Verification

[0243] Simulation environment settings

[0244] In the simulation environment, the fault detection and isolation process of the three parallel inverter system is simulated. The self-healing algorithm is used to isolate the faulty inverter and redistribute the load when a fault occurs.

[0245] Results and Analysis

[0246] 1. Voltage curve: shows the voltage changes of the three inverters before and after the fault occurs. It can be seen that when the fault occurs (marked by the red line), the voltage curve of Node C does not change significantly, because the voltage adjustment does not directly affect the fault isolation operation.

[0247] 2. Current curve: When a fault occurs, the current of Node C drops to zero quickly, while the current of Node A and Node B increases accordingly, redistributing the load to ensure the stability and continuous operation of the system.

[0248] 3. Frequency curve: shows the frequency change of the inverter, indicating the stability of the system frequency during the fault isolation process.

[0249] 4. Temperature curve: shows the temperature change of Node C. After the fault is detected and the temperature exceeds the threshold, Node C is isolated to ensure the safe operation of the system.

[0250] Through the above two embodiments and the analysis of their results, the effectiveness and reliability of the self-healing algorithm in the parallel inverter system can be verified.

[0251] Among them, the parallel inverter control system for adaptively adjusting the active droop coefficient includes a parallel inverter system architecture, a data acquisition and processing subsystem, a reinforcement learning control subsystem, a blockchain decentralized control subsystem, a real-time control and adaptive adjustment subsystem, and a system monitoring and self-healing maintenance subsystem.

[0252] Specifically, the parallel inverter system architecture includes an inverter unit and a blockchain network. The inverter unit includes multiple parallel inverters, and each inverter is equipped with the following modules:

[0253] Controller: responsible for executing the control algorithm, adjusting the active power droop coefficient, and executing the received control instructions;

[0254] Communication module: supports communication with other inverters, ensures data sharing and control collaboration, and supports blockchain network communication;

[0255] IoT sensors: including voltage sensors, current sensors, and temperature sensors, used to collect operating data;

[0256] Edge computing devices: process sensor data, perform preliminary data screening and noise filtering, and pass processed data to the controller and blockchain network;

[0257] The blockchain network includes:

[0258] Private blockchain: Establish a private blockchain, and all inverters join the blockchain network as nodes;

[0259] Blockchain nodes: The inverter and its controller act as blockchain nodes, responsible for recording, broadcasting and sharing operating data;

[0260] Smart contract module: deployed on the blockchain network to perform data sharing and control collaboration;

[0261] The data acquisition and processing subsystem includes an IoT sensor network and an edge computing module. The IoT sensor network is an IoT sensor network integrated on each inverter, which monitors and collects voltage, current, power, and frequency data in real time. The edge computing module is responsible for performing preliminary processing on the collected data, reducing data noise, and providing preliminary system performance feedback. The feedback mechanism transmits the processed data to the controller and blockchain network to provide real-time data support for the reinforcement learning model.

[0262] The reinforcement learning control subsystem includes a reinforcement learning model module: an input port: receiving operating data from the inverter; an output port: providing an adjusted active power droop coefficient for real-time control of the inverter operation; a reward function: motivating the model to maintain the stability of the system voltage and frequency and achieve load balancing; a model training module: using historical data and simulation data to train the model, and regularly updating the model parameters to adapt to new conditions of the system.

[0263] More specifically, the blockchain decentralized control subsystem includes a data management module: data on-chain: the inverter operation data is uploaded to the chain through the IoT gateway to ensure data transparency and non-tamperability; smart contract execution module: based on the on-chain data and the output of the reinforcement learning model, the smart contract is executed to dynamically adjust the active droop coefficient of the inverter; consensus algorithm module: a consensus algorithm is used to ensure the consistency of data and control instructions between inverter nodes;

[0264] The real-time control and adaptive regulation subsystem includes a control instruction generation module and an adaptive regulation module; the control instruction generation module generates and issues real-time control instructions according to the output of the smart contract and the reinforcement learning model; the adaptive regulation module includes an adjustment module: each inverter adaptively adjusts the active droop coefficient according to the received control instruction to ensure system stability and load balance; a feedback module: the inverter feeds back the adjusted operating status to the blockchain network to achieve closed-loop control;

[0265] The system monitoring and self-healing maintenance subsystem includes a real-time monitoring module, a fault isolation module and a maintenance module; the real-time monitoring module implements a self-healing algorithm to monitor and detect faulty inverters in the system in real time; the fault isolation module: when a faulty inverter is detected, the system automatically isolates the faulty inverter and adjusts the operation of other inverters to maintain the continuity and optimized performance of the system; the maintenance module: generates a fault report and shares it through the blockchain network to facilitate system maintenance and optimization.

[0266] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A parallel inverter control method for adaptively adjusting active droop coefficient, characterized in that: The following steps are involved: Step 1: System architecture design Parallel inverter network: Establish multiple parallel inverters to form a distributed power generation system, and each inverter is equipped with a controller and communication module; Blockchain network establishment: Create a private blockchain network, join all inverters as nodes, and configure the blockchain network to support smart contracts and distributed ledger functions; Step 2: Data collection and processing IoT sensor integration: IoT sensors are deployed on each inverter to collect voltage, current, power, and frequency operation data in real time. Edge computing devices are used to process sensor data and preliminarily screen and filter noise. System performance feedback: Establish a data feedback mechanism to send processed data to the controller and blockchain network; Step 3: Reinforcement Learning Model Development Model construction: Build a reinforcement learning model with the inverter operation data as input and the adjusted active power droop coefficient as output; Reward function design: Design a reward function to motivate the model to maintain voltage and frequency stability while achieving load balancing; Model training and optimization: Use historical operation data and simulation data to train reinforcement learning models and continuously optimize model parameters; Regularly retrain models to adapt to new environments and load conditions; Step 4: Decentralized blockchain control Data on-chain: The real-time operation data of the inverter is uploaded to the blockchain through the IoT gateway to ensure data transparency and non-tamperability; Each inverter node records and broadcasts its own and other nodes’ operating data; Smart Contract Execution: Deploy smart contracts to achieve data sharing and control collaboration between inverters; smart contracts dynamically adjust the active droop coefficient of each inverter based on the operating data recorded in the blockchain network and the output of the reinforcement learning model; Consensus Algorithm: Use consensus algorithms to ensure the consistency of data and control instructions among inverter nodes; consensus algorithms guarantee the decentralization and fault resistance of the control system; Step 5: Real-time control and adaptive adjustment Control command issuance: Generate real-time control commands based on the output of smart contracts and reinforcement learning models, and send the control commands to each inverter through edge computing devices; Adaptive adjustment: Each inverter adaptively adjusts the active power droop coefficient according to the received control instructions to ensure stable operation and load balancing of the system; the inverter feeds back the adjustment results in real time and updates the operation data in the blockchain network; Step 6: System Monitoring and Maintenance Fault detection and isolation: Implement self-healing algorithms, monitor system operating status in real time, detect and isolate faulty inverters, and ensure continuous operation and performance optimization of the system in the event of a fault.

2. The parallel inverter control method for adaptively adjusting the active power droop coefficient according to claim 1 is characterized in that: The reinforcement learning model in step 3 includes: Status: The current status of the system, including the inverter’s operating data, voltage, current, frequency, and load; Action: The action taken by the system to adjust the active power droop coefficient; Reward: The feedback the system gets after taking an action, used to measure the quality of the action; Strategy: determines the strategy of the system to choose a certain action in a certain state; Value function: evaluates the quality of a state or state-action pair; Among them, the status represents: Status S t Represented by a vector, including the key operating data of the inverter: S t =[V t , I t , f t , L t ],V t Indicates voltage, I t represents the current, f t Indicates frequency, L t Indicates load; Action Space: Action A t Is to adjust the value of active power droop coefficient k: A t =Δk, where Δk is the increase or decrease of the active droop coefficient; Reward function: Reward function R t Designed for: R t =-(w1·Voltage Deviation+W2·Frequency Deviation+W3·Load Imbalance+W4·Power Loss), Where: W1, W2, w3, w4 are weight coefficients, which are adjusted according to actual applications; Voltage Deviation represents voltage deviation, which is defined as the difference between the target voltage and the actual voltage; Frequency Deviation means frequency deviation, which is defined as the difference between the target frequency and the actual frequency; LoadImbalance indicates the load imbalance; Strategy and value function: Use the DQN algorithm as the reinforcement learning algorithm. DQN approximates the value function S(s, a; θ) through a deep neural network, where θ is the parameter of the neural network.

3. The parallel inverter control method for adaptively adjusting the active power droop coefficient according to claim 2, characterized in that: The DQN algorithm steps include: S1. Initialize the experience replay pool D; S2, initialize the Q network and the target Q network, with parameters θ and θ′ respectively; S3. For each round of training: Get the current state S t ; Select action A according to the ∈-greedy strategy t ; Execute action A t , get the next state S t+1 and reward R t ; (S t , A t , R t , S t+1 ) is stored in the experience replay pool D; Randomly sample a batch of data (S i , A i , R i , S i+1 ); Calculate the target Q value: y i =R i +ymax a′ Q(S i+1 , a′; θ′); Calculate the loss function: Update the Q network parameters θ by gradient descent method; The target Q network parameter θ′=θ is updated periodically.

4. The parallel inverter control method for adaptively adjusting the active power droop coefficient according to claim 3 is characterized in that: The reinforcement learning model training process uses historical operation data and simulation data for model training, continuously optimizing the neural network parameters θ. In actual operation, the current state S is input t To the trained DQN model, get the optimal action A t , adjust the control parameters of the inverter in real time.

5. The parallel inverter control method for adaptively adjusting active power droop coefficient according to claim 1, characterized in that: The consensus algorithm in step 4 adopts practical Byzantine fault tolerance, and the specific algorithm steps include: A 1. System model: Assume there are n nodes, of which f nodes may be malicious, and n≥3f+1; Practical Byzantine Fault Tolerance includes three main stages: pre-preparation, preparation, and submission; A2. Phase 1: Pre-preparation. The master node sends a pre-preparation message to all backup nodes. The pre-preparation message includes a proposal m to reach consensus and a sequence number s. A3. Phase 2: Preparation. After receiving the pre-prepare message, the backup node verifies the correctness of the message and broadcasts the prepare message to all nodes. The prepare message includes the proposal m and the sequence number s. A4. Phase 3: Commit. After receiving at least 2f prepare messages, the backup node broadcasts the commit message to all nodes. The commit message includes the proposal m and the sequence number s. A5. Reaching consensus: After all nodes receive at least 2f+1 commit messages, they consider that proposal m has reached consensus and execute the proposal. The message transmission formula is as follows: Message total =n·Message prepare +n·Message commit Among them, Message prepare and Message commit The number of prepare messages and commit messages, respectively.

6. The parallel inverter control method for adaptively adjusting active power droop coefficient according to claim 1, characterized in that: The specific steps of the self-healing algorithm in step 6 are as follows: B1. Real-time monitoring system operation status: Collect the operating data of each inverter in the system, including voltage, current, frequency and temperature, and use the data acquisition module to obtain and update the status information of the inverter in real time; Formula: Let S i (t) is the state vector of the i-th inverter at time t: S i (t)=[V i (t),I i (t),f i (t),T i (t)] Among them, V i (t) represents the voltage of the i-th inverter at time t; I i (t) represents the current of the i-th inverter at time t; f i (t) represents the frequency of the i-th inverter at time t; T i (t) represents the temperature of the i-th inverter at time t; B2. Fault detection: Define fault detection thresholds and use anomaly detection algorithms to analyze inverter status data in real time to determine whether a fault has occurred; Formula: Let the threshold be {V min , V max , I min , I max , f min , f max , T max }, the fault detection condition is: B3. Fault isolation: When an inverter fault is detected, the faulty inverter is immediately isolated to prevent it from affecting the normal operation of the system; the load is redistributed to ensure stable operation of the system; Formula: Assume that the faulty inverter is the i-th inverter, and its state is S i (t), the isolation operation is: Isolate(S i (t)), the formula for redistributing the load is: Where: L new (t) is the load of each inverter after redistribution; L total (t) is the total system load; L i (t) is the load of the faulty inverter; n is the total number of inverters in the system.

7. The parallel inverter control method for adaptively adjusting active power droop coefficient according to claim 6, characterized in that: The self-healing algorithm also includes self-healing control, which uses prediction models and historical data to predict and analyze the system operation status, dynamically adjust the control parameters of the inverter, and optimize the system performance; The prediction model is: Predict(S i (t)), the adjustment amount of self-healing control is AP(t), and the control formula is: AP(t)=Predict(S(t))-S(t) Update the inverter control parameters according to the adjustment amount: P new (t)=P(t)+ΔP(t) Where: Predict(S(t)) is the predicted system state; AP(t) is the difference between the predicted state and the actual state; P(t) is the control parameter of the current inverter; P new (t) is the updated control parameter.

8. A parallel inverter control system for adaptively adjusting active power droop coefficient, characterized in that: Including parallel inverter system architecture, data acquisition and processing subsystem, reinforcement learning control subsystem, blockchain decentralized control subsystem, real-time control and adaptive regulation subsystem and system monitoring and self-healing maintenance subsystem; Wherein, the parallel inverter system architecture includes an inverter unit and a blockchain network; The data acquisition and processing subsystem includes an IoT sensor network and an edge computing module. The IoT sensor network is an IoT sensor network integrated on each inverter, which monitors and collects voltage, current, power, and frequency data in real time. The edge computing module is responsible for performing preliminary processing on the collected data, reducing data noise, and providing preliminary system performance feedback. The feedback mechanism transmits the processed data to the controller and blockchain network to provide real-time data support for the reinforcement learning model. The reinforcement learning control subsystem includes a reinforcement learning model module: an input port: receiving operation data from the inverter; an output port: providing an adjusted active power droop coefficient for real-time control of the inverter operation; a reward function: motivating the model to maintain the stability of the system voltage and frequency and achieve load balancing; a model training module: training the model using historical data and simulation data, and regularly updating the model parameters to adapt to new conditions of the system; The blockchain decentralized control subsystem includes a data management module: data on-chain: the inverter operation data is uploaded to the chain through the IoT gateway to ensure data transparency and non-tamperability; smart contract execution module: based on the on-chain data and the output of the reinforcement learning model, the smart contract is executed to dynamically adjust the active droop coefficient of the inverter; consensus algorithm module: a consensus algorithm is used to ensure the consistency of data and control instructions between inverter nodes; The real-time control and adaptive regulation subsystem includes a control instruction generation module and an adaptive regulation module; the control instruction generation module generates and issues real-time control instructions according to the output of the smart contract and the reinforcement learning model; the adaptive regulation module includes an adjustment module: each inverter adaptively adjusts the active droop coefficient according to the received control instruction to ensure system stability and load balance; a feedback module: the inverter feeds back the adjusted operating status to the blockchain network to achieve closed-loop control; The system monitoring and self-healing maintenance subsystem includes a real-time monitoring module, a fault isolation module and a maintenance module; the real-time monitoring module implements a self-healing algorithm to monitor and detect faulty inverters in the system in real time; the fault isolation module: when a faulty inverter is detected, the system automatically isolates the faulty inverter and adjusts the operation of other inverters to maintain the continuity and optimized performance of the system; the maintenance module: generates a fault report and shares it through the blockchain network to facilitate system maintenance and optimization.

9. The parallel inverter control system for adaptively adjusting active power droop coefficient according to claim 8, characterized in that: The inverter unit includes a plurality of parallel inverters, each of which is equipped with the following modules: Controller: responsible for executing the control algorithm, adjusting the active power droop coefficient, and executing the received control instructions; Communication module: supports communication with other inverters, ensures data sharing and control collaboration, and supports blockchain network communication; IoT sensors: including voltage sensors, current sensors, and temperature sensors, used to collect operating data; Edge computing devices: process sensor data, perform preliminary data screening and noise filtering, and pass processed data to the controller and blockchain network.

10. The parallel inverter control system for adaptively adjusting active power droop coefficient according to claim 8, characterized in that: The blockchain network includes: Private blockchain: Establish a private blockchain, and all inverters join the blockchain network as nodes; Blockchain nodes: The inverter and its controller act as blockchain nodes, responsible for recording, broadcasting and sharing operating data; Smart contract module: deployed on the blockchain network to perform data sharing and control collaboration.

Images