Optimization method based on distributed solar photovoltaic power generation control system

Abstract

The invention relates to an optimization method based on a distributed solar photovoltaic power generation control system. The method comprises the following steps: collecting generating capacity data, voltage data, current data and solar radiation data; inputting a photovoltaic multi-mode deep learning prediction model for processing, and generating an active power adjustment strategy and a reactive power adjustment strategy; generating a control instruction, performing hierarchical security constraint check on the control instruction, and generating a remote control instruction and a local control instruction; performing hierarchical reinforcement learning control and power optimization adjustment on the inverters in the plurality of control groups to obtain a group total output value; performing real-time monitoring to generate operation parameter data; and calculating the active power qualified rate, the control response time, the control precision and the system volatility, and carrying out multi-target optimization on the adjustment dead zone range, the control gain and the response time constant to obtain a target power distribution scheme. According to the invention, reasonable load distribution of each inverter is ensured, and the operation stability and reliability of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation control, and in particular to an optimization method based on a distributed solar photovoltaic power generation control system. Background Art

[0002] With the rapid development of photovoltaic power generation technology, the proportion of distributed photovoltaic power generation systems in the power system has continued to increase. Traditional distributed photovoltaic power generation control systems mainly rely on single-site independent control and lack group coordinated regulation capabilities, making it difficult to meet the grid's requirements for large-scale distributed photovoltaic grid-connected operation.

[0003] The current photovoltaic power generation control system has safety risks in the process of data collection and transmission, slow system response speed, low control accuracy and other problems. Especially when multiple photovoltaic power stations are operated across regions, the lack of a unified control strategy and safety constraint mechanism can easily cause system instability and affect the safe operation of the power grid. Summary of the invention

[0004] The main purpose of the present invention is to provide an optimization method based on a distributed solar photovoltaic power generation control system, which ensures reasonable load distribution of each inverter and improves the operating stability and reliability of the system.

[0005] To achieve the above object, the present invention provides an optimization method based on a distributed solar photovoltaic power generation control system, comprising the following steps:

[0006] Real-time collection and encrypted transmission of photovoltaic power station operation data to obtain power generation data, voltage data, current data and solar radiation data;

[0007] Inputting the power generation data, voltage data, current data and solar radiation data into a photovoltaic multimodal deep learning prediction model for processing to generate an active power regulation strategy and a reactive power regulation strategy;

[0008] Generate control instructions based on the active power regulation strategy and the reactive power regulation strategy, and perform hierarchical safety constraint verification on the control instructions to generate remote control instructions and local control instructions;

[0009] According to the remote control command and the local control command, hierarchical reinforcement learning control and power optimization adjustment are performed on the inverters in the multiple control groups to obtain the total output value of the group;

[0010] The total output value of the group and the operating status of the equipment are monitored in real time to generate operating parameter data; based on the operating parameter data, the active power qualification rate, control response time, control accuracy and system fluctuation rate are calculated, and the adjustment dead zone range, control gain and response time constant are optimized by multiple objectives to obtain the target power allocation plan.

[0011] The present invention also provides an optimization device based on a distributed solar photovoltaic power generation control system, comprising:

[0012] The acquisition module is used to collect and encrypt the operation data of the photovoltaic power station in real time and transmit it to obtain power generation data, voltage data, current data and solar radiation data;

[0013] A processing module, used for inputting the power generation data, voltage data, current data and solar radiation data into a photovoltaic multimodal deep learning prediction model for processing, and generating an active power regulation strategy and a reactive power regulation strategy;

[0014] A verification module, used to generate control instructions based on the active power regulation strategy and the reactive power regulation strategy, and perform hierarchical safety constraint verification on the control instructions to generate remote control instructions and local control instructions;

[0015] A regulating module, configured to perform hierarchical reinforcement learning control and power optimization regulation on the inverters in the plurality of control groups according to the remote control command and the local control command, so as to obtain a total output value of the group;

[0016] A monitoring module, used to monitor the total output value of the group and the operating status of the equipment in real time and generate operating parameter data;

[0017] The optimization module is used to calculate the active power qualification rate, control response time, control accuracy and system fluctuation rate based on the operating parameter data, and perform multi-objective optimization on the adjustment dead zone range, control gain and response time constant to obtain a target power allocation plan.

[0018] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0019] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0020] In summary, the technical solution provided by the present invention improves the security and reliability of data transmission through multi-layer encrypted transmission and distributed storage technology, and realizes secure storage and efficient access to data; adopts a photovoltaic multimodal deep learning prediction model, combined with a multi-head attention mechanism and a bidirectional LSTM structure, to enhance the system's modeling capability and prediction accuracy for photovoltaic power generation characteristics; based on a hierarchical safety constraint verification mechanism, multi-level security verification of control instructions is achieved, ensuring the safety and reliability of system operation; through hierarchical reinforcement learning control and power optimization adjustment, collaborative control of multiple groups of photovoltaic power stations is achieved, improving the overall control effect of the system; a multi-objective optimization algorithm is introduced to dynamically adjust system parameters, realizing adaptive optimization of system control parameters, and improving the control accuracy and response speed of the system; a power distribution scheme based on a weighted allocation algorithm ensures reasonable load distribution of each inverter and improves the operation stability and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic diagram of the steps of an optimization method based on a distributed solar photovoltaic power generation control system in one embodiment of the present invention;

[0022] Figure 2 It is a structural block diagram of an optimization device based on a distributed solar photovoltaic power generation control system in one embodiment of the present invention;

[0023] Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0024] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0026] Reference Figure 1 This embodiment provides an optimization method based on a distributed solar photovoltaic power generation control system, comprising the following steps:

[0027] S1, real-time collection and encrypted transmission processing of photovoltaic power station operation data to obtain power generation data, voltage data, current data and solar radiation data;

[0028] Among them, the operation data of the inverter is collected by telemetry. This process relies on the high-precision data acquisition module deployed in the system. The real-time operation parameters are obtained through the communication interface of the inverter to form a set of inverter telemetry data, including the real-time startup capacity value, power change rate value, output upper limit value and output lower limit value of the inverter. These data are analyzed in real time by the data calculation module inside the system, especially the active power is calculated, and the inverter power adjustment range is generated by combining the output upper limit value and lower limit value of the inverter. The inverter telemetry data set is input into the SSL security encryption module for private protocol encryption. The encryption process is based on the high requirements for data security and confidentiality in the current industry standards. The data packet is encrypted and processed using an advanced encryption algorithm to generate a first-level encrypted data packet. The first-level encrypted data packet is distributed to the server through the routing management module to realize the directional encrypted transmission of data between different servers. The directional transmission method can ensure the security of data, improve the efficiency and real-time performance of data transmission, and meet the requirements for efficient data transmission in distributed photovoltaic control systems. The encrypted transmission data is input into the cloud platform for secure encryption processing. As a centralized data storage and processing center, the cloud platform encrypts these data vertically and provides a higher level of protection for the first-level encrypted data packets through secondary encryption technology. At the same time, in order to ensure the dynamic security of data transmission, a key dynamic update mechanism is deployed in the cloud platform. The complexity of data encryption is increased by regularly replacing the key to prevent the key from being stolen from outside, and a second-level encrypted data packet with a higher security level is generated. The second-level encrypted data packet is deployed in a distributed manner. Through the efficient distributed storage architecture in the system, the encrypted data is synchronously stored in each data node, thereby ensuring the high availability and security of the data and forming a real-time database storage record, which includes all encrypted power generation data, voltage data, current data and solar radiation data. The real-time database storage records are classified and stored. According to the timestamp and data type identification, the recorded data is finely managed through the data classification module, and the real-time collected data is classified according to different time periods and types to form an orderly data structure and generate historical database backup records. The historical database records are used for data backtracking, trend analysis, fault diagnosis and other functions of the subsequent system. In order to improve the security and isolation of historical data, the historical database is protected by firewall business isolation technology to ensure that the data is not attacked or tampered with by external malicious attacks during storage and transmission. The historical database is security-verified and the integrity and consistency of the data are verified by the verification algorithm to ensure that the stored data will not be lost or erroneous, and ultimately stable and secure power generation data, voltage data, current data and solar radiation data can be generated.

[0029] S2, inputting power generation data, voltage data, current data and solar radiation data into the photovoltaic multimodal deep learning prediction model for processing to generate active power regulation strategy and reactive power regulation strategy;

[0030] Specifically, the power generation, voltage, current and solar radiation data are input into the multi-layer convolution feature extraction layer in the photovoltaic multimodal deep learning prediction model for processing. The multi-layer convolution feature extraction layer consists of 4 convolution modules, each of which contains two convolution layers and a maximum pooling layer. The convolution layer extracts features from the input data through a sliding window and weight sharing mechanism, which can capture the local correlation of photovoltaic power station data in the spatial dimension, while the maximum pooling layer selects key local features through dimensionality reduction processing to obtain the feature vector of power station operation. The power station operation feature vector is input into the bidirectional LSTM timing analysis layer in the photovoltaic multimodal deep learning prediction model for timing processing. The bidirectional LSTM timing analysis layer contains two LSTM layers, each of which consists of 128 hidden units. The design of this layer can effectively capture the timing dependency characteristics of photovoltaic power station data. As a neural network suitable for time series data, LSTM (Long Short-Term Memory Network) can model long-term and short-term dependencies in time series through a gating mechanism. The introduction of a bidirectional structure strengthens the correlation of data in the forward and reverse directions in time, allowing the model to consider both past and future time information and obtain more accurate time series dependency features. The time series dependency features are input into the multi-head attention layer in the photovoltaic multimodal deep learning prediction model for processing. The multi-head attention layer adopts a multi-head self-attention structure, which contains 8 attention heads, and the dimension of each attention head is 64. The multi-head attention mechanism captures the importance and relevance of time series dependency features from different angles by calculating the attention weight matrices of multiple different subspaces in parallel, and generates a feature attention matrix. The feature attention matrix weights the importance of different time steps and feature dimensions in the input data, ensuring that the model can focus on the data features that are most critical to the prediction of power regulation strategies, thereby improving the model's ability to understand and process complex photovoltaic data. The feature attention matrix is ​​input into the power prediction layer in the photovoltaic multimodal deep learning prediction model for power prediction. The power prediction layer consists of three fully connected layers, with 512, 256 and 128 neurons respectively, and uses the ReLU activation function to introduce nonlinear mapping. The fully connected layer reduces the dimension and abstracts the feature attention matrix through layer-by-layer weight transformation to generate a power prediction vector. The power prediction vector is input into the constraint optimization layer in the photovoltaic multimodal deep learning prediction model for processing. The constraint optimization layer adopts a multi-objective optimization algorithm, in which the grid dispatch instruction is set as a hard constraint condition, and the installed capacity change rate is set as a soft constraint condition. By balancing the conflict between hard constraints and soft constraints, the maximum power tracking parameter set that meets the requirements of grid safety and stability is determined to ensure that the system can maintain efficient and stable power output during operation. The maximum power tracking parameter set is input into the inverter parameter optimization layer in the photovoltaic multimodal deep learning prediction model for optimization. The inverter parameter optimization layer contains two fully connected layers and uses the Sigmoid activation function.This layer adjusts and optimizes the various parameters of the inverter through the optimization algorithm, generates the inverter optimization parameter set, and ensures that the inverter can achieve maximum power output within the safety constraint range. The inverter optimization parameter set is input into the strategy generation layer in the photovoltaic multimodal deep learning prediction model for processing. The strategy generation layer adopts a hierarchical reinforcement learning structure, which contains a policy neural network and a value assessment network. Through the reinforcement learning mechanism, the control strategy is dynamically adjusted based on the current grid demand and inverter status to generate the initial control strategy. The introduction of the hierarchical reinforcement learning structure enables the system to make decisions more efficiently in multi-level control tasks, ensuring that the control strategy has high accuracy and stability. The initial control strategy is input into the authority control layer in the photovoltaic multimodal deep learning prediction model for authority allocation and verification. The authority control layer contains a three-level authority verification module, which manages the use of control strategies according to user levels. Management authority users have complete control rights, while maintenance authority and operation authority users can only adjust or view some parameters. After passing the authority verification, the active power regulation strategy and reactive power regulation strategy are generated.

[0031] S3, generating control instructions based on the active power regulation strategy and the reactive power regulation strategy, and performing hierarchical safety constraint verification on the control instructions to generate remote control instructions and local control instructions;

[0032] It should be noted that the dispatching control module is used to generate instructions based on the active power regulation strategy and the reactive power regulation strategy to obtain a set of power generation control instruction sets including the inverter output upper limit value, output lower limit value and regulation rate parameters. Based on the power generation control instruction set, remote control parameter calculation and local control parameter calculation are performed according to different control scenarios, wherein the calculation of the remote control parameters is based on the automatic control target issued by the master station, and the closed-loop control algorithm is used for dynamic adjustment. The power output of the inverter and the set target value are kept within the controllable range through the real-time feedback mechanism, and the remote control benchmark instruction is formed. The calculation of the local control parameters is based on the power generation plan issued in advance by the master station, and the open-loop control algorithm is used for predictive adjustment. Without relying on real-time feedback, the inverter power gradually follows the predetermined power generation plan trajectory to obtain the local control benchmark instruction. The dual mechanism of remote closed-loop control and local open-loop control enables the system to flexibly respond to the grid dispatching requirements and equipment operating conditions in different scenarios. In order to ensure the safety and effectiveness of the control instructions, the remote control benchmark instructions and the local control benchmark instructions are graded for safety constraint verification. In the first stage, equipment fault detection is carried out. By evaluating key indicators such as the inverter's operating status, power supply status, and grounding status, it is determined whether the equipment is in normal working condition and the first-level safety detection result is obtained. If the equipment has a fault, abnormal power supply, or grounding fault, the system will mark the corresponding instruction as a risk state and suspend the execution of the control task to ensure the safety of the equipment. After completing the equipment fault detection, the communication status detection is carried out to ensure the reliability of data transmission by evaluating the communication status and communication delay status between the equipment and the master station. The communication delay status is determined by a preset time threshold. When the communication delay exceeds the threshold, the system will determine that the current communication status is unstable and generate the second-level safety detection result. The purpose of this process is to ensure the timely transmission and feedback of control instructions to avoid inverter misoperation or system instability caused by communication anomalies. After the second-level safety detection is passed, electrical parameter detection is carried out to verify the executableness of the control instruction by real-time evaluating whether the voltage and power values ​​of the inverter are in the safe operating range, and generate the third-level safety detection result. The detection of electrical parameters can prevent equipment damage or grid safety hazards caused by the inverter voltage or power exceeding the allowable range, and ensure the safe execution of control instructions. Based on the third-level safety detection results, control blocking signals are generated, which mainly include power increase blocking signals and power reduction blocking signals, which are used to automatically block the corresponding control functions when safety problems such as equipment failure, communication abnormality or electrical parameter exceeding the limit occur, thereby preventing the spread of risks. These control blocking signals have a higher safety priority, and the system stipulates that they can only be released by manual operation to ensure manual intervention and recovery control of the system in an emergency, ensuring the safety and stability of power station operation.The generated control blocking vector is combined with the remote control reference instruction to form a remote control instruction, and the blocking control vector is combined with the local control reference instruction to form a local control instruction. These two types of control instructions are transmitted to the corresponding inverter equipment through different execution paths, and are executed in an orderly manner according to the current operating status and safety constraints of the system, thereby achieving the real-time active power regulation and reactive power regulation goals of the photovoltaic power station.

[0033] S4, according to the remote control instructions and the local control instructions, hierarchical reinforcement learning control and power optimization adjustment are performed on the inverters in the multiple control groups to obtain the total output value of the group;

[0034] Specifically, the remote control instructions and local control instructions are input into the high-level decision module of the hierarchical reinforcement learning control network for processing. In the high-level decision module, there are policy neural networks and value evaluation networks, where the policy neural network consists of 3 convolutional layers and 2 fully connected layers, and the value evaluation network consists of 2 convolutional layers and 3 fully connected layers. The policy neural network extracts and abstracts the features of the input control instructions, and combines the value evaluation network to quantitatively analyze the current control state. The system can generate a set of optimal group control action sets in a high-dimensional space. The group control action set is encoded for control state, each control group is encoded as an independent control unit, and detailed state information is attached to each unit, including group identification, number of inverters, total installed capacity, and current power output and other real-time parameters. The encoded control state information is integrated into a group control state vector through the system's data integration module for subsequent control decisions and state evaluation. The group control state vector is input into the execution control module, and the execution effect of the control strategy is evaluated by defining a precise reward calculation function. In the reward calculation process, three key evaluation indicators, namely power tracking deviation, regulation response time and system stability, are comprehensively considered to calculate the group control reward value. Among them, the power tracking deviation is evaluated by calculating the difference between the actual power of the group and the target power, the regulation response time is measured by recording the time required for the system to complete the regulation task, and the system stability is comprehensively evaluated based on the power fluctuation amplitude and frequency during the inverter regulation process. This process enables the system to quantitatively evaluate the execution effect of the current control state and provide feedback for the subsequent update of reinforcement learning. Based on the group control reward value, the deep Q learning algorithm is used to optimize and update the group control state vector. In this process, the experience replay buffer and target network mechanism are introduced. By storing past control experience and calculating the target Q value in the current state, the optimal control strategy is iteratively updated in combination with the time difference algorithm, and the optimal control action in the current state is calculated. The introduction of the deep Q learning algorithm effectively improves the learning efficiency and decision-making accuracy of the system, enabling the system to continuously optimize the control strategy in a dynamic environment and achieve accurate power regulation of the inverter group. The updated optimal control action is input into the power distribution module. According to the operating status and capacity parameters of each inverter, the power is accurately distributed through the weighted distribution algorithm to calculate the target power command of each inverter. The power distribution algorithm achieves the optimal power distribution through weight adjustment under the premise of considering the real-time operating status, installed capacity and equipment load capacity of each inverter, ensuring that the power output of the entire group meets the target power demand without causing load overload to individual inverters. The inverter power command is executed and verified through the power regulation judgment mechanism. When the system detects that the deviation between the total power of the group and the target power exceeds the preset safety interval, the regulation control mechanism is immediately triggered to generate a power regulation trigger signal.Based on the trigger signal, the active power and reactive power of each inverter are optimized in a coordinated manner. The optimization algorithm ensures that the grid's demand for reactive power is met while regulating active power, maintaining voltage stability and system security. In this process, the real-time power output data of the inverter is continuously monitored, and the real-time power data of all inverters is weighted and summed to finally obtain the total output value of the entire control group.

[0035] The optimal control action is transmitted as input data to the data processing unit of the power distribution module. In the data processing unit, the system performs a strategy analysis on the optimal control action, and obtains the power target vector of the entire group through analysis, which reflects the target power level that each photovoltaic group needs to achieve at a specific time. The group power target vector is divided into groups. Based on the geographic location data and electrical connection relationship of the inverter, the inverter is reasonably calibrated for the group through the distributed power grid topology analysis and the network communication configuration between sites, and the group configuration data is generated. This process ensures that the inverter has clear grouping information in terms of spatial layout and power physical connection relationship, so that accurate power regulation control can be achieved within the group, while reducing power coupling and unnecessary system interference between groups. Based on the group configuration data, the installed capacity of each inverter is normalized, and the capacity normalization coefficient is generated by proportionally normalizing the actual installed capacity of each inverter. In order to adapt to the dynamic changes in the operating status of the inverter, the capacity normalization coefficient is dynamically corrected, and the real-time weight adjustment is performed in combination with the communication delay and device status indicators of the inverter to calculate the dynamic adjustment coefficient. The communication delay reflects the delay of data transmission between the inverter and the control system, while the equipment status indicators include parameters such as the real-time operating temperature, output efficiency and fault status of the inverter. Through the comprehensive evaluation of these indicators, different inverters are given weight values ​​that adapt to the current operating status, making power allocation more accurate and efficient. The dynamic adjustment coefficient and the group power target vector are matrix-operated, and the overall power target is reasonably allocated to each inverter in the group through matrix calculation to generate a set of initial power allocation values. In order to ensure the safety and stability of inverter operation, the initial power allocation value is limited. By introducing the power adjustment range of the inverter (including the upper and lower output limits) for constraint calculation, it is ensured that the output power of each inverter is always kept within the safe range, and a set of power limit control values ​​is obtained. Based on the power limit control value, the power change rate is optimized. By adjusting the control algorithm, it is ensured that the power adjustment rate of the inverter meets the dynamic requirements of the power grid operation, and the power grid oscillation or system instability caused by too fast power changes is avoided. This optimization process generates a set of optimized control values ​​by smoothing the power adjustment rate and limiting the power change slope. On this basis, the optimized control value is converted into a command according to the communication protocol supported by each inverter, and the standardized control data is converted into a command format that meets the communication interface requirements of each inverter, ensuring that the command can be accurately recognized and executed by the inverter to obtain the inverter power command.

[0036] S5, real-time monitoring of the total output value of the group and the operating status of the equipment, and generation of operating parameter data;

[0037] Among them, data acquisition modules are deployed at each inverter and group level. These modules are connected to the control interface of the inverter through a high-speed communication network, and can obtain the operating status parameters of the inverter in real time, including key indicators such as real-time power output, voltage, current, temperature, equipment fault status and communication status. These data are transmitted to the centralized monitoring server through communication methods such as fieldbus or Ethernet. Security measures such as SSL encryption and private protocols are adopted during the transmission process to ensure the integrity and confidentiality of the data. On the centralized monitoring server, a high-performance data processing unit is deployed to parse and store the received real-time data. The data processing unit preprocesses the original data, including data format conversion, outlier filtering and time synchronization operations to ensure the accuracy and consistency of the data. The preprocessed data is stored in the real-time database, and some key data is stored in the memory database as needed to improve the data access speed and system response performance. In order to support the query and analysis of historical data, the real-time data is regularly archived in the historical database, and the data is compressed and backed up to ensure the long-term availability and security of the data. The total output value of the group and the operating status of the equipment are calculated and monitored in real time. By weighted summing the real-time power output of each inverter, the total output value of each group is obtained, and compared with the preset target power, the power deviation and adjustment requirements are calculated. Monitor the operating status of each inverter, including the operating mode of the equipment (such as standby, operation, fault), communication status (online, offline, delay) and key operating parameters (such as temperature, voltage, current, etc.). The monitoring interface uses visualization technology to display the total output value of the group, the operating status of the equipment and the key operating parameters in a graphical way. For example, a real-time curve chart is used to show the changing trend of the total output value of the group, a bar chart or pie chart is used to show the power contribution ratio of each inverter, and color coding or icons are used to indicate the operating status and fault information of the equipment. The interface supports alarm and notification functions. When the equipment fails or the operating parameters exceed the preset threshold, the system can send alarm information to the operation and maintenance personnel in time to help them quickly locate and handle the problem. In order to improve the real-time and reliability of the system, the monitoring system needs to have high concurrent processing capabilities and fault tolerance capabilities. At the software level, a distributed architecture and multi-threading technology are used to ensure that the system can handle a large amount of device data and user requests at the same time. At the hardware level, high-performance servers and network equipment are deployed, and load balancing and redundant backup technologies are used to prevent single point failures from affecting the system. At the same time, the system needs to have good scalability and be able to flexibly increase computing and storage resources according to the expansion of the scale of photovoltaic power plants and the increase in the number of equipment to maintain stable system performance. In order to ensure data security and compliance, the system needs to comply with relevant national standards and industry specifications. In the process of data transmission and storage, encryption and authentication mechanisms are used to prevent unauthorized access and data leakage.In terms of data storage and processing, the principle of data minimization is followed, only necessary operating parameter data is collected and stored, and unnecessary data is cleaned up regularly. In terms of logs and audits, the user's operating behavior and the system's operating status are recorded to support post-audit and responsibility tracing. In order to meet the needs of different users, the system needs to support multi-level permission management and personalized customization. Through the permission control module, the system grants different access rights and operation rights according to the user's role and responsibilities. For example, managers view all operating parameter data and historical records, and perform system configuration and maintenance; operation and maintenance personnel view the equipment status and alarm information in the area they are responsible for, and perform remote control operations on the equipment; ordinary users can only view public operating data and basic information.

[0038] S6, based on the operating parameter data, calculates the active power qualification rate, control response time, control accuracy and system fluctuation rate, and performs multi-objective optimization on the adjustment dead zone range, control gain and response time constant to obtain the target power allocation plan.

[0039] Specifically, the operating parameter data collected by the system in real time include the real-time output power of the inverter, the operating status of the equipment, the execution feedback of the control instructions, and the communication data between the power grid dispatching system. After these data enter the data processing module through the high-speed data transmission channel, the power deviation is calculated. By comparing the real-time power value with the control target value, the difference between the two is calculated point by point to generate the power tracking error data. Based on the power tracking error data, the statistical analysis of the active power qualification rate is performed. By screening and evaluating the time series of the power error data, the proportion of the time when the active power is within the allowable deviation range is calculated to obtain the active power qualification rate. At the same time, the timing response analysis of the operating parameter data is performed, specifically including the time difference between the issuance of the control instruction and the completion of the equipment execution. By monitoring the timestamps of the control instruction and the feedback data, the control response time is accurately calculated. These two indicators jointly reflect the control accuracy and execution efficiency of the system. The active power qualification rate and the control response time are input into the multi-objective genetic optimizer. As a global search algorithm, the genetic optimizer optimizes the parameters through the non-dominated sorting genetic algorithm. In the iterative process of the genetic algorithm, the Pareto optimal solution boundary is continuously approached through the steps of initializing the population, calculating fitness, non-dominated sorting, crossover mutation and selection operations, and a set of Pareto optimal solution sets that meet multi-objective constraints are generated, including the optimal combination of different adjustment dead zone ranges, control gains and response time constants, and fully weighing the mutual influence between control accuracy, response time and system stability. Based on the Pareto optimal solution set, the adjustment dead zone range is optimized. By analyzing the system power fluctuation rate and adjustment stability corresponding to different solutions, a dead zone optimization vector that best suits the current system operation state is determined. This optimization vector effectively reduces the invalid adjustment interval of the control system, thereby improving the control sensitivity and adjustment accuracy. The PID controller is optimized using the optimized dead zone vector. The optimization process of the PID controller includes the calculation of the optimal control gain and response time constant. By integrating and differentiating the error signal, the PID parameters (proportional gain P, integral time constant I, differential time constant D) are adjusted in combination with the genetic algorithm, so that the system achieves the best balance between power response time and stability, and a set of optimized controller parameter vectors are obtained. According to the capacity ratio of each inverter, the optimized controller parameter vector is allocated, and each control parameter is weighted according to the installed capacity, current operating status and response capability of the inverter, so that each inverter can output the most appropriate power adjustment instruction according to its own characteristics, thereby generating the target power allocation plan for the overall system.

[0040] In one example, the operation data of a photovoltaic power station is collected and encrypted for transmission in real time to obtain power generation data, voltage data, current data, and solar radiation data, including:

[0041] Perform telemetry collection on the inverter operation data to obtain the inverter telemetry data set, which includes the real-time startup capacity value, power change rate value, output upper limit value and output lower limit value of the inverter, and perform active power calculation to obtain the inverter power adjustment range;

[0042] Input the inverter telemetry data set into the SSL security encryption module for private protocol encryption to obtain the first-level encrypted data packet, and perform directional server routing assignment on the first-level encrypted data packet to obtain encrypted transmission data;

[0043] Input the encrypted transmission data into the cloud platform for vertical encryption and dynamic key update to obtain the second-level encrypted data package, and distribute the second-level encrypted data package to obtain real-time database storage records;

[0044] The real-time database storage records are classified and stored according to data type and timestamp to obtain historical database backup records, and the historical database backup records are firewall-isolated and security-verified to obtain power generation data, voltage data, current data and solar radiation data.

[0045] In this example, a real-time data collection module is deployed at the inverter level to collect the inverter's operating data set, including the real-time startup capacity C, through a remote terminal unit or smart sensor. inv , power change rate R power , output upper limit value P max And the output lower limit P min For the calculation of active power, the real-time voltage V output by the inverter is used. inv , output current I inv And the power factor cos(θ) is calculated in real time. The specific formula is:

[0046] P act =V inv I inv cos(θ);

[0047] Among them, P act Indicates real-time active power in kW, V inv is the output voltage (V), I inv is the output current (A), and cos(θ) is the power factor, which is usually close to 1 when the inverter is operating normally. act , the system calculates the power regulation interval P of the inverter range , whose range is expressed by the following formula:

[0048] P range =[P min ,P max ] Among them, Padj =P max -P act ;

[0049] Where P adj is the remaining adjustable power, which is used to indicate the current output margin of the inverter. inv ={C inv ,R power ,P act ,P max ,P min} is transmitted as input to the SSL security encryption module and encrypted using the Advanced Encryption Standard. The specific encryption process is described as follows:

[0050] E 1 =Encrypt(D inv ,K priv );

[0051] Among them, E 1 is the first level encrypted data packet, D inv is the inverter telemetry data set, K priv It is the static encryption key of the private protocol. 1 Data packets are transmitted through directional server routing distribution technology. This process ensures that data is distributed along the optimal path based on the network topology and the location of the target server, thereby achieving secure data transmission. The transmission path is defined as:

[0052] R path =Route(E 1 ,S target );

[0053] Where R path is the transmission path of the data packet, S target is the target server address. The encrypted data E after routing distribution 1 Upload to the cloud platform, where the data is encrypted vertically. By introducing a dynamic key update mechanism, it is ensured that the key will not be reused. The vertical encryption formula is:

[0054] E 2 =Encrypt(E 1 ,K dyn );

[0055] Where E 2 is the second level encrypted data packet, K dyn It is a dynamic key, which is automatically updated every period T. The cloud platform will encrypt the data packet E 2The data is stored in the real-time database through a distributed deployment mechanism to achieve high availability and redundant backup of the data. After the data is stored in the real-time database, it is classified and stored according to the data type and timestamp. The specific classification formula is as follows:

[0056] D class ={D t ∣t∈[t 0 ,t n ],Type(D)};

[0057] Where D class is a collection of classified and stored data, D t Indicates the data record at a specific time t, and Type (D) indicates the type of data, such as power generation, voltage, current, solar radiation, etc. The classified data is archived to the historical database and subjected to security verification. The verification process is implemented through a hash function, and the formula is as follows:

[0058] H=Hash(D class );

[0059] Where H is the data hash value generated by the checksum, which is used to verify the integrity and tamper-proof of the data. During the storage process, the historical database is protected by the firewall business isolation mechanism to ensure that the data will not be subject to unauthorized access or malicious attacks. gen , voltage data V inv , current data I inv and solar radiation data S rad Historical database records.

[0060] In one example, power generation data, voltage data, current data, and solar radiation data are input into a photovoltaic multimodal deep learning prediction model for processing to generate an active power regulation strategy and a reactive power regulation strategy, including:

[0061] The power generation data, voltage data, current data and solar radiation data are input into the multi-layer convolution feature extraction layer in the photovoltaic multimodal deep learning prediction model for processing. The multi-layer convolution feature extraction layer contains 4 convolution modules, each of which consists of two convolution layers and a maximum pooling layer to obtain the power station operation feature vector;

[0062] The power station operation feature vector is input into the bidirectional LSTM time series analysis layer in the photovoltaic multimodal deep learning prediction model for processing. The bidirectional LSTM time series analysis layer contains two LSTM layers, each of which contains 128 hidden units, to obtain the time series dependency features.

[0063] The time-dependent features are input into the multi-head attention layer in the photovoltaic multimodal deep learning prediction model for processing. The multi-head attention layer adopts a multi-head self-attention structure, including 8 attention heads, and the dimension of each attention head is 64, and the feature attention matrix is ​​obtained;

[0064] The feature attention matrix is ​​input into the power prediction layer in the photovoltaic multimodal deep learning prediction model for processing. The power prediction layer contains three fully connected layers with 512, 256, and 128 neurons respectively. The ReLU activation function is used to obtain the power prediction vector.

[0065] The power prediction vector is input into the constraint optimization layer in the photovoltaic multimodal deep learning prediction model for processing. The constraint optimization layer adopts a multi-objective optimization algorithm, sets the grid dispatch instruction as a hard constraint condition, and the installed capacity change rate as a soft constraint condition, and obtains the maximum power tracking parameter set;

[0066] The maximum power tracking parameter set is input into the inverter parameter optimization layer in the photovoltaic multimodal deep learning prediction model for processing. The parameter optimization layer includes two fully connected layers and uses the Sigmoid activation function to obtain the inverter optimization parameter set.

[0067] The inverter optimization parameter set is input into the strategy generation layer in the photovoltaic multimodal deep learning prediction model for processing. The strategy generation layer adopts a hierarchical reinforcement learning structure, including a strategy neural network and a value evaluation network, to obtain the initial control strategy.

[0068] The initial control strategy is input into the authority control layer in the photovoltaic multimodal deep learning prediction model for processing. The authority control layer contains a three-level authority verification module, which allocates control authority according to user level to obtain active power regulation strategy and reactive power regulation strategy.

[0069] In this example, an end-to-end photovoltaic prediction system is constructed, in which the data input layer includes a set of photovoltaic power station operation data collected in real time, including the power generation P gen , voltage V inv 、Current I inv and solar radiation data S rad These data are normalized and mapped to the standardized range required for model training. The normalization formula is:

[0070]

[0071] Where X norm is the normalized data, X is the original input data, and X min and X max are the minimum and maximum values ​​of the data respectively. The normalized input data is used as the input vector X input = {Pgen ,V inv ,I inv ,S rad} is input into the multi-layer convolution feature extraction layer in the photovoltaic multimodal deep learning prediction model for processing. In the feature extraction stage, four convolution modules are set in the model, each of which consists of two convolution layers and a maximum pooling layer. For the i-th convolution layer, the input data is extracted through f convolution kernels, and the calculation formula of the output feature map is:

[0072]

[0073] in is the output feature map of the lth layer, is the weight matrix of the i-th convolution kernel, * represents the convolution operation, is the bias term and σ is the activation function (such as ReLU). After the convolution operation, the dimension is reduced by the maximum pooling operation. The formula for the maximum pooling is:

[0074]

[0075] Where P i represents the feature map after pooling, and k×k is the pooling window size. After layer-by-layer processing by four convolutional modules, the high-dimensional feature vector F of the power station operation is obtained. conv . conv The input is processed by the bidirectional LSTM time series analysis layer in the photovoltaic multimodal deep learning prediction model. The bidirectional LSTM consists of two LSTM layers, each of which contains 128 hidden units. For each time step t, the LSTM passes the input vector x t and the hidden state h t-1 Calculate the current hidden state h t and output o t , the specific calculation is as follows:

[0076] f t =σ(W f ·[h t-1 ,x t ]+b f ),i t =σ(W i ·[h t-1 ,x t ]+b i );

[0077]

[0078] o t =σ(W o ·[h t-1 ,x t]+b o ),h t =o t ⊙tanh(C t );

[0079] where f t 、i t , o t are the weights of the forget gate, input gate, and output gate, respectively. t is the cell state, h t is the hidden state, W and b are the weight matrix and bias vector respectively. Through the bidirectional LSTM structure, the forward and reverse dependencies of the time series data are captured to generate the time series dependency feature vector F lstm . lstm Input to the multi-head attention layer. The multi-head attention mechanism contains 8 attention heads, each with a dimension of 64. The attention weight matrix A of the input feature is calculated through the self-attention mechanism. The formula is:

[0080]

[0081] where Q, K, and V are query, key, and value matrices respectively, and d k is the dimension of the key vector, A is the attention score matrix, and the feature attention matrix F is obtained by weighted calculation attn . attn The power prediction layer contains three fully connected layers with 512, 256 and 128 neurons respectively. The ReLU activation function is used for nonlinear transformation and the power prediction vector P is output. pred For the jth layer, the calculation formula of the fully connected layer is:

[0082] H j =ReLU(W j ·H j-1 +b j );

[0083] Where W j is the weight matrix, b j is the bias vector, H j is the output vector of the current layer. pred Input to the constraint optimization layer, the constraint optimization layer adopts a multi-objective optimization algorithm to grid As a hard constraint, the inverter installed capacity change rate R inv is a soft constraint and is solved by the following objective function:

[0084] minJ=∥P pred -P grid ∥ 2 +λ·R inv;

[0085] Where λ is the trade-off coefficient, J is the objective function, and the optimized maximum power tracking parameter set P mppt As output. mppt Input the inverter parameter optimization layer, which contains two fully connected layers. The Sigmoid activation function is used for nonlinear mapping to obtain the inverter optimization parameter set P. opt Then P opt Input strategy generation layer, the strategy generation layer adopts hierarchical reinforcement learning structure, in which the strategy neural network generates control strategy, the value evaluation network evaluates the strategy, and generates the initial control strategy π through the optimal value function Q(s,a) init . init Input permission control layer, which contains three-level permission verification module, assigns control permissions by verifying user level, and outputs the final active power regulation strategy P ctrl And reactive power regulation strategy Q ctrl .

[0086] In one example, a control instruction is generated based on an active power regulation strategy and a reactive power regulation strategy, and a hierarchical safety constraint check is performed on the control instruction to generate a remote control instruction and a local control instruction, including:

[0087] Based on the active power regulation strategy and the reactive power regulation strategy, command generation processing is performed to obtain a power generation control command set, where the power generation control command set includes an inverter output upper limit value, an output lower limit value and a regulation rate parameter;

[0088] Calculate the remote control parameters of the power generation control instruction set, and use the closed-loop control algorithm to calculate the automatic control target issued by the master station to obtain the remote control benchmark instruction;

[0089] Calculate the local control parameters of the power generation control instruction set, and use the open-loop control algorithm to calculate based on the power generation plan issued by the master station to obtain the local control benchmark instruction;

[0090] Perform equipment fault detection on remote control benchmark instructions and local control benchmark instructions, and obtain the first-level safety detection results by evaluating the inverter operation status, power supply status and grounding status;

[0091] Perform communication status detection on the first-level security detection result, and obtain the second-level security detection result by evaluating the communication status and communication delay status of the device. The communication delay status is determined by the preset time threshold.

[0092] Conduct electrical parameter testing on the second-level safety test results, and obtain the third-level safety test results by evaluating whether the inverter voltage and power values ​​are within the safe range;

[0093] Based on the third-level safety detection result, a control blocking signal is calculated, the control blocking signal includes a power increase blocking signal and a power decrease blocking signal, and the control blocking signal is released only by manual operation to obtain a blocking control vector;

[0094] The locking control vector is combined with the remote control reference instruction to generate the remote control instruction, and the locking control vector is combined with the local control reference instruction to generate the local control instruction.

[0095] In this example, the generated active power regulation strategy P is generated according to the real-time dispatching requirements of the power grid and the operating status of the photovoltaic power station. ctrl And reactive power regulation strategy Q ctrl Decompose to form a power generation control instruction set, which includes the inverter output upper limit value P max , output lower limit P min and the adjustment rate parameter R adj The output upper and lower limits are calculated using the following formula:

[0096] P max =min(C inv ,P grid ),P min =max(0,P act -R adj ·T);

[0097] Among them, C inv is the current installed capacity of the inverter, P grid is the maximum power allowed by the grid dispatch, P act is the current active power, R adj Represents the power regulation rate, and T is the time interval. Through the above formula, the system ensures that the inverter power output meets the grid dispatching requirements and the equipment safe operation conditions. The remote control parameter calculation of the power generation control instruction set is carried out. This stage uses a closed-loop control algorithm for processing. The goal is to make the inverter power output follow the automatic control target P issued by the master station in real time. target The closed-loop control is realized by the PID controller, and the control error calculation formula is:

[0098] e(t)=P target -P act ;

[0099] Where e(t) is the power error at the current moment. The output u(t) of the PID closed-loop controller is calculated by the following formula:

[0100]

[0101] Where K p , Ki and K d are proportional, integral and differential gain coefficients respectively. The system generates a remote control reference instruction P through the adjustment output of the PID controller. ref,remote , thus achieving real-time closed-loop tracking of active power. At the same time, the local control parameter calculation of the power generation control instruction set is performed. This process is based on the power generation plan P issued by the master station. plan , using open-loop control algorithm for processing. Open-loop control does not require real-time feedback, and directly calculates the target power according to the power generation plan curve, and controls the benchmark instruction P ref,local It is expressed as:

[0102] P ref,local =P plan (t);

[0103] Where P plan (t) is the target value of the power generation plan at time t. Through closed-loop and open-loop control algorithms, remote control benchmark instructions and local control benchmark instructions are generated. In order to ensure the safety and reliability of the control instructions, equipment fault detection is performed on the remote control benchmark instructions and the local control benchmark instructions. By real-time monitoring of the inverter's operating status S inv , power supply status S power and ground state S ground , to determine whether the equipment is in normal operating conditions, the first-level safety test results are defined by the following logical conditions:

[0104] S safe,1 =(S inv ∧S power ∧S ground );

[0105] If S safe,1 = True, the device fault detection passes, otherwise the device is marked abnormal. After passing the device fault detection, the communication status detection is performed. By detecting the device communication status S comm and communication delay T delay To determine whether the communication is normal, the communication delay determination formula is:

[0106] S safe,2 =(S comm ∧T delay <T thresh );

[0107] Where T thresh is the threshold of communication delay. If the communication delay exceeds the threshold, the system will mark the communication status as abnormal. After the communication status is detected, the electrical parameters are tested to evaluate the inverter voltage V inv and power P act Whether it is within the safe range, the detection conditions are:

[0108] S safe,3 =(V min ≤V inv ≤V max )∧(P min ≤P act ≤P nax );

[0109] Where V min and V max After equipment fault detection, communication status detection and electrical parameter detection, a control blocking signal is generated, including a power increase blocking signal S lock,+ and power reduction lock signal S lock,- These signals can only be released by manual operation, and finally form the locking control vector S lock . The locking control vector and the remote control reference command P ref,remote Combine to generate the final remote control command P final,remote :

[0110] P final,remote =P ref,remote ·S lock ;

[0111] At the same time, the locking control vector and the local control reference instruction P ref,local Combine to generate the final local control instruction P final,local :

[0112] P final,local =P ref,local ·S lock .

[0113] In one example, hierarchical reinforcement learning control and power optimization adjustment are performed on the inverters in multiple control groups according to remote control instructions and local control instructions to obtain the total output value of the group, including:

[0114] The remote control instructions and local control instructions are input into the high-level decision module of the hierarchical reinforcement learning control network for processing. The high-level decision module includes a policy neural network and a value evaluation network. The policy neural network includes 3 convolutional layers and 2 fully connected layers, and the value evaluation network includes 2 convolutional layers and 3 fully connected layers to obtain a group control action set.

[0115] The control state of the group control action set is encoded, and each control group is encoded as a control unit, including the group identification, the number of inverters, the total installed capacity, and the current power output status information to obtain the group control state vector;

[0116] The group control state vector is input into the execution control module for reward calculation. The reward calculation includes three evaluation indicators: power tracking deviation, regulation response time, and system stability, and the group control reward value is obtained;

[0117] Based on the group control reward value, the group control state vector is updated by deep Q learning. The target Q value is calculated by the temporal difference algorithm using the experience replay buffer and target network mechanism to obtain the optimal control action.

[0118] The optimal control action is input into the power distribution module for group power regulation. According to the operating status and capacity parameters of each inverter, a weighted distribution algorithm is used to calculate the target power of each inverter to obtain the inverter power instruction;

[0119] Perform power regulation judgment on the inverter power command, and trigger regulation control when the deviation between the total power of the group and the target power exceeds the preset range to obtain a power regulation trigger signal;

[0120] Based on the power regulation trigger signal, the active power and reactive power of each inverter are collaboratively optimized to obtain the real-time power data of the inverter, and the real-time power data of the inverter is weighted and summed to obtain the total output value of the group.

[0121] In this example, the remote control command P remote And local control command P local As input, it is passed into the high-level decision module of the hierarchical reinforcement learning control network. This module contains a policy neural network and a value assessment network. The policy neural network extracts policy-related decision information from the input features. Its network structure includes 3 convolutional layers and 2 fully connected layers. The output feature map of the lth convolutional layer Calculated by the following formula:

[0122]

[0123] in is the weight matrix of the i-th convolution kernel, is the corresponding bias, * represents the convolution operation, and σ is the ReLU activation function. After extracting the deep features through the stacking of multiple layers of convolution, it enters the fully connected layer and obtains the output vector through linear transformation:

[0124] Z policy =σ(W fc ·F conv +b fc );

[0125] Where W fc and b fc are the weights and biases of the fully connected layer, Z policyis the output vector of the policy network. At the same time, the value evaluation network is used to evaluate the value of the current policy. Its structure contains 2 convolutional layers and 3 fully connected layers. The value function V(s) of the current state is calculated through convolution and linear transformation. The specific formula is:

[0126] V(s)=W value ·F value +b value ;

[0127] Among them, F value is the convolution output of the value network, and V(s) represents the value evaluation result under the current state s. The output of the policy network and the value network jointly determine the group control action set A group , where A group The control state of the group control action set is encoded, and each control group is encoded as an independent control unit. The characteristics of the control unit include the group identifier G id 、Number of inverters inv 、Total installed capacity C total and the current power output state P current , these features are combined into the group control state vector S group :

[0128] S group = {G id ,N inv ,C total ,P current};

[0129] S group Input execution control module to calculate reward, which includes three indicators: power tracking deviation e(t), adjustment response time T response and system stability S stability The power tracking deviation is calculated by the following formula:

[0130] e(t)=P target -P current ;

[0131] Where P target is the target power, P current is the current power output. The reward function R is defined as:

[0132] R=-α|e(t)|-βT response +γS stability ;

[0133] Among them, α, β, γ are weight coefficients, S stability Represents the inverse value of the system power fluctuation, which is used to measure the stability of the system. Based on the group control reward value R, the group control state vector Sgroup Perform deep Q learning updates, store historical states and rewards through the experience replay buffer, and use the temporal difference (TD) algorithm to calculate the target Q value Q in combination with the target network mechanism target :

[0134]

[0135] Where r is the current reward, γ is the discount factor, Q(s ′ ,a ′ ) is the next state s ′ Take action a ′ The Q value of target -Q(s,a) 2 , the system updates the parameters θ of the Q network and obtains the optimal control action A opt The optimal control action is input into the power distribution module, and the system inv and installed capacity C inv , the weighted allocation algorithm is used to calculate the target power P of each inverter inv , the formula is as follows:

[0136]

[0137] Among them C inv,i is the installed capacity of the i-th inverter, P group is the target power of the group, and N is the number of inverters. The calculated inverter power command is used to make power adjustment decisions, and the total power P of the group is determined by total With the target power P target The deviation e, when |e|>ΔP thresh When the regulation control is triggered, the power regulation trigger signal S is generated trigger Based on the adjustment trigger signal, the active power and reactive power of each inverter are optimized in a coordinated manner, and the power output P is calculated in real time through the optimization control algorithm. opt,i and reactive power Q opt,i , and finally the total output value P of the group is obtained by real-time summation total :

[0138]

[0139] In one example, the optimal control action is input into the power distribution module for group power regulation. According to the operating status and capacity parameters of each inverter, a weighted distribution algorithm is used to calculate the target power of each inverter to obtain the inverter power instruction, including:

[0140] The optimal control action is input into the data processing unit of the power allocation module for strategy analysis to obtain the group power target vector;

[0141] The group power target vectors are divided into groups, and the inverters are grouped and calibrated based on the geographic location data and the electrical connection relationship to obtain the group configuration data;

[0142] Performing normalization calculation on the installed capacity of each inverter based on the group configuration data to obtain a capacity normalization coefficient;

[0143] Dynamically correct the capacity normalization coefficient, adjust the weight according to the inverter's communication delay and equipment status indicators, and obtain the dynamic adjustment coefficient;

[0144] The dynamic adjustment coefficient and the group power target vector are matrix operated to obtain the initial power allocation value of each inverter, and the initial power allocation value is limited. Constraint calculation is performed according to the inverter power adjustment range to obtain the power limit control value;

[0145] The power change rate is optimized based on the power limit control value to ensure that the power regulation rate meets the grid operation requirements, and the optimized control value is obtained. The optimized control value is converted into an instruction according to the communication protocol of each inverter to obtain the inverter power instruction.

[0146] In this example, the optimal control action A calculated by the upper decision network or reinforcement learning module is opt As the data processing unit of the input power allocation module, this module maps and transforms the input action through strategy analysis and converts the optimal control action A opt Decomposed into group power target vector P group , which is expressed as:

[0147] P group,i =A opt ·W group,i ;

[0148] Among them, P group,i is the target power of the i-th group, W group,i is the corresponding group weight coefficient, and the weight is assigned based on the group priority or total installed capacity. Through this analytical process, the power target vector P of all groups is obtained group = {P group,1 ,P group,2 ,…,P group,n}. For the group power target vector P group Divide groups based on geographic location data geo And electrical connection relationship R elec All inverters are logically grouped and calibrated to form group configuration data. The specific rules for group calibration are as follows:

[0149] G k = {Ij ∣L geo,j ∈L k ∧R elec,j ∈R k};

[0150] Among them, G k represents the kth group, I j represents the jth inverter, L k and R k are the geographical location area and electrical connection area of ​​the kth group respectively. Through this process, the group configuration data G = {G 1 ,G 2 ,…,G k}. Based on the group configuration data, the installed capacity C of each inverter inv,j Perform normalization to eliminate the differences in capacity between different inverters and calculate the normalization coefficient α j , the formula is:

[0151]

[0152] Among them, α j is the normalization coefficient of the jth inverter, C inv,i is the installed capacity of the jth inverter, and N is the number of inverters in the group. The normalization process maps the installed capacity of all inverters to a unified proportional interval to facilitate subsequent power allocation calculations. j Perform dynamic correction, combined with the inverter communication delay T comm,j and equipment status indicator S inv,j Calculate the dynamic adjustment coefficient β j The dynamic correction formula is:

[0153]

[0154] Among them, ω is the delay impact factor, T comm,j is the communication delay of the jth inverter, S inv,j is the equipment status coefficient. When the equipment is normal, S inv,j =1, when fault occurs S inv,j = 0. Dynamic adjustment coefficient β j Based on the communication delay and device status, the power allocation is dynamically modified. The dynamic adjustment coefficient β j and the group power target vector P group Perform matrix operations to obtain the initial power allocation value P of each inverter init,j , the calculation formula is:

[0155] P init,j =β j·P group,k ,I j ∈G k ;

[0156] Among them, P init,j is the initial power allocation value of the jth inverter, P group,k For group G k The initial power allocation value is limited, combined with the power adjustment range of the inverter [P min,j ,P max,j ] to constrain the limit control value P lim,j The calculation formula is:

[0157] P lim,j =min(P max,j ,max(P min,j ,P init,j ));

[0158] Among them, P lim,j is the power allocation value after limiting, ensuring that the allocation result meets the safe operation constraints of the inverter. lim,j , optimize the power change rate to ensure the power regulation rate R adj,j To meet the grid operation requirements, the calculation formula is:

[0159] P opt,j =P prev,j +sgn(P lim,j -P prev,j )·min(R adj,j ·Δt,|P lim,j -P prev,j |);

[0160] Among them, P opt,j is the optimized power allocation value, P prev,j is the power value of the previous step, Δt is the time step, sgn is the sign function, R adj,j is the maximum power regulation rate. The optimized power allocation value P opt,j The command conversion is performed according to the communication protocol of each inverter to generate the inverter power command P cmd,j , and sends it to the corresponding inverter for execution, thereby achieving accurate adjustment of the power of each inverter.

[0161] In one example, the active power qualification rate, control response time, control accuracy and system fluctuation rate are calculated based on the operating parameter data, and the adjustment dead zone range, control gain and response time constant are optimized by multiple objectives to obtain the target power allocation scheme, including:

[0162] Power deviation is calculated based on the operating parameter data, and power tracking error data is obtained by comparing the real-time power value with the control target value;

[0163] Based on the power tracking error data, the pass rate statistics are carried out to obtain the active power pass rate, and the timing response analysis is carried out on the operating parameter data to calculate the control instruction execution completion time and obtain the control response time;

[0164] The active power qualification rate and control response time are input into the multi-objective genetic optimizer, and the non-dominated sorting genetic algorithm is used to optimize the parameters to obtain the Pareto optimal solution set.

[0165] Based on the Pareto optimal solution set, the parameters of the adjustment dead zone range are optimized to obtain the dead zone optimization vector;

[0166] The PID controller is optimized for the dead zone optimization vector, the optimal control gain and response time constant are calculated, and the controller parameter vector is obtained. The controller parameter vector is allocated according to the inverter capacity ratio to obtain the target power allocation scheme.

[0167] In this example, the operating parameter data including the real-time power value P is obtained from the real-time monitoring system of the inverter. real (t) and control target value P target (t), and the power tracking error e(t) is calculated by the difference between the two. The calculation formula of the power tracking error data is as follows:

[0168] e(t)=P target (t)-P real (t);

[0169] Where e(t) represents the power error at time t, P target (t) is the target power set by the dispatching system, P real (t) is the actual power monitored in real time. By statistically analyzing the time series data e(t), the regulation accuracy and real-time tracking capability of the system are evaluated. Based on the power tracking error data e(t), the active power qualification rate is statistically analyzed. The qualification rate R pass It refers to the proportion of time that the actual power error e(t) is within the allowable deviation range [-∈,∈] during the operating cycle T. The calculation formula is as follows:

[0170]

[0171] Among them, 1(·) is an indicator function, which takes 1 when |e(t)|≤∈, otherwise it takes 0, and ∈ is the allowable error threshold. By statistically evaluating the pass rate, the stability and compliance of the system in achieving performance requirements in the process of adjusting the target power are evaluated. The timing response analysis is performed on the operating parameter data to calculate the execution completion time of the control instruction. The timing response analysis focuses on the system from the control instruction P cmd Send to actual power P real Time to reach the set target T resp , which is calculated based on the detection of time points:

[0172] T resp =t settle -t cmd ;

[0173] Among them, t cmd is the time when the control command is issued, t settle is the moment when the system stabilizes near the target value, that is, |P real (t settle )-P target |≤δ, where δ is the stability threshold. By evaluating the timing response, the rapidity and execution efficiency of the system control are measured. pass and control response time T resp Input the multi-objective genetic optimizer and use the non-dominated sorting genetic algorithm to optimize the parameters and find a balanced solution between maximizing the qualified rate and minimizing the response time. The objective function of the optimization process is defined as:

[0174] minJ=[-R pass ,T resp ];

[0175] The genetic algorithm iteratively updates the population through operations such as initial population generation, fitness calculation, non-dominated sorting, crossover mutation, and elite selection to obtain the Pareto optimal solution set P. Pareto , where each solution corresponds to a set of parameter combinations. The Pareto optimal solution set reflects the control parameter set under different trade-offs, providing a selection basis for subsequent controller optimization. Based on the Pareto optimal solution set, the dead zone range is optimized, and the dead zone range D is adjusted. opt It is defined as the interval in which the controller does not perform adjustment when the error is small. Specifically, the optimal dead zone vector D is obtained by optimization search. opt , the result is expressed as:

[0176] Where J(D) = -R pass +λ·T resp ;

[0177] Among them, λ is the trade-off coefficient. By optimizing the dead zone parameters, frequent adjustment actions can be effectively reduced and the stability of the system can be improved. Based on the optimized dead zone vector D opt Optimize the parameters of the PID controller. The goal of the PID controller is to use the proportional gain K p , integration time K i and differential time K d The power error is adjusted. The PID control output u(t) is expressed as follows:

[0178]

[0179] Search for the optimal K through genetic optimizer p ,K i ,K d , so that the system responds quickly and minimizes the error during the adjustment process. The final optimized PID parameter vector is:

[0180]

[0181] The optimal PID control parameter vector is allocated according to the installed capacity ratio of the inverter. The specific parameter allocation formula is:

[0182]

[0183] Among them, θ inv,j is the PID parameter assigned to the jth inverter, C inv,j is the installed capacity of the inverter, and N is the total number of inverters. The control output of each inverter is calculated according to the allocated PID parameters and used as the target power allocation scheme P target,inv,j .

[0184] Reference Figure 2 This embodiment provides an optimization device based on a distributed solar photovoltaic power generation control system, including:

[0185] The acquisition module 1 is used to collect and encrypt the operation data of the photovoltaic power station in real time to obtain power generation data, voltage data, current data and solar radiation data;

[0186] Processing module 2, used for inputting power generation data, voltage data, current data and solar radiation data into the photovoltaic multimodal deep learning prediction model for processing, and generating active power regulation strategy and reactive power regulation strategy;

[0187] Verification module 3, used to generate control instructions based on active power regulation strategy and reactive power regulation strategy, and perform hierarchical safety constraint verification on the control instructions to generate remote control instructions and local control instructions;

[0188] The adjustment module 4 is used to perform hierarchical reinforcement learning control and power optimization adjustment on the inverters in multiple control groups according to the remote control instructions and the local control instructions to obtain the total output value of the group;

[0189] Monitoring module 5, used to monitor the total output value of the group and the operating status of the equipment in real time and generate operating parameter data;

[0190] The optimization module 6 is used to calculate the active power qualification rate, control response time, control accuracy and system fluctuation rate based on the operating parameter data, and to perform multi-objective optimization on the adjustment dead zone range, control gain and response time constant to obtain the target power allocation scheme.

[0191] In this embodiment, for the specific implementation of each unit in the above device embodiment, please refer to the above method embodiment, which will not be repeated here.

[0192] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0193] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0194] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0195] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0196] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0197] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An optimization method based on a distributed solar photovoltaic power generation control system, characterized in that: The following steps are involved: Real-time collection and encrypted transmission of photovoltaic power station operation data to obtain power generation data, voltage data, current data and solar radiation data; Inputting the power generation data, voltage data, current data and solar radiation data into a photovoltaic multimodal deep learning prediction model for processing to generate an active power regulation strategy and a reactive power regulation strategy; Generate control instructions based on the active power regulation strategy and the reactive power regulation strategy, and perform hierarchical safety constraint verification on the control instructions to generate remote control instructions and local control instructions; According to the remote control command and the local control command, hierarchical reinforcement learning control and power optimization adjustment are performed on the inverters in the multiple control groups to obtain the total output value of the group; Monitor the total output value of the group and the operating status of the equipment in real time to generate operating parameter data; Based on the operating parameter data, the active power qualification rate, control response time, control accuracy and system fluctuation rate are calculated, and the adjustment dead zone range, control gain and response time constant are multi-objective optimized to obtain a target power allocation scheme.

2. The optimization method based on distributed solar photovoltaic power generation control system according to claim 1 is characterized in that: The real-time collection and encrypted transmission processing of photovoltaic power station operation data to obtain power generation data, voltage data, current data and solar radiation data includes: Performing telemetry collection on inverter operation data to obtain an inverter telemetry data set, wherein the inverter telemetry data set includes a real-time startup capacity value, a power change rate value, an output upper limit value, and an output lower limit value of the inverter, and performing active power calculation to obtain an inverter power adjustment range; Input the inverter telemetry data set into the SSL security encryption module for private protocol encryption to obtain a first-level encrypted data packet, and perform directional server routing assignment on the first-level encrypted data packet to obtain encrypted transmission data; Input the encrypted transmission data into the cloud platform for vertical encryption and dynamic key update to obtain a second-level encrypted data packet, and distribute the second-level encrypted data packet to obtain a real-time database storage record; The real-time database storage records are classified and stored according to data types and timestamps to obtain historical database backup records, and firewall business isolation and security verification are performed on the historical database backup records to obtain power generation data, voltage data, current data and solar radiation data.

3. The optimization method based on distributed solar photovoltaic power generation control system according to claim 2 is characterized in that: The power generation data, voltage data, current data and solar radiation data are input into the photovoltaic multi-modal deep learning prediction model for processing to generate an active power regulation strategy and a reactive power regulation strategy, including: Inputting the power generation data, voltage data, current data and solar radiation data into the multi-layer convolution feature extraction layer in the photovoltaic multimodal deep learning prediction model for processing, the multi-layer convolution feature extraction layer comprises 4 convolution modules, each convolution module consists of two convolution layers and a maximum pooling layer, and obtaining a power station operation feature vector; Inputting the power station operation feature vector into the bidirectional LSTM timing analysis layer in the photovoltaic multimodal deep learning prediction model for processing, the bidirectional LSTM timing analysis layer includes two LSTM layers, each LSTM layer includes 128 hidden units, and obtaining a timing dependency feature; Inputting the time-dependent features into the multi-head attention layer in the photovoltaic multimodal deep learning prediction model for processing, the multi-head attention layer adopts a multi-head self-attention structure, including 8 attention heads, each with a dimension of 64, to obtain a feature attention matrix; Input the feature attention matrix into the power prediction layer in the photovoltaic multimodal deep learning prediction model for processing, wherein the power prediction layer comprises three fully connected layers, the number of neurons is 512, 256, and 128 respectively, and a ReLU activation function is used to obtain a power prediction vector; The power prediction vector is input into the constraint optimization layer in the photovoltaic multimodal deep learning prediction model for processing, wherein the constraint optimization layer adopts a multi-objective optimization algorithm, sets the grid dispatch instruction as a hard constraint condition, and the installed capacity change rate as a soft constraint condition, to obtain a maximum power tracking parameter set; Inputting the maximum power tracking parameter set into the inverter parameter optimization layer in the photovoltaic multimodal deep learning prediction model for processing, wherein the parameter optimization layer includes two fully connected layers and uses a Sigmoid activation function to obtain an inverter optimization parameter set; Inputting the inverter optimization parameter set into the strategy generation layer in the photovoltaic multimodal deep learning prediction model for processing, wherein the strategy generation layer adopts a hierarchical reinforcement learning structure, includes a strategy neural network and a value evaluation network, and obtains an initial control strategy; The initial control strategy is input into the authority control layer in the photovoltaic multimodal deep learning prediction model for processing. The authority control layer includes a three-level authority verification module, which allocates control authority according to user level to obtain active power regulation strategy and reactive power regulation strategy.

4. The optimization method based on distributed solar photovoltaic power generation control system according to claim 3 is characterized in that: The generating of control instructions based on the active power regulation strategy and the reactive power regulation strategy, and performing hierarchical safety constraint check on the control instructions to generate remote control instructions and local control instructions include: Based on the active power regulation strategy and the reactive power regulation strategy, instruction generation processing is performed to obtain a power generation control instruction set, wherein the power generation control instruction set includes an inverter output upper limit value, an output lower limit value, and a regulation rate parameter; Perform remote control parameter calculation on the power generation control instruction set, and use a closed-loop control algorithm to calculate based on the automatic control target issued by the master station to obtain a remote control reference instruction; Calculating local control parameters for the power generation control instruction set, using an open-loop control algorithm to calculate based on the power generation plan issued by the master station, and obtaining a local control benchmark instruction; Performing equipment fault detection on the remote control reference command and the local control reference command, and obtaining a first-level safety detection result by evaluating the inverter operation state, power supply state and grounding state; Performing communication status detection on the first-level security detection result, by evaluating the communication status and communication delay status of the device, wherein the communication delay status is determined by a preset time threshold, a second-level security detection result is obtained; Conducting electrical parameter testing on the second-level safety test results, and obtaining the third-level safety test results by evaluating whether the inverter voltage value and power value are within the safety range; Calculate a control lock signal based on the third-level safety detection result, wherein the control lock signal includes a power increase lock signal and a power decrease lock signal, and the control lock signal is released only by manual operation to obtain a lock control vector; The locking control vector is combined with the remote control reference instruction to generate a remote control instruction, and the locking control vector is combined with the local control reference instruction to generate a local control instruction.

5. The optimization method based on distributed solar photovoltaic power generation control system according to claim 4 is characterized in that: The step of performing hierarchical reinforcement learning control and power optimization adjustment on the inverters in the plurality of control groups according to the remote control command and the local control command to obtain the total output value of the group includes: Inputting the remote control command and the local control command into a high-level decision module of a hierarchical reinforcement learning control network for processing, wherein the high-level decision module comprises a policy neural network and a value evaluation network, wherein the policy neural network comprises 3 convolutional layers and 2 fully connected layers, and the value evaluation network comprises 2 convolutional layers and 3 fully connected layers, to obtain a group control action set; Performing control state encoding on the group control action set, encoding each control group into a control unit, including group identification, number of inverters, total installed capacity, and current power output status information, to obtain a group control state vector; The group control state vector is input into the execution control module for reward calculation, wherein the reward calculation includes three evaluation indicators: power tracking deviation, adjustment response time, and system stability, to obtain a group control reward value; Based on the group control reward value, the group control state vector is updated by deep Q learning, and the target Q value is calculated by a temporal difference algorithm using an experience replay buffer and a target network mechanism to obtain an optimal control action; The optimal control action is input into the power distribution module for group power regulation, and the target power of each inverter is calculated by a weighted distribution algorithm according to the operating status and capacity parameters of each inverter to obtain the inverter power instruction; Performing power regulation judgment on the inverter power command, triggering regulation control when the deviation between the total power of the group and the target power exceeds a preset interval, and obtaining a power regulation trigger signal; Based on the power regulation trigger signal, active power and reactive power of each inverter are collaboratively optimized to obtain real-time power data of the inverter, and the real-time power data of the inverter is weighted and summed to obtain the total output value of the group.

6. The optimization method based on distributed solar photovoltaic power generation control system according to claim 5 is characterized in that: The optimal control action is input into the power distribution module for group power regulation, and a weighted distribution algorithm is used to calculate the target power of each inverter according to the operating state and capacity parameters of each inverter to obtain the inverter power instruction, including: Inputting the optimal control action into a data processing unit of a power allocation module for strategy analysis to obtain a group power target vector; Dividing the group power target vector into groups, grouping and calibrating the inverters based on the geographical location data and the electrical connection relationship, and obtaining group configuration data; Performing normalization operation on the installed capacity of each inverter based on the group configuration data to obtain a capacity normalization coefficient; Dynamically correct the capacity normalization coefficient, adjust the weight according to the communication delay and device status index of the inverter, and obtain a dynamic adjustment coefficient; Performing a matrix operation on the dynamic adjustment coefficient and the group power target vector to obtain an initial power allocation value of each inverter, performing a limit processing on the initial power allocation value, performing a constraint calculation according to the inverter power adjustment interval, and obtaining a power limit control value; The power change rate is optimized based on the power limit control value to ensure that the power regulation rate meets the power grid operation requirements, and the optimized control value is obtained. The optimized control value is converted into an instruction according to the communication protocol of each inverter to obtain an inverter power instruction.

7. The optimization method based on distributed solar photovoltaic power generation control system according to claim 6 is characterized in that: The active power qualification rate, control response time, control accuracy and system fluctuation rate are calculated based on the operating parameter data, and the adjustment dead zone range, control gain and response time constant are optimized by multiple objectives to obtain a target power allocation scheme, including: Calculating the power deviation based on the operating parameter data, and obtaining the power tracking error data by comparing the real-time power value with the control target value; Performing pass rate statistics based on the power tracking error data to obtain the active power pass rate, and performing timing response analysis on the operating parameter data to calculate the control instruction execution completion time to obtain the control response time; Inputting the active power qualified rate and the control response time into a multi-objective genetic optimizer, using a non-dominated sorting genetic algorithm to perform parameter optimization, and obtaining a Pareto optimal solution set; Optimize the parameters of the dead zone range based on the Pareto optimal solution set to obtain a dead zone optimization vector; The dead zone optimization vector is optimized by a PID controller, and the optimal control gain and response time constant are calculated to obtain a controller parameter vector. The controller parameter vector is allocated parameters according to the inverter capacity ratio to obtain a target power allocation scheme.

8. An optimization device based on a distributed solar photovoltaic power generation control system, characterized in that: For implementing the steps of the method according to any one of claims 1 to 7, the device comprises: The acquisition module is used to collect and encrypt the operation data of the photovoltaic power station in real time to obtain power generation data, voltage data, current data and solar radiation data; A processing module, used for inputting the power generation data, voltage data, current data and solar radiation data into a photovoltaic multimodal deep learning prediction model for processing, and generating an active power regulation strategy and a reactive power regulation strategy; A verification module, used to generate control instructions based on the active power regulation strategy and the reactive power regulation strategy, and perform hierarchical safety constraint verification on the control instructions to generate remote control instructions and local control instructions; A regulating module, configured to perform hierarchical reinforcement learning control and power optimization regulation on the inverters in the plurality of control groups according to the remote control command and the local control command, so as to obtain a total output value of the group; A monitoring module, used to monitor the total output value of the group and the operating status of the equipment in real time and generate operating parameter data; The optimization module is used to calculate the active power qualification rate, control response time, control accuracy and system fluctuation rate based on the operating parameter data, and perform multi-objective optimization on the adjustment dead zone range, control gain and response time constant to obtain a target power allocation plan.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. 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 1 to 7 are implemented.

Images