Substation control system based on cloud control and local area network

Abstract

The invention relates to the technical field of substation control, in particular to a substation control system based on cloud control and a local area network. Comprising a substation data acquisition module, a data analysis module, a cloud cooperative control module, an edge calculation response module and a safety guarantee module. The substation data acquisition module acquires multi-dimensional data through a local area network, and the data analysis module identifies abnormal and fault modes by adopting a dynamic multivariate autoregression tree algorithm. The cloud cooperative control module performs global load scheduling by using a sparse distributed optimization algorithm, and the edge calculation response module realizes rapid local response control based on a Markov random field model. And the safety guarantee module is combined with deep learning and a multi-factor identity authentication technology to ensure data transmission safety. According to the invention, the automatic control level and the overall operation efficiency of the transformer substation are improved, and efficient, stable and safe intelligent power management is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of substation control, and in particular to a substation control system based on cloud control and local area network. Background Art

[0002] In modern power systems, substations are the core nodes for realizing power conversion, dispatching and distribution. The control system of traditional substations usually adopts a distributed architecture and mainly relies on on-site equipment control and operation. However, with the increase in power demand and the increase in the complexity of the power grid, traditional control systems have certain limitations in response speed, data processing capabilities and information sharing. Therefore, how to improve the automation level and intelligent management capabilities of substations has become the focus of current research and development. At present, there are still the following problems: the existing system lacks multi-dimensional real-time data analysis methods, and it is difficult to accurately identify nonlinear dependencies and abnormal patterns between multiple variables, which affects the real-time and accuracy of fault diagnosis; the load dispatching of traditional substations is mostly local control, lacking global optimization across sites, resulting in resource waste and unreasonable energy consumption; the existing system mainly relies on central system control, with high latency, and it is difficult to meet the rapid response requirements of local equipment. Summary of the invention

[0003] To solve the above problems, the present invention provides a substation control system based on cloud control and local area network, which solves the problem of how to improve the automation and intelligent management level of substations while realizing multi-dimensional real-time data analysis, improving the accuracy and real-time performance of fault diagnosis, and realizing global optimization and rapid response of local equipment across sites, thereby improving the automation control level and overall operation efficiency of substations.

[0004] To achieve the above object, the technical solution adopted by the present invention is: A substation control system based on cloud control and local area network, comprising a substation data acquisition module, a data analysis module, a cloud collaborative control module, an edge computing response module and a security assurance module which are sequentially communicatively connected; The substation data acquisition module is used to collect multi-dimensional data of the substation through a local area network; The data analysis module is used to perform regression analysis based on the multidimensional data using a dynamic multivariate autoregressive tree algorithm to capture nonlinear dependencies between multiple variables, identify potential anomalies and failure modes, and generate an analysis report; The cloud collaborative control module is used to perform global load dispatching and control of multiple substations based on the analysis report using a sparse distributed optimization algorithm, generate control instructions through sparse communication collaboration between distributed nodes, and dynamically adjust control parameters of each device in the substation; The edge computing response module is used to perform local processing on the key data of the analysis report through the local area network, and adopts the Markov random field model to model the spatiotemporal dependency relationship between edge nodes as a probabilistic graph structure. At the same time, after receiving the control instruction, the local equipment of the substation is quickly responded to and controlled, and dynamic real-time strategy adjustment is realized; The security assurance module is used to monitor the overall operating status of the system, and based on deep learning intrusion detection algorithms, multi-factor identity authentication and encrypted transmission technology, it implements all-round security assurance for data transmission and command execution, and pushes relevant information to the terminals of operation and maintenance personnel.

[0005] Furthermore, the multi-dimensional data includes environmental parameters of the substation, operating parameters and status parameters of the power equipment.

[0006] Furthermore, the operation process of the data analysis module includes the following steps: receiving the multidimensional data and performing preprocessing operations, including removing noise and correcting anomalies using time series smoothing; Based on the preprocessed multidimensional data, the dynamic multivariate autoregressive tree algorithm is used to identify the nonlinear relationship between variables and generate a key feature mapping table; Based on the key feature mapping table, a multi-dimensional cause-effect relationship diagram is constructed to identify risk paths between equipment and environmental parameters; Compare the characteristic patterns with the preset failure mode library in real time, identify potential failure trends, and generate risk index reports; Based on the multi-dimensional cause-and-effect relationship diagram and the fault pattern matching results, a comprehensive analysis report is generated and transmitted to the cloud collaborative control module; the comprehensive analysis report includes the equipment health index in the substation, abnormal cause analysis, fault risk level and trend prediction.

[0007] Furthermore, the formula of the multivariate autoregressive tree algorithm is as follows: in, represents the predicted output variable at the current time t, which is used to analyze the results of key data in the substation; m represents the number of multi-dimensional input features, that is, the different types of data monitored in the substation; k represents the multi-level branch structure set on each input feature; represents the influence weight of the input characteristics of the substation on the current output prediction; p and q represent the order of the lag term; represents the l-th order lag coefficient of the i-th input feature in the j-th branch; represents the nonlinear mapping function of the i-th input feature at lag time tl; represents the weight coefficient of the nth-order lag term of the i-th feature in the j-th branch; represents the nonlinear transfer function at the lag time tn; Represents the bias term of the feature branch.

[0008] Furthermore, the operation process of the cloud collaborative control module includes the following steps: Receive and analyze the comprehensive analysis report transmitted by the data analysis module, and extract key data, wherein the key data includes equipment health status, fault risk level and trend prediction; Based on the comprehensive analysis results and the real-time load demand of multiple substations, a sparse distributed optimization algorithm is used to determine the load distribution and control priority of each substation and generate control instructions, including equipment start and stop and parameter adjustment; Distribute the control instructions to each substation node, optimize the instructions in real time using a distributed coordination mechanism, and make dynamic adjustments based on node feedback data; The final optimized control instructions are transmitted to the edge computing response module through the local area network, the control execution is started, and the execution feedback is monitored in real time.

[0009] Furthermore, the formula of the sparse distributed optimization algorithm is as follows: in, represents the minimization of the global load dispatch cost function F; N represents the number of substations involved in load dispatch and control; t represents the execution status of the control and optimization algorithm in a specific time period; represents the control parameters of the ith substation node at time t; represents the load scheduling cost function of the i-th node; represents other substation nodes that communicate sparsely with the i-th substation node through the local area network in the distributed system; represents the sparse regularization coefficient; It represents the sum of squares of the differences in control parameters between nodes i and j.

[0010] Furthermore, the operation process of the edge computing response module includes the following steps: Receive control instructions transmitted by the cloud collaborative control module, parse the instruction content and extract control parameters of related devices; Rapidly localize the key data in the analysis report generated by the data analysis module, use the Markov random field model to build the spatiotemporal dependency relationship between edge nodes, and map the key data into a probabilistic graph structure; Combined with the real-time environmental data and control instructions of the local area network, the local equipment in the substation is responded to and controlled, and the operation instructions of key equipment are processed first; Based on the real-time feedback mechanism, the equipment response is monitored and the immediate operation status of the equipment is compared with the expected control effect. If there is a deviation, the control strategy is dynamically adjusted; The operating status and control adjustment of edge nodes are summarized and feedback reports are generated, and key operating data and adjustment information are transmitted to the cloud collaborative control module.

[0011] Furthermore, the Markov random field model specifically includes constructing a dependency graph structure between substation edge nodes, where nodes represent device state variables and edges represent spatiotemporal associations between devices; constraining node relationships through conditional probability distribution functions to form a joint probability model of state variables.

[0012] Furthermore, the security assurance module implements dynamic management of user rights based on a multi-factor identity authentication module, and uses symmetric and asymmetric encryption technologies to encrypt data transmission content.

[0013] The beneficial effects of the present invention are: The present invention realizes the real-time collection of multi-dimensional data of substations through the substation data acquisition module, and uses the dynamic multivariate autoregressive tree algorithm to perform deep regression analysis through the data analysis module, which can effectively identify the nonlinear dependency between multiple variables, thereby accurately identifying potential abnormalities and fault modes, and improving the accuracy and real-time performance of fault diagnosis. The cloud collaborative control module is based on the sparse distributed optimization algorithm, and through the sparse communication collaboration between distributed nodes, it can perform global load scheduling on multiple substations to achieve efficient resource configuration and energy consumption optimization. At the same time, the system can dynamically generate control instructions according to the analysis results, and automatically adjust the control parameters of each device in the substation, thereby improving the intelligence and control accuracy of the system. The edge computing response module processes key data in the local area network and uses the Markov random field model to model the spatiotemporal dependency relationship, ensuring the rapid response control of local substation equipment, and realizing the combination of local processing and real-time strategy adjustment. This not only reduces the computing load on the cloud, but also improves the response speed and reliability of the system. The security assurance module builds a complete security system through deep learning intrusion detection, multi-factor identity authentication and encrypted transmission technology to ensure the security of data transmission and control instruction execution. Monitor the system's operating status in real time, effectively prevent data leakage and illegal access, and push relevant information to operation and maintenance personnel, improving the system's overall security protection level. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a module schematic diagram of a substation control system based on cloud control and local area network of the present invention.

[0015] Figure 2It is a flowchart of the operation process of the data analysis module provided by one embodiment of the present invention.

[0016] Figure 3 It is a flowchart of the operation process of the cloud collaborative control module provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0017] See also Figure 1-3 As shown, the present invention relates to a substation control system based on cloud control and local area network.

[0018] Example A substation control system based on cloud control and local area network, comprising a substation data acquisition module, a data analysis module, a cloud collaborative control module, an edge computing response module and a security assurance module which are sequentially communicatively connected; The substation data acquisition module is used to collect multi-dimensional data of the substation through a local area network; the multi-dimensional data includes environmental parameters of the substation, operating parameters and status parameters of power equipment.

[0019] It should be noted that in the substation data acquisition module, a group of high-precision sensors and intelligent acquisition devices are deployed to achieve comprehensive data collection of the substation. This module connects all acquisition devices to a data concentrator through a local area network, and the concentrator connects the acquisition end device and the data analysis module with a high-speed interface. The data collected by the module includes the following categories: Environmental parameters: Environmental variables such as temperature, humidity, and air pressure monitor the meteorological information around the substation through a multi-sensor array. This information has an important impact on the heat dissipation and working stability of the equipment in the substation.

[0020] Operating parameters of power equipment: including electrical parameters such as current, voltage, and power. Data is collected at a frequency of seconds or milliseconds to ensure sufficient real-time performance.

[0021] Status parameters: such as equipment health, component wear, operating time, etc., are recorded by sensors and status monitoring devices. To ensure data quality, each acquisition node is equipped with fault tolerance and outlier filtering algorithms to avoid interference from abnormal or erroneous data.

[0022] The data analysis module is used to perform regression analysis based on the multidimensional data using a dynamic multivariate autoregressive tree algorithm to capture nonlinear dependencies between multiple variables, identify potential anomalies and failure modes, and generate an analysis report; The operation process of the data analysis module includes the following steps: receiving the multidimensional data and performing preprocessing operations, including removing noise and correcting anomalies using time series smoothing; Based on the preprocessed multidimensional data, the dynamic multivariate autoregressive tree algorithm is used to identify the nonlinear relationship between variables and generate a key feature mapping table; Specifically, all multidimensional data are used as input to the autoregressive tree model, and the algorithm models the data according to the set regression tree structure and parameter initialization operation. The model adopts a dynamic multivariate regression approach and can adapt to changes in equipment status and environmental conditions. The algorithm gradually analyzes the interdependence between variables to capture complex nonlinear relationships. Each branch node of the autoregressive tree model divides different branch paths according to the degree of dependency and change trend of the variables. Through this process, the model can identify hidden correlations between different variables, such as the nonlinear correlation between transformer temperature and load current. The main variables identified by the algorithm and their interrelationships are summarized into a key feature mapping table, which records the value of each important variable and its dependence strength on other variables. For example, the table will mark the weight of the load current on the equipment temperature and give the trend of the characteristic value.

[0023] Based on the key feature mapping table, a multi-dimensional cause-effect relationship diagram is constructed to identify risk paths between equipment and environmental parameters; Specifically, a causal reasoning algorithm based on a graph model is used to transform the variable relationships identified in the feature mapping table into a directed graph structure. Each node represents a parameter (such as temperature, voltage), and the directed edges between nodes represent causal relationships. For example, an increase in current will cause an increase in temperature. In the causal graph, an edge from the "current" node to the "temperature" node represents this risk path. The module marks the high-risk paths in the causal graph, and the nodes and edges in the path represent specific risk transfers. For example, when the equipment load is too high and the temperature rises, the causal graph will mark the high-risk path from load to temperature, thereby warning of potential equipment failure risks. A weight is assigned to each causal path, and the weight value is determined based on the strength of the dependency between the variables and the potential risk impact. Based on these weights, the module prioritizes possible risk paths to help with subsequent fault mode identification.

[0024] Compare the characteristic patterns with the preset failure mode library in real time, identify potential failure trends, and generate risk index reports; Specifically, the module contains a preset fault mode library, which stores historically common fault modes and their characteristic values. For example, a transformer overheating fault mode may include characteristics that both the current and temperature are higher than the normal threshold. By real-time monitoring of the current key feature mapping table and comparing it with the fault mode library one by one, the module can identify the similarity between the current feature and the existing fault mode. If it is detected that the current feature has a high degree of match with a known fault mode, the module will record the situation as a potential fault trend. A risk index is generated based on the matching results, and the higher the index value, the closer the current system state is to the fault mode. For example, when the voltage, current and temperature all exceed the threshold, the risk index will increase significantly. The module generates a risk index report based on the risk index and marks high-risk equipment and potential fault types.

[0025] Based on the multi-dimensional cause-and-effect relationship diagram and the fault pattern matching results, a comprehensive analysis report is generated and transmitted to the cloud collaborative control module; the comprehensive analysis report includes the equipment health index in the substation, abnormal cause analysis, fault risk level and trend prediction.

[0026] Furthermore, the formula of the multivariate autoregressive tree algorithm is as follows: in, represents the predicted output variable at the current time t, which is used to analyze the results of key data in the substation; m represents the number of multi-dimensional input features, that is, the different types of data monitored in the substation; k represents the multi-level branch structure set on each input feature; represents the influence weight of the input characteristics of the substation on the current output prediction; p and q represent the order of the lag term; represents the l-th order lag coefficient of the i-th input feature in the j-th branch; The nonlinear mapping function representing the i-th input feature at the lag time tl is used to transform the lag effect of the environmental parameters or the power equipment status of the substation to identify the nonlinear dependency; The weight coefficient representing the nth-order hysteresis term of the ith feature in the jth branch is used to transform the hysteresis effect of the environmental parameters or power equipment status of the substation to identify nonlinear dependencies; represents the nonlinear transfer function at the lag time tn; Represents the bias term of the feature branch.

[0027] The cloud collaborative control module is used to perform global load dispatching and control of multiple substations based on the analysis report using a sparse distributed optimization algorithm, generate control instructions through sparse communication collaboration between distributed nodes, and dynamically adjust control parameters of each device in the substation; The operation process of the cloud collaborative control module includes the following steps: Receive and analyze the comprehensive analysis report transmitted by the data analysis module, and extract key data, wherein the key data includes equipment health status, fault risk level and trend prediction; Based on the comprehensive analysis results and the real-time load demand of multiple substations, a sparse distributed optimization algorithm is used to determine the load distribution and control priority of each substation and generate control instructions, including equipment start and stop and parameter adjustment; Specifically, the current load demand data is obtained from each substation node, including the real-time current, voltage, power demand and other data of each site. The demand data is regularly updated through the local area network connection to ensure the real-time nature of the dispatch decision basis. Based on the collected load demand and key data in the comprehensive analysis report, the module initializes the sparse distributed optimization algorithm. The algorithm divides the entire dispatch task into several subtasks and assigns them to different substation nodes to achieve distributed computing. The algorithm optimizes the load distribution based on data such as the equipment health status, risk level and trend prediction of each substation. For example, substations with low health index and high failure risk give priority to reducing load or temporarily shutting down some equipment to reduce the risk of failure. The algorithm dynamically allocates load proportions and generates control priorities based on the health status, load demand and environmental data of each substation node. After the optimization calculation is completed, the module generates specific control instructions, which include equipment start and stop operations (such as shutting down or starting power generation equipment) and key parameter adjustments (such as current and voltage settings) to meet the dispatch needs of the global load.

[0028] Distribute the control instructions to each substation node, optimize the instructions in real time using a distributed coordination mechanism, and make dynamic adjustments based on node feedback data; Specifically, the generated control instructions are sent to the control nodes of each substation through the local area network. The instructions include specific requirements for equipment operation and parameter adjustment. The module uses the instruction distributor to divide the control instructions into node instruction packets, and each substation node receives its own instruction content. After receiving the instructions, each substation node begins to perform preliminary control operations. At this time, the cloud collaborative control module monitors the execution status and feedback data of each node in real time through a distributed collaborative mechanism. For example, if a node is abnormal when performing start-stop operations, the module will dynamically adjust according to the feedback data, reallocate tasks or adjust control strategies. The module receives and analyzes the feedback data of each node, including the current load status, equipment response status and environmental parameters, to ensure the effectiveness of instruction execution. If the feedback data indicates that the load of a node is too high or the equipment status is abnormal, the module will dynamically adjust the load distribution strategy to avoid overload or failure. For example, if the feedback temperature of a substation node exceeds expectations, the module will issue an instruction to reduce the load of the node.

[0029] The final optimized control instructions are transmitted to the edge computing response module through the local area network, the control execution is started, and the execution feedback is monitored in real time.

[0030] Furthermore, the formula of the sparse distributed optimization algorithm is as follows: in, represents the minimization of the global load dispatch cost function F to find the optimal control parameter allocation and achieve global load balancing and cost minimization of multiple substations; N represents the number of substations involved in load dispatching and control; t represents the execution status of the control and optimization algorithm in a specific time period; represents the control parameters of the ith substation node at time t, that is, the control variables that need to be adjusted, such as the start and stop status of the equipment or the load distribution weight, to meet the real-time load demand; represents the load scheduling cost function of the i-th node, which is used to measure the control parameters The dispatching cost at this node includes cost factors such as the health status of substation equipment, operating parameters and status parameters of power equipment; represents other substation nodes that communicate sparsely with the i-th substation node through the local area network in the distributed system; represents the sparse regularization coefficient, which controls the communication intensity between nodes in different substations; It represents the sum of squares of the differences in control parameters between nodes i and j. It is used to measure the load scheduling coordination between two substation nodes and to make the load control parameters of adjacent nodes close to each other, thereby achieving stable load balance.

[0031] The edge computing response module is used to perform local processing on the key data of the analysis report through the local area network, and adopts the Markov random field model to model the spatiotemporal dependency relationship between edge nodes as a probabilistic graph structure. At the same time, after receiving the control instruction, the local equipment of the substation is quickly responded to and controlled, and dynamic real-time strategy adjustment is realized; The operation process of the edge computing response module includes the following steps: Receive control instructions transmitted by the cloud collaborative control module, parse the instruction content and extract control parameters of related devices; The key data in the analysis report generated by the data analysis module is quickly localized, and the spatiotemporal dependency relationship between edge nodes is constructed using a Markov random field model, and the key data is mapped into a probability graph structure; the Markov random field model specifically includes constructing a dependency graph structure between substation edge nodes, where nodes represent device state variables and edges represent spatiotemporal associations between devices; node relationships are constrained by conditional probability distribution functions to form a joint probability model of state variables; It should be noted that the module uses the Markov random field (MRF) model to establish the dependency graph structure between substation equipment according to the spatial layout and data dependency of edge nodes.

[0032] Node definition: Each node in the graph structure represents a state variable of a device (such as temperature, load, voltage). The node status is updated through real-time data.

[0033] Edge definition: An edge represents the spatial or temporal relationship between devices. For example, an edge connection between adjacent devices means that their temperature or load will affect each other.

[0034] Probabilistic constraint definition: Use conditional probability distribution functions to define the relationships between nodes, and use these probability distributions to constrain the dependencies between nodes to form an overall joint probability model. This model allows you to infer the possibility of device state changes and helps identify potential anomalies in key devices.

[0035] Combined with the real-time environmental data and control instructions of the local area network, the local equipment in the substation is responded to and controlled, and the operation instructions of key equipment are processed first; Specifically, environmental data (such as temperature, humidity, voltage fluctuations, etc.) are collected in real time from the local area network to ensure that control operations are based on the latest environmental status. Real-time data is collected by edge node sensors and transmitted to the response module for decision support. Control instructions are assigned according to priority, and operation instructions of key equipment are executed first. For example, for high-risk equipment or equipment with abnormal operating status, the module prioritizes adjusting its load or start-stop status to ensure overall safety. The module adjusts parameters and operates the target equipment based on control instructions and real-time data. For example, when the temperature of a device exceeds the safety range, the module will prioritize reducing its load or temporarily shutting it down; for other lower-priority devices, the module will adjust them step by step in sequence.

[0036] Based on the real-time feedback mechanism, the equipment response is monitored and the immediate operation status of the equipment is compared with the expected control effect. If there is a deviation, the control strategy is dynamically adjusted; Specifically, in the process of the device executing the control instructions, the feedback data of the device is collected in real time, such as changes in parameters such as load, voltage, and temperature, to monitor the actual effect of the control operation. The module compares the actual operating status of the device with the expected control effect to determine whether the control execution effect meets expectations. For example, if the expected temperature drops but the actual temperature does not drop significantly, the module identifies it as a deviation. When it is found that the actual state of the device deviates from the expected state, the module automatically adjusts the control strategy. For example, if the load of a certain device fails to decrease as expected, the module may further reduce the power of the device or start a backup device to achieve the control target. The module's dynamic adjustment function of the control strategy ensures that the device status always meets the safe operation requirements of the system.

[0037] The operating status and control adjustment of edge nodes are summarized and feedback reports are generated, and key operating data and adjustment information are transmitted to the cloud collaborative control module.

[0038] The security assurance module is used to monitor the overall operating status of the system, and based on deep learning intrusion detection algorithms, multi-factor identity authentication and encrypted transmission technology, it realizes all-round security protection of data transmission and instruction execution, and pushes relevant information to the terminals of operation and maintenance personnel; the security assurance module realizes dynamic management of user rights based on the multi-factor identity authentication module, and uses symmetric and asymmetric encryption technology to encrypt data transmission content.

[0039] In one embodiment, in order to improve the system's ability to identify potential network attacks, the security module uses an intrusion detection system based on deep learning to monitor and analyze the system's network traffic and operating behavior in real time. The specific design and implementation methods are as follows: extract multidimensional features from network traffic, including communication frequency, packet size, source IP address, and destination IP address. These features are combined to characterize normal and abnormal communication behaviors. A deep model combining convolutional neural network (CNN) and recurrent neural network (RNN) is used for training based on substation historical data and known attack patterns. CNN is responsible for capturing spatial features in network traffic (such as the distribution of data packets), while RNN is used to capture temporal features (such as the time series of data packet transmission). The trained model will analyze network traffic in real time. When abnormal data features (such as traffic surge, malicious IP address connection, etc.) are detected, the module will immediately trigger an alarm and isolate suspicious communication nodes to protect the system from potential attacks. In order to improve the detection accuracy, the module is equipped with a self-learning function, which can continuously collect new data features and update the model during the operation of the system to improve the ability to identify unknown attacks.

[0040] Multi-factor authentication ensures the legitimacy of system visitors and prevents unauthorized personnel from accessing the system. Authentication uses a multi-factor authentication mechanism that combines physical and biometric features, including the following steps: When logging in for the first time, the operation and maintenance personnel need to use two-factor authentication (2FA), such as entering a password and a dynamic verification code on their mobile phone. This ensures that only personnel with authorized devices can enter the system. Biometric technologies such as face recognition or fingerprint scanning are used to ensure that the person entering the system each time is indeed a registered user. The face recognition algorithm is built on a convolutional neural network (CNN) and can accurately match the user's biometric information stored in the system database. Based on the sensitivity of the operation and maintenance tasks and operations, the system dynamically adjusts the user's permissions. For example, ordinary equipment inspection operations do not require advanced permissions, while equipment debugging and control operations require advanced permission verification. The system dynamically determines the task requirements and requires additional identity verification when necessary. Different roles and permissions are set for different operators to prevent unauthorized operations. For example, data analysts can only view and analyze data, while equipment operation and maintenance personnel have the authority to control the equipment.

[0041] The encryption mechanism of data transmission ensures the security of data flow inside and outside the system. The module adopts a combination of symmetric encryption and asymmetric encryption to achieve efficient and secure data encryption. The specific implementation is as follows: Symmetric encryption (AES): AES encryption algorithm is used for real-time data (such as collected equipment status, environmental parameters, etc.) transmitted in the substation's internal LAN. Symmetric encryption has a fast calculation speed during the transmission process and can ensure transmission speed while ensuring data security.

[0042] Asymmetric encryption (RSA): For data transmission across networks (such as from a substation to the cloud), an asymmetric encryption (RSA) algorithm is used to encrypt important information and instructions. The RSA public key is used to encrypt sensitive data, and the private key is used for decryption at the receiving end, which ensures that only the legitimate cloud server can decrypt the data content.

[0043] End-to-end encrypted transmission: To avoid data leakage or tampering during transmission, the module uses SSL / TLS protocol to encrypt the transmission channel to ensure the confidentiality and integrity of the data on the transmission path. The SSL certificate will be issued by a third-party security certification agency to enhance trust.

[0044] Key Management System (KMS): The module is equipped with a key management system (KMS) to automatically generate, store and manage encryption keys, and regularly update keys to prevent risks caused by key leakage. KMS also has a key audit function to record the use and update records of all keys for security review.

[0045] The module provides security incident alarms and automated maintenance notification mechanisms to ensure that maintenance personnel can respond to security incidents in a timely manner. The alarms and notifications are as follows: Real-time alarm system: When the system detects potential security threats (such as intrusion, unauthorized login), the module will trigger multiple alarms. Including: Visual Alarm: Alarm information is highlighted on the control center display screen, with icons or text indicating the specific threat type and location.

[0046] Sound alarm: An alarm is sounded through audio equipment to attract the attention of operation and maintenance personnel.

[0047] Mobile push: Alarm information is pushed to the mobile phones of authorized operation and maintenance personnel in real time via SMS, email or operation and maintenance app, prompting immediate response.

[0048] Fault log recording: The module has a built-in log recording system that automatically records the details of each security incident, including the time of the incident, threat type, response measures, etc. The log can help operation and maintenance personnel conduct post-event analysis and optimize security policies.

[0049] Adaptive defense response: When a major threat is detected, the module automatically activates preset defense strategies, such as automatically blocking specific IP addresses, reducing network access rights, and even switching the system to safe mode to allow only critical operations.

[0050] In summary, the present invention realizes comprehensive and refined collection of environmental parameters, power equipment operating parameters and status parameters through the deployment of high-precision sensors and intelligent collection equipment in the substation data acquisition module. This module uses the high-speed interface of the local area network and the concentrator to achieve fast and stable data transmission, ensuring the real-time and accuracy of data collection, and providing a solid foundation for subsequent data analysis. The data analysis module adopts a dynamic multivariate autoregressive tree algorithm to identify the nonlinear dependencies between variables by constructing a key feature mapping table and a multidimensional cause-and-effect diagram, and effectively discovers the potential causes and risk paths of equipment failures. This process can timely identify and analyze abnormal data trends, and provide real-time fault warning and risk analysis.

[0051] The cloud collaborative control module in the present invention is based on a sparse distributed optimization algorithm. Through the collaboration and optimization between distributed nodes, it globally optimizes and dispatches the load of the substation and dynamically adjusts the control parameters of each device. The system distributes the load according to the health status of the equipment and the priority of the fault risk, reduces the load of high-risk equipment, and ensures the safety of the equipment and the overall operating efficiency of the system. After receiving the cloud control instructions, the edge computing response module uses the local area network data for local processing, adopts the Markov random field model to establish the spatiotemporal dependency relationship between nodes, and performs rapid response control on the local equipment in the substation. The module combines a real-time feedback mechanism to ensure the effectiveness of the control strategy, and automatically makes dynamic adjustments during the execution process, which improves the response speed and decision-making accuracy of the system.

[0052] The security module in the present invention adopts deep learning intrusion detection algorithms, multi-factor identity authentication and encryption technology to ensure the security of data transmission and control instructions. The intrusion detection system in the module uses a deep learning model to monitor and analyze network traffic in real time, identify potential network attacks, and has a self-learning function to continuously improve the detection capability of unknown threats. The adaptive defense response mechanism can quickly adjust the system status when a security incident occurs to protect the operational safety and stability of the system. The system generates a comprehensive analysis report based on the multi-dimensional cause-and-effect relationship diagram and the fault mode library matching results, which includes equipment health index, abnormal cause analysis, fault risk level and trend prediction, to help operation and maintenance personnel more clearly understand the equipment status and fault risk, making management and maintenance more accurate and efficient.

[0053] The above implementation modes are merely descriptions of the preferred implementation modes of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary engineering and technical personnel in the field shall fall within the protection scope determined by the claims of the present invention.

Claims

1. A substation control system based on cloud control and local area network, characterized in that: It includes a substation data acquisition module, a data analysis module, a cloud collaborative control module, an edge computing response module and a security assurance module which are sequentially connected in communication; The substation data acquisition module is used to collect multi-dimensional data of the substation through a local area network; The data analysis module is used to perform regression analysis based on the multidimensional data using a dynamic multivariate autoregressive tree algorithm to capture nonlinear dependencies between multiple variables, identify potential anomalies and failure modes, and generate an analysis report; The cloud collaborative control module is used to perform global load dispatching and control of multiple substations based on the analysis report using a sparse distributed optimization algorithm, generate control instructions through sparse communication collaboration between distributed nodes, and dynamically adjust control parameters of each device in the substation; The edge computing response module is used to perform local processing on the key data of the analysis report through the local area network, and adopts the Markov random field model to model the spatiotemporal dependency relationship between edge nodes as a probabilistic graph structure. At the same time, after receiving the control instruction, the local equipment of the substation is quickly responded to and controlled, and dynamic real-time strategy adjustment is realized; The security assurance module is used to monitor the overall operating status of the system, and based on deep learning intrusion detection algorithms, multi-factor identity authentication and encrypted transmission technology, it implements all-round security assurance for data transmission and command execution, and pushes relevant information to the terminals of operation and maintenance personnel.

2. A substation control system based on cloud control and local area network according to claim 1, characterized in that: The multi-dimensional data includes environmental parameters of the substation, operating parameters and status parameters of the power equipment.

3. A substation control system based on cloud control and local area network according to claim 1, characterized in that: The operation process of the data analysis module includes the following steps: receiving the multidimensional data and performing preprocessing operations, including removing noise and correcting anomalies using time series smoothing; Based on the preprocessed multidimensional data, the dynamic multivariate autoregressive tree algorithm is used to identify the nonlinear relationship between variables and generate a key feature mapping table; Based on the key feature mapping table, a multi-dimensional cause-effect relationship diagram is constructed to identify risk paths between equipment and environmental parameters; Compare the characteristic patterns with the preset failure mode library in real time, identify potential failure trends, and generate risk index reports; Based on the multi-dimensional cause-and-effect relationship diagram and the fault pattern matching results, a comprehensive analysis report is generated and transmitted to the cloud collaborative control module; the comprehensive analysis report includes the equipment health index in the substation, abnormal cause analysis, fault risk level and trend prediction.

4. A substation control system based on cloud control and local area network according to claim 3, characterized in that: The formula of the multivariate autoregressive tree algorithm is as follows: in, represents the predicted output variable at the current time t, which is used to analyze the results of key data in the substation; m represents the number of multi-dimensional input features, that is, the different types of data monitored in the substation; k represents the multi-level branch structure set on each input feature; represents the influence weight of the input characteristics of the substation on the current output prediction; p and q represent the order of the lag term; represents the l-th order lag coefficient of the i-th input feature in the j-th branch; represents the nonlinear mapping function of the i-th input feature at lag time tl; represents the weight coefficient of the nth-order lag term of the i-th feature in the j-th branch; represents the nonlinear transfer function at the lag time tn; Represents the bias term of the feature branch.

5. The substation control system based on cloud control and local area network according to claim 1 is characterized in that: The operation process of the cloud collaborative control module includes the following steps: Receive and analyze the comprehensive analysis report transmitted by the data analysis module, and extract key data, wherein the key data includes equipment health status, fault risk level and trend prediction; Based on the comprehensive analysis results and the real-time load demand of multiple substations, a sparse distributed optimization algorithm is used to determine the load distribution and control priority of each substation and generate control instructions, including equipment start and stop and parameter adjustment; Distribute the control instructions to each substation node, optimize the instructions in real time using a distributed coordination mechanism, and make dynamic adjustments based on node feedback data; The final optimized control instructions are transmitted to the edge computing response module through the local area network, the control execution is started, and the execution feedback is monitored in real time.

6. A substation control system based on cloud control and local area network according to claim 5, characterized in that: The formula of the sparse distributed optimization algorithm is as follows: in, represents the minimization of the global load dispatch cost function F; N represents the number of substations involved in load dispatch and control; t represents the execution status of the control and optimization algorithm in a specific time period; represents the control parameters of the ith substation node at time t; represents the load scheduling cost function of the i-th node; represents other substation nodes that communicate sparsely with the i-th substation node through the local area network in the distributed system; represents the sparse regularization coefficient; It represents the sum of squares of the differences in control parameters between nodes i and j.

7. A substation control system based on cloud control and local area network according to claim 1, characterized in that: The operation process of the edge computing response module includes the following steps: Receive control instructions transmitted by the cloud collaborative control module, parse the instruction content and extract control parameters of related devices; Rapidly localize the key data in the analysis report generated by the data analysis module, use the Markov random field model to build the spatiotemporal dependency relationship between edge nodes, and map the key data into a probabilistic graph structure; Combined with the real-time environmental data and control instructions of the local area network, the local equipment in the substation is responded to and controlled, and the operation instructions of key equipment are processed first; Based on the real-time feedback mechanism, the equipment response is monitored and the immediate operation status of the equipment is compared with the expected control effect. If there is a deviation, the control strategy is dynamically adjusted; The operating status and control adjustment of edge nodes are summarized and feedback reports are generated, and key operating data and adjustment information are transmitted to the cloud collaborative control module.

8. A substation control system based on cloud control and local area network according to claim 7, characterized in that: The Markov random field model specifically includes constructing a dependency graph structure between substation edge nodes, where nodes represent device state variables and edges represent spatiotemporal associations between devices; constraining node relationships through conditional probability distribution functions to form a joint probability model of state variables.

9. The substation control system based on cloud control and local area network according to claim 1 is characterized in that: The security guarantee module implements dynamic management of user rights based on a multi-factor identity authentication module, and uses symmetric and asymmetric encryption technologies to encrypt data transmission content.

Images