Power network risk management system and method based on big data

Abstract

The invention discloses a power network risk management system and method based on big data, and relates to the technical field of power network management, and the system comprises an application micro-service platform, a big data memory, a streaming data processing engine, a risk identification and evaluation module, a machine learning algorithm module, and an intelligent authority management module. The output end of the application micro-service platform is connected with the input end of the big data memory, the output end of the big data memory is connected with the input end of the streaming data processing engine, and the output end of the streaming data processing engine is connected with the input end of the machine learning algorithm module. By applying the micro-service platform, cross-domain data analysis is realized, the problems that an existing system is lack of integration with other industry systems and cannot perform cross-domain data sharing and analysis are solved, and the comprehensive risk management capability and the flexibility and maintainability of application programs are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power network management, and in particular to a power network risk management system and method based on big data. Background Art

[0002] With the rapid development of society, electricity has become an indispensable energy source in modern society. The power industry is actively promoting green and low-carbon development, reducing carbon emissions and improving energy efficiency. The improvement of the power network risk management system will help support this transformation process, ensure the security and reliability of the power grid in terms of new energy access and distributed energy management, and ensure the stability and security of power supply, which is of great significance for maintaining national energy security, promoting economic development and social stability. However, the network security threats faced by the power network are becoming increasingly severe. Frequent hacker attacks, virus intrusions and other incidents pose a serious threat to the safe and stable operation of the power network. At this time, the power industry needs to accelerate its transformation to digitalization and intelligence. As an important part of digital transformation, the power network risk management system needs to make full use of advanced technologies such as big data, cloud computing, and artificial intelligence to improve risk identification, assessment, early warning and response capabilities.

[0003] Therefore, it is necessary for this application to propose a power network risk management system and method based on big data to solve the problems in the background.

[0004] Patent document CN110287186B discloses a smart grid data management system and method based on sovereign blockchain technology. The above patent realizes the advantages of controllable electricity user identity information in the blockchain, supervised legality of smart contracts, targeted opening of electricity information, etc., and improves the storage and utilization efficiency of electricity data through the blockchain structure identified by the business type of electricity data application. However, the above patent cannot realize large-scale data processing and analysis functions.

[0005] Patent document CN113688381B discloses an information security risk management system based on big data. The above patent realizes the evaluation of effective prevention and control values ​​in information networks, so that users can timely understand the risk prevention and control capabilities of information networks, weaken risks when facing risks, and evaluate damaged assets in combination with effective prevention and control evaluation values, and classify damaged assets, sort them according to importance, and finally select damaged assets that need to be repaired according to importance for repair. The repair cost is evaluated through the expression of the repair cost evaluation value, so that the repair cost can be clearly understood, and the cost consumption caused by unnecessary asset repair can be reduced. Risk management is effectively carried out by using risk prevention and control, loss assessment, and cost assessment. However, the above patent cannot realize cross-domain data analysis functions.

[0006] Patent document CN111882453B discloses a power grid enterprise management system based on the application of new technologies such as big cloud, Internet of Things, mobile and intelligence. The above patent realizes real-time monitoring, display, risk warning and evaluation of major operating cost data such as "quantity, price, fee, loss and cost". It can provide early warning and proactive response to abnormal cost information, and at the same time establish an equipment asset cost analysis decision model to improve the scientific and lean level of the company's investment decision management and enhance the decision-making support capabilities. However, the above patent cannot achieve the function of strong scalability and efficient processing of large-scale data.

[0007] Patent document CN117390495B discloses a multi-source data risk management system and method based on big data. The above patent realizes the selection and access of data sources for the same type of users through the data source access management module, reduces the probability of increased risk of abnormal situations in data calls due to improper selection of third-party data sources, and improves the efficiency and success rate of data calls. However, the above patent cannot achieve effective integration and fusion of diversified data types.

[0008] In summary, the above patents cannot realize the functions of large-scale data processing and analysis, cross-domain data analysis, strong scalability, efficient processing of large-scale data, and effective integration and fusion of diversified data types, resulting in untimely risk identification, inaccurate assessment, delayed warning and response, data silos and inconsistency, unreasonable resource allocation, lack of flexibility and scalability, and poor user experience; To this end, this application proposes a power network risk management system and method based on big data that can realize large-scale data processing and analysis functions, cross-domain data analysis functions, strong scalability, efficient processing of large-scale data, and effective integration and fusion of diversified data types. Summary of the invention

[0009] The purpose of the present invention is to provide a power network risk management system and method based on big data to solve the technical problems proposed in the above background technology, such as the inability to realize large-scale data processing and analysis functions, cross-domain data analysis functions, strong scalability, efficient processing of large-scale data and effective integration and fusion of diversified data types, resulting in untimely risk identification, inaccurate assessment, delayed early warning and response, data silos and inconsistency, unreasonable resource allocation, lack of flexibility and scalability, and poor user experience.

[0010] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a power network risk management system based on big data, the system comprising an application microservice platform, a big data storage device, a streaming data processing engine, a risk identification and assessment module, a machine learning algorithm module, and an intelligent authority management module; The output end of the application microservice platform is connected to the input end of the big data storage device, the output end of the big data storage device is connected to the input end of the streaming data processing engine, the output end of the streaming data processing engine is connected to the input end of the machine learning algorithm module, and the output ends of the machine learning algorithm module and the big data storage device are connected to the input end of the intelligent authority management module; The application microservice platform includes an API gateway module, a configuration management module, a service discovery and registration module, and a distributed tracking module; The service discovery and registration module registers and discovers external modules through the service registration center, the API gateway module communicates and exchanges data through a RESTful-style API, and the configuration management module transmits information and responds to the distributed tracking module through an event-driven mechanism.

[0011] Preferably, the big data storage device includes a data acquisition module, a data storage module, a distributed computing framework, a data query engine, and a data visualization tool; The data acquisition module is connected to the data storage module through data signals, the distributed computing framework processes the information in the data storage module through ETL, and the data storage module is connected to the data query engine and data visualization tool through the network.

[0012] Preferably, the streaming data processing engine includes a data processor, a window operation engine and a state management engine; The data processor, window operation engine and state management engine are connected through internal communication.

[0013] Preferably, the risk identification and assessment module includes a risk identification module, a risk assessment module, and a risk monitoring module; The risk identification module transmits the identified risks to the risk assessment module, and the risk assessment module transmits the results to the risk monitoring module.

[0014] Preferably, the machine learning algorithm module includes a feature extraction module, a machine learning model module, a model training and evaluation module, and a user interaction module; Data is transmitted between the data preprocessing and feature extraction modules through message queues. The feature vector extracted by the feature extraction module is passed to the machine learning algorithm module through the data interface. The model results output by the machine learning algorithm module are passed to the model training and evaluation module through RESTful API calls. The model training and evaluation module is called to the user interaction module through remote procedure calls, and the user interaction module is connected to the user.

[0015] Preferably, the intelligent rights management module includes a user identity authentication module, an information control module, an access control module and a log audit module; The user authentication module is connected to the information control module through the API interface. The information control module defines the user's permissions and roles. The access control module controls the user's access to resources based on the permission information. The information control module and the access control module are connected through data transmission. The access control module records the user's operation log and connects to the log audit module for auditing and monitoring through message queue transmission.

[0016] Preferably, the output end of the data acquisition module is connected to the input end of the data processor, the output end of the data processor is connected to the input end of the distributed tracking module, and the output end of the distributed tracking module is connected to the input end of the feature extraction module.

[0017] Preferably, the output end of the user identity authentication module is connected to the input end of the data storage module, and the output end of the data storage module is connected to the input end of the user interaction module; The output end of the API gateway module is connected to the input end of the service discovery and registration module, the output end of the service discovery and registration module is connected to the input end of the risk monitoring module, and the output end of the risk monitoring module is connected to the input end of the access control module.

[0018] Preferably, the implementation method of the power network risk management system comprises the following steps: Big data storage establishes a huge data warehouse to collect structured data such as power system operation data, equipment status information, risk assessment reports, and unstructured data such as network security problem lists and daily inspection records. The data will be stored in the basic database and dynamically stored in the real-time database through real-time data collection technology; The streaming data processing engine uses big data processing technology to verify and clean the collected data. The risk identification and assessment module establishes a network security risk assessment and analysis model to calculate the network security risk indicators of each management object. The results are stored in a specific result database in the big data storage, and are classified and compared. The user authentication module will identify the user according to the user authority management matrix of the information control module. The access control module will restrict user operations and access rights. Through dynamic report generation and export, document query and download, it will present personalized risk indicator comparison results to users. The power network risk management system based on big data also integrates digital certificates and login passwords to enhance the security of user identity authentication. Add data verification logic to the system design, use data verification technology to ensure data accuracy, and combine big data technology to perform data visualization, machine learning and real-time data processing.

[0019] Preferably, the implementation method further comprises the following steps: (5) Collect real-time operation data of the power network, including electrical parameters of each node, equipment status parameters, environmental parameters, power quality parameters, network status parameters, and user power consumption data; (6) Multimodal data fusion technology obtains real-time data and historical data by accessing big data storage, and fuses data from different sources; (7) The application microservice platform splits the data into multiple microservices, each of which is deployed and operated independently to share and integrate data; (8) The streaming data processing engine uses distributed computing and big data processing technology to clean the processed data to generate a continuous data stream, and performs real-time analysis and calculation to build a data system framework; (9) The data system framework uses artificial intelligence and machine learning algorithms to analyze, identify potential risks and anomalies, build intelligent prediction models, and intelligently analyze and predict real-time data of the power network.

[0020] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention realizes cross-domain data analysis by applying a microservice platform. The application program on the application microservice platform is split into multiple microservices, each of which is responsible for a specific functional module. Independent deployment and operation are achieved through containerization technology, which solves the problem that the existing system lacks integration with other industry systems and cannot perform cross-domain data sharing and analysis, and improves the comprehensive risk management capability, flexibility and maintainability of the application program; 2. The present invention uses a streaming data processing engine to achieve the functions of rapid processing and analysis of large amounts of data, monitoring, early warning and decision support, solve the problem of data processing delay in the power system, improve data processing efficiency, risk identification and early warning capabilities, and help reduce the possibility of risk occurrence; 3. The present invention uses multimodal data fusion technology to effectively integrate and fuse data from different sensors, different data sources and different modalities, solving the problem that traditional systems have limited processing capabilities for diversified data types and are unable to fully utilize various types of data information, thereby improving the system's analysis, processing and integration of multivariate data; 4. The present invention realizes comprehensive and rapid monitoring and analysis of the power network through distributed computing and big data processing technology, solves the problem that the existing system lacks the ability to process and analyze large-scale data and is difficult to cope with the complex power network environment, and constructs a system architecture with strong scalability and efficient processing of large-scale data. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a structural diagram of the power network risk management system based on big data of the present invention; Figure 2This is a structural diagram of the microservice platform used in the present invention; Figure 3 This is a structural diagram of a large data storage device of the present invention; Figure 4 It is a structural diagram of the streaming data processing engine of the present invention; Figure 5 This is a structural diagram of the risk identification and assessment module of the present invention; Figure 6 This is a structural diagram of the machine learning algorithm module of the present invention; Figure 7 This is a structural diagram of the intelligent rights management module of the present invention; Figure 8 The present invention provides a flowchart for the power network risk management system based on big data.

[0022] In the figure: 1. Application microservice platform; 2. Big data storage; 3. Streaming data processing engine; 4. Risk identification and assessment module; 5. Machine learning algorithm module; 6. Intelligent permission management module; 7. API gateway module; 8. Configuration management module; 9. Service discovery and registration module; 10. Distributed tracking module; 11. Data acquisition module; 12. Data storage module; 13. Distributed computing framework; 14. Data query engine; 15. Data visualization tool; 16. Data processor; 17. Window operation engine; 18. State management engine; 19. Risk identification module; 20. Risk assessment module; 21. Risk monitoring module; 22. Feature extraction module; 23. Machine learning model module; 24. Model training and evaluation module; 25. User interaction module; 26. User identity authentication module; 27. Information control module; 28. Access control module; 29. ​​Log audit module. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] See also Figure 1 and Figure 2 , an embodiment provided by the present invention: a power network risk management system based on big data includes an application microservice platform 1, a big data storage 2, a streaming data processing engine 3, a risk identification and evaluation module 4, a machine learning algorithm module 5, and an intelligent authority management module 6; The output end of the application microservice platform 1 is connected to the input end of the big data storage 2, the output end of the big data storage 2 is connected to the input end of the streaming data processing engine 3, the output end of the streaming data processing engine 3 is connected to the input end of the machine learning algorithm module 5, and the output ends of the machine learning algorithm module 5 and the big data storage 2 are connected to the input end of the intelligent authority management module 6; the application microservice platform 1 includes an API gateway module 7, a configuration management module 8, a service discovery and registration module 9 and a distributed tracking module 10; the service discovery and registration module 9 registers and discovers external modules through a service registration center, the API gateway module 7 communicates and exchanges data through a RESTful-style API, and the configuration management module 8 transmits information and responds to the distributed tracking module 10 through an event-driven mechanism; Furthermore, real-time operation data of the power network is collected, including electrical parameters of each node, equipment status parameters, environmental parameters, power quality parameters, network status parameters, and user power consumption data; the data collected by smart grid equipment, SCADA, fault recording devices, and video surveillance are split into multiple microservices using the microservice platform 1 for data sharing and integration, and the streaming data processing engine 3 performs distributed computing (user requests data update from the power grid N1, and program A updates database V0 to V1. Distributed synchronization operation M synchronizes V1 with V0 in the power grid N2, so that the data in the power grid N2 is synchronized with V1. According to V0, it is also updated to V1, and the data in the power grid N2 responds to the request of the power grid N2) for the audio, visual combination and time consistency of three-dimensional target detection, monitors the power grid data, the actual location of the 3D positioning data, cleans it to generate a continuous data stream, and performs real-time analysis and calculation to build a data system framework. The luminous efficiency, start-up time, voltage change, and rated power range are scheduled from the network platform, and the offline data and real-time data are stored in different areas. The multimodal data fusion technology obtains the real-time data and historical data of the three parties by accessing the big data storage 2, and fuses the data from different sources.

[0025] See also Figure 1 , Figure 3 and Figure 4 , an embodiment provided by the present invention: a power network risk management system and method based on big data, the big data storage 2 includes a data acquisition module 11, a data storage module 12, a distributed computing framework 13, a data query engine 14, and a data visualization tool 15; the data acquisition module 11 is connected to the data storage module 12 through a data signal, the distributed computing framework 13 processes the information in the data storage module 12 through ETL, and the data storage module 12 is connected to the data query engine 14 and the data visualization tool 15 through a network; the streaming data processing engine 3 includes a data processor 16, a window operation engine 17 and a state management engine 18; the data processor 16, the window operation engine 17 and the state management engine 18 are connected through internal communication; Furthermore, firstly, a large data warehouse is established in the big data storage 2 to collect structured data including power system operation data, equipment status information, risk assessment reports, and unstructured data such as network security problem lists and daily inspection records. The data will be stored in the basic database, and real-time collection technology will be run on the smart meter data (introducing standard current files and user connection files, specifying the proxy service platform, subscribing to remote meter reading, time-sharing metering, and electricity parameters as operation topics, and infinite loop calls); The real-time data is dynamically stored in the real-time database, and then the streaming data processing engine 3 uses big data processing technology to verify and clean the collected data. Finally, the risk identification and assessment module 4 establishes a network security risk assessment and analysis model. SELECT field1, field2 FROM myDataStream WHERE field3 > 100 Calculate the network security risk index of each management object, and store the results in a specific result database in the big data storage 2, and classify and compare them; Use the above syntax to query the data stream of the power network, select specific fields, and filter the data that meets the conditions.

[0026] See also Figure 1 , Figure 5 and Figure 6 , an embodiment provided by the present invention: a power network risk management system and method based on big data, the risk identification and evaluation module 4 includes a risk identification module 19, a risk assessment module 20, and a risk monitoring module 21; the risk identification module 19 transmits the identified risk to the risk assessment module 20, and the risk assessment module 20 transmits the result to the risk monitoring module 21; the machine learning algorithm module 5 includes a feature extraction module 22, a machine learning model module 23, a model training and evaluation module 24, and a user interaction module 25; data preprocessing and feature extraction modules 22 are transmitted through message queues, the feature vector extracted by the feature extraction module 22 is transmitted to the machine learning model module 23 through a data interface, the model result output by the machine learning model module 23 is transmitted to the model training and evaluation module 24 through a RESTful API call, the model training and evaluation module 24 is called to the user interaction module 25 through a remote procedure, and the user interaction module 25 is connected to the user; Furthermore, the power network security risk prediction model is defined as follows: Train the model: Train the model using the random forest algorithm; predict: Use the trained model to predict risk level; Simulated power network security risk data: Assume risk level label: 0-low risk, 1-high risk; Create a model and train it: Use models to predict risk; newDataFeatures = {1.5, 3.0}; Risk level; Returns 0.

[0027] See also Figure 1 and Figure 7 , an embodiment provided by the present invention: a power network risk management system and method based on big data, the intelligent authority management module 6 includes a user identity authentication module 26, an information control module 27, an access control module 28 and a log audit module 29; the user identity authentication module 26 is connected to the information control module 27 through an API interface, the information control module 27 defines the user's authority and role, the access control module 28 controls the user's access to resources according to the authority information, the information control module 27 and the access control module 28 are connected by data transmission, the access control module 28 records the user's operation log and connects to the log audit module 29 for auditing and monitoring through a message queue transmission method; Furthermore, first, the user identity authentication module 26 will identify the user identity according to the user authority management matrix of the information control module 27, and then the access control module 28 will restrict the user's operation and access rights, and present personalized risk indicator comparison results to the user through dynamic report generation and export, document query and download. The power network risk management system based on big data also integrates digital certificates plus login passwords to enhance the security of user identity authentication; finally, data verification logic is added to the system design to verify whether the user's assigned permissions are legal and exist in the system-defined permission list, to ensure that the user will not be granted unknown or invalid permissions, and to check whether there are conflicts in the user's assigned permissions, such as the user simultaneously Having permissions to read and write the same resources may lead to security risks or inconsistencies. Verify that the permissions granted to users comply with the principle of least privilege, that is, users can only have the minimum permission level required to complete their work to reduce potential security risks. Ensure that users' permissions are correctly inherited from their roles or groups, and that there are no conflicts in permission rules between roles. According to business needs, verify whether user permissions have validity limits, update or delete expired permissions in a timely manner to prevent security vulnerabilities caused by permission retention. Record permission changes and authorized operations to audit and track the history of permission changes when necessary. Review user permissions regularly to ensure consistency between permission configuration and business needs, and promptly detect and correct abnormal permission settings.

[0028] User rights management matrix: user Real-time monitoring center SCADA database Control Center administrator Read Read Read / Write Read / Write Operation and maintenance personnel Read Read Read Read Security Analyst Read Read-only Read Read-only Technical Support Read Read Read Read See also Figure 1-Figure 8 , an embodiment provided by the present invention: a power network risk management system and method based on big data, the output end of the data acquisition module 11 is connected to the input end of the data processor 16, the output end of the data processor 16 is connected to the input end of the distributed tracking module 10, the output end of the distributed tracking module 10 is connected to the input end of the feature extraction module 22; the output end of the user identity authentication module 26 is connected to the input end of the data storage module 12, the output end of the data storage module 12 is connected to the input end of the user interaction module 25; the output end of the API gateway module 7 is connected to the input end of the service discovery and registration module 9, the output end of the service discovery and registration module 9 is connected to the input end of the risk monitoring module 21, and the output end of the risk monitoring module 21 is connected to the input end of the access control module 28; Furthermore, the electrical parameters collected are first processed and integrated, data features are extracted, and then decomposed into the corresponding database for storage. The API gateway handles user authentication and authorization, controls their access rights according to their permission level, and converts requests and responses from one data format to another to adapt to the differences between the client and the backend service. When the microservice instance is started, it registers its own information with the service registration center, including the IP address, port number, and service name. User interaction provides clear and concise guidance to help users understand how to operate.

[0029] Working principle: the data acquisition module 11 collects data, the microservice platform 1 is used to decompose the platform data, realize independent deployment and operation, share and analyze cross-domain data, the streaming data processing engine 3 uses multimodal data fusion technology to fuse and process various types of data, distributed computing and big data processing technology build a system framework and monitor and analyze data, machine learning and artificial intelligence algorithms build intelligent prediction models to achieve more accurate risk assessment and prediction, and the intelligent authority management module 6 manages user access rights and controls user access to power network resources.

[0030] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A power network risk management system based on big data, characterized by: The system comprises an application microservice platform (1), a big data storage device (2), a streaming data processing engine (3), a risk identification and assessment module (4), a machine learning algorithm module (5), and an intelligent rights management module (6); The output end of the application microservice platform (1) is connected to the input end of the big data storage (2), the output end of the big data storage (2) is connected to the input end of the streaming data processing engine (3), the output end of the streaming data processing engine (3) is connected to the input end of the machine learning algorithm module (5), and the output ends of the machine learning algorithm module (5) and the big data storage (2) are connected to the input end of the intelligent rights management module (6); The application microservice platform (1) includes an API gateway module (7), a configuration management module (8), a service discovery and registration module (9) and a distributed tracing module (10); The service discovery and registration module (9) registers and discovers external modules through a service registration center, the API gateway module (7) communicates and exchanges data through a RESTful-style API, and the configuration management module (8) transmits information and responds to the distributed tracking module (10) through an event-driven mechanism.

2. The power network risk management system based on big data according to claim 1 is characterized by: The big data storage device (2) comprises a data acquisition module (11), a data storage module (12), a distributed computing framework (13), a data query engine (14), and a data visualization tool (15); The data acquisition module (11) is connected to the data storage module (12) via a data signal, the distributed computing framework (13) processes the information in the data storage module (12) via ETL, and the data storage module (12) is connected to the data query engine (14) and the data visualization tool (15) via a network.

3. The power network risk management system based on big data according to claim 1 is characterized by: The streaming data processing engine (3) includes a data processor (16), a window operation engine (17) and a state management engine (18); The data processor (16), the window operation engine (17) and the state management engine (18) are connected via internal communication.

4. The power network risk management system based on big data according to claim 1 is characterized by: The risk identification and assessment module (4) comprises a risk identification module (19), a risk assessment module (20), and a risk monitoring module (21); The risk identification module (19) transmits the identified risks to the risk assessment module (20), and the risk assessment module (20) transmits the results to the risk monitoring module (21).

5. The power network risk management system based on big data according to claim 1 is characterized by: The machine learning algorithm module (5) includes a feature extraction module (22), a machine learning model module (23), a model training and evaluation module (24), and a user interaction module (25); Data is transferred between the data preprocessing and feature extraction modules (22) via a message queue. The feature vector extracted by the feature extraction module (22) is transferred to the machine learning model module (23) via a data interface. The model result output by the machine learning model module (23) is transferred to the model training and evaluation module (24) via a RESTful API call. The model training and evaluation module (24) is called to the user interaction module (25) via a remote procedure call, and the user interaction module (25) is connected to the user.

6. The power network risk management system based on big data according to claim 1, characterized in that: The intelligent rights management module (6) comprises a user identity authentication module (26), an information control module (27), an access control module (28) and a log audit module (29); The user identity authentication module (26) is connected to the information control module (27) via an API interface. The information control module (27) defines the user's authority and role. The access control module (28) controls the user's access to resources based on the authority information. The information control module (27) and the access control module (28) are connected via data transmission. The access control module (28) records the user's operation log and connects to the log audit module (29) via a message queue transmission method for auditing and monitoring.

7. The power network risk management system based on big data according to claim 2 is characterized by: The output end of the data acquisition module (11) is connected to the input end of the data processor (16), the output end of the data processor (16) is connected to the input end of the distributed tracking module (10), and the output end of the distributed tracking module (10) is connected to the input end of the feature extraction module (22).

8. The power network risk management system based on big data according to claim 6 is characterized by: The output end of the user identity authentication module (26) is connected to the input end of the data storage module (12), and the output end of the data storage module (12) is connected to the input end of the user interaction module (25); The output end of the API gateway module (7) is connected to the input end of the service discovery and registration module (9), the output end of the service discovery and registration module (9) is connected to the input end of the risk monitoring module (21), and the output end of the risk monitoring module (21) is connected to the input end of the access control module (28).

9. A method for using a power network risk management system based on big data, applicable to a power network risk management system based on big data described in any one of 1-8, characterized in that: The implementation method of the power network risk management system comprises the following steps: Big data storage (2) Establish a huge data warehouse to collect structured data such as power system operation data, equipment status information, risk assessment reports, and unstructured data such as network security problem lists and daily inspection records. The data will be stored in the basic database and dynamically stored in the real-time database through real-time data collection technology; The streaming data processing engine (3) uses big data processing technology to verify and clean the collected data. The risk identification and assessment module (4) establishes a network security risk assessment and analysis model to calculate the network security risk index of each management object. The results are stored in a specific result database of the big data storage (2) and classified and compared. The user identity authentication module (26) will identify the user identity according to the user authority management matrix of the information control module (27), and the access control module (28) will limit the user's operation and access rights, and present personalized risk indicator comparison results to the user through dynamic report generation and export, document query and download. The power network risk management system based on big data also integrates a digital certificate plus login password method to enhance the security of user identity authentication; Add data verification logic to the system design, use data verification technology to ensure data accuracy, and combine big data technology to perform data visualization, machine learning and real-time data processing.

10. The method for using the power network risk management system based on big data according to claim 9 is characterized in that: The implementation method also includes the following steps: (5) Collect real-time operation data of the power network, including electrical parameters of each node, equipment status parameters, environmental parameters, power quality parameters, network status parameters, and user power consumption data; (6) Multimodal data fusion technology obtains real-time data and historical data by accessing big data storage (2) and fusing data from different sources; (7) Application microservice platform (1) Split data into multiple microservices, each of which is independently deployed and operated to share and integrate data; (8) Streaming data processing engine (3) uses distributed computing and big data processing technology to clean the processed data to generate a continuous data stream, and performs real-time analysis and calculation to build a data system framework; (9) The data system framework uses artificial intelligence and machine learning algorithms to analyze, identify potential risks and anomalies, build intelligent prediction models, and intelligently analyze and predict real-time data of the power network.

Images