Data security management and control method and system for new energy power grid system

Abstract

The invention relates to a data security management and control method and system for a new energy power grid system, and the method comprises the steps: collecting power grid data based on a preset data collection mode, and the power grid data comprises power grid operation state data, energy supply and demand data, energy price data, new energy power generation data and user power consumption data; identifying and classifying the power grid data through a preset data classification algorithm; and encrypting the classified power grid data, and storing the encrypted power grid data in a power grid database. The method has the effect of improving the adaptability of the data security management and control algorithm of the new energy power grid system and the power grid operation state.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid data security, and in particular to a data security management and control method and system for a new energy power grid system. Background Art

[0002] As global carbon emissions continue to increase and climate change becomes increasingly severe, new energy power systems, as an important means to achieve low-carbon economy and environmental protection goals, are receiving more and more attention and investment. However, while bringing clean energy, new energy power systems also face many challenges, especially in data security management. The massive data generated by new energy power grid systems, including marketing, power grids, materials, finance, etc., has the characteristics of large data volume, large user scale, multiple data collection points, and complex data types, making data security management particularly important.

[0003] New energy power grid systems have potential security risks throughout the entire data life cycle, from data collection, transmission, storage to processing and use. Security issues such as data leakage and cyber attacks not only affect the stable operation of the power system, but may also pose a major threat to the country's critical infrastructure. In addition, the electricity generated by new energy power systems is volatile, which makes power grid control more complicated and further increases the difficulty of data security management and control.

[0004] In the current data security management and control methods, although a variety of technical means are adopted, such as data encryption, access control, abnormal behavior monitoring, etc., there are still some problems, especially the problem of insufficient adaptability of algorithms to reality, mainly including the following aspects: the new energy power grid system needs to process a large amount of data in real time, but some existing advanced algorithms, although with high accuracy, have high computational complexity and are difficult to meet real-time requirements; the new energy power grid system is greatly affected by the natural environment. For example, extreme weather such as high temperature and strong wind may cause power grid failures, and existing algorithms often find it difficult to accurately predict and respond to these complex environmental changes; intelligent sensors and monitoring equipment can monitor the status of the power grid in real time, but existing algorithms often find it difficult to accurately identify and warn of potential safety risks when processing these data, resulting in high false alarm and missed alarm rates; the intelligent energy management system is one of the most important technologies in the new energy power system, but existing algorithms often find it difficult to adapt to real-time changes in the power grid in terms of optimizing energy storage, transmission and use, resulting in inflexible and inefficient power dispatching. Summary of the invention

[0005] In order to improve the adaptability of the data security management and control algorithm of the new energy power grid system to the power grid operation status, the present application provides a data security management and control method and system for the new energy power grid system.

[0006] In the first aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions: A data security control method for a new energy power grid system, the data security control method for a new energy power grid system comprising: Based on a preset data collection method, collect power grid data, the power grid data includes power grid operation status data, energy supply and demand data, energy price data, new energy power generation data and user power consumption data; Identify and classify the power grid data using a preset data classification algorithm; The classified power grid data is encrypted and stored in a power grid database.

[0007] By adopting the above technical solution, the grid operation status data, energy supply and demand data, energy price data, new energy power generation data and user electricity consumption data are widely collected to ensure that the collected data covers all aspects of grid operation, providing a comprehensive and detailed information basis for subsequent data analysis and decision-making. Through the preset data collection method, the latest data of the grid can be obtained in real time or quasi-real time, which is helpful to timely discover and deal with potential security issues. The collected grid data is automatically identified and classified using the preset data classification algorithm. The automatic classification algorithm can significantly improve the data processing efficiency and reduce manual intervention and errors. Through the sophisticated classification algorithm, the grid data can be divided into different categories according to the security level of the grid data, which is convenient for subsequent data management and analysis. The classified grid data is encrypted and securely stored in the grid database. Encryption technology can effectively protect the grid data from unauthorized access and tampering, and ensure the confidentiality and integrity of the data. As the core of data storage, the security and stability of the grid database are directly related to the operation of the entire grid system. Through encrypted storage, the protection capability of the database can be further improved, and the encrypted data maintains a high level of security during storage and transmission. Once data leakage or tampering occurs, it can be traced and located through the traceability mechanism provided by encryption technology.

[0008] In a preferred example, the present application may be further configured as follows: after encrypting the classified power grid data and storing it in the power grid database, the data security management and control method of the new energy power grid system further includes: Monitoring algorithm analysis status data during the collection, classification, encryption, transmission and storage of power grid data; Inputting the algorithm analysis state number into a preset algorithm ecological model, and determining the current algorithm evaluation score based on the algorithm ecological model; According to the current algorithm evaluation score, the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing the power grid data is adjusted accordingly.

[0009] By adopting the above technical solution, by monitoring the algorithm analysis status data in the process of power grid data processing, the operation efficiency and performance of the algorithm can be understood in real time. According to the actual performance of the algorithm, the algorithm parameters can be dynamically adjusted and optimized or an algorithm more suitable for the current data characteristics can be selected, thereby improving the overall efficiency and accuracy of data processing. The data volume and complexity of the new energy power grid system will continue to increase. By dynamically adjusting the algorithm, the system can better adapt to this change and maintain efficient and stable operation. The algorithm ecological model not only evaluates the performance of the current algorithm, but also predicts potential problems or bottlenecks. When the algorithm ecological model finds that the performance of an algorithm begins to decline or is about to reach its limit, it can issue an early warning so that the operation and maintenance personnel have enough time to intervene and optimize, avoiding service interruptions caused by a sudden decline in system performance. Through continuous algorithm performance monitoring and evaluation, potential algorithm defects or errors can be discovered and repaired in time, preventing system failures and data security problems caused by algorithm problems. The decision-making process based on algorithm evaluation scores is more objective and accurate, reducing the subjectivity and uncertainty of human judgment, and improving decision-making efficiency and accuracy. According to the results of algorithm performance evaluation, computing resources and storage resources can be allocated more reasonably to ensure that key business and data processing tasks are given priority.

[0010] In a preferred example, the present application can be further configured as follows: the algorithm ecological model is obtained by: Acquire historical algorithm analysis status data, and classify the historical algorithm analysis status data based on the collection, classification, encryption, transmission and storage process of power grid data; The classified algorithm analysis status data is input into a preset machine learning model, and based on the algorithm ecological analysis rules preset in the machine learning model, the algorithm analysis status data in the process of collecting, classifying, encrypting, transmitting and storing the power grid data are respectively analyzed to obtain algorithm health evaluation rules corresponding to different processes; According to the algorithm health evaluation rules, an algorithm ecological model is generated.

[0011] By adopting the above technical solutions, using historical algorithms to analyze status data, and analyzing these data through machine learning models, the establishment of the algorithm ecological model is more objective based on the analysis of a large amount of historical data, reducing the influence of human bias and subjective judgment, making decisions more scientific, and the machine learning model can capture subtle patterns and trends in the data, thereby generating more accurate algorithm health evaluation rules, improving the accuracy and reliability of the evaluation, and automatically building and updating the algorithm ecological model, reducing the workload of human intervention and manual adjustment, and improving work efficiency. With the continuous learning and optimization of the machine learning model, the algorithm ecological model can gradually adapt to changes in the power grid system and realize more intelligent data security management and control. The algorithm ecological model can continuously receive new algorithm analysis status data and update and optimize it through the machine learning model. With the continuous development and changes of the power grid system, the algorithm ecological model can continuously learn and adapt to new data characteristics and algorithm performance, and maintain its advanced evaluation and optimization capabilities.

[0012] In a preferred example, the present application can be further configured as follows: the algorithm ecology analysis rules include algorithm analysis variable analysis rules, data transmission variable analysis rules, valid data variable analysis rules, and invalid identification variable analysis rules.

[0013] By adopting the above technical solution, by subdividing the analysis rules, special rules are formulated for different links such as algorithm analysis, data transmission, valid data, invalid identification, etc. The detailed rules enable the system to more accurately identify and handle problems in each link, quickly locate faults or abnormal points, and improve the efficiency of problem solving. According to the characteristics and needs of different links, computing resources and storage resources can be allocated more reasonably to improve resource utilization efficiency. For example, the invalid identification variable analysis rule pays special attention to the identification and processing of invalid or abnormal data. By timely identifying and filtering invalid or abnormal data, the risk of sensitive information leakage can be reduced, user privacy and power grid data security can be protected, and only high-quality data can be ensured to be used for subsequent analysis and processing, thereby improving The accuracy of data analysis and decision-making; the algorithm analysis variable analysis rules focus on the performance and stability of the algorithm itself. By continuously monitoring the algorithm analysis status data, it is possible to promptly detect algorithm performance degradation or potential failures, and take measures in advance to prevent system crashes or data loss. When problems occur in the algorithm, it is possible to quickly switch to a backup algorithm or adjust the algorithm parameters to ensure the continuous and stable operation of the system; the data transmission variable analysis rules focus on the efficiency and security of the data transmission process. In order to meet the requirements of high efficiency and security of data transmission, it is necessary to continuously explore and apply new technologies and methods, such as encryption technology, compression algorithms, etc., so as to promote technological innovation and upgrading. By optimizing the data transmission process, user waiting time can be reduced and user experience and satisfaction can be improved.

[0014] In a preferred example, the present application may be further configured as follows: the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing power grid data is correspondingly adjusted according to the current algorithm evaluation score, including: Generate algorithm adjustment methods corresponding to different algorithms according to the sensitivity and security level of the classified power grid data and the current algorithm evaluation score; Based on the algorithm adjustment method, the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing the power grid data is adjusted accordingly.

[0015] By adopting the above technical solution, combined with the sensitivity and security level of power grid data, a customized algorithm adjustment method is generated. Power grid data with different sensitivities and security levels require different levels of protection. Through customized algorithm adjustment, it can be ensured that high-sensitivity and high-security data are more strictly encrypted, transmitted and stored for protection, while low-sensitivity and low-security data can adopt relatively lightweight processing strategies, thereby optimizing system performance while ensuring security; algorithm adjustment is based on the current algorithm evaluation score, because the environment and data status of the power grid system are dynamically changing, by real-time monitoring of the algorithm evaluation score and adjusting the algorithm accordingly, it can quickly adapt to these changes and maintain effective protection of power grid data, and algorithm adjustment is not a one-time adjustment, but can be carried out at any time as needed, which can respond to various emergencies and new security threats and maintain long-term security and stability.

[0016] In the second aspect, the above invention objective of the present application is achieved through the following technical solutions: A data security management and control system for a new energy power grid system, the data security management and control system for the new energy power grid system comprising: A data collection module is used to collect power grid data based on a preset data collection method, wherein the power grid data includes power grid operation status data, energy supply and demand data, energy price data, new energy power generation data and user power consumption data; A data classification module, used to identify and classify the power grid data using a preset data classification algorithm; The data encryption storage module is used to encrypt the classified power grid data and store it in the power grid database.

[0017] Optionally, the data security management and control system of the new energy power grid system further includes: Algorithm status monitoring module, used to monitor algorithm analysis status data during the collection, classification, encryption, transmission and storage of power grid data; An algorithm scoring module, used to input the algorithm analysis state number into a preset algorithm ecological model, and determine the current algorithm evaluation score based on the algorithm ecological model; The algorithm adjustment module is used to adjust the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing power grid data according to the current algorithm evaluation score.

[0018] Optionally, the data security management and control system of the new energy power grid system further includes: A historical algorithm data classification module is used to obtain historical algorithm analysis status data and classify the historical algorithm analysis status data based on the collection, classification, encryption, transmission and storage process of power grid data; A rule generation module, used to input the classified algorithm analysis status data into a preset machine learning model, and based on the algorithm ecological analysis rules preset in the machine learning model, respectively analyze the algorithm analysis status data in the process of collecting, classifying, encrypting, transmitting and storing the power grid data, and obtain algorithm health evaluation rules corresponding to different processes; The model generation module is used to generate an algorithm ecological model according to the algorithm health evaluation rules.

[0019] In the third aspect, the above invention objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the data security management and control method of the new energy power grid system when executing the computer program.

[0020] In a fourth aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the data security management and control method of the new energy power grid system.

[0021] In summary, the present application includes at least one of the following beneficial technical effects: 1. Extensively collect grid operation status data, energy supply and demand data, energy price data, new energy power generation data and user electricity consumption data to ensure that the collected data covers all aspects of grid operation and provide a comprehensive and detailed information basis for subsequent data analysis and decision-making. Through the preset data collection method, the latest data of the grid can be obtained in real time or quasi-real time, which is helpful to timely discover and deal with potential security issues. The collected grid data can be automatically identified and classified using the preset data classification algorithm. The automated classification algorithm can significantly improve data processing efficiency and reduce manual intervention and errors. Through the sophisticated classification algorithm, the grid data can be divided into different categories according to the security level of the grid data, which is convenient for subsequent data management and analysis. The classified grid data is encrypted and securely stored in the grid database. Encryption technology can effectively protect the grid data from unauthorized access and tampering, and ensure the confidentiality and integrity of the data. As the core of data storage, the security and stability of the grid database are directly related to the operation of the entire grid system. Through encrypted storage, the protection capability of the database can be further improved, and the encrypted data maintains a high level of security during storage and transmission. Once data leakage or tampering occurs, it can be traced and located through the traceability mechanism provided by encryption technology; 2. By monitoring the algorithm analysis status data during the power grid data processing process, the algorithm's operating efficiency and performance can be understood in real time. According to the actual performance of the algorithm, the algorithm parameters can be dynamically adjusted and optimized or an algorithm that is more suitable for the current data characteristics can be selected, thereby improving the overall efficiency and accuracy of data processing. The data volume and complexity of the new energy power grid system will continue to increase. By dynamically adjusting the algorithm, the system can better adapt to this change and maintain efficient and stable operation. The algorithm ecological model not only evaluates the performance of the current algorithm, but also predicts potential problems or bottlenecks. When the algorithm ecological model finds that the performance of an algorithm begins to decline or is about to reach its limit, it can issue an early warning so that the operation and maintenance personnel have enough time to intervene and optimize, avoiding service interruptions caused by a sudden decline in system performance. Through continuous algorithm performance monitoring and evaluation, potential algorithm defects or errors can be discovered and repaired in a timely manner, preventing system failures and data security issues caused by algorithm problems. The decision-making process based on algorithm evaluation scores is more objective and accurate, reducing the subjectivity and uncertainty of human judgment, and improving decision-making efficiency and accuracy. According to the results of algorithm performance evaluation, computing resources and storage resources can be allocated more reasonably to ensure that key business and data processing tasks are given priority. 3. Use historical algorithm analysis status data, and analyze these data through machine learning models. Based on the analysis of a large amount of historical data, the establishment of the algorithm ecological model is more objective, reducing the impact of human bias and subjective judgment, making decision-making more scientific. The machine learning model can capture subtle patterns and trends in the data, thereby generating more accurate algorithm health evaluation rules, improving the accuracy and reliability of the evaluation, and automatically building and updating the algorithm ecological model, reducing the workload of human intervention and manual adjustment, and improving work efficiency. With the continuous learning and optimization of the machine learning model, the algorithm ecological model can gradually adapt to changes in the power grid system and achieve more intelligent data security management and control. The algorithm ecological model can continuously receive new algorithm analysis status data and update and optimize it through the machine learning model. With the continuous development and changes of the power grid system, the algorithm ecological model can continuously learn and adapt to new data characteristics and algorithm performance, and maintain its advanced evaluation and optimization capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a first implementation flow chart of the data security control method of the new energy power grid system in the embodiment of the present application; Figure 2 This is a second implementation flow chart of the data security control method of the new energy power grid system in the embodiment of the present application; Figure 3 It is a flowchart of the method for obtaining the algorithm ecological model in the embodiment of the present application; Figure 4 It is a flowchart for implementing S60 of the data security control method of the new energy power grid system in the embodiment of the present application; Figure 5 This is a principle block diagram of a data security management and control system of a new energy power grid system in an embodiment of the present application; Figure 6 It is a diagram of the internal structure of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following is combined with Figure 1-6 This application is described in further detail.

[0024] In one embodiment, if Figure 1 As shown, the present application discloses a data security management and control method for a new energy power grid system, which specifically includes the following steps: S10: Based on a preset data collection method, power grid data is collected, where the power grid data includes power grid operation status data, energy supply and demand data, energy price data, new energy power generation data, and user electricity consumption data.

[0025] Specifically, based on the preset data collection method, the power grid data is collected, wherein the power grid data includes power grid operation status data, energy supply and demand data, energy price data, new energy power generation data and user power consumption data. The power grid operation status data includes power grid load, power grid frequency, power grid voltage, power grid topology and other data, which reflect the operation status of the power grid and are the basis for power grid dispatch and operation; energy supply and demand data includes energy demand, supply, reserve and other data, which reflect the supply and demand status of the energy market and are the basis for energy market regulation and decision-making; energy price data includes power market price, energy transaction price, fuel price and other data, which reflect the price changes in the energy market and are important references for energy market transactions and decision-making; new energy power generation data includes photovoltaic, wind power, hydropower and other new energy power generation, power generation efficiency, power generation cost and other data; user power consumption data includes user power consumption, power consumption time, power consumption area and other data. These data are of great significance to the operation and market regulation of new energy power grids. If leaked or tampered with, they may lead to problems such as chaotic power grid operation and imbalance of energy market order. Therefore, measures must be taken to prevent data leakage.

[0026] In this embodiment, the preset data collection method may be an endpoint detection method, and the specific steps are as follows: (a) Data collection: Network management personnel manually record asset information and network connection relationships through physical inspections and checks of plants and stations, and input them into the EDR (Endpoint Detection and Response) system to establish an asset library and topology model, or introduce mobile inspection applications or RFID (radio frequency identification) technology to assist in recording asset information and network connection relationships, automatically record data during the inspection process, reduce manual entry errors, and improve data accuracy. The EDR system is used to continuously monitor, detect and respond to malicious activities of terminal devices (such as computers, servers, mobile devices, etc.). The EDR system integrates detection, defense and operation and maintenance functions. By monitoring the activities of terminal devices in real time, analyzing and identifying abnormal behaviors, it can quickly respond to and handle security incidents to prevent potential network threats. In this embodiment, the functions of the EDR system are as follows: The EDR system continuously collects key data through agents installed on terminal devices, including file access, process execution, network connection, etc., to ensure that the security team can understand the activity status of terminal devices in real time; Using advanced technologies such as behavioral analysis and machine learning, EDR systems can detect known and unknown threats. By analyzing the collected data in real time, potential malicious activities and attack patterns can be identified; Once a threat is detected, the EDR system can automatically execute predefined response measures, such as isolating infected devices, blocking malicious network connections, and terminating malicious processes, effectively controlling and mitigating the impact of security incidents; The EDR system provides detailed event logs and threat intelligence to help the security team conduct in-depth investigation and analysis, trace the source of the attack, reveal the complete path of the attack chain, and provide a basis for subsequent security reinforcement; The EDR system has good integration and can be seamlessly integrated with other security tools and platforms such as SIEM systems, firewalls, and anti-virus software to build a more comprehensive and coordinated security protection system; Supports proactive threat hunting, allowing security teams to use rich behavioral analysis and programmable query tools to actively search for potential unknown threats in the network, further reducing security risks.

[0027] (b) Network discovery: The EDR system deploys network scanning and discovery tools to conduct a comprehensive scan of the internal network of the plant, automatically discover network equipment, servers, industrial computers and other assets, as well as the network connection relationships between them, and can efficiently collect asset and topology data. In addition, according to the characteristics of the internal network of the plant, the scanning strategy can be customized to reduce unnecessary scanning scope and improve scanning efficiency. At the same time, large-scale scanning during business peak hours can be avoided to avoid affecting network performance. More advanced network scanning and discovery tools are used to improve the recognition accuracy of network equipment, servers, industrial computers and other assets. At the same time, the scanning results are manually reviewed to ensure the accuracy of the data.

[0028] (c) Configuration import: obtain asset information, network equipment configuration and topology relationship data from the existing asset management and network management systems of the plant, import them into the EDR system, translate them into the asset model and topology model formats used by it, and use the existing data to initialize the EDR data. In addition, before importing the data, clean and convert the source data to ensure data consistency and accuracy, including removing duplicate data, correcting erroneous data, and unifying data formats. The EDR system is compatible with asset management and network management system data in multiple formats, so that data can be imported from multiple source systems. After importing the data, verify and test the data to ensure that the data can be correctly displayed and used in the EDR system. At the same time, establish a data backup and recovery mechanism to prevent data loss or damage.

[0029] S20: Identify and classify the power grid data using a preset data classification algorithm.

[0030] Specifically, through a preset data classification algorithm, the grid data is identified and classified according to the characteristics of the new energy grid, especially the data security characteristics of distributed energy.

[0031] For example, data can be classified based on real-time requirements to obtain real-time data: including real-time operating parameters such as current, voltage, and power. These data are crucial to the stable operation of the power grid and need to be collected and processed in real time; non-real-time data: such as historical maintenance records of equipment, long-term electricity usage habits of users, etc. Although these data are also helpful for power grid management, they do not need to be processed in real time; real-time data can reflect the immediate status of the power grid and is of great significance for rapid response to power grid failures and optimization of scheduling strategies. Therefore, these data need to be classified separately and efficient data collection and processing technologies need to be adopted to ensure the real-time and accuracy of the data; although non-real-time data are not as urgent as real-time data, they are an important basis for power grid planning, equipment maintenance, user behavior analysis, etc. Classifying and managing these data will help to better utilize these data resources and improve the scientificity and effectiveness of power grid management; It is also possible to classify data based on security requirements, and obtain highly sensitive data: such as user privacy information, key equipment parameters, etc. Once these data are leaked or tampered with, they may have a serious impact on the operation of the power grid and the interests of users; low-sensitivity data: such as some public statistical data, operation logs of non-critical equipment, etc., the security requirements of these data are relatively low; highly sensitive data involves the core confidentiality of the power grid and user privacy, and strict security measures must be taken to protect them. By classifying these data separately and implementing higher-level encryption, access control and auditing and other security measures, the risk of data leakage and tampering can be significantly reduced; although low-sensitivity data also needs to be properly managed, the security requirements can be appropriately relaxed to improve the efficiency and flexibility of data processing; You can also classify data based on value density to obtain high-value density data: such as operating parameters of key equipment, user electricity consumption behavior data, etc. These data are of great value for power grid optimization scheduling, user behavior analysis and other tasks; low-value density data: such as some redundant log information, monitoring data of non-critical equipment, etc. Although these data also contain certain information, their value is relatively low; high-value density data is an important basis for power grid management and optimization. By in-depth mining and analysis of these data, potential problems and optimization space in power grid operation can be discovered, providing strong support for the intelligent and refined management of power grids. Although low-value density data also needs to be properly stored and managed, when resources are limited, priority can be given to storing and processing high-value density data to improve data utilization efficiency and effectiveness.

[0032] Furthermore, machine learning algorithms and natural language processing techniques can be used to achieve data classification and identification. S30: Encrypting the classified power grid data and storing it in the power grid database.

[0033] Specifically, the classified power grid data is encrypted, and advanced encryption technology and security protocols are used to protect the data during transmission and storage, and stored in the power grid database to ensure the confidentiality, integrity and availability of the data; In addition, for smart meters, charging piles and other equipment in the new energy power grid, technologies such as security chips can be used to ensure the secure transmission and storage of data, and symmetric encryption and asymmetric encryption algorithms can be used to implement data encryption to ensure that data is not stolen or tampered with during transmission and storage. At the same time, data watermarking technology can be combined to protect the integrity and traceability of data to ensure that data is not tampered with or forged during transmission and storage.

[0034] In one embodiment, if Figure 2 As shown, in step S30: after encrypting the classified power grid data and storing it in the power grid database, the data security management and control method of the new energy power grid system further includes: S40: Monitoring algorithm analysis status data during the collection, classification, encryption, transmission and storage of power grid data.

[0035] In this embodiment, the algorithm analysis status data refers to usage status data of using an algorithm to perform calculation analysis.

[0036] Specifically, in the process of collecting, classifying, encrypting, transmitting and storing power grid data, the usage status data of the algorithms used in all processes are monitored, namely, the algorithm analysis status data. The algorithm analysis status data can characterize the operation efficiency and performance of the algorithm. There are many types of algorithms used in the process of collecting, classifying, encrypting, transmitting and storing power grid data, for example, The behavioral analysis algorithms used by the EDR system when collecting power grid data may include: statistical anomaly detection algorithms, which calculate the statistical characteristics of terminal device activities (such as mean, standard deviation, etc.) and compare them with the baseline of normal behavior to identify abnormal behavior; rule matching algorithms, which predefine a series of security rules and match terminal device activities with these rules to identify potential malicious behavior; sequence analysis algorithms, which analyze the sequence patterns of terminal device activities and identify abnormal patterns that do not match the normal behavior sequence; graph analysis algorithms, which represent terminal device activities as graph structures and use algorithms in graph theory (such as path search, community detection, etc.) to identify abnormal behavior; machine learning algorithms used by the EDR system when collecting power grid data may include supervised learning algorithms, which use data sets with known labels to train models so that they can be used to identify abnormal behaviors. Able to identify activities similar to known malicious behaviors, including decision trees, random forests, support vector machines, etc.; unsupervised learning algorithms, that is, training on unlabeled data sets to identify abnormal behaviors by discovering the inherent structure and patterns in the data, including cluster analysis, anomaly detection, etc.; semi-supervised learning algorithms, that is, combining the characteristics of supervised learning and unsupervised learning, using a small amount of labeled data and a large amount of unlabeled data to train the model; reinforcement learning algorithms, that is, using simulated environments to let the model learn how to make the best decision to deal with potential threats; deep learning algorithms, namely recurrent neural networks (RNN), long short-term memory networks (LSTM) and convolutional neural networks (CNN), etc., are used in EDR systems to process and analyze large amounts of time series data (such as network traffic, system logs, etc.) to identify potential malicious behaviors; The algorithms used in classifying power grid data may include: clustering algorithms, i.e. using K-means, DBSCAN and other clustering algorithms to group power grid data and divide them into different categories according to the similarity of the data, which is helpful for subsequent data analysis and processing; decision trees and random forests, i.e. in classification tasks, used to build classification rules and divide power grid data into different categories according to feature attributes; support vector machines (SVM), i.e. for high-dimensional power grid data, finding the best hyperplane to separate different categories of data and achieve efficient classification; The algorithms used when encrypting power grid data may include: symmetric encryption algorithms, such as AES (Advanced Encryption Standard), which use the same key for encryption and decryption; asymmetric encryption algorithms: such as RSA, which use a pair of public and private keys for encryption and decryption; hybrid encryption systems: combining the advantages of symmetric and asymmetric encryption, using asymmetric encryption to transmit symmetric encryption keys, and then using symmetric encryption to encrypt actual data, improving encryption efficiency and security; The algorithms used in the transmission of power grid data may include: compression algorithms, such as LZ77, LZSS, etc., which are used to reduce the transmission volume of power grid data and improve transmission efficiency; secure transmission protocols, such as TLS / SSL (Transport Layer Security Protocol / Secure Sockets Layer), which ensure the confidentiality, integrity and authentication of power grid data during transmission; network coding, in distributed power grid data transmission, the use of network coding technology can improve the reliability and efficiency of data transmission, especially in the case of complex network topology or packet loss; The algorithms used when storing power grid data may include: data compression and archiving algorithms, such as GZIP, BZIP2 and other compression algorithms to reduce storage space usage, or use archiving tools (such as TAR, ZIP) to package and store infrequently accessed data; data indexing and query optimization algorithms, building indexes (such as B-tree, hash table) to improve data query efficiency, and using query optimization technology to reduce query time and resource consumption; Therefore, correspondingly, the algorithm analysis status data that characterizes the algorithm's operating efficiency and performance can be time complexity data that represents an indicator of how the algorithm's running time changes with the growth of the input scale, space complexity data used to measure the size of the additional space required by the algorithm during its operation, actual time data required for the algorithm to complete a specific task under a specific hardware and software environment, data on the amount of data that the algorithm can process per unit time, time delay data required for the algorithm to go from receiving the input to generating the output, data on the occupation of system resources such as the CPU and memory by the algorithm during its operation, and data on the algorithm's ability to maintain efficient operation as the input scale increases, etc.

[0037] S50: Input the algorithm analysis state number into a preset algorithm ecological model, and determine the current algorithm evaluation score based on the algorithm ecological model.

[0038] Specifically, the algorithm analysis state number is input into a preset algorithm ecological model, which is used to judge the adaptability of each algorithm to the current new energy power grid system network environment based on the overall performance of the algorithm in the process of collecting, classifying, encrypting, transmitting and storing power grid data, and to comprehensively judge the health score of the new energy power grid system network and the current algorithm evaluation score based on the network operation status data of the new energy power grid system represented by the power grid data.

[0039] For example, first determine the adaptability of each algorithm to the current network environment of the new energy power grid system. For example, determine the amount of bandwidth required by each algorithm during data transmission, including the data exchange requirements of the algorithm itself and the additional overhead that may be generated (such as encryption, compression, etc.), and compare the amount of bandwidth required by the algorithm with the actual available bandwidth of the current network environment. If the actual bandwidth is lower than the algorithm requirement, it may cause slow data transmission or failure. Then analyze the fluctuation of network bandwidth and evaluate the performance of the algorithm when the bandwidth is unstable. Some algorithms may have better bandwidth adaptability and can maintain stable performance when the bandwidth fluctuates; in addition, determine the tolerance of each algorithm to delay, measure the average delay and maximum delay of the current network environment, and compare them with the delay tolerance of the algorithm, and analyze the specific impact of delay on the performance of the algorithm, such as whether it will cause data loss, error accumulation or slow system response; analyze whether each algorithm has mechanisms such as packet loss retransmission and error correction, as well as the effectiveness and overhead of these mechanisms, monitor the packet loss rate of the current network environment, and compare it with the packet loss tolerance of the algorithm, analyze the impact of packet loss on the stability and accuracy of the algorithm, and whether additional measures are needed to reduce the packet loss rate or improve the packet loss tolerance of the algorithm; Then, the algorithm performance, network environment adaptability, and system operation status data represented by the power grid data are combined to calculate the current algorithm evaluation score through the algorithm ecological model, for example, Evaluation indicators are determined: Algorithm performance indicators: including running time, resource consumption (such as CPU, memory), error rate, etc.; Network environment adaptability indicators: evaluation results based on network characteristics such as bandwidth, delay, and packet loss rate; System operation status indicators: such as stability (failure rate, recovery time), efficiency (energy conversion efficiency, data transmission efficiency), security (data leakage risk, system attack protection capability), etc. Weight distribution: Assign a corresponding weight to each indicator based on its importance and impact on the overall system performance. The weight assignment can be based on expert experience, historical data or user preferences; Data Standardization: Since different indicators have different dimensions and units, they need to be standardized so that they can be compared and calculated on the same scale; Use weighted scoring method, fuzzy comprehensive evaluation method or other comprehensive evaluation models to combine the standardized indicator values ​​and weights to calculate the health score of the new energy power grid system network and the current algorithm evaluation score.

[0040] S60: According to the current algorithm evaluation score, the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing the power grid data is correspondingly adjusted.

[0041] Specifically, according to the current algorithm evaluation score, the algorithms used in the collection, classification, encryption, transmission and / or storage of power grid data that are below a preset algorithm score threshold are adjusted by replacement or adjustment. For example, when the evaluation score of the clustering algorithm used in the data classification process is low, the parameters of the clustering algorithm can be adjusted or a more suitable clustering algorithm can be selected according to the actual distribution of the power grid data.

[0042] In one embodiment, if Figure 3 As shown, the algorithm ecological model is obtained in the following way: S01: Obtain historical algorithm analysis status data, and classify the historical algorithm analysis status data based on the collection, classification, encryption, transmission and storage process of power grid data.

[0043] Specifically, historical algorithm analysis status data is obtained, and based on the collection, classification, encryption, transmission and storage process of power grid data, the historical algorithm analysis status data is correspondingly classified into data obtained in each process.

[0044] S02: Input the classified algorithm analysis status data into the preset machine learning model. Based on the preset algorithm ecological analysis rules in the machine learning model, respectively analyze the algorithm analysis status data in the process of power grid data collection, classification, encryption, transmission and storage to obtain algorithm health evaluation rules corresponding to different processes.

[0045] Specifically, the classified algorithm analysis status data is input into a preset machine learning model, and the machine learning model has preset algorithm ecological analysis rules. Through the algorithm ecological analysis rules, an algorithm ecological environment can be formed for the algorithms in the process of collecting, classifying, encrypting, transmitting and storing power grid data. In addition, the algorithm ecological analysis rules also define the standards for stable and healthy operation in this algorithm ecological environment. Therefore, based on the algorithm ecological analysis rules preset in the machine learning model, firstly, according to the algorithm types in the process of collecting, classifying, encrypting, transmitting and storing power grid data, an algorithm ecological environment corresponding to the current new energy power grid system network is created, and then the corresponding analysis is performed in the process of collecting, classifying, encrypting, transmitting and storing power grid data respectively. The algorithm analysis status data is analyzed. By analyzing the algorithm analysis status data, a standard for evaluating the stable and healthy operation of the current new energy power grid system network is defined. This standard can be the time complexity data of the indicator that the algorithm running time changes with the increase of the input scale, the space complexity data used to measure the size of the additional space required by the algorithm during the operation, the actual time data required for the algorithm to complete a specific task under a specific hardware and software environment, the amount of data that the algorithm can process per unit time, the time delay data required for the algorithm from receiving the input to generating the output, the occupation of the CPU, memory and other system resources during the operation of the algorithm, and the minimum standard for the ability of the algorithm to maintain efficient operation when the input scale increases; Since the types of algorithms are different in the different processes of power grid data collection, classification, encryption, transmission and storage, this standard is adaptively adjusted according to the characteristics of the corresponding algorithms in each process to obtain algorithm health evaluation rules corresponding to different processes.

[0046] S03: Generate an algorithm ecological model based on the algorithm health evaluation rules.

[0047] Specifically, based on the algorithm health evaluation rules, an algorithm ecological model is generated. The algorithm health evaluation rules can be adjusted dynamically, and the algorithm ecological model can also be adjusted dynamically accordingly.

[0048] In one embodiment, the algorithm ecology analysis rules include algorithm analysis variable analysis rules, data transmission variable analysis rules, valid data variable analysis rules, and invalid identification variable analysis rules.

[0049] Specifically, the algorithm ecology analysis rules include algorithm analysis variable analysis rules, data transmission variable analysis rules, valid data variable analysis rules, and invalid identification variable analysis rules; Among them, the algorithm analysis variable analysis rule refers to the rule used to analyze the change in the amount of the algorithm's calculation results for power grid data. For example, when the algorithm has a high adaptability to the current new energy power grid system network environment, the algorithm's operating efficiency and performance are excellent. At this time, the change in the algorithm's calculation results for power grid data will be stable within a range. For example, the statistical anomaly detection algorithm calculates the statistical characteristics of terminal device activities and compares them with the baseline of normal behavior to identify the amount of abnormal behavior. It should be within a stable range. When the amount of identified abnormal behavior is abnormal, it means that the algorithm has a low adaptability to the current new energy power grid system network environment. Therefore, through the analysis of the historical algorithm analysis state data by the algorithm analysis variable analysis rule, the normal range of the change in the amount of the calculation results of the power grid data corresponding to different processes is determined, thereby determining an algorithm health evaluation rule corresponding to different processes; The data transmission variable analysis rule refers to the rule used to analyze the change in the amount of data of the power grid data when the algorithm compresses and transmits the power grid data. For example, when the algorithm has a high adaptability to the current new energy power grid system network environment, the algorithm's operating efficiency and performance are excellent. At this time, the change in the amount of data after the algorithm compresses and transmits the power grid data will be stable within a range. Therefore, through the analysis of the historical algorithm analysis state data by the data transmission variable analysis rule, the normal range of the change in the amount of data of the power grid data when the power grid data is compressed and transmitted corresponding to different processes is determined, thereby determining an algorithm health evaluation rule corresponding to different processes; The effective data variable analysis rule refers to the rule used to analyze the change in the amount of effective power grid data used in the algorithm calculation. For example, when the algorithm has a high adaptability to the current new energy power grid system network environment, the algorithm's operating efficiency and performance are excellent. At this time, the change in the amount of effective power grid data used in the algorithm calculation will be stable within a range. Therefore, through the analysis of the historical algorithm analysis state data by the effective data variable analysis rule, the normal range of the change in the amount of effective power grid data used in the algorithm calculation corresponding to different processes is determined, thereby determining an algorithm health evaluation rule corresponding to different processes; The invalid identification variable analysis rule refers to a rule used to analyze the change in the amount of invalid data identified by the algorithm in the power grid data. For example, when the algorithm has a high adaptability to the current new energy power grid system network environment, the algorithm's operating efficiency and performance are excellent. At this time, the change in the amount of invalid data identified by the algorithm in the power grid data will be stable within a range. Therefore, through the analysis of the historical algorithm analysis state data by the invalid identification variable analysis rule, the normal range of the change in the amount of invalid data identified by the algorithm corresponding to different processes in the power grid data is determined, thereby determining an algorithm health evaluation rule corresponding to different processes; In this way, by combining the multiple algorithm health evaluation rules corresponding to different processes obtained above, comprehensive algorithm health evaluation rules corresponding to different processes are obtained.

[0050] In one embodiment, if Figure 4 As shown, in step S60, according to the current algorithm evaluation score, the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing the power grid data is adjusted accordingly, including: S61: Generate algorithm adjustment methods corresponding to different algorithms based on the sensitivity and security level of the classified power grid data and the current algorithm evaluation score.

[0051] Specifically, when the power grid data is identified and classified by the preset data classification algorithm, the sensitivity and security level of the power grid data are analyzed by the preset data classification algorithm, and the power grid data is classified according to the sensitivity and security level. Therefore, according to the sensitivity and security level of the classified power grid data, a comprehensive sensitivity and comprehensive security level are obtained, and then combined with the performance and operating efficiency of the algorithm in different processes represented by the current algorithm evaluation score, the adjustment or replacement method is judged and selected to generate algorithm adjustment methods corresponding to different algorithms. For example, when the comprehensive sensitivity and comprehensive security level are higher, the adjustment method should be used instead of the replacement method, and the adjustment range should be smaller to ensure system stability. When the performance and operating efficiency of the algorithm represented by the current algorithm evaluation score are higher, the adjustment method should also be used instead of the replacement method, and the adjustment range should be smaller. When the comprehensive sensitivity and comprehensive security level are lower, the replacement method should be used. When the performance and operating efficiency of the algorithm represented by the current algorithm evaluation score are higher, the replacement method should be used; therefore, combined with the current algorithm evaluation score, the comprehensive sensitivity and comprehensive security level, the algorithm adjustment method corresponding to different algorithms is generated.

[0052] S62: Based on the algorithm adjustment method, the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing the power grid data is correspondingly adjusted.

[0053] Specifically, based on the algorithm adjustment method, the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing the power grid data is adjusted accordingly.

[0054] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0055] In one embodiment, a data security control system for a new energy power grid system is provided, and the data security control system for the new energy power grid system corresponds one-to-one to the data security control method for the new energy power grid system in the above embodiment. Figure 5 As shown, the data security management and control system of the new energy power grid system includes a data collection module, a data classification module and a data encryption storage module. The detailed description of each functional module is as follows: A data collection module is used to collect power grid data based on a preset data collection method. The power grid data includes power grid operation status data, energy supply and demand data, energy price data, new energy power generation data and user power consumption data; A data classification module is used to identify and classify power grid data using a preset data classification algorithm; The data encryption storage module is used to encrypt the classified power grid data and store it in the power grid database.

[0056] Optionally, the data security management and control system of the new energy power grid system also includes: Algorithm status monitoring module, used to monitor algorithm analysis status data during the collection, classification, encryption, transmission and storage of power grid data; The algorithm scoring module is used to input the algorithm analysis state number into the preset algorithm ecological model, and determine the current algorithm evaluation score based on the algorithm ecological model; The algorithm adjustment module is used to adjust the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing power grid data according to the current algorithm evaluation score.

[0057] Optionally, the data security management and control system of the new energy power grid system also includes: The historical algorithm data classification module is used to obtain the historical algorithm analysis status data and classify the historical algorithm analysis status data based on the collection, classification, encryption, transmission and storage process of power grid data; A rule generation module is used to input the classified algorithm analysis status data into a preset machine learning model, and based on the preset algorithm ecological analysis rules in the machine learning model, respectively analyze the algorithm analysis status data in the process of power grid data collection, classification, encryption, transmission and storage, and obtain algorithm health evaluation rules corresponding to different processes; The model generation module is used to generate an algorithm ecological model based on the algorithm health evaluation rules.

[0058] Optionally, the algorithm ecology analysis rules include algorithm analysis variable analysis rules, data transmission variable analysis rules, valid data variable analysis rules, and invalid identification variable analysis rules.

[0059] Optionally, the algorithm adjustment module includes: The adjustment method acquisition submodule is used to generate algorithm adjustment methods corresponding to different algorithms based on the sensitivity and security level of the classified power grid data and the current algorithm evaluation score; The algorithm adjustment submodule is used to adjust the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing power grid data based on the algorithm adjustment method.

[0060] For the specific definition of the data security control system of the new energy power grid system, please refer to the definition of the data security control method of the new energy power grid system mentioned above, which will not be repeated here. Each module in the data security control system of the above-mentioned new energy power grid system can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0061] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store power grid data and power grid database, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a data security management and control method of a new energy power grid system is implemented.

[0062] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Collect power grid data based on the preset data collection method, including power grid operation status data, energy supply and demand data, energy price data, new energy power generation data and user power consumption data; Identify and classify power grid data through a preset data classification algorithm; The classified power grid data is encrypted and stored in the power grid database.

[0063] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Collect power grid data based on the preset data collection method, including power grid operation status data, energy supply and demand data, energy price data, new energy power generation data and user power consumption data; Identify and classify power grid data through a preset data classification algorithm; The classified power grid data is encrypted and stored in the power grid database.

[0064] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0065] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0066] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A data security management and control method for a new energy power grid system, characterized in that: The data security control method of the new energy power grid system includes: Based on a preset data collection method, collect power grid data, the power grid data includes power grid operation status data, energy supply and demand data, energy price data, new energy power generation data and user power consumption data; Identify and classify the power grid data using a preset data classification algorithm; The classified power grid data is encrypted and stored in a power grid database.

2. The data security management and control method of the new energy power grid system according to claim 1 is characterized in that: After encrypting the classified power grid data and storing it in the power grid database, the data security management and control method of the new energy power grid system further includes: Monitoring algorithm analysis status data during the collection, classification, encryption, transmission and storage of power grid data; Inputting the algorithm analysis state number into a preset algorithm ecological model, and determining the current algorithm evaluation score based on the algorithm ecological model; According to the current algorithm evaluation score, the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing the power grid data is adjusted accordingly.

3. The data security management and control method of the new energy power grid system according to claim 2 is characterized in that: The algorithm ecological model is obtained in the following way: Acquire historical algorithm analysis status data, and classify the historical algorithm analysis status data based on the collection, classification, encryption, transmission and storage process of power grid data; The classified algorithm analysis status data is input into a preset machine learning model, and based on the algorithm ecological analysis rules preset in the machine learning model, the algorithm analysis status data in the process of collecting, classifying, encrypting, transmitting and storing the power grid data are respectively analyzed to obtain algorithm health evaluation rules corresponding to different processes; According to the algorithm health evaluation rules, an algorithm ecological model is generated.

4. The data security management and control method of the new energy power grid system according to claim 3 is characterized in that: The algorithm ecology analysis rules include algorithm analysis variable analysis rules, data transmission variable analysis rules, valid data variable analysis rules, and invalid identification variable analysis rules.

5. The data security management and control method of the new energy power grid system according to claim 1 is characterized in that: The method of adjusting the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing the power grid data according to the current algorithm evaluation score includes: Generate algorithm adjustment methods corresponding to different algorithms according to the sensitivity and security level of the classified power grid data and the current algorithm evaluation score; Based on the algorithm adjustment method, the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing the power grid data is adjusted accordingly.

6. A data security management and control system for a new energy power grid system, characterized in that: The data security management and control system of the new energy power grid system includes: A data collection module is used to collect power grid data based on a preset data collection method, wherein the power grid data includes power grid operation status data, energy supply and demand data, energy price data, new energy power generation data and user power consumption data; A data classification module, used to identify and classify the power grid data using a preset data classification algorithm; The data encryption storage module is used to encrypt the classified power grid data and store it in the power grid database.

7. The data security management and control system of the new energy power grid system according to claim 6 is characterized in that: The data security management and control system of the new energy power grid system also includes: Algorithm status monitoring module, used to monitor algorithm analysis status data during the collection, classification, encryption, transmission and storage of power grid data; An algorithm scoring module, used to input the algorithm analysis state number into a preset algorithm ecological model, and determine the current algorithm evaluation score based on the algorithm ecological model; The algorithm adjustment module is used to adjust the algorithm in the process of collecting, classifying, encrypting, transmitting and / or storing power grid data according to the current algorithm evaluation score.

8. The data security management and control system of the new energy power grid system according to claim 7 is characterized in that: The data security management and control system of the new energy power grid system also includes: A historical algorithm data classification module is used to obtain historical algorithm analysis status data and classify the historical algorithm analysis status data based on the collection, classification, encryption, transmission and storage process of power grid data; A rule generation module, used to input the classified algorithm analysis status data into a preset machine learning model, and based on the algorithm ecological analysis rules preset in the machine learning model, respectively analyze the algorithm analysis status data in the process of collecting, classifying, encrypting, transmitting and storing the power grid data, and obtain algorithm health evaluation rules corresponding to different processes; The model generation module is used to generate an algorithm ecological model according to the algorithm health evaluation rules.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the data security management and control method of the new energy power grid system as described in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of the data security management and control method of the new energy power grid system as described in any one of claims 1 to 5 are implemented.

Images