Power grid data analysis scheduling system based on big data

Abstract

The invention discloses a power grid data analysis scheduling system based on big data, relates to the technical field of power grid data scheduling, and aims to solve the problems of inaccurate power grid data acquisition and inaccurate analysis in the prior art. According to the method, different assessment methods and models are adopted for different types of risks, so that the accuracy and pertinence of risk assessment are improved, adjustment strategies of different risk levels are formulated according to the comprehensive risk levels, the flexible and targeted scheduling strategy can better adapt to the actual requirements of power grid operation, and the risk assessment efficiency is improved. Special model establishment is carried out on different types of power grid data, the characteristics and change rules of various types of data can be more accurately captured, the accuracy and reliability of data analysis are improved through refined modeling, and the accuracy and reliability of data analysis are improved through extraction and identifier distribution of characteristic data in each model. Rapid retrieval and analysis of data can be conveniently achieved, and each piece of feature data has a clear source and meaning due to distribution of identifiers.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid data dispatching, and in particular to a power grid data analysis and dispatching system based on big data. Background Art

[0002] Grid data dispatch is an important means of power system management, which involves the collection, analysis, processing and decision-making of various data information in the power grid, aiming to ensure the safe, stable and economical operation of the power grid.

[0003] The Chinese patent with publication number CN103577939A discloses a power grid data management method and a power grid data management system, which mainly integrates the data of different professional systems required for the operation of the power grid into a panoramic model, so that the data of the power grid operation forms a unified whole, which is easier to manage, maintain, search and use, thereby improving the management efficiency of the entire power grid data system. In addition, the power grid operation panoramic model can be expanded online according to different actual situations through expansion modules, so the expansion capability of the above-mentioned power grid data management system is also stronger. Although the above-mentioned patent solves the problem of power grid data management, there are still the following problems in actual operation:

[0004] 1. The power grid data is not collected and analyzed from multiple aspects, resulting in the inability to make analysis and adjustments based on the actual power grid data.

[0005] 2. After the power grid data is acquired, the feature data in the data is not extracted more effectively, resulting in insufficient data for subsequent analysis.

[0006] 3. The final grid data obtained is not subjected to further risk analysis, resulting in the inability to carry out targeted scheduling based on the risk situation of each grid data. Summary of the invention

[0007] The purpose of the present invention is to provide a power grid data analysis and dispatching system based on big data. By adopting different assessment methods and models for different types of risks, the accuracy and pertinence of risk assessment are improved. According to the comprehensive risk level, adjustment strategies for different risk levels are formulated. This flexible and targeted dispatching strategy can better adapt to the actual needs of power grid operation. By establishing special models for different types of power grid data, the characteristics and change laws of various types of data can be captured more accurately. Refined modeling improves the accuracy and reliability of data analysis. By extracting the feature data in each model and assigning identifiers, rapid retrieval and analysis of data can be easily achieved. The assignment of identifiers ensures that each feature data has a clear source, which can solve the problems in the prior art.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] The power grid data analysis and dispatching system based on big data includes:

[0010] Power grid data acquisition unit, used for:

[0011] The power grid data is collected from the database, and the collected power grid data is distinguished. After the distinction is completed, a unique coding number is performed, and the target power grid data is obtained after the unique coding number is obtained;

[0012] Acquisition data analysis unit, used for:

[0013] Perform data analysis on the target power grid data to obtain target analysis data;

[0014] Analytical data model building unit, used to:

[0015] The target analysis data is used to establish a power grid information model, and the established power grid information model is marked with characteristic data, and the power grid model data is obtained after the characteristic data is marked;

[0016] Scheduling instruction generation unit, used to:

[0017] The grid model data is used to generate a dispatching plan, and the generated dispatching plan is transmitted to different control centers. The control center dispatches the grid data according to the dispatching plan.

[0018] Preferably, the power grid data acquisition unit is further used for:

[0019] Retrieving power grid data from a database, wherein the power grid data includes basic data, operation data, monitoring data, load data, economic data, management data and external data;

[0020] The basic data, operation data, monitoring data, load data, economic data, management data and external data are classified respectively, and after the classification, independent basic data, operation data, monitoring data, load data, economic data, management data and external data are obtained;

[0021] Uniquely code and label independent basic data, operation data, monitoring data, load data, economic data, management data and external data;

[0022] The coding structure of the unique code includes a data category code, a data type code, a serial code and a timestamp. The data category code is a specific data category, the data type code is a data type under each data category, the serial code is different data records under the same data type, and the timestamp is the collection time of different data;

[0023] Basic data, operation data, monitoring data, load data, economic data, management data and external data are uniquely coded and labeled to obtain target power grid data.

[0024] Preferably, the power grid data acquisition unit comprises:

[0025] An operation parameter real-time monitoring module is used to monitor the operation parameters of the database for retrieving power grid data in real time, wherein the operation parameters include data integrity rate, data retrieval response time and number of concurrent retrieval threads;

[0026] The first operation evaluation coefficient acquisition module is used to obtain the first operation evaluation coefficient by using the data integrity rate and the data retrieval response time; wherein the first operation evaluation coefficient is obtained by the following formula:

[0027]

[0028] Among them, F 01 represents the first operation evaluation coefficient; n represents the total number of times data is retrieved from the database; P i represents the data integrity rate corresponding to the i-th data retrieval; T i represents the data retrieval response time corresponding to the i-th data retrieval; P b represents the standard deviation of the data integrity rate corresponding to n data retrievals; T b represents the standard deviation of the data retrieval response time corresponding to n data retrievals; T c Indicates the preset reference value of data retrieval response time;

[0029] A first coefficient comparison module, used for comparing the first operation evaluation coefficient with a preset first operation coefficient threshold value to obtain a comparison result;

[0030] The quality determination module is used to determine the retrieval operation quality of the power grid data retrieved from the database according to the comparison result between the first operation evaluation coefficient and the preset first operation coefficient threshold.

[0031] Preferably, the quality determination module includes:

[0032] A first quality evaluation model extraction module, configured to extract the first operation evaluation coefficient and call the first quality evaluation model when a comparison result between the first operation evaluation coefficient and a preset first operation coefficient threshold value indicates that the first operation evaluation coefficient is lower than the preset first operation coefficient threshold value;

[0033] A first-level second operation evaluation coefficient acquisition module, used to obtain a second operation evaluation coefficient by using the first quality evaluation model in combination with the first operation evaluation coefficient and the number of concurrently called threads;

[0034] Wherein, the structure of the first quality evaluation model is as follows:

[0035]

[0036] Among them, F 02 represents the second operation evaluation coefficient obtained by the first quality evaluation model; F 01 represents the first operation evaluation coefficient; n represents the total number of times data is retrieved from the database; F y represents the preset first operating coefficient threshold; T i T represents the data retrieval response time corresponding to the i-th data retrieval; b represents the standard deviation of the data retrieval response time corresponding to n data retrievals; M i Indicates the number of concurrent call threads corresponding to the i-th data call; M b Indicates the standard deviation of the number of concurrent call threads corresponding to n data calls;

[0037] A second quality evaluation model extraction module, configured to extract the first operation evaluation coefficient and a preset first operation coefficient threshold value, and when the comparison result shows that the first operation evaluation coefficient is not lower than the preset first operation coefficient threshold value, call the second quality evaluation model;

[0038] A second-level second operation evaluation coefficient acquisition module, used to obtain a second operation evaluation coefficient by using the second quality evaluation model in combination with the first operation evaluation coefficient and the number of concurrently called threads;

[0039] Wherein, the structure of the second quality evaluation model is as follows:

[0040]

[0041] Among them, F 03 represents the second operation evaluation coefficient obtained by the second quality evaluation model; F 01 represents the first operation evaluation coefficient; n represents the total number of times data is retrieved from the database; F y represents the preset first operating coefficient threshold; T n P represents the total delay rate of the data retrieval response time corresponding to n data retrievals; n Indicates the data integrity rate corresponding to n data retrievals; M i Indicates the number of concurrent call threads corresponding to the i-th data call; M i-1 Indicates the number of concurrent call threads corresponding to the i-1th data call; M i-1 Indicates the number of concurrent call threads corresponding to the i-1th data call; T ni represents the data retrieval response time delay rate corresponding to the i-th data retrieval; Tni-1 Indicates the data retrieval response time delay rate corresponding to the i-1th data retrieval;

[0042] A second coefficient comparison module, used for comparing the second operation evaluation coefficient with a preset second operation coefficient threshold;

[0043] The abnormality determination and alarm module is used to determine that the operation quality of retrieving power grid data from the database is abnormal when the second operation evaluation coefficient is lower than the preset second operation coefficient threshold, and to issue a quality abnormality warning.

[0044] Preferably, the collected data analysis unit includes:

[0045] Acquisition data processing module, used for:

[0046] Integrate the basic data, operation data, monitoring data, load data, economic data, management data and external data in the target power grid data set;

[0047] After the data set is integrated, an integrated data set of basic data, operation data, monitoring data, load data, economic data, management data and external data is obtained;

[0048] Perform data preprocessing on the acquired integrated data set;

[0049] Data preprocessing involves data cleaning, data conversion, and data standardization on the integrated data set at one time;

[0050] After data preprocessing is completed, the integrated data set to be analyzed is obtained.

[0051] Preferably, the collected data analysis unit further includes:

[0052] Processing data analysis module for:

[0053] Conduct data analysis on the integrated data set to be analyzed;

[0054] Analyze the basic data, operation data, monitoring data, load data, economic data, management data and external data in the integrated data set to be analyzed respectively;

[0055] Among them, the data analysis of basic data is to obtain the mean, median and variance of the basic data through statistical methods; the data analysis of operating data is to obtain the change trend of the operating data through the Kalman filter method; the analysis of monitoring data is to identify the monitoring signal through the Fourier transform method; the data analysis of load data is to predict the load through regression analysis; the data analysis of economic data is to analyze the economic benefits of the power grid through cost-benefit economics; the data analysis of management data is to analyze the management data through the fault tree analysis method to optimize the allocation and use of power grid resources; the data analysis of external data is to analyze the impact of weather, economic conditions and policy changes on the power grid through the Pearson correlation coefficient method;

[0056] The integrated data set to be analyzed after analysis is marked as target analysis data.

[0057] Preferably, the analysis data model building unit includes:

[0058] Model building modules for:

[0059] Establish a power grid information model for each data in the target analysis data;

[0060] The model of basic data is established by taking the mean, median and variance in the basic data as features, and building a statistical model of the basic state of the power grid based on the features;

[0061] The model of the operating data is established by using the Kalman filter method to obtain the changing trend of the operating data and establish a time series model for the operating data;

[0062] The monitoring data model is established by using the signal features identified by Fourier transform method to establish the signal processing model of the monitoring data;

[0063] The load data model is established by using regression analysis to predict the load data, and the load data is used to establish a load prediction model;

[0064] The economic data model is established by using the economic data obtained through cost-benefit analysis to establish an economic evaluation model;

[0065] The management data model is established by applying the fault tree analysis method to the management data, and the risk assessment model is established for the management data;

[0066] The model of external data is established by using the Pearson correlation coefficient method to analyze the influence of external data, and the correlation analysis model of external data is established;

[0067] After the models are established, the target analysis model data are obtained.

[0068] Preferably, the analysis data model building unit further includes:

[0069] Model feature data labeling module, used for:

[0070] Feature data extraction is performed on target analysis model data respectively;

[0071] Extract the mean, median and variance from the statistical model of the basic state of the power grid;

[0072] Extract the changing trend characteristics of the operating data in the time series model;

[0073] Extract the signal frequency and amplitude features identified in the signal processing model;

[0074] Extract the load forecasting features with high weight values ​​in the load forecasting model;

[0075] Extract economic indicator data from the economic evaluation model;

[0076] Extract management indicator data from the risk assessment model;

[0077] Extract the factor data with the highest correlation with the power grid operation in the correlation analysis model;

[0078] Assigning an identifier to each extracted feature data;

[0079] After the identifier allocation is completed, the power grid model data is obtained.

[0080] Preferably, the scheduling instruction generating unit is further used for:

[0081] Summarize each feature data in the power grid model data to obtain a feature set;

[0082] Conduct risk assessment on the feature set, where the risk assessment includes operational risk assessment, economic risk assessment and management risk assessment;

[0083] Assign a weight to each feature in the feature set before subjecting the feature set to risk assessment;

[0084] After the weight allocation is completed, operational risk assessment, economic risk assessment and management risk assessment are carried out in sequence;

[0085] Among them, the operation risk assessment is to use logistic regression to conduct risk assessment on the change trend characteristics of the operation data in the time series model and the signal frequency and amplitude characteristics in the signal processing model, and obtain the risk level of the operation risk assessment after the assessment;

[0086] Economic risk assessment is to conduct risk assessment by sampling sensitivity analysis of economic indicator data in the economic assessment model, and obtain the risk level of economic risk assessment after evaluation;

[0087] Management risk assessment is to conduct risk assessment on the management indicator data in the risk assessment model through event tree analysis, and obtain the risk level of the management risk assessment after evaluation.

[0088] Preferably, the scheduling instruction generating unit is further used for:

[0089] The risk levels in the operational risk assessment, the economic risk assessment and the management risk assessment are classified into low risk, medium risk and high risk;

[0090] After the classification is completed, the subsequent risk matrix will be constructed to cross-analyze operational risk, economic risk and management risk, and the comprehensive risk level will be obtained after cross-analysis;

[0091] Formulate dispatch strategies based on comprehensive risk levels, including low-risk, medium-risk and high-risk adjustments;

[0092] The data included in low risk is optimized according to the risk threshold, the data included in medium risk is adjusted according to the risk threshold, and the data protected by high risk is subject to power restriction measures according to the risk threshold;

[0093] Finally, a completed dispatching plan is obtained, and the dispatching plan is transmitted to the corresponding control center according to the dispatching data type. The control center dispatches the power grid data according to the dispatching plan.

[0094] Compared with the prior art, the present invention has the following beneficial effects:

[0095] 1. The power grid data analysis and dispatching system based on big data provided by the present invention can more accurately predict the power grid load and energy demand by comprehensively analyzing the integrated data sets, thereby optimizing resource allocation. Different analysis methods are used for different types of data. Targeted analysis methods can more effectively extract and utilize information in the data, thereby improving the accuracy and efficiency of the analysis.

[0096] 2. The big data-based power grid data analysis and dispatching system provided by the present invention can more accurately capture the characteristics and changing patterns of various types of data by establishing special models for different types of power grid data. Refined modeling improves the accuracy and reliability of data analysis. By extracting the feature data in each model and assigning identifiers, it is convenient to realize rapid retrieval and analysis of data. The allocation of identifiers ensures that each feature data has a clear source and meaning.

[0097] 3. The power grid data analysis and dispatching system based on big data provided by the present invention adopts different assessment methods and models for different types of risks, thereby improving the accuracy and pertinence of risk assessment. According to the comprehensive risk level, adjustment strategies for different risk levels are formulated. This flexible and targeted dispatching strategy can better adapt to the actual needs of power grid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] Figure 1 A schematic diagram of a power grid data analysis and dispatching unit according to the present invention;

[0099] Figure 2 It is a schematic diagram of the power grid data analysis and dispatching process of the present invention. DETAILED DESCRIPTION

[0100] 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.

[0101] In order to solve the problem that the existing technology does not collect and analyze the power grid data from multiple aspects, thus making it impossible to analyze and adjust according to the actual power grid data, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions:

[0102] The power grid data analysis and dispatching system based on big data includes:

[0103] Power grid data acquisition unit, used for:

[0104] The power grid data is collected from the database, and the collected power grid data is distinguished. After the distinction is completed, a unique coding number is performed, and the target power grid data is obtained after the unique coding number is obtained;

[0105] Acquisition data analysis unit, used for:

[0106] Perform data analysis on the target power grid data to obtain target analysis data;

[0107] Analytical data model building unit, used to:

[0108] The target analysis data is used to establish a power grid information model, and the established power grid information model is marked with characteristic data, and the power grid model data is obtained after the characteristic data is marked;

[0109] Scheduling instruction generation unit, used to:

[0110] The grid model data is used to generate a dispatching plan, and the generated dispatching plan is transmitted to different control centers. The control center dispatches the grid data according to the dispatching plan.

[0111] Specifically, through real-time monitoring and analysis of data by the power grid data acquisition unit, the operating status of the power grid can be automatically adjusted to achieve optimal configuration and scheduling of power resources. By collecting different types of data, the data analysis unit adopts different analysis methods to more effectively extract and utilize information in the data, thereby improving the accuracy and efficiency of the analysis. The data analysis model establishment unit extracts and integrates characteristic data from multiple models, providing rich information support for power grid scheduling. The scheduling instruction generation unit can derive a comprehensive risk level, providing a more comprehensive and in-depth basis for the formulation of scheduling strategies.

[0112] The power grid data acquisition unit is also used for:

[0113] Retrieving power grid data from a database, wherein the power grid data includes basic data, operation data, monitoring data, load data, economic data, management data and external data;

[0114] The basic data, operation data, monitoring data, load data, economic data, management data and external data are classified respectively, and after the classification, independent basic data, operation data, monitoring data, load data, economic data, management data and external data are obtained;

[0115] Uniquely code and label independent basic data, operation data, monitoring data, load data, economic data, management data and external data;

[0116] The coding structure of the unique code includes a data category code, a data type code, a serial code and a timestamp. The data category code is a specific data category, the data type code is a data type under each data category, the serial code is different data records under the same data type, and the timestamp is the collection time of different data;

[0117] Basic data, operation data, monitoring data, load data, economic data, management data and external data are uniquely coded and labeled to obtain target power grid data.

[0118] Specifically, the power grid data is subdivided into seven categories, including basic data, operation data, monitoring data, load data, economic data, management data and external data, making the management of various types of data clearer and more organized. A unique coding number is assigned to each record under each type of data, including data category code, data type code, serial code and timestamp, which greatly improves the traceability of data and the accuracy of management. Through unique coding, the system can quickly locate the required data records, improve the efficiency of data retrieval, and thus support faster and more accurate power grid data analysis and scheduling. The unique coding makes each data record traceable, which helps to discover and prevent data tampering and misoperation, and ensure the authenticity and integrity of the data. Different access rights can be set according to different user roles and data categories to ensure the security and confidentiality of data. Through real-time monitoring and analysis of data, the operating status of the power grid can be automatically adjusted to achieve optimal configuration and scheduling of power resources and improve the stability and reliability of the power grid.

[0119] Specifically, the power grid data acquisition unit includes:

[0120] An operation parameter real-time monitoring module is used to monitor the operation parameters of the database for retrieving power grid data in real time, wherein the operation parameters include data integrity rate, data retrieval response time and number of concurrent retrieval threads;

[0121] The first operation evaluation coefficient acquisition module is used to obtain the first operation evaluation coefficient by using the data integrity rate and the data retrieval response time; wherein the first operation evaluation coefficient is obtained by the following formula:

[0122]

[0123] Among them, F 01 represents the first operation evaluation coefficient; n represents the total number of times data is retrieved from the database; P i represents the data integrity rate corresponding to the i-th data retrieval; T i represents the data retrieval response time corresponding to the i-th data retrieval; P b represents the standard deviation of the data integrity rate corresponding to n data retrievals; T b represents the standard deviation of the data retrieval response time corresponding to n data retrievals; T c Indicates the preset reference value of data retrieval response time;

[0124] A first coefficient comparison module, used for comparing the first operation evaluation coefficient with a preset first operation coefficient threshold value to obtain a comparison result;

[0125] The quality determination module is used to determine the retrieval operation quality of the power grid data retrieved from the database according to the comparison result between the first operation evaluation coefficient and the preset first operation coefficient threshold.

[0126] The technical effect of the above technical solution is: through the real-time monitoring module of operating parameters, the key operating parameters when the database retrieves power grid data can be monitored in real time, including data integrity rate, data retrieval response time and the number of concurrent retrieval threads. These parameters are crucial for evaluating the operating status and performance of the database. The first operation evaluation coefficient acquisition module uses the data integrity rate and data retrieval response time to calculate the first operation evaluation coefficient through a specific formula. This coefficient not only takes into account the integrity and response speed of a single data retrieval, but also takes into account the consistency and stability of multiple retrievals through standard deviations (Pb and Tb), as well as the comparison with the preset response time reference value (Tc), thereby providing a comprehensive evaluation index. The first coefficient comparison module compares the calculated first operation evaluation coefficient with the preset first operation coefficient threshold to obtain a comparison result. This step provides a basis for subsequent optimization. If the evaluation coefficient is lower than the threshold, it means that there may be problems with the performance of the database retrieving power grid data, which needs to be adjusted or optimized. The quality judgment module determines the retrieval operation quality of the database retrieving power grid data based on the comparison result. This judgment helps to promptly discover and solve problems in the data retrieval process, thereby improving the quality of the data and the stability of the system. Overall, this technical solution achieves comprehensive management and optimization of the grid data retrieval process through real-time monitoring, comprehensive evaluation, dynamic adjustment and intelligent judgment. This helps to improve the level of intelligent grid data management and provide strong guarantees for the safe, stable and efficient operation of the power system.

[0127] In summary, this technical solution provides strong support for the intelligent, efficient and stable management of power grid data by comprehensively evaluating the performance and quality of power grid data retrieved from the database.

[0128] Specifically, the quality determination module includes:

[0129] A first quality evaluation model extraction module, configured to extract the first operation evaluation coefficient and call the first quality evaluation model when a comparison result between the first operation evaluation coefficient and a preset first operation coefficient threshold value indicates that the first operation evaluation coefficient is lower than the preset first operation coefficient threshold value;

[0130] A first-level second operation evaluation coefficient acquisition module, used to obtain a second operation evaluation coefficient by using the first quality evaluation model in combination with the first operation evaluation coefficient and the number of concurrently called threads;

[0131] Wherein, the structure of the first quality evaluation model is as follows:

[0132]

[0133] Among them, F 02 represents the second operation evaluation coefficient obtained by the first quality evaluation model; F 01 represents the first operation evaluation coefficient; n represents the total number of times data is retrieved from the database; F y represents the preset first operating coefficient threshold; T i T represents the data retrieval response time corresponding to the i-th data retrieval; b represents the standard deviation of the data retrieval response time corresponding to n data retrievals; M i Indicates the number of concurrent call threads corresponding to the i-th data call; M b Indicates the standard deviation of the number of concurrent call threads corresponding to n data calls;

[0134] A second quality evaluation model extraction module, configured to extract the first operation evaluation coefficient and a preset first operation coefficient threshold value, and when the comparison result shows that the first operation evaluation coefficient is not lower than the preset first operation coefficient threshold value, call the second quality evaluation model;

[0135] A second-level second operation evaluation coefficient acquisition module, used to obtain a second operation evaluation coefficient by using the second quality evaluation model in combination with the first operation evaluation coefficient and the number of concurrently called threads;

[0136] Wherein, the structure of the second quality evaluation model is as follows:

[0137]

[0138] Among them, F 03 represents the second operation evaluation coefficient obtained by the second quality evaluation model; F 01 represents the first operation evaluation coefficient; n represents the total number of times data is retrieved from the database; F y represents the preset first operating coefficient threshold; T n P represents the total delay rate of the data retrieval response time corresponding to n data retrievals; n Indicates the data integrity rate corresponding to n data retrievals; M i Indicates the number of concurrent call threads corresponding to the i-th data call; M i-1 Indicates the number of concurrent call threads corresponding to the i-1th data call; M i-1 Indicates the number of concurrent call threads corresponding to the i-1th data call; T ni represents the data retrieval response time delay rate corresponding to the i-th data retrieval; T ni-1 Indicates the data retrieval response time delay rate corresponding to the i-1th data retrieval;

[0139] A second coefficient comparison module, used for comparing the second operation evaluation coefficient with a preset second operation coefficient threshold;

[0140] The abnormality determination and alarm module is used to determine that the operation quality of retrieving power grid data from the database is abnormal when the second operation evaluation coefficient is lower than the preset second operation coefficient threshold, and to issue a quality abnormality warning.

[0141] The technical effect of the above technical solution is: the solution realizes a refined evaluation of the quality of power grid data retrieval by introducing the first quality evaluation model and the second quality evaluation model. According to the comparison result of the first operation evaluation coefficient and the preset threshold, a suitable quality evaluation model is selected, and the second operation evaluation coefficient is further calculated in combination with parameters such as the number of concurrent retrieval threads. This evaluation method not only takes into account the efficiency of data retrieval, but also takes into account the stability and quality of data retrieval. By comparing the second operation evaluation coefficient with the preset second operation coefficient threshold, potential problems in the process of database retrieval of power grid data can be discovered in time. When the second operation evaluation coefficient is lower than the threshold, the abnormal judgment and alarm module will trigger a quality abnormality warning, prompting the management personnel to make timely adjustments and optimizations. This dynamic adjustment mechanism helps to ensure the stability and efficiency of the data retrieval process.

[0142] The solution effectively improves the data quality and system stability by comprehensively considering multiple key parameters in the data retrieval process, such as data integrity rate, data retrieval response time, number of concurrent retrieval threads, etc., and introducing quality evaluation models and threshold comparison mechanisms. This helps to ensure the accuracy and reliability of power grid data and provide strong guarantees for the safe, stable and efficient operation of the power system. The solution realizes the intelligent management of the power grid data retrieval process. Through real-time monitoring, comprehensive evaluation, dynamic adjustment and intelligent judgment, comprehensive monitoring and optimization of data retrieval quality can be achieved. This intelligent management method not only improves management efficiency, but also reduces the cost and risk of manual intervention. The design of the solution has certain scalability and flexibility. With the development of the power system and changes in demand, the quality evaluation model, parameters and thresholds can be adjusted and optimized according to actual conditions to adapt to new data retrieval needs and challenges.

[0143] In summary, this technical solution, by introducing a quality evaluation model and a threshold comparison mechanism, achieves refined evaluation and dynamic adjustment of the quality of power grid data retrieval, effectively improves the quality of data and the stability of the system, and provides strong support for the safe, stable and efficient operation of the power system. At the same time, the solution also has the advantages of intelligent management, scalability and flexibility, providing a strong guarantee for the future development of the power system.

[0144] Acquisition data analysis unit, including:

[0145] Acquisition data processing module, used for:

[0146] Integrate the basic data, operation data, monitoring data, load data, economic data, management data and external data in the target power grid data set;

[0147] After the data set is integrated, an integrated data set of basic data, operation data, monitoring data, load data, economic data, management data and external data is obtained;

[0148] Perform data preprocessing on the acquired integrated data set;

[0149] Data preprocessing involves data cleaning, data conversion, and data standardization on the integrated data set at one time;

[0150] After data preprocessing is completed, the integrated data set to be analyzed is obtained.

[0151] Specifically, by integrating the basic data, operation data, monitoring data, load data, economic data, management data and external data in the target power grid data, the comprehensiveness and integrity of the data are ensured. This comprehensive data set helps to understand the operation status of the power grid more deeply and provide a solid foundation for data analysis. Through data preprocessing steps (including data cleaning, data conversion and data standardization), errors, redundancy and inconsistency in the data can be eliminated, thereby improving the accuracy and reliability of the data. This is crucial for subsequent data analysis and decision-making. The integrated data set reduces the number and complexity of data access during data analysis because all relevant data are concentrated in one data set. This helps to improve the efficiency of data analysis and shorten the analysis time, so as to respond more quickly to problems and challenges in power grid operation. By integrating multiple types of data, it provides a foundation for the future expansion of the system. As the scale of the power grid expands and the technology continues to develop, new data types and sources can be easily added to meet the changing analysis needs. By comprehensively analyzing the integrated data set, the load and energy demand of the power grid can be more accurately predicted, thereby optimizing resource allocation. This helps to reduce energy waste and improve the reliability and stability of the power grid.

[0152] Processing data analysis module for:

[0153] Conduct data analysis on the integrated data set to be analyzed;

[0154] Analyze the basic data, operation data, monitoring data, load data, economic data, management data and external data in the integrated data set to be analyzed respectively;

[0155] Among them, the data analysis of basic data is to obtain the mean, median and variance of the basic data through statistical methods; the data analysis of operating data is to obtain the change trend of the operating data through the Kalman filter method; the analysis of monitoring data is to identify the monitoring signal through the Fourier transform method; the data analysis of load data is to predict the load through regression analysis; the data analysis of economic data is to analyze the economic benefits of the power grid through cost-benefit economics; the data analysis of management data is to analyze the management data through the fault tree analysis method to optimize the allocation and use of power grid resources; the data analysis of external data is to analyze the impact of weather, economic conditions and policy changes on the power grid through the Pearson correlation coefficient method;

[0156] The integrated data set to be analyzed after analysis is marked as target analysis data.

[0157] Specifically, different analysis methods are used for different types of data. For example, statistical methods are used to analyze basic data, Kalman filtering methods are used to analyze operating data, and Fourier transform methods are used to analyze monitoring data. This targeted analysis method can more effectively extract and utilize information from the data, improve the accuracy and efficiency of the analysis, and the multiple dimensions required for power grid data analysis include basic data, operating data, monitoring data, load data, economic data, management data, and external data. This comprehensive data analysis can provide a more complete evaluation of the power grid's operating status and performance, which helps decision makers make more accurate judgments. Load forecasting through regression analysis helps power grid dispatchers plan power supply in advance and ensure the stable operation of the power grid. At the same time, cost-benefit economic analysis can evaluate the economic benefits of the power grid and provide decision support for power grid investment and operation. The application of fault tree analysis in management data can identify potential problems in power grid management, thereby optimizing the allocation and use of power grid resources. This helps to reduce resource waste and improve the overall operational efficiency of the power grid. The Pearson correlation coefficient method is used to analyze the impact of weather, economic conditions, and policy changes on the power grid. This solution can consider the potential impact of external factors on the operation of the power grid. This helps power grid dispatchers better respond to external changes and ensure the stability and security of the power grid.

[0158] In order to solve the problem in the prior art that after acquiring the power grid data, the feature data in the data is not extracted more effectively, resulting in insufficient data for later analysis, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions:

[0159] Analytical data model building unit, including:

[0160] Model building modules for:

[0161] Establish a power grid information model for each data in the target analysis data;

[0162] The model of basic data is established by taking the mean, median and variance in the basic data as features, and building a statistical model of the basic state of the power grid based on the features;

[0163] The model of the operating data is established by using the Kalman filter method to obtain the changing trend of the operating data and establish a time series model for the operating data;

[0164] The monitoring data model is established by using the signal features identified by Fourier transform method to establish the signal processing model of the monitoring data;

[0165] The load data model is established by using regression analysis to predict the load data, and the load data is used to establish a load prediction model;

[0166] The economic data model is established by using the economic data obtained through cost-benefit analysis to establish an economic evaluation model;

[0167] The management data model is established by applying the fault tree analysis method to the management data, and the risk assessment model is established for the management data;

[0168] The model of external data is established by using the Pearson correlation coefficient method to analyze the influence of external data, and the correlation analysis model of external data is established;

[0169] After the models are established, the target analysis model data are obtained.

[0170] Specifically, by establishing special models for different types of power grid data (basic data, operating data, monitoring data, load data, economic data, management data, external data), it is possible to more accurately capture the characteristics and changing patterns of various types of data. Refined modeling improves the accuracy and reliability of data analysis, and helps the power grid dispatching system make more scientific decisions. Different models can quickly extract key information for different data types, reducing the complexity and time cost of data processing. Different models can quickly extract key information for different data types, reducing the complexity and time cost of data processing. Through Kalman filtering analysis of operating data, it is possible to accurately predict the changing trend of the power grid operation status and timely discover potential operating risks. The load forecasting model can predict future load demand, provide strong support for power grid dispatching, and ensure the stability and safety of power grid operation. The risk assessment model can assess the potential risks in power grid operation, provide risk warnings and response suggestions, and reduce power grid operation risks. After different types of power grid data are modeled and analyzed through their respective models, data fusion and sharing can be achieved, thereby improving data utilization and value.

[0171] Model feature data labeling module, used for:

[0172] Feature data extraction is performed on target analysis model data respectively;

[0173] Extract the mean, median and variance from the statistical model of the basic state of the power grid;

[0174] Extract the changing trend characteristics of the operating data in the time series model;

[0175] Extract the signal frequency and amplitude features identified in the signal processing model;

[0176] Extract the load forecasting features with high weight values ​​in the load forecasting model;

[0177] Extract economic indicator data from the economic evaluation model;

[0178] Extract management indicator data from the risk assessment model;

[0179] Extract the factor data with the highest correlation with the power grid operation in the correlation analysis model;

[0180] Assigning an identifier to each extracted feature data;

[0181] After the identifier allocation is completed, the power grid model data is obtained.

[0182] Specifically, by extracting key feature data from each model, the operating status, development trend, economy and risk level of the power grid can be fully reflected, covering multiple key aspects of the power grid data analysis and dispatching system, including the basic status of the power grid, time series operating data, signal processing, load forecasting, economic evaluation, risk assessment and correlation analysis. The extracted feature data include the mean, median and variance in the statistical model, the changing trend of operating data in the time series model, the signal frequency and amplitude in the signal processing model, etc. These are all accurate descriptions of the operating status of the power grid. The extraction of high-weight load forecasting features, economic indicator data and management indicator data helps to more accurately grasp the future development trend and potential risks of the power grid. By extracting and assigning identifiers to the feature data in each model, it is convenient to quickly retrieve and analyze the data. The assignment of identifiers makes each feature data have a clear source and meaning, which helps to enhance the interpretability of the data analysis results. By extracting and integrating feature data from multiple models, rich information support is provided for power grid dispatching.

[0183] In order to solve the problem in the prior art that the final acquired power grid data is not further analyzed for risk, which leads to the inability to carry out targeted dispatch according to the risk situation of each power grid data, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions:

[0184] The scheduling instruction generation unit is also used to:

[0185] Summarize each feature data in the power grid model data to obtain a feature set;

[0186] Conduct risk assessment on the feature set, where the risk assessment includes operational risk assessment, economic risk assessment and management risk assessment;

[0187] Assign a weight to each feature in the feature set before subjecting the feature set to risk assessment;

[0188] After the weight allocation is completed, operational risk assessment, economic risk assessment and management risk assessment are carried out in sequence;

[0189] Among them, the operation risk assessment is to use logistic regression to conduct risk assessment on the change trend characteristics of the operation data in the time series model and the signal frequency and amplitude characteristics in the signal processing model, and obtain the risk level of the operation risk assessment after the assessment;

[0190] Economic risk assessment is to conduct risk assessment by sampling sensitivity analysis of economic indicator data in the economic assessment model, and obtain the risk level of economic risk assessment after evaluation;

[0191] Management risk assessment is to conduct risk assessment on the management indicator data in the risk assessment model through event tree analysis, and obtain the risk level of the management risk assessment after evaluation.

[0192] The risk levels in the operational risk assessment, the economic risk assessment and the management risk assessment are classified into low risk, medium risk and high risk;

[0193] After the classification is completed, the subsequent risk matrix will be constructed to cross-analyze operational risk, economic risk and management risk, and the comprehensive risk level will be obtained after cross-analysis;

[0194] Formulate dispatch strategies based on comprehensive risk levels, including low-risk, medium-risk and high-risk adjustments;

[0195] The data included in low risk is optimized according to the risk threshold, the data included in medium risk is adjusted according to the risk threshold, and the data protected by high risk is subject to power restriction measures according to the risk threshold;

[0196] Finally, a completed dispatching plan is obtained, and the dispatching plan is transmitted to the corresponding control center according to the dispatching data type. The control center dispatches the power grid data according to the dispatching plan.

[0197] Specifically, multiple feature data of the power grid model are aggregated to form a feature set, and then a multi-dimensional assessment of operation risk, economic risk and management risk is conducted. This comprehensive and systematic analysis method can more accurately reflect the actual operation status and potential risks of the power grid. For different types of risks (operation risk, economic risk and management risk), the scheme adopts different assessment methods and models (such as logistic regression, sensitivity analysis and event tree analysis), thereby improving the accuracy and pertinence of risk assessment. Before conducting risk assessment, the scheme assigns weights to each feature in the feature set. This weight allocation method can reflect the importance of different features in risk assessment, thereby improving the rationality of the assessment results, and dividing the risk level into low risk, medium risk and high risk. This clear division helps decision makers to understand the risk situation more clearly and adopt corresponding dispatching strategies. By constructing a risk matrix for cross-analysis, the scheme can derive a comprehensive risk level, providing a more comprehensive and in-depth basis for the formulation of dispatching strategies. According to the comprehensive risk level, the scheme formulates adjustment strategies for different risk levels, including low-risk data optimization, medium-risk parameter adjustment and high-risk power restriction measures. This flexible and targeted dispatching strategy can better adapt to the actual needs of power grid operation, and ultimately transmit the dispatching plan to the corresponding control center according to the type of dispatched data, and the control center dispatches the power grid data according to the dispatching plan. This data transmission and control method can achieve rapid information transmission and efficient execution, and improve the real-time and accuracy of power grid dispatching.

[0198] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0199] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A power grid data analysis and dispatching system based on big data, characterized in that: include: Power grid data acquisition unit, used for: The power grid data is collected from the database, and the collected power grid data is distinguished. After the distinction is completed, a unique coding number is performed, and the target power grid data is obtained after the unique coding number is obtained; Acquisition data analysis unit, used for: Perform data analysis on the target power grid data to obtain target analysis data; Analytical data model building unit, used to: The target analysis data is used to establish a power grid information model, and the established power grid information model is marked with characteristic data, and the power grid model data is obtained after the characteristic data is marked; Scheduling instruction generation unit, used to: The grid model data is used to generate a dispatching plan, and the generated dispatching plan is transmitted to different control centers. The control center dispatches the grid data according to the dispatching plan.

2. The power grid data analysis and dispatching system based on big data according to claim 1 is characterized in that: The power grid data acquisition unit is also used for: Retrieving power grid data from a database, wherein the power grid data includes basic data, operation data, monitoring data, load data, economic data, management data and external data; The basic data, operation data, monitoring data, load data, economic data, management data and external data are classified respectively, and after the classification, independent basic data, operation data, monitoring data, load data, economic data, management data and external data are obtained; Uniquely code and label independent basic data, operation data, monitoring data, load data, economic data, management data and external data; The coding structure of the unique code includes a data category code, a data type code, a serial code and a timestamp. The data category code is a specific data category, the data type code is a data type under each data category, the serial code is different data records under the same data type, and the timestamp is the collection time of different data; Basic data, operation data, monitoring data, load data, economic data, management data and external data are uniquely coded and labeled to obtain target power grid data.

3. The power grid data analysis and dispatching system based on big data according to claim 2 is characterized in that: The power grid data acquisition unit comprises: An operation parameter real-time monitoring module is used to monitor the operation parameters of the database for retrieving power grid data in real time, wherein the operation parameters include data integrity rate, data retrieval response time and number of concurrent retrieval threads; The first operation evaluation coefficient acquisition module is used to obtain the first operation evaluation coefficient by using the data integrity rate and the data retrieval response time; wherein the first operation evaluation coefficient is obtained by the following formula: Among them, F 01 represents the first operation evaluation coefficient; n represents the total number of times data is retrieved from the database; P i represents the data integrity rate corresponding to the i-th data retrieval; T i represents the data retrieval response time corresponding to the i-th data retrieval; P b represents the standard deviation of the data integrity rate corresponding to n data retrievals; T b represents the standard deviation of the data retrieval response time corresponding to n data retrievals; T c Indicates the preset reference value of data retrieval response time; A first coefficient comparison module, used for comparing the first operation evaluation coefficient with a preset first operation coefficient threshold value to obtain a comparison result; The quality determination module is used to determine the retrieval operation quality of the power grid data retrieved from the database according to the comparison result between the first operation evaluation coefficient and the preset first operation coefficient threshold.

4. The power grid data analysis and dispatching system based on big data according to claim 3 is characterized in that: The quality determination module comprises: A first quality evaluation model extraction module, configured to extract the first operation evaluation coefficient and call the first quality evaluation model when a comparison result between the first operation evaluation coefficient and a preset first operation coefficient threshold value indicates that the first operation evaluation coefficient is lower than the preset first operation coefficient threshold value; A first-level second operation evaluation coefficient acquisition module, used to obtain a second operation evaluation coefficient by using the first quality evaluation model in combination with the first operation evaluation coefficient and the number of concurrently called threads; Wherein, the structure of the first quality evaluation model is as follows: Among them, F 02 represents the second operation evaluation coefficient obtained by the first quality evaluation model; F 01 represents the first operation evaluation coefficient; n represents the total number of times data is retrieved from the database; F y represents the preset first operating coefficient threshold; T i represents the data retrieval response time corresponding to the i-th data retrieval; T b represents the standard deviation of the data retrieval response time corresponding to n data retrievals; M i Indicates the number of concurrent call threads corresponding to the i-th data call; M b Indicates the standard deviation of the number of concurrent call threads corresponding to n data calls; A second quality evaluation model extraction module, configured to extract the first operation evaluation coefficient and a preset first operation coefficient threshold value, and when the comparison result shows that the first operation evaluation coefficient is not lower than the preset first operation coefficient threshold value, call the second quality evaluation model; A second-level second operation evaluation coefficient acquisition module, used to obtain a second operation evaluation coefficient by using the second quality evaluation model in combination with the first operation evaluation coefficient and the number of concurrently called threads; Wherein, the structure of the second quality evaluation model is as follows: Among them, F 03 represents the second operation evaluation coefficient obtained by the second quality evaluation model; F 01 represents the first operation evaluation coefficient; n represents the total number of times data is retrieved from the database; F y represents the preset first operating coefficient threshold; T n P represents the total delay rate of the data retrieval response time corresponding to n data retrievals; n Indicates the data integrity rate corresponding to n data retrievals; M i Indicates the number of concurrent call threads corresponding to the i-th data call; M i-1 Indicates the number of concurrent retrieval threads corresponding to the i-1th data retrieval; M i-1 Indicates the number of concurrent call threads corresponding to the i-1th data call; T ni represents the data retrieval response time delay rate corresponding to the i-th data retrieval; T ni-1 Indicates the data retrieval response time delay rate corresponding to the i-1th data retrieval; A second coefficient comparison module, used for comparing the second operation evaluation coefficient with a preset second operation coefficient threshold; The abnormality determination and alarm module is used to determine that the operation quality of retrieving power grid data from the database is abnormal when the second operation evaluation coefficient is lower than the preset second operation coefficient threshold, and to issue a quality abnormality warning.

5. The power grid data analysis and dispatching system based on big data according to claim 2 is characterized in that: The data collection and analysis unit comprises: Acquisition data processing module, used for: Integrate the basic data, operation data, monitoring data, load data, economic data, management data and external data in the target power grid data set; After the data set is integrated, an integrated data set of basic data, operation data, monitoring data, load data, economic data, management data and external data is obtained; Perform data preprocessing on the acquired integrated data set; Data preprocessing involves data cleaning, data conversion, and data standardization on the integrated data set at one time; After data preprocessing is completed, the integrated data set to be analyzed is obtained.

6. The power grid data analysis and dispatching system based on big data according to claim 5 is characterized in that: The collected data analysis unit also includes: Processing data analysis module for: Conduct data analysis on the integrated data set to be analyzed; Analyze the basic data, operation data, monitoring data, load data, economic data, management data and external data in the integrated data set to be analyzed respectively; Among them, the data analysis of basic data is to obtain the mean, median and variance of the basic data through statistical methods; the data analysis of operating data is to obtain the change trend of the operating data through the Kalman filter method; the analysis of monitoring data is to identify the monitoring signal through the Fourier transform method; the data analysis of load data is to predict the load through regression analysis; the data analysis of economic data is to analyze the economic benefits of the power grid through cost-benefit economics; the data analysis of management data is to analyze the management data through the fault tree analysis method to optimize the allocation and use of power grid resources; the data analysis of external data is to analyze the impact of weather, economic conditions and policy changes on the power grid through the Pearson correlation coefficient method; The integrated data set to be analyzed after analysis is marked as target analysis data.

7. The power grid data analysis and dispatching system based on big data according to claim 6 is characterized in that: The analysis data model building unit includes: Model building modules for: Establish a power grid information model for each data in the target analysis data; The model of basic data is established by taking the mean, median and variance in the basic data as features, and building a statistical model of the basic state of the power grid based on the features; The model of the operating data is established by using the Kalman filter method to obtain the changing trend of the operating data and establish a time series model for the operating data; The monitoring data model is established by using the signal features identified by Fourier transform method to establish the signal processing model of the monitoring data; The load data model is established by using regression analysis to predict the load data, and the load data is used to establish a load prediction model; The economic data model is established by using the economic data obtained through cost-benefit analysis to establish an economic evaluation model; The management data model is established by applying the fault tree analysis method to the management data, and the risk assessment model is established for the management data; The model of external data is established by using the Pearson correlation coefficient method to analyze the influence of external data, and the correlation analysis model of external data is established; After the models are established, the target analysis model data are obtained.

8. The power grid data analysis and dispatching system based on big data according to claim 7 is characterized in that: The analysis data model building unit further includes: Model feature data labeling module, used for: Feature data extraction is performed on target analysis model data respectively; Extract the mean, median and variance from the statistical model of the basic state of the power grid; Extract the changing trend characteristics of the operating data in the time series model; Extract the signal frequency and amplitude features identified in the signal processing model; Extract the load forecasting features with high weight values ​​in the load forecasting model; Extract economic indicator data from the economic evaluation model; Extract management indicator data from the risk assessment model; Extract the factor data with the highest correlation with the power grid operation in the correlation analysis model; Assigning an identifier to each extracted feature data; After the identifier allocation is completed, the power grid model data is obtained.

9. The power grid data analysis and dispatching system based on big data according to claim 8, characterized in that: The scheduling instruction generating unit is further used for: Summarize each feature data in the power grid model data to obtain a feature set; Conduct risk assessment on the feature set, where the risk assessment includes operational risk assessment, economic risk assessment and management risk assessment; Assign a weight to each feature in the feature set before subjecting the feature set to risk assessment; After the weight allocation is completed, operational risk assessment, economic risk assessment and management risk assessment are carried out in sequence; Among them, the operation risk assessment is to use logistic regression to conduct risk assessment on the change trend characteristics of the operation data in the time series model and the signal frequency and amplitude characteristics in the signal processing model, and obtain the risk level of the operation risk assessment after the assessment; Economic risk assessment is to conduct risk assessment by sampling sensitivity analysis of economic indicator data in the economic assessment model, and obtain the risk level of economic risk assessment after evaluation; Management risk assessment is to conduct risk assessment on the management indicator data in the risk assessment model through event tree analysis, and obtain the risk level of the management risk assessment after evaluation.

10. The power grid data analysis and dispatching system based on big data according to claim 9, characterized in that: The scheduling instruction generating unit is further used for: The risk levels in the operational risk assessment, the economic risk assessment and the management risk assessment are classified into low risk, medium risk and high risk; After the classification is completed, the subsequent risk matrix will be constructed to cross-analyze operational risk, economic risk and management risk, and the comprehensive risk level will be obtained after cross-analysis; Formulate dispatch strategies based on comprehensive risk levels, including low-risk, medium-risk and high-risk adjustments; The data included in low risk is optimized according to the risk threshold, the data included in medium risk is adjusted according to the risk threshold, and the data protected by high risk is subject to power restriction measures according to the risk threshold; Finally, a completed dispatching plan is obtained, and the dispatching plan is transmitted to the corresponding control center according to the dispatching data type. The control center dispatches the power grid data according to the dispatching plan.

Images