An intelligent power consumption load management method based on big data analysis

Abstract

The present invention relates to the technical field of big data analysis and data processing. An intelligent power consumption load management method based on big data analysis provided by the present invention constructs an accurate power consumption load prediction model by integrating historical power consumption data, climate data, power grid equipment status, and user behavior data. This method uses blockchain technology to improve the security and traceability of prediction data and realizes the automation of the power consumption load management process with the help of smart contracts. The specific steps include data acquisition and preprocessing, construction and verification of the load prediction model, storage of prediction data and generation of hash values, writing and execution of smart contracts, and processing and evaluation of process node data. This method effectively solves the problems of abnormal load data and model errors and improves the stability and management efficiency of the power grid system.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis and data processing, and particularly to an intelligent power consumption load management method based on big data analysis. Background Art

[0002] The application of big data analysis in intelligent power consumption load management is mainly reflected in the following aspects: Power grid enterprises can integrate various data resources, such as historical power consumption data, climate data, etc., to build complex prediction models and achieve accurate prediction of future power consumption loads. Such prediction helps power grid enterprises reasonably arrange power generation plans, reduce operating costs, and improve power quality. Big data analysis can monitor the operating status of power grid equipment in real time. By mining the massive data collected by sensors and monitoring points, potential fault risks can be discovered in a timely manner and preventive maintenance can be carried out. This can effectively avoid the occurrence of large-scale power outages and improve the reliability of the power grid. By analyzing the operating data of each link of the power grid, big data technology can assist managers in achieving the optimal allocation of resources, including the optimization of transmission line capacity, the transformation and upgrading of substations, etc. This helps to improve the overall operating efficiency of the power grid and promote energy conservation and emission reduction.

[0003] Although big data analysis has shown significant advantages in intelligent power consumption load management, there are the following technical pain points: Although big data analysis can monitor the operating status of power grid equipment in real time, the power grid power consumption load management depends on the accuracy and timeliness of big data analysis. In practical applications, due to abnormal power grid power consumption load data and data analysis model errors, etc., the intelligent power consumption load management based on big data analysis may make mistakes. If the mistakes in power consumption load management are not discovered in time, it will affect the normal operation of the power grid system. For example, the power grid power consumption load data may be abnormal in practical applications, such as data missing, incorrect records, or inaccurate values. Data missing, incorrect records, or inaccurate values will directly affect the accuracy of load prediction. At the same time, the data analysis model may also have errors, resulting in the prediction results deviating from the actual power consumption load situation. If the above mistakes are not discovered and corrected in time, it will lead to deviations in the decision-making of intelligent power consumption load management based on big data analysis, and further affect the normal operation of the power grid system. Incorrect load prediction may lead to insufficient power supply during peak hours or over-generation during off-peak hours, thus wasting resources and possibly damaging the lifespan of power grid equipment. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the present invention provides an intelligent power consumption load management method based on big data analysis. Through data preprocessing steps such as data cleaning and outlier removal, the quality of the input data is improved, and the impact of data anomalies on the prediction model is reduced, thus solving the problem of inaccurate prediction caused by abnormal power grid power consumption load data. By comparing the predicted data with the actual power consumption load data, analyzing the reasons for the prediction error, and adjusting the model parameters according to the error reasons, the prediction model is continuously optimized, and the accuracy and credibility of the prediction results are improved. Using blockchain technology to store power consumption load prediction data and generate hash values enhances the time traceability, security, and immutability of the data, solving the problems of data security and traceability in power grid operation management. The present invention realizes the automatic allocation, monitoring, and recording of the nodes in the power consumption load management process through smart contract technology, reduces human intervention, improves management efficiency, and solves the problems of low efficiency and error-proneness caused by the traditional power consumption load management process relying on manual operations.

[0005] Continuously comparing the predicted data with the actual load data, analyzing the prediction error, and adjusting the model parameters realizes the continuous optimization of the prediction model and improves the accuracy of long-term prediction. Integrating historical power consumption data, climate data, power grid equipment status, and user behavior data, a precise power consumption load prediction model is constructed, and the power grid operation management data is obtained and processed in real time, realizing the real-time nature of data processing and enhancing the ability to respond promptly to changes in power grid operation.

[0006] The present invention improves the accuracy of power consumption load prediction and the introduction of an automated management process significantly improves the stability and management efficiency of the power grid system, provides strong support for the intelligent management of power grid enterprises, and solves the problems of low stability and management efficiency of the power grid system.

[0007] To solve the above technical problems, the specific technical solutions of the present invention are as follows:

[0008] The present invention provides an intelligent power consumption load management method based on big data analysis, including:

[0009] Step S101, obtaining power grid operation management data, where the power grid operation management data includes historical power consumption data, climate data, power grid equipment operation status data, and user behavior data;

[0010] Step S102, constructing a power consumption load prediction model based on historical power consumption data, climate data, power grid equipment operation status data, and user behavior data, obtaining real-time power grid operation management data, and substituting the real-time power grid operation management data into the power consumption load prediction model to obtain power consumption load prediction data;

[0011] Step S103: Establish a timestamp for the electricity load prediction data based on the data generation time, and store it in the blockchain to generate the hash value corresponding to the electricity load prediction data;

[0012] Step S104: Obtain the electricity load management process nodes and the process node management rules, and construct an electricity load process node smart contract based on the electricity load management process nodes, the process node management rules, and the hash value corresponding to the electricity load prediction data stored in the blockchain;

[0013] Step S105: Establish a data matching label for the electricity load process node smart contract, match the grid operation management data with the data matching label, transmit the grid operation management data to the corresponding electricity load process node smart contract according to the matching result to obtain the first process node smart contract data processing result, randomly sort the electricity load process node smart contracts to obtain the randomly sorted electricity load process node smart contracts, match the randomly sorted electricity load process node smart contracts with the electricity load prediction data to obtain the second process node smart contract data processing result, match the randomly sorted electricity load process node smart contracts with the grid operation management data to obtain the third process node smart contract data processing result, and perform data analysis on the first process node smart contract data processing result, the second process node smart contract data processing result, and the third process node smart contract data processing result to obtain the completion degree of each process node of the electricity load management.

[0014] Furthermore, for the intelligent electricity load management method based on big data analysis provided by the present invention, the step S101 includes:

[0015] Obtain historical electricity consumption data from the data center or database of the power grid enterprise. The historical electricity consumption data includes the electricity consumption, peak load, and valley load in different time periods;

[0016] Obtain the climate data corresponding to the time period through the meteorological department database. The climate data includes temperature, humidity, wind speed, and sunshine time;

[0017] Utilize the sensors and monitoring systems deployed on the power grid equipment to obtain the operation status data of the power grid equipment in real time. The operation status data of the power grid equipment includes the voltage of the power grid equipment, the current of the power grid equipment, the power factor of the power grid equipment, and the temperature of the power grid equipment.

[0018] Furthermore, for the intelligent electricity load management method based on big data analysis provided by the present invention, the step S101 includes:

[0019] Preprocess the obtained power grid operation management data, clean the power grid operation management data, remove abnormal power grid operation management data, and obtain the preprocessed power grid operation management data;

[0020] Store the preprocessed power grid operation management data, classify the stored preprocessed power grid operation management data according to the data type, and establish retrieval tags for the classified preprocessed power grid operation management data.

[0021] Furthermore, for the intelligent power consumption load management method based on big data analysis provided by the present invention, the step S102 includes:

[0022] Conduct a correlation analysis on historical power consumption data, climate data, power grid equipment operation status data, and user behavior data to obtain features highly correlated with the power consumption load. The features highly correlated with the power consumption load include historical load features, temperature features, and humidity features;

[0023] Construct a load prediction model based on the historical load features, temperature features, and humidity features;

[0024] Obtain real-time power grid operation management data, where the real-time power grid operation management data includes real-time power consumption load, climate conditions, power grid equipment status, and user behavior information. Substitute the real-time data into the constructed power consumption load prediction model for power consumption load prediction, and calculate the power consumption load prediction data through the power consumption load prediction model.

[0025] Furthermore, for the intelligent power consumption load management method based on big data analysis provided by the present invention, the step S102 includes:

[0026] Obtain the actual power consumption load data, compare the prediction data with the actual power consumption load data to obtain the prediction data and actual power consumption load error data, match the prediction data and actual power consumption load error data in the knowledge base to obtain the error cause information, and the error cause information includes data quality problems, model irrationality, and external factor influences;

[0027] Adjust the parameters of the power consumption load prediction model according to the error cause information, use the adjusted power consumption load prediction model for re-prediction, and verify the prediction effect of the adjusted power consumption load prediction model through comparison with the actual data.

[0028] Furthermore, for the intelligent power consumption load management method based on big data analysis provided by the present invention, the step S103 includes:

[0029] Create a time stamp corresponding to each power consumption load prediction data according to the generation time of each power consumption load prediction data, and the time stamp is used to identify the generation time of the data;

[0030] Write the electricity load prediction data with timestamps into the blockchain. For each piece of electricity load prediction data stored on the blockchain, calculate its hash value using a hash function;

[0031] Store the generated hash value together with the original data on the blockchain, and record each piece of data and its corresponding hash value.

[0032] Furthermore, for the intelligent electricity load management method based on big data analysis provided by the present invention, step S104 includes:

[0033] Obtain the information of each node in the electricity load management process from the power management system or documents. The information of each node in the electricity load management process includes electricity application, approval, allocation, and monitoring links;

[0034] Obtain the management rules corresponding to the information of each node in the electricity load management process. The management rules define the operation specifications, permission settings, and data processing methods for each process node;

[0035] Generate a hash value according to the electricity load management process node and the process node management rule:

[0036] Use the obtained information of the electricity load management process node and the corresponding management rule as input data to generate a hash value.

[0037] Furthermore, for the intelligent electricity load management method based on big data analysis provided by the present invention, step S104 includes:

[0038] Store the generated hash value, as well as the relevant information of the electricity load management process node and the management rule, on the blockchain;

[0039] Utilize the intelligent contract function of the blockchain platform to write intelligent contract code according to the electricity load management process node and the management rule;

[0040] The intelligent contract will automatically execute the management rules of the process node. The intelligent contract automatically allocates, monitors, and records the electricity load according to the automatically executed management rules of the process node.

[0041] Furthermore, for the intelligent electricity load management method based on big data analysis provided by the present invention, step S105 includes:

[0042] Establish data matching tags according to the functions and requirements of each intelligent contract, and preprocess the power grid operation management data;

[0043] Use the established data matching tags to match the power grid operation management data to obtain the data corresponding to the intelligent contracts of each electricity load process node;

[0044] Transmit the power grid operation management data to the corresponding intelligent contract of the electricity load process node according to the matching result:

[0045] Classify the successfully matched power grid operation management data according to the corresponding intelligent contract of the electricity load process node;

[0046] Transmit the classified data to the corresponding intelligent contracts respectively. Each intelligent contract of the electricity load process node processes the received power grid operation management data, generates corresponding data processing results, and randomly sorts the intelligent contracts of the electricity load process nodes to obtain a list of randomly sorted intelligent contracts.

[0047] Furthermore, for the intelligent electricity load management method provided by the present invention, the step S105 includes:

[0048] Collect the data processing results of the first process node intelligent contract, the data processing results of the second process node intelligent contract, and the data processing results of the third process node intelligent contract;

[0049] Perform clustering analysis on the data processing results of the first process node intelligent contract, the data processing results of the second process node intelligent contract, and the data processing results of the third process node intelligent contract, as well as the completion degree of the intelligent contract in the data analysis of the first process node and the electricity load data of each node. Evaluate according to the clustering analysis results to obtain the completion degree of each process node of the data processing results of the first process node intelligent contract, the data processing results of the second process node intelligent contract, and the data processing results of the third process node intelligent contract. If there is data with a completion degree lower than the preset completion degree value in the data processing results of each process node of the first process node intelligent contract, the second process node intelligent contract, and the third process node intelligent contract, recheck the data with a completion degree lower than the preset value. If the recheck result is a data error, generate a data error warning message.

[0050] The beneficial effects of the present invention are mainly reflected in the following aspects:

[0051] By integrating historical electricity consumption data, climate data, power grid equipment operation status data, and user behavior data, and using correlation analysis to construct a load forecasting model, the present invention significantly improves the accuracy of electricity load forecasting. This not only helps power grid enterprises reasonably arrange power generation plans, but also effectively reduces operating costs and improves power quality.

[0052] By storing the electricity load forecasting data in the blockchain and generating a hash value, the time traceability, security, and immutability of the data are improved. The blockchain technology provides a distributed ledger, and any modification of the data will be recorded on the chain, thus preventing the data from being maliciously tampered with and enhancing the trust and security of the data.

[0053] Using smart contract technology, the automated allocation, monitoring, and recording of nodes in the electricity load management process are realized. The smart contract automatically executes according to preset management rules, reducing human intervention, improving the transparency and efficiency of the process, and reducing the risk of human errors.

[0054] By preprocessing the power grid operation management data, including data cleaning and outlier removal, the quality of the input data is improved, further enhancing the accuracy and reliability of the prediction model. Through data analysis, the completion degree of each process node is evaluated to timely discover and handle potential problems. If data errors or low processing efficiency are found, the system will generate warning messages to notify relevant personnel for timely handling, thus ensuring the normal operation of the power grid system. By continuously comparing the predicted data with the actual load data, analyzing the reasons for the prediction errors, and adjusting the model parameters, the continuous optimization of the prediction model is achieved, improving the accuracy and effectiveness of long-term prediction.

[0055] In summary, by introducing big data analysis, blockchain technology, and smart contracts, the present invention significantly improves the accuracy and efficiency of power grid electricity load management, enhances the security and stability of the system, and provides strong support for the intelligent management of power grid enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] To more clearly illustrate the technical solutions of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0057] Figure 1 It is a schematic flowchart of the intelligent electricity load management method based on big data analysis provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0058] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the specific embodiments and corresponding drawings of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention. The following will detail the technical solutions provided by each embodiment of the present invention in conjunction with the drawings.

[0059] To better understand the objectives of the present invention, the present invention will be further described in detail below.

[0060] Please refer to Figure 1 , the present invention provides an intelligent electricity load management method based on big data analysis, including:

[0061] Step S101: Obtain power grid operation management data, which includes historical electricity consumption data, climate data, power grid equipment operation status data, and user behavior data.

[0062] Step S101 mainly involves obtaining power grid operation management data. These data are an indispensable basis for subsequent electricity load forecasting and management. Specifically, the following types of data need to be obtained:

[0063] Historical electricity consumption data: It includes information such as electricity consumption, peak load, and valley load in different time periods, providing a reference for subsequent load forecasting.

[0064] Climate data: Obtained through the meteorological department's database, mainly including temperature, humidity, wind speed, and sunshine duration. Climate factors have a significant impact on power load, especially temperature and humidity. Therefore, climate data is crucial for improving the accuracy of load forecasting.

[0065] Power grid equipment operation status data: The power grid equipment operation status data is obtained in real time through sensors and monitoring systems deployed on power grid equipment, reflecting the status of the power grid equipment such as voltage, current, power factor, and equipment temperature. Understanding the equipment status helps to predict and maintain the stable operation of the power grid in a timely manner.

[0066] User behavior data: It includes users' electricity consumption habits, power consumption patterns, etc. User behavior data can help us more accurately predict future electricity loads, thereby optimizing power distribution and management.

[0067] After obtaining these data, preprocessing steps such as data cleaning, removing outliers, and classifying and storing are also required. These preprocessing operations can improve the quality and accuracy of the data, laying a solid foundation for subsequent analysis and prediction work.

[0068] Step S102: Build an electricity load forecasting model based on historical electricity consumption data, climate data, power grid equipment operation status data, and user behavior data. Obtain real-time power grid operation management data, and substitute the real-time power grid operation management data into the electricity load forecasting model to obtain electricity load forecasting data.

[0069] Historical electricity consumption data includes electricity consumption, peak, and valley loads in each time period.

[0070] Obtain climate data from the meteorological department's database, such as temperature, humidity, wind speed, and sunshine duration.

[0071] Using sensors and monitoring systems deployed on power grid equipment, real-time operation status data of power grid equipment is obtained, including voltage, current, power factor, etc. At the same time, considering user behavior data helps to more accurately predict the electricity load.

[0072] Perform correlation analysis on various types of collected data, identify features highly correlated with the electricity load, and construct a load prediction model. Obtain real-time power grid operation management data, including the current electricity load, climate conditions, power grid equipment status, and user behavior information. Input these real-time data into the constructed prediction model, and calculate the predicted data of the electricity load through calculation.

[0073] Obtain the actual electricity load data, and compare the prediction results with the actual data to evaluate the accuracy of the model. Analyze the reasons for the prediction errors, and adjust the model parameters based on these reasons to improve the prediction accuracy.

[0074] Step S103: Establish a timestamp for the electricity load prediction data based on the time of data generation, and store it in the blockchain to generate a hash value corresponding to the electricity load prediction data;

[0075] The processing flow of the electricity load prediction data in step S103 mainly includes the following steps:

[0076] Establish a timestamp: Create a corresponding timestamp for each piece of electricity load prediction data according to its generation time. The timestamp is used to uniquely identify the generation time of the data, enhancing the timeliness and traceability of the data.

[0077] Store in the blockchain: Write the electricity load prediction data with a timestamp into the blockchain. As a decentralized and tamper-proof distributed ledger technology, the blockchain enhances the security and immutability of the data.

[0078] Generate a hash value: For each piece of electricity load prediction data stored on the blockchain, calculate its hash value using a hash function. The hash value is a fixed-length digital fingerprint that can uniquely represent the original data. Any minor change in the original data will result in a significant change in the hash value, thus ensuring the integrity of the data.

[0079] Record the hash value: Store the generated hash value together with the original data on the blockchain, recording each piece of data and its corresponding hash value. Doing so can verify the integrity and non-tampering of the data without directly exposing the original data.

[0080] In summary, through the combined application of timestamps, blockchain, and hash values in step S103, the time traceability, security, and data integrity of the electricity load prediction data are enhanced, providing a reliable data foundation for subsequent electricity load management.

[0081] In step S104, obtain the power consumption load management process nodes and the process node management rules. Based on the power consumption load management process nodes, the process node management rules, and the power consumption load prediction data stored in the blockchain, generate the hash value corresponding to the power consumption load prediction data, and construct a smart contract for the power consumption load process nodes;

[0082] Step S104 describes how to obtain the power consumption load management process nodes and the process node management rules, and construct a smart contract for the power consumption load process nodes based on this information and the hash value of the power consumption load prediction data stored on the blockchain. The specific steps are as follows:

[0083] Obtain the power consumption load management process nodes: Collect information on each node of the power consumption load management process from the power management system or relevant documents. These nodes usually include links such as power consumption applications, approvals, allocations, and monitoring.

[0084] Obtain the process node management rules: The management rules define the operation specifications, permission settings, and data processing methods for each process node. These rules enhance the orderly and compliant execution of the process nodes.

[0085] Construct a smart contract in combination with the hash value: Use the power consumption load management process node information, the process node management rules, and the hash value corresponding to the power consumption load prediction data stored on the blockchain as inputs to construct a smart contract. The hash value serves as a unique identifier for the power consumption load prediction data, enhancing data integrity and traceability.

[0086] Write a smart contract using the blockchain platform: Utilize the smart contract function provided by the blockchain platform to write the smart contract code according to the process nodes and management rules. The smart contract will automatically execute the management rules of the process nodes to automatically allocate, monitor, and record the power consumption load.

[0087] Automatic execution of the smart contract: Once the smart contract is deployed on the blockchain, it will automatically execute the power consumption load management process according to the preset rules. This reduces human intervention and improves the transparency and efficiency of the process.

[0088] In this way, step S104 improves the standardization, automation, and traceability of the power consumption load management process, thereby enhancing the efficiency and accuracy of power grid operation management.

[0089] Step S105: Establish data matching tags for the smart contracts of the electricity load process nodes, match the grid operation management data with the data matching tags, transfer the grid operation management data to the corresponding smart contracts of the electricity load process nodes according to the matching results to obtain the data processing results of the first process node smart contracts, randomly sort the smart contracts of the electricity load process nodes to obtain the randomly sorted smart contracts of the electricity load process nodes, match the randomly sorted smart contracts of the electricity load process nodes with the electricity load prediction data to obtain the data processing results of the second process node smart contracts, match the randomly sorted smart contracts of the electricity load process nodes with the grid operation management data to obtain the data processing results of the third process node smart contracts, and perform data analysis on the data processing results of the first process node smart contracts, the data processing results of the second process node smart contracts, and the data processing results of the third process node smart contracts to obtain the completion degrees of each process node of the electricity load management.

[0090] Step S105 details a key step in the intelligent electricity load management method based on big data analysis, mainly involving the data processing process of the smart contracts of the electricity load process nodes. The following is the specific content and process of this step:

[0091] Establish data matching tags: For each smart contract of the electricity load process node, establish corresponding data matching tags according to its functions and requirements. The tags are used to identify and distinguish different types of grid operation management data.

[0092] Data matching and transfer: Match the grid operation management data with these matching tags so that the data can be accurately transferred to the corresponding smart contracts of the electricity load process nodes. According to the matching results, transfer the grid operation management data to the corresponding smart contracts for subsequent processing.

[0093] Data processing of the first process node smart contract: Each smart contract of the electricity load process node receives and processes the transferred grid operation management data to generate the data processing results of the first process node smart contract.

[0094] Random sorting of smart contracts: Randomly sort all the smart contracts of the electricity load process nodes to generate a list of randomly sorted smart contracts of the electricity load process nodes. This step aims to increase the robustness of the system and avoid potential prediction biases.

[0095] Data processing of the second process node smart contract: Match the randomly sorted smart contracts of the electricity load process nodes with the electricity load prediction data to generate the data processing results of the second process node smart contract. This step is used to verify the applicability and accuracy of the prediction data in the actual process nodes.

[0096] Intelligent contract data processing for the third process node: Once again, match the randomly sorted intelligent contract of the electrical load process node with the original power grid operation management data to generate the data processing result of the third process node intelligent contract. This step is used to further confirm the consistency and accuracy of the data at different processing stages.

[0097] Data analysis and evaluation: Comprehensively analyze the data processing results of the first, second, and third process node intelligent contracts, and evaluate the completion degree of each process node. Through data analysis, determine whether there is data below the preset completion degree value. If so, review this data and generate a data error warning message after confirming data errors.

[0098] This step realizes the automated processing and analysis of power grid operation management data through the application of intelligent contracts, improving the accuracy and efficiency of electricity load management. At the same time, through random sorting and multiple matching verifications, the stability and reliability of the system are enhanced.

[0099] Specifically, for the intelligent electricity load management method based on big data analysis provided by the present invention, the step S101 includes:

[0100] Obtain historical electricity consumption data from the data center or database of the power grid enterprise. The historical electricity consumption data includes electricity consumption, peak load, and valley load in different time periods;

[0101] Obtain climate data for the corresponding time period through the meteorological department database. The climate data includes temperature, humidity, wind speed, and sunshine duration;

[0102] Utilize sensors and monitoring systems deployed on power grid equipment to obtain real-time operation status data of power grid equipment. The operation status data of power grid equipment includes power grid equipment voltage, power grid equipment current, power grid equipment power factor, and power grid equipment temperature.

[0103] Specifically, for the intelligent electricity load management method based on big data analysis provided by the present invention, the step S101 includes:

[0104] Preprocess the obtained power grid operation management data, clean the power grid operation management data, and remove abnormal power grid operation management data to obtain preprocessed power grid operation management data;

[0105] Store the preprocessed power grid operation management data, classify the stored preprocessed power grid operation management data according to the type of data, and establish retrieval tags for the classified preprocessed power grid operation management data.

[0106] Specifically, for the intelligent electricity load management method based on big data analysis provided by the present invention, the step S102 includes:

[0107] Perform a correlation analysis on historical power consumption data, climate data, grid equipment operation status data, and user behavior data to obtain characteristics highly correlated with power consumption load. The characteristics highly correlated with power consumption load include historical load characteristics, temperature characteristics, and humidity characteristics;

[0108] Construct a load forecasting model based on historical load characteristics, temperature characteristics, and humidity characteristics;

[0109] Obtain real-time grid operation management data, which includes real-time power consumption load, climate conditions, grid equipment status, and user behavior information. Substitute the real-time data into the constructed power consumption load forecasting model for power consumption load forecasting, and calculate the power consumption load forecasting data through the power consumption load forecasting model.

[0110] Specifically, for the intelligent power consumption load management method based on big data analysis provided by the present invention, step S102 includes:

[0111] Obtain actual power consumption load data, compare the forecasting data with the actual power consumption load data to obtain the error data between the forecasting data and the actual power consumption load. Match the error data between the forecasting data and the actual power consumption load in the knowledge base to obtain information on the causes of errors. The information on the causes of errors includes data quality problems, unreasonable models, and external factor influences;

[0112] According to the information on the causes of errors, adjust the parameters of the power consumption load forecasting model, and use the adjusted power consumption load forecasting model for re-forecasting. Verify the forecasting effect of the adjusted power consumption load forecasting model by comparing with the actual data.

[0113] Specifically, for the intelligent power consumption load management method based on big data analysis provided by the present invention, step S103 includes:

[0114] Create a time stamp corresponding to each power consumption load forecasting data according to the generation time of each power consumption load forecasting data. The time stamp is used to identify the generation time of the data;

[0115] Write the power consumption load forecasting data with time stamps into the blockchain, and calculate the hash value of each power consumption load forecasting data stored on the blockchain using a hash function;

[0116] Store the generated hash value and the original data together on the blockchain, and record each data and its corresponding hash value.

[0117] Specifically, for the intelligent power consumption load management method based on big data analysis provided by the present invention, step S104 includes:

[0118] Obtain information on each node of the electricity load management process from the power management system or document. The information on each node of the electricity load management process includes the electricity application, approval, allocation, and monitoring links.

[0119] Obtain the management rules corresponding to the information on each node of the electricity load management process. The management rules define the operation specifications, permission settings, and data processing methods for each process node.

[0120] Generate a hash value based on the electricity load management process node and the management rule of the process node:

[0121] Use the obtained information on the electricity load management process node and the corresponding management rule as input data to generate a hash value.

[0122] Specifically, for the intelligent electricity load management method based on big data analysis provided by the present invention, step S104 includes:

[0123] Store the generated hash value, as well as the relevant information on the electricity load management process node and the management rule, on the blockchain.

[0124] Utilize the smart contract function of the blockchain platform to write smart contract code according to the electricity load management process node and the management rule.

[0125] The smart contract will automatically execute the management rules of the process node. The smart contract automatically allocates, monitors, and records the electricity load according to the management rules of the automatically executed process node.

[0126] Specifically, for the intelligent electricity load management method based on big data analysis provided by the present invention, step S105 includes:

[0127] Establish data matching tags according to the functions and requirements of each smart contract, and preprocess the power grid operation management data.

[0128] Use the established data matching tags to match the power grid operation management data to obtain data corresponding to the smart contracts of each electricity load process node.

[0129] Transmit the power grid operation management data to the smart contract of the corresponding electricity load process node according to the matching result:

[0130] Classify the successfully matched power grid operation management data according to the smart contract of the corresponding electricity load process node;

[0131] Transmit the classified data to the corresponding smart contracts respectively. The smart contracts of each electricity load process node process the received power grid operation management data to generate corresponding data processing results, and randomly sort the smart contracts of the electricity load process nodes to obtain a randomly sorted list of smart contracts.

[0132] First, according to the functions and requirements of each smart contract for the power consumption load process node, corresponding data matching tags are established, and the collected power grid operation management data is preprocessed to improve the accuracy and availability of the data.

[0133] Next, the established data matching tags are used to perform matching operations on the power grid operation management data, with the aim of finding the data corresponding to each smart contract for the power consumption load process node.

[0134] Then, according to the matching results, we accurately transmit the power grid operation management data to the corresponding smart contracts for the power consumption load process nodes, and classify the successfully matched power grid operation management data according to the corresponding smart contracts for the power consumption load process nodes. After classification, the various types of data are respectively sent to the corresponding smart contracts. After receiving these data, each smart contract for the power consumption load process node performs independent data processing and generates corresponding data processing results.

[0135] In addition, to enhance the flexibility and robustness of the system, the smart contracts for the power consumption load process nodes are randomly sorted to obtain a list of smart contracts after random sorting.

[0136] Specifically, for the intelligent power consumption load management method based on big data analysis provided by the present invention, step S105 includes:

[0137] Collect the data processing results of the first process node smart contract, the data processing results of the second process node smart contract, and the data processing results of the third process node smart contract;

[0138] Perform clustering analysis on the data processing results of the first process node smart contract, the data processing results of the second process node smart contract, and the data processing results of the third process node smart contract, as well as the completion degree of the smart contract in the data analysis of the first process node and the power consumption load data of each node. According to the clustering analysis results, an evaluation is carried out to obtain the completion degree of each process node in the data processing results of the first process node smart contract, the data processing results of the second process node smart contract, and the data processing results of the third process node smart contract. If there is data with a completion degree lower than the preset completion degree value in the data processing results of each process node in the data processing results of the first process node smart contract, the data processing results of the second process node smart contract, and the data processing results of the third process node smart contract, then the data with a completion degree lower than the preset completion degree is rechecked. If the recheck result is that the data is incorrect, a data error warning message is generated.

[0139] First, collect the data processing results of the smart contracts of the first process node, the second process node, and the third process node. These data are the key information generated during the execution of the smart contracts of each process node, reflecting the actual situation of power consumption load management.

[0140] Cluster analysis: Perform cluster analysis on the data processing results of the smart contracts of the first, second, and third process nodes collected. Cluster analysis is an unsupervised learning method used to divide data into several groups or clusters, such that the data within the same group has high similarity, while the data between different groups has low similarity.

[0141] During this process, the system pays special attention to the completion degree of the smart contracts and the power consumption load data of each node. Through the cluster analysis of these data, the efficiency and performance differences of different process nodes in processing power consumption loads can be revealed.

[0142] Evaluation and judgment: According to the results of the cluster analysis, the system evaluates the data processing completion degrees of the smart contracts of the first, second, and third process nodes. The purpose of the evaluation is to determine the actual effects of each process node in processing power consumption loads and whether there are areas that need improvement or optimization.

[0143] The system sets a preset completion degree value as the judgment criterion. If the completion degree of a certain process node is lower than this preset value, it indicates that there are problems or low efficiency in this node when processing power consumption loads.

[0144] Data recheck and warning: For the process nodes with completion degrees lower than the preset value, the system will conduct further data recheck. The purpose of the recheck is to confirm whether there are errors or abnormalities in the data to improve the accuracy of the evaluation results.

[0145] If the recheck results confirm that there are errors in the data, the system will immediately generate data error warning information. These warning information will promptly notify relevant personnel so that they can quickly take measures to correct the errors and ensure the normal progress of power consumption load management.

[0146] Through the above steps, the present invention realizes a comprehensive analysis and evaluation of the data processing results of the smart contracts of the power consumption load management process nodes in step S105, timely discovers and processes potential data problems, thereby improving the efficiency and reliability of power consumption load management.

[0147] The technical solution of the present invention solves the problems caused by reasons such as abnormal power grid power consumption load data and data analysis model errors in the following ways:

[0148] Obtain historical power consumption data, climate data, etc. from the data center or database of the power grid enterprise, and perform preprocessing, including cleaning to remove abnormal data, to improve the data quality input into the model. Based on correlation analysis, select highly correlated features such as historical load characteristics, temperature characteristics, humidity characteristics, etc. to construct a load prediction model to improve the accuracy of prediction.

[0149] Substitute the real-time power grid operation management data into the model for prediction, and verify and adjust the model according to the actual power consumption load data, and improve the model prediction effect through repeated optimization.

[0150] Generate timestamps for the power consumption load prediction data and store them on the blockchain, generating hash values to enhance the integrity and immutability of the data. Through blockchain technology, every operation of the data can be traced, enhancing the transparency and security of data processing. Construct smart contracts according to the power consumption load management process nodes and management rules, automatically execute the management rules, and reduce human errors. The smart contract is responsible for the automatic allocation, monitoring and recording of the power consumption load, improving the management efficiency and accuracy.

[0151] Classify the power grid operation management data, establish retrieval tags, and perform matching processing through smart contracts to enhance the accurate transmission of data to the corresponding process nodes. Analyze the data of the smart contract processing results, evaluate the completion degree of each process node, and promptly discover problems and conduct rechecks.

[0152] By comparing the predicted data with the actual load data, discover the prediction errors, match the error reasons in the knowledge base, and adjust the model parameters. Verify the prediction effect of the adjusted model, continuously optimize the model, and improve the prediction accuracy.

[0153] Through the above measures, the technical solution of the present invention not only improves the accuracy of the power grid power consumption load data, but also reduces the risk of human errors through automated and intelligent management methods, and improves the normal operation of the power grid system.

[0154] The technical solution of the present invention has practicality

[0155] The intelligent power consumption load management method based on big data analysis provided by the present invention has remarkable practicality, which is mainly reflected in the following aspects:

[0156] Improve the accuracy of power consumption load prediction: By integrating historical power consumption data, climate data, power grid equipment status and user behavior data, and using correlation analysis to construct a load prediction model, the accuracy of power consumption load prediction is significantly improved. This helps power grid enterprises to arrange power generation plans more precisely, reduce operating costs, and improve power quality.

[0157] Enhance the security and traceability of data: The blockchain technology is adopted to store the power load prediction data and generate hash values, improving the time traceability, security and immutability of the data. The blockchain technology provides a distributed ledger, and any modification of the data will be recorded on the chain, preventing the data from being maliciously tampered with and enhancing the trust and security of the data.

[0158] Automate the power load management process: Utilize smart contract technology to automate the allocation, monitoring and recording of nodes in the power load management process. The smart contract is automatically executed according to the preset management rules, reducing human intervention, improving the transparency and efficiency of the process, and reducing the risk of human errors.

[0159] Improve the stability and management efficiency of the power grid system: By preprocessing and classifying and storing the power grid operation management data, the quality of the input data is improved. At the same time, data analysis is carried out on the data processing results of the smart contract of the power load management process nodes to timely discover and handle potential problems, improving the stability and management efficiency of the power grid system.

[0160] Promote the intelligent management of power grid enterprises: The technical solution of the present invention provides strong support for the intelligent management of power grid enterprises by introducing big data analysis, blockchain technology and smart contracts. This not only helps to improve the management level of power grid enterprises, but also promotes the intelligent development of the entire power industry. Specific embodiments

[0162] The following is a specific embodiment based on the technical solution of the present invention:

[0163] Obtain the historical power consumption data of the past year from the data center of the power grid enterprise, including the power consumption, peak load and valley load in different time periods. Obtain the climate data of the corresponding time period from the meteorological department database, including temperature, humidity, wind speed and sunshine time. Use the sensors and monitoring systems deployed on the power grid equipment to obtain the status data of the voltage, current, power factor and equipment temperature of the power grid equipment in real time. Clean and preprocess the collected data to remove outliers and duplicate data, and improve the data quality.

[0164] Conduct a correlation analysis on the historical power consumption data, climate data, power grid equipment status data and user behavior data to determine the features highly correlated with the power load (such as historical load features, temperature features and humidity features). Build a load prediction model based on these features and verify the model using the real-time power grid operation management data. Compare the prediction results with the actual power load data, analyze the reasons for the prediction errors, and adjust the model parameters according to the error reasons to optimize the prediction effect.

[0165] Generate timestamps for the electricity load prediction data and store them in the blockchain. Use a hash function to calculate the hash value of each prediction data, and store the hash value and the original data together on the blockchain to enhance the integrity and immutability of the data.

[0166] Obtain the electricity load management process node information and management rules, such as the operation specifications, permission settings, and data processing methods in the links of electricity application, approval, allocation, and monitoring. According to the process node information, management rules, and the hash value of the prediction data stored on the blockchain, write the smart contract code.

[0167] Deploy the smart contract on the blockchain platform. The smart contract will automatically execute the management rules of the electricity load management process nodes to achieve the automatic allocation, monitoring, and recording of the electricity load.

[0168] Classify the power grid operation management data and establish retrieval tags, and use the data matching tags to transmit the data to the corresponding smart contract. Each smart contract processes the received data and generates corresponding data processing results. Analyze the processing results of the smart contract to evaluate the completion degree of each process node. If data errors or low processing efficiency are found, generate warning information and notify relevant personnel for processing.

[0169] Through the above steps, the technical solution of the present invention can significantly improve the accuracy and efficiency of the power grid electricity load management, enhance the security and stability of the system, and provide strong support for the intelligent management of power grid enterprises.

[0170] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications. The above-described embodiments of the present invention do not constitute a limitation on the protection scope of the present invention.

Claims

1. An intelligent power consumption load management method based on big data analysis, characterized in that, Including: Step S101: Obtain power grid operation management data, which includes historical power consumption data, climate data, power grid equipment operation status data, and user behavior data; Step S102: Based on the historical power consumption data, climate data, power grid equipment operation status data, and user behavior data, construct a power load forecasting model, obtain real-time power grid operation management data, and substitute the real-time power grid operation management data into the power load forecasting model to obtain power load forecasting data; Step S103: Establish a timestamp for the power load forecasting data based on the time of data generation, and store it in the blockchain to generate a hash value corresponding to the power load forecasting data; Step S104: Obtain the power load management process nodes and process node management rules, store the power load management process nodes and process node management rules in the blockchain to generate a hash value corresponding to the power load forecasting data, and construct a power load process node smart contract; Step S105: Establish data matching tags for the power load process node smart contract, match the power grid operation management data with the data matching tags, transmit the power grid operation management data to the corresponding power load process node smart contract according to the matching result to obtain the first process node smart contract data processing result, randomly sort the power load process node smart contracts to obtain randomly sorted power load process node smart contracts, match the randomly sorted power load process node smart contracts with the power load forecasting data to obtain the second process node smart contract data processing result, match the randomly sorted power load process node smart contracts with the power grid operation management data to obtain the third process node smart contract data processing result, and perform data analysis on the first process node smart contract data processing result, the second process node smart contract data processing result, and the third process node smart contract data processing result to obtain the completion degree of each process node of the power load management.

2. The intelligent power consumption load management method based on big data analysis according to claim 1, wherein, The said step S101 includes: Obtain historical power consumption data from the data center or database of the power grid enterprise. The historical power consumption data includes power consumption, peak load, and valley load in different time periods; Obtain climate data for the corresponding time period through the meteorological department database. The climate data includes temperature, humidity, wind speed, and sunshine duration; Utilize sensors and monitoring systems deployed on power grid equipment to obtain the operation status data of power grid equipment in real time. The operation status data of power grid equipment includes power grid equipment voltage, power grid equipment current, power grid equipment power factor, and power grid equipment temperature.

3. The intelligent power consumption load management method based on big data analysis according to claim 2, characterized in that, The said step S101 includes: Preprocess the obtained power grid operation management data, clean the power grid operation management data, and remove abnormal power grid operation management data to obtain preprocessed power grid operation management data; Store the preprocessed power grid operation management data, classify the stored preprocessed power grid operation management data according to the data type, and establish retrieval tags for the classified preprocessed power grid operation management data.

4. The intelligent power consumption load management method based on big data analysis according to claim 1, characterized in that The said step S102 includes: Perform a correlation analysis on historical electricity consumption data, climate data, power grid equipment operation status data, and user behavior data to obtain features highly correlated with electricity load. The features highly correlated with electricity load include historical load features, temperature features, and humidity features; Construct a load forecasting model based on historical load features, temperature features, and humidity features; Obtain real-time power grid operation management data, which includes real-time electricity load, climate conditions, power grid equipment status, and user behavior information. Substitute the real-time data into the constructed electricity load forecasting model to perform electricity load forecasting, and calculate the electricity load forecasting data through the electricity load forecasting model.

5. The intelligent power consumption load management method based on big data analysis according to claim 4, characterized in that The step S102 includes: Obtain actual electricity load data, compare the forecasting data with the actual electricity load data to obtain the error data between the forecasting data and the actual electricity load. Match the error data between the forecasting data and the actual electricity load in the knowledge base to obtain information on the causes of errors. The information on the causes of errors includes data quality problems, unreasonable models, and external factor influences; Adjust the parameters of the electricity load forecasting model according to the information on the causes of errors, and use the adjusted electricity load forecasting model to perform forecasting again. Verify the forecasting effect of the adjusted electricity load forecasting model through comparison with the actual data.

6. The intelligent power consumption load management method based on big data analysis according to claim 1, characterized in that The step S103 includes: Create a time stamp corresponding to each piece of electricity load forecasting data according to the generation time of each piece of electricity load forecasting data. The time stamp is used to identify the generation time of the data; Write the electricity load forecasting data with time stamps into the blockchain, and calculate the hash value of each piece of electricity load forecasting data stored on the blockchain using a hash function; Store the generated hash value and the original data together on the blockchain, and record each piece of data and its corresponding hash value.

7. The intelligent power consumption load management method based on big data analysis according to claim 1, characterized in that The step S104 includes: Obtain information on each node of the electricity load management process from the power management system or documents. The information on each node of the electricity load management process includes electricity application, approval, allocation, and monitoring links; Obtain management rules corresponding to the information on each node of the electricity load management process. The management rules define the operation specifications, permission settings, and data processing methods for each process node; Generate a hash value according to the electricity load management process node and the management rules of the process node: Use the obtained information on the electricity load management process node and the corresponding management rules as input data to generate a hash value.

8. The intelligent power consumption load management method based on big data analysis according to claim 7, characterized in that, The step S104 includes: Store the generated hash value and the relevant information on the electricity load management process node and the management rules on the blockchain; Utilize the smart contract function of the blockchain platform to write smart contract code according to the electricity load management process node and the management rules; The smart contract will automatically execute the management rules of the process node, and the smart contract will perform automatic allocation, monitoring, and recording of electricity load according to the automatically executed management rules of the process node.

9. The intelligent power consumption load management method based on big data analysis according to claim 1, characterized in that The step S105 includes: Establish data matching tags according to the functions and requirements of each smart contract, and preprocess the power grid operation management data; Match the power grid operation management data using the established data matching tags to obtain the data of the smart contracts for each power consumption load process node; Transmit the power grid operation management data to the corresponding smart contracts of the power consumption load process nodes according to the matching results: Classify the successfully matched power grid operation management data according to the corresponding smart contracts of the power consumption load process nodes; Transmit the classified data to the corresponding smart contracts respectively. Each smart contract of the power consumption load process nodes processes the received power grid operation management data to generate corresponding data processing results, and randomly sorts the smart contracts of the power consumption load process nodes to obtain a randomly sorted list of smart contracts.

10. The intelligent power consumption load management method based on big data analysis according to claim 9, characterized in that, The step S105 includes: Collect the data processing results of the smart contracts of the first process node, the data processing results of the smart contracts of the second process node, and the data processing results of the smart contracts of the third process node; Perform clustering analysis on the data processing results of the smart contracts of the first process node, the data processing results of the smart contracts of the second process node, and the data processing results of the smart contracts of the third process node, the completion degree of the smart contracts in the data analysis of the first process node, and the power consumption load data of each node, and conduct an evaluation according to the clustering analysis results to obtain the completion degree of each process node of the data processing results of the smart contracts of the first process node, the data processing results of the smart contracts of the second process node, and the data processing results of the smart contracts of the third process node. If there is data with a completion degree lower than the preset completion degree value among the completion degrees of each process node of the data processing results of the smart contracts of the first process node, the data processing results of the smart contracts of the second process node, and the data processing results of the smart contracts of the third process node, then recheck the data with a completion degree lower than the preset completion degree. If the recheck result is that the data is incorrect, then generate a data error warning message.

Images