Multi-energy data transmission control method based on error prediction

Abstract

The invention provides a multi-energy data transmission control method based on error prediction, and relates to the technical field of energy data analysis, and the method comprises the steps: 1, obtaining the energy data of a plurality of data sources in real time through a preset node, and outputting initial data; 2, training and optimizing the first model in combination with the obtained historical energy data, and outputting an error prediction model; 3, inputting the initial data into an error prediction model for prediction analysis, and outputting an error prediction result; and 4, dynamically adjusting the transmission control strategy selected from the strategy database based on the error prediction result, and controlling and optimizing the data transmission method corresponding to each data source based on the transmission control strategy. According to the invention, a multi-energy data transmission method can be adjusted and controlled in real time, the data transmission efficiency and reliability are improved, and more intelligent and optimized data transmission management is realized.

Description

Technical Field

[0001] This invention relates to the field of energy data analysis technology, and in particular to a multi-energy data transmission control method based on error prediction. Background Technology

[0002] Data transmission control is a technique used to optimize data transmission efficiency. By predicting errors during data transmission, data transmission strategies can be dynamically adjusted based on the error situation, thereby improving transmission efficiency and reliability.

[0003] Currently, energy data transmission typically employs fixed transmission strategies, failing to dynamically adjust based on real-time network conditions and error rates, resulting in low transmission efficiency. Especially in diverse energy environments, some transmission control methods lack real-time capability, failing to respond promptly to changes in network status and effectively handle unforeseen circumstances, thus impacting the stability and reliability of data transmission.

[0004] Therefore, the present invention provides a multi-energy data transmission control method based on error prediction. Summary of the Invention

[0005] This invention provides a multi-energy data transmission control method based on error prediction, which is used to adjust and control the multi-energy data transmission method in real time, improve data transmission efficiency and reliability, and achieve more intelligent and optimized data transmission management.

[0006] This invention provides a multi-energy data transmission control method based on error prediction, comprising:

[0007] Step 1: Acquire energy data from multiple data sources in real time through preset nodes and output initial data;

[0008] Step 2: Train and optimize the first model using the acquired historical energy data, and output the error prediction model;

[0009] Step 3: Input the initial data into the error prediction model for prediction analysis, and output the error prediction results;

[0010] Step 4: Based on the error prediction results, dynamically adjust the transmission control strategy selected in the strategy database, and control and optimize the data transmission method corresponding to each data source based on the transmission control strategy.

[0011] Preferably, before acquiring energy data from multiple data sources in real time through preset nodes, the process includes:

[0012] The system acquires the user's data analysis needs, outputs data requirement information, determines the data source for the corresponding data based on the data requirement information, and determines the preset node corresponding to each data source by combining the mapping relationship between the data source and the communication node.

[0013] Preferably, step 1 further includes:

[0014] Based on the data requirement information, the data type and data volume of the data to be acquired are determined, the data sampling requirements are output, and based on the data sampling requirements, the energy data of each data source is captured through the preset nodes, and the initial data is summarized and output.

[0015] Preferably, in step 1, after outputting the initial data, the method further includes:

[0016] The initial data is subjected to feature recognition and feature extraction using a preset data feature library, and an initial feature set is output.

[0017] Historical data that matches each feature in the initial feature set is filtered from the historical database, and historical data that meets the first preset matching degree is output as historical energy data.

[0018] Preferably, in step 2, before training and optimizing the first model using the acquired historical energy data, the following steps are included:

[0019] The historical energy data is preprocessed, and the historical energy data that meets the preset quality conditions is determined as the first data;

[0020] Simultaneously, based on the user's model selection instruction, a first model is selected from the model database to perform predictive analysis on the first data.

[0021] Preferably, step 2 includes:

[0022] The first data is divided using a preset data partitioning method to obtain a training set, a test set, and a validation set for training and optimizing the first model.

[0023] The first model is trained and optimized based on the training set, test set, and validation set, and the first model that meets the preset model performance conditions is output as an error prediction model.

[0024] Preferably, step 3 includes:

[0025] Obtain the data types and corresponding data formats from the initial data, and output a data type-format lookup table;

[0026] Simultaneously, the format requirement data of the error prediction model is obtained, and the adaptation format information is output;

[0027] Based on the data type-format lookup table and the matching format information, a matching format conversion method is selected from the method database, and the initial data is converted into second data that meets the matching format information based on the format conversion method.

[0028] The initial data and the second data are compared and verified using a preset data verification method. The second data that meets the preset verification conditions is output as the data to be analyzed.

[0029] Obtain the user's predictive analysis needs, select predictive indicators that match the predictive analysis needs from the indicator database, and construct a predictive indicator set;

[0030] Simultaneously, the mapping relationship between each prediction indicator in the prediction indicator set is obtained by combining the preset indicator mapping diagram, and an indicator relationship diagram is constructed.

[0031] By combining the predicted indicator set and the indicator relationship diagram, and by performing predictive analysis on the second data through the error prediction model, the predicted sub-data under each predicted indicator is obtained, and the first predicted data is obtained by summarizing them.

[0032] Obtain the prediction performance data and historical error data of the error prediction model for each prediction index, wherein the historical error data includes the historical variation data of the inherent error and random error of the error prediction model.

[0033] Based on the predicted performance data and historical error data, the correction coefficient of the error prediction model is dynamically adjusted, and the dynamic correction coefficient is output. Based on the dynamic correction coefficient, the first predicted data is corrected in real time, and the second predicted data is output.

[0034] The second predicted data is analyzed by a preset data processing method. The standard parameters and preset redundancy under each predicted index are combined to construct the data trend of multi-energy data under each predicted index and output the error prediction result.

[0035] Preferably, step 4 includes:

[0036] Based on the preset nodes, the transmission method of energy data corresponding to each data source is determined, and a source-method list is constructed;

[0037] Keyword identification and extraction are performed on the data within a preset time period in the error prediction results, and a keyword set corresponding to the preset time period is constructed based on the extracted keywords;

[0038] Based on a preset word-state lookup table, the data transmission status of each data source corresponding to the keyword set is determined, and a status analysis table is output.

[0039] At the same time, the user's optimization control requirements are obtained, and the optimization objectives corresponding to each data source and the optimization content under the corresponding objectives are determined based on the optimization control requirements.

[0040] Based on the optimization objectives and optimization content corresponding to each data source, a transmission control strategy matching the data transmission status of each data source in the status analysis table is selected from the strategy database.

[0041] Based on the aforementioned transmission control strategy, optimization objectives, and optimization content, the transmission methods corresponding to each data source are adjusted;

[0042] The data transmission status of the corresponding data source for each of the aforementioned transmission methods during the adjustment process is acquired in real time, and the adjustment process data is output.

[0043] The adjustment process data is compared and analyzed with the corresponding optimization objectives and optimization content, and the transmission control strategy of the corresponding data source is adjusted and optimized based on the comparison and analysis results.

[0044] This invention provides a multi-energy data transmission control method based on error prediction. The method acquires energy data in real time and trains an error prediction model using historical data to predict errors during data transmission. Then, it dynamically adjusts the transmission control strategy based on the prediction results to optimize the data transmission process. This invention can improve data transmission efficiency by dynamically adjusting the transmission control strategy based on error prediction results. By optimizing the data transmission method, it can reduce energy consumption and transmission costs. Timely adjustment of the transmission control strategy can improve the stability and reliability of data transmission. Furthermore, it can achieve intelligent data transmission management and optimization by utilizing the error prediction model and dynamic adjustment strategy. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating a multi-energy data transmission control method based on error prediction provided in an embodiment of the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0048] like Figure 1 As shown in the figure, an embodiment of the present invention provides a multi-energy data transmission control method based on error prediction, comprising:

[0049] Step 1: Acquire energy data from multiple data sources in real time through preset nodes and output initial data;

[0050] Step 2: Train and optimize the first model using the acquired historical energy data, and output the error prediction model;

[0051] Step 3: Input the initial data into the error prediction model for prediction analysis, and output the error prediction results;

[0052] Step 4: Based on the error prediction results, dynamically adjust the transmission control strategies selected in the strategy database, and control and optimize the data transmission methods corresponding to each data source based on the transmission control strategies.

[0053] In this embodiment, the preset node is a node pre-set in the system for acquiring energy data from multiple data sources in real time.

[0054] In this embodiment, the data source refers to the source of the data, which can be a sensor, device, or other system.

[0055] In this embodiment, energy data refers to energy-related data generated by the data source, such as electricity consumption and power output.

[0056] In this embodiment, the initial data is energy data from multiple data sources acquired in real time through preset nodes, which serves as the initial input data.

[0057] In this embodiment, historical energy data refers to energy data from data sources collected in the past, which is used to train the error prediction model.

[0058] In this embodiment, the error prediction model is a model trained and optimized using historical energy data, used to predict possible errors during data transmission.

[0059] In this embodiment, the error prediction result is the error prediction result obtained after analyzing the initial data through the error prediction model.

[0060] In this embodiment, the strategy database is a database that stores various transmission control strategies and is used to dynamically adjust the transmission control strategies.

[0061] In this embodiment, the transmission control strategy is a transmission control strategy selected from the strategy database based on the error prediction results, which is used to adjust the data transmission process.

[0062] In this embodiment, the data transmission method may include data compression, chunked transmission, priority adjustment, etc., depending on the data transmission method or strategy for each data source.

[0063] The implementation principle and beneficial effects of this embodiment are as follows: This invention acquires energy data in real time and combines it with historical data to train an error prediction model, predicting errors during data transmission. Then, based on the prediction results, it dynamically adjusts the transmission control strategy to optimize the data transmission process. This invention can dynamically adjust the transmission control strategy according to the error prediction results, improving data transmission efficiency. By optimizing the data transmission method, it can reduce energy consumption and transmission costs. Timely adjustment of the transmission control strategy can improve the stability and reliability of data transmission. Furthermore, it can utilize the error prediction model and dynamic adjustment strategy to achieve intelligent data transmission management and optimization.

[0064] This invention provides a multi-energy data transmission control method based on error prediction, which includes the following steps before acquiring energy data from multiple data sources in real time through preset nodes:

[0065] The system acquires users' data analysis needs, outputs data requirement information, determines the data source for the corresponding data based on the data requirement information, and determines the preset node corresponding to each data source by combining the mapping relationship between the data source and the communication node.

[0066] In this embodiment, data analysis requirements refer to the specific needs and requirements of users when analyzing data, including the required data types, frequency, and accuracy.

[0067] In this embodiment, data requirement information refers to information determined based on the user's data analysis needs, which is used to guide the selection of data sources and the optimization of the data transmission process.

[0068] In this embodiment, the communication node is a node or device used for data transmission and communication, which may be a sensor, a wireless module, a server, etc.

[0069] In this embodiment, the mapping relationship—the correspondence between the data source and the communication node—determines which data source corresponds to which communication node, so as to obtain data in real time.

[0070] The implementation principle and beneficial effects of this embodiment are as follows: Before acquiring energy data from the data source, this invention first obtains the user's data analysis requirements, determines the data requirement information, and then maps the data source to the communication node according to the mapping relationship, so as to acquire data in real time and perform subsequent processing. This invention determines the mapping relationship between the data source and the communication node according to the user's requirements, ensuring accurate acquisition of the required data; by determining the data requirement information and mapping relationship in advance, the speed of data transmission and processing can be accelerated; and the data transmission process can be customized according to the user's requirements to meet the data analysis needs in different scenarios.

[0071] The present invention provides a multi-energy data transmission control method based on error prediction, wherein step 1 further includes:

[0072] Based on the data requirement information, the data type and volume of the data to be acquired are determined, the data sampling requirements are output, and based on the data sampling requirements, the energy data of each data source is captured through preset nodes, and the initial data is summarized and output.

[0073] In this embodiment, the data type is the type or category of the data to be acquired, such as the temperature, humidity, and pressure of energy or fuel.

[0074] In this embodiment, data volume refers to the quantity or magnitude of data to be acquired, which can be data points per second, data packet size, etc.

[0075] In this embodiment, the data sampling requirements are determined based on the data type and data volume, including sampling frequency, sampling accuracy, etc.

[0076] The implementation principle and beneficial effects of this embodiment are as follows: This invention determines the data type and volume based on data requirement information, then outputs data sampling requirements. Energy data from various data sources is captured through preset nodes, and the initial data is aggregated and output. This invention enables more accurate and efficient data collection, contributing to energy conservation, improved data transmission efficiency, and optimized data processing workflows.

[0077] The present invention provides a multi-energy data transmission control method based on error prediction. In step 1, after outputting the initial data, the method further includes:

[0078] The initial data is used to perform feature recognition and feature extraction based on a pre-defined data feature library, and an initial feature set is output.

[0079] Historical data that matches each feature in the initial feature set is filtered from the historical database, and historical data that meets the first preset matching degree is output as historical energy data.

[0080] In this embodiment, a preset data feature library stores predefined data feature information for identifying and extracting features from the initial data.

[0081] In this embodiment, feature recognition involves identifying feature information in the initial data and determining which data attributes are important and have analytical significance.

[0082] In this embodiment, feature extraction involves extracting representative and distinctive features from the initial data for subsequent data analysis and prediction.

[0083] In this embodiment, the initial feature set is the initial feature set obtained after feature recognition and extraction.

[0084] In this embodiment, the first preset degree refers to the matching degree threshold between historical data and the initial feature set, which is used to filter historical data. Data that meets the matching degree requirement is output as historical energy data.

[0085] The implementation principle and beneficial effects of this embodiment are as follows: This invention combines a preset data feature library to perform feature recognition and extraction on initial data to obtain an initial feature set. Then, historical data with a matching degree higher than a set threshold in the historical database is selected and output as historical energy data. By combining feature recognition and extraction with historical data matching, this invention can improve the accuracy and reliability of data, optimize data analysis results, reduce the uncertainty of error prediction, and thus improve the intelligence level and efficiency of data transmission control.

[0086] This invention provides a multi-energy data transmission control method based on error prediction. In step 2, before training and optimizing the first model using acquired historical energy data, the method includes:

[0087] Historical energy data is preprocessed, and historical energy data that meets the preset quality conditions is determined as the first data;

[0088] At the same time, based on the user's model selection instruction, a first model is selected from the model database to perform predictive analysis on the first data.

[0089] In this embodiment, preprocessing involves processing historical energy data to meet pre-set quality conditions, such as data cleaning, noise reduction, and filling in missing values.

[0090] In this embodiment, preset quality conditions are defined as the quality standards for historical energy data. Only data that meets these conditions is considered the first data.

[0091] In this embodiment, the first data is historical energy data that meets preset quality conditions after preprocessing.

[0092] In this embodiment, the model selection instruction is a user-defined instruction used to select a first model from the model database that is suitable for predictive analysis of the first data.

[0093] In this embodiment, the model database stores various available models, allowing users to select the appropriate model for data analysis and prediction based on their needs.

[0094] The implementation principle and beneficial effects of this embodiment are as follows: This invention preprocesses historical energy data, filters out first data that meets preset quality conditions, and then selects a suitable model from the model database based on the user's model selection instructions for predictive analysis. By preprocessing historical data and selecting appropriate models, this invention can improve the accuracy and reliability of data analysis, optimize the training and prediction effects of models, thereby improving the intelligence level and efficiency of data transmission control methods and providing better support for real-time data transmission.

[0095] The present invention provides a multi-energy data transmission control method based on error prediction, wherein step 2 includes:

[0096] The first data is divided into training sets, test sets, and validation sets for training and optimizing the first model by using a preset data partitioning method.

[0097] The first model is trained and optimized based on the training set, test set, and validation set, and the first model that meets the preset model performance conditions is output as the error prediction model.

[0098] In this embodiment, a preset data partitioning method is used: the first data is divided into a training set, a test set, and a validation set according to a preset method, so as to carry out model training and performance evaluation;

[0099] In this embodiment, the training set, test set, and validation set are datasets used for model training, model testing, and model validation, respectively.

[0100] In this embodiment, preset model performance conditions are used to evaluate model performance. Only models that meet these conditions can be output as error prediction models. For example, only models with a mean absolute error of less than 5% on the validation set will be output as error prediction models.

[0101] The implementation principle and beneficial effects of this embodiment are as follows: This invention divides the first data into a training set, a test set, and a validation set using a preset data partitioning method. Then, based on these datasets, the first model is trained and optimized, ultimately outputting an error prediction model that meets preset model performance conditions. Through reasonable data partitioning and model training, this invention can improve the model's generalization ability and prediction accuracy, ensuring good performance in practical applications, thereby optimizing the data transmission control process and improving system efficiency and stability.

[0102] The present invention provides a multi-energy data transmission control method based on error prediction, wherein step 3 includes:

[0103] Retrieve the data types and corresponding data formats from the initial data, and output a data type-format lookup table;

[0104] Simultaneously, acquire the format requirements data of the error prediction model and output the adaptation format information;

[0105] Based on the data type-format lookup table and the matching format information, the matching format conversion method is selected from the method database, and the initial data is converted into second data that meets the matching format information based on the format conversion method.

[0106] The initial data and the second data are compared and verified by combining the preset data verification method. The second data that meets the preset verification conditions is output as the data to be analyzed.

[0107] Obtain the user's predictive analysis needs, select predictive indicators that match the predictive analysis needs from the indicator database, and construct a predictive indicator set;

[0108] At the same time, the mapping relationship between each prediction indicator in the prediction indicator set is obtained by combining the preset indicator mapping diagram, and an indicator relationship diagram is constructed.

[0109] By combining the set of prediction indicators and the indicator relationship diagram, and by using the error prediction model to predict and analyze the second data, the predicted sub-data under each prediction indicator is obtained, and the first prediction data is obtained by summarizing them.

[0110] Obtain the prediction performance data of the error prediction model for each prediction index and historical error data. The historical error data includes the historical variation data of the inherent error and random error of the error prediction model.

[0111] Based on prediction performance data and historical error data, the error prediction model correction coefficient is dynamically adjusted, the dynamic correction coefficient is output, and the first prediction data is corrected in real time based on the dynamic correction coefficient, and the second prediction data is output.

[0112] The second prediction data is analyzed by a preset data processing method. Combined with the standard parameters and preset redundancy under each prediction indicator, the data trend of multi-energy data under each prediction indicator is constructed, and the error prediction result is output.

[0113] In this embodiment, the data type is the data category, such as numbers, text, time, etc.

[0114] In this embodiment, the data format refers to the way or structure in which the data is presented, such as CSV, JSON, timestamps, etc.

[0115] In this embodiment, the data type-format lookup table records the correspondence between data types and data formats for subsequent data format conversion;

[0116] In this embodiment, the format requirement data refers to the specific requirements of the error prediction model for the data format.

[0117] In this embodiment, the adaptation format information is: data format information that meets the format requirements of the error prediction model;

[0118] In this embodiment, the method database is a database that stores various data format conversion methods;

[0119] In this embodiment, the format conversion method is a method for converting data from one format to another.

[0120] In this embodiment, the second data, which is the data after format conversion and processing, is used for subsequent predictive analysis;

[0121] In this embodiment, the preset data verification method is a method for verifying whether the data meets preset conditions.

[0122] In this embodiment, preset verification conditions are defined as conditions or standards used to verify data.

[0123] In this embodiment, the data to be analyzed is data that has been verified to meet the conditions and is used for subsequent predictive analysis.

[0124] In this embodiment, predictive analytics needs refer to the user's needs or goals for predictive analytics of data.

[0125] In this embodiment, the indicator database is a database that stores various predictive indicators;

[0126] In this embodiment, the prediction indicator is an indicator used to measure and evaluate the prediction results.

[0127] In this embodiment, the prediction indicator set is a set of prediction indicators selected according to the user's needs.

[0128] In this embodiment, a preset indicator mapping diagram is used: a chart that displays the mapping relationship between predictive indicators;

[0129] In this embodiment, the indicator relationship diagram is a chart that shows the relationship between predictive indicators, which helps to understand the mutual influence between indicators;

[0130] In this embodiment, the prediction sub-data refers to the specific prediction result data obtained under each prediction indicator.

[0131] In this embodiment, the first prediction data is the summary of the prediction results data under each prediction indicator;

[0132] In this embodiment, prediction performance data refers to data used to evaluate the performance of the error prediction model during the prediction process.

[0133] In this embodiment, historical error data includes historical variation data of inherent error and random error, which is used to analyze the characteristics and trends of error.

[0134] In this embodiment, the inherent error is the error inherent in the error prediction model itself, which is usually caused by the model structure or assumptions.

[0135] In this embodiment, random error; error caused by random factors, is unpredictable and irregular;

[0136] In this embodiment, the correction coefficient is a coefficient used to dynamically adjust the parameters of the error prediction model to improve the prediction accuracy.

[0137] In this embodiment, the second prediction data is the prediction data after correction and adjustment, in order to improve the accuracy of the prediction results;

[0138] In this embodiment, standard parameters are the standard parameters used under the prediction index to evaluate the passivity of the prediction results.

[0139] In this embodiment, a preset redundancy is defined as redundant data or information reserved for supplementation or correction when needed.

[0140] The implementation principle and beneficial effects of this embodiment are as follows: This invention uses a data type-format lookup table and matching format information to select an appropriate format conversion method to convert the initial data into second data. Then, based on the error prediction model, predictive analysis is performed, and the correction coefficient is dynamically adjusted. Finally, the corrected prediction data and error prediction results are output. This invention achieves effective processing and prediction of multi-energy data through data format conversion, predictive analysis, and dynamic correction, improving the accuracy and real-time performance of data transmission control, providing reliable data support for decision-making and resource optimization, thereby improving system efficiency and performance.

[0141] The present invention provides a multi-energy data transmission control method based on error prediction, wherein step 4 includes:

[0142] Based on the preset nodes, determine the transmission method of energy data corresponding to each data source, and construct a source-method list;

[0143] Keyword identification and extraction are performed on the data within a preset time period in the error prediction results, and a keyword set corresponding to the preset time period is constructed based on the extracted keywords;

[0144] Based on the preset word-state lookup table, determine the data transmission status of each data source corresponding to the keyword set, and output a status analysis table;

[0145] At the same time, the user's optimization control requirements are obtained, and the optimization objectives corresponding to each data source and the optimization content under the corresponding objectives are determined based on the optimization control requirements.

[0146] Based on the optimization objectives and optimization content corresponding to each data source, a transmission control strategy matching the data transmission status of each data source in the status analysis table is selected from the strategy database.

[0147] Based on the transmission control strategy, optimization objectives, and optimization content, the transmission methods corresponding to each data source are adjusted;

[0148] Real-time acquisition of the data transmission status of the corresponding data source for each transmission method during the adjustment process, and output of adjustment process data;

[0149] The adjustment process data is compared and analyzed with the corresponding optimization objectives and content, and the transmission control strategy of the corresponding data source is adjusted and optimized based on the comparison and analysis results.

[0150] In this embodiment, the source-method list is a list of energy data transmission methods corresponding to each data source.

[0151] In this embodiment, the preset time period is a pre-defined time period used for data analysis and control.

[0152] In this embodiment, keyword identification and extraction involves identifying and extracting keywords within a preset time period from the error prediction results.

[0153] In this embodiment, the keyword set is a collection of keywords constructed based on the extracted keywords, which is used for subsequent data analysis.

[0154] In this embodiment, a preset word-state lookup table is used: a lookup table that corresponds to the data transmission status of the keyword set and the data source.

[0155] In this embodiment, data transmission status describes the transmission status of the data source during a specific time period, such as normal transmission, abnormal transmission, etc.

[0156] In this embodiment, the status analysis table is an analysis table that displays the data transmission status of each data source.

[0157] In this embodiment, the optimization control requirement refers to the user's optimization requirements or objectives for data transmission control.

[0158] In this embodiment, the optimization objective is defined as the optimization objective corresponding to each data source, which describes the desired optimization effect.

[0159] In this embodiment, the optimization content refers to the specific optimization measures or content required for each optimization objective.

[0160] In this embodiment, the transmission method is: the data transmission method or strategy corresponding to each data source;

[0161] In this embodiment, the adjustment process data refers to data acquired in real time during the adjustment of the transmission method, which is used to analyze and optimize the transmission control strategy.

[0162] The implementation principle and beneficial effects of this embodiment are as follows: This invention determines the transmission method and status of the data source, identifies the keyword set and determines the data transmission status, determines the optimization target and content based on optimization control requirements, selects an appropriate transmission control strategy, adjusts the transmission method and acquires the adjustment process data in real time, and finally compares and analyzes the results to adjust and optimize the transmission control strategy. By combining keyword identification, status analysis, and optimization control requirements, this invention achieves dynamic adjustment and optimization of the data transmission control strategy, improving the efficiency and accuracy of data transmission while meeting user optimization needs. This optimizes the control process of multi-energy data transmission, improving system performance and resource utilization efficiency.

[0163] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-energy data transmission control method based on error prediction, characterized in that, include: Step 1: Acquire energy data from multiple data sources in real time through preset nodes and output initial data; Step 2: Train and optimize the first model using the acquired historical energy data, and output the error prediction model; Step 3: Input the initial data into the error prediction model for prediction analysis, and output the error prediction results; Step 4: Based on the error prediction results, dynamically adjust the transmission control strategy selected in the strategy database, and control and optimize the data transmission method corresponding to each data source based on the transmission control strategy.

2. The multi-energy data transmission control method based on error prediction according to claim 1, characterized in that, Before acquiring energy data from multiple data sources in real time through preset nodes, the process includes: The system acquires the user's data analysis needs, outputs data requirement information, determines the data source for the corresponding data based on the data requirement information, and determines the preset node corresponding to each data source by combining the mapping relationship between the data source and the communication node.

3. The multi-energy data transmission control method based on error prediction according to claim 2, characterized in that, Step 1 also includes: Based on the data requirement information, the data type and data volume of the data to be acquired are determined, the data sampling requirements are output, and based on the data sampling requirements, the energy data of each data source is captured through the preset nodes, and the initial data is summarized and output.

4. The multi-energy data transmission control method based on error prediction according to claim 1, characterized in that, In step 1, after outputting the initial data, the following steps are also included: The initial data is subjected to feature recognition and feature extraction using a preset data feature library, and an initial feature set is output. Historical data that matches each feature in the initial feature set is filtered from the historical database, and historical data that meets the first preset matching degree is output as historical energy data.

5. The multi-energy data transmission control method based on error prediction according to claim 1, characterized in that, Step 2, before training and optimizing the first model using the acquired historical energy data, includes: The historical energy data is preprocessed, and the historical energy data that meets the preset quality conditions is determined as the first data; Simultaneously, based on the user's model selection instruction, a first model is selected from the model database to perform predictive analysis on the first data.

6. The multi-energy data transmission control method based on error prediction according to claim 1, characterized in that, Step 2 includes: The first data is divided using a preset data partitioning method to obtain a training set, a test set, and a validation set for training and optimizing the first model. The first model is trained and optimized based on the training set, test set, and validation set, and the first model that meets the preset model performance conditions is output as an error prediction model.

7. The multi-energy data transmission control method based on error prediction according to claim 1, characterized in that, Step 3 includes: Obtain the data types and corresponding data formats from the initial data, and output a data type-format lookup table; Obtain the format requirement data of the error prediction model and output the adaptation format information; Based on the data type-format lookup table and the matching format information, a matching format conversion method is selected from the method database, and the initial data is converted into second data that meets the matching format information based on the format conversion method. The initial data and the second data are compared and verified using a preset data verification method. The second data that meets the preset verification conditions is output as the data to be analyzed. Obtain the user's predictive analysis needs, select predictive indicators that match the predictive analysis needs from the indicator database, and construct a predictive indicator set; The mapping relationship between each prediction indicator in the prediction indicator set is obtained by combining the preset indicator mapping diagram, and an indicator relationship diagram is constructed. First prediction data is generated based on the error prediction model, dynamic correction coefficients are generated, and second prediction data is generated based on the dynamic correction coefficients and the first prediction data.

8. The multi-energy data transmission control method based on error prediction according to claim 7, characterized in that, The process of generating first prediction data based on the error prediction model, generating dynamic correction coefficients, and generating second prediction data based on the dynamic correction coefficients and the first prediction data includes: By combining the predicted indicator set and the indicator relationship diagram, and by performing predictive analysis on the second data through the error prediction model, the predicted sub-data under each predicted indicator is obtained, and the first predicted data is obtained by summarizing them. Obtain the prediction performance data and historical error data of the error prediction model for each prediction index, wherein the historical error data includes the historical variation data of the inherent error and random error of the error prediction model. Based on the predicted performance data and historical error data, the correction coefficient of the error prediction model is dynamically adjusted, and the dynamic correction coefficient is output. Based on the dynamic correction coefficient, the first predicted data is corrected in real time, and the second predicted data is output. The second predicted data is analyzed by a preset data processing method. The standard parameters and preset redundancy under each predicted index are combined to construct the data trend of multi-energy data under each predicted index and output the error prediction result.

9. The multi-energy data transmission control method based on error prediction according to claim 1, characterized in that, Step 4 includes: Based on the preset nodes, the transmission method of energy data corresponding to each data source is determined, and a source-method list is constructed; Keyword identification and extraction are performed on the data within a preset time period in the error prediction results, and a keyword set corresponding to the preset time period is constructed based on the extracted keywords; Based on a preset word-state lookup table, the data transmission status of each data source corresponding to the keyword set is determined, and a status analysis table is output. Based on the user's optimization control requirements, a matching transmission control strategy is selected from the strategy database; The data transmission status of the corresponding data source for each of the aforementioned transmission methods during the adjustment process is acquired in real time, and the adjustment process data is output. The adjustment process data is compared and analyzed with the corresponding optimization objectives and optimization content, and the transmission control strategy of the corresponding data source is adjusted and optimized based on the comparison and analysis results.

10. The multi-energy data transmission control method based on error prediction according to claim 9, characterized in that, The step of selecting a matching transmission control strategy from the policy database based on the user's optimized control requirements includes: Obtain the user's optimization control requirements, and determine the optimization objectives and optimization content for each data source based on the optimization control requirements; Based on the optimization objectives and optimization content corresponding to each data source, a transmission control strategy matching the data transmission status of each data source in the status analysis table is selected from the strategy database. Based on the aforementioned transmission control strategy, optimization objectives, and optimization content, the transmission methods corresponding to each data source are adjusted.

Images