New energy data prediction method and system based on multi-factor modeling
Through the new energy data prediction method based on multi-factor modeling, historical data are correlated and preprocessed and timing prediction models are trained, the problem of low prediction accuracy of new energy power generation in the existing technology is solved, and higher prediction accuracy and economic operational benefits are achieved.
Patent Information
- Application Number
- CN202510079822.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-18
- Publication Date
- 2025-05-13
AI Technical Summary
The existing new energy data prediction methods are difficult to fully consider the interaction of various factors such as meteorological conditions, equipment status and market demand, resulting in low prediction accuracy of new energy power generation.
A new energy data prediction method based on multi-factor modeling is adopted to obtain and correlate the historical electricity data, historical electricity price data, historical meteorological data and energy management information of new energy stations, and multi-dimensional data are constructed, and data preprocessing and timing prediction model training are carried out to predict future electricity and electricity prices in real time.
It improves the accuracy and reliability of new energy data prediction and provides scientific basis to achieve the economic operation and maximum benefits of new energy stations throughout their life cycle.
Smart Images
Figure CN119990434A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of new energy data prediction, and in particular to a new energy data prediction method and system based on multi-factor modeling. Background Art
[0002] With the intensification of global climate change and the continuous depletion of energy resources, renewable energy (such as solar energy, wind energy, hydropower, etc.) has become increasingly important in the global energy structure. However, the volatility and uncertainty of renewable energy power generation have always been an important factor restricting its development. In addition, the construction of a new power system based on renewable energy, the construction process of a national unified power market, and the operation mode of new energy stations all need to deeply integrate the impact of the power market. In the case of fluctuations in electricity prices and electricity, maximizing the benefits of new energy power stations throughout their life cycle is another important factor. Therefore, accurately predicting renewable energy power generation is of great significance for energy managers to formulate scheduling plans, optimize energy structures, and ensure stable operation of the power grid.
[0003] At present, the new energy data prediction methods mainly include time series methods, regression analysis-based methods and neural network methods. Although these methods have achieved certain results in new energy data prediction, there are still many challenges in practical application. Therefore, new energy power generation is affected by many factors, such as meteorological conditions, equipment status, market demand, etc. The interaction between these factors makes new energy power generation highly complex and uncertain. Traditional prediction methods often find it difficult to fully consider the impact of these factors, resulting in low accuracy in new energy data prediction. Summary of the invention
[0004] In order to solve at least one of the above-mentioned technical problems, the present application provides a new energy data prediction method and system based on multi-factor modeling.
[0005] In a first aspect, the present application provides a new energy data prediction method based on multi-factor modeling, which adopts the following technical solution: Acquire historical electricity data, historical electricity price data, historical meteorological data and energy management information of the new energy station, wherein the historical electricity data, the historical electricity price data and the historical meteorological data are all data generated in the same historical time period, and the energy management information is energy policy management data information of the area where the new energy station is located; The historical electricity data, the historical electricity price data, the historical meteorological data and the energy management information are associated with each other according to time series nodes, and the associated data information is selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes; Performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data; Performing training and testing on the time series prediction model based on the multi-dimensional data to obtain test results; Determine whether the test result meets the preset test result standard. If so, collect real-time meteorological data and real-time energy management information, and input the real-time meteorological data and the real-time energy management information into the trained time series prediction model to obtain future electricity data and future electricity price data; Based on the preset economic evaluation standard, the future electricity quantity data and the future electricity price data are matched and analyzed to obtain the economic indicator value of the new energy station.
[0006] By adopting the above technical solution, the historical electricity data, historical electricity price data, historical meteorological data and energy management information of the new energy station in the same historical time period are obtained, ensuring the consistency and relevance of the data. These data, as the basis of multi-dimensional information, provide comprehensive and accurate input for subsequent data processing and model training. By constructing these data according to the time series node association, the changing trend of each factor over time can be clearly reflected, laying a solid foundation for subsequent analysis. By selecting the associated data information according to the preset time interval, the data redundancy is effectively reduced, while retaining the key information, making the obtained multi-dimensional data more streamlined and representative. Further data preprocessing improves the quality and availability of the data, providing reliable data support for the training of the time series prediction model. The time series prediction model is trained and tested based on the processed multi-dimensional data, and the accuracy and reliability of the model are ensured by judging whether the test results meet the preset standards. Subsequently, the real-time meteorological data and energy management information are input into the trained model, which can predict the future electricity and future electricity prices in real time, providing a scientific basis for the economic operation of the new energy station and achieving the maximum benefit of the new energy station throughout its life cycle. By matching and analyzing future electricity volume and future electricity price data based on preset economic evaluation standards, the two key factors of electricity volume and electricity price are comprehensively considered, and the economic indicator values of new energy stations are evaluated more comprehensively and accurately, providing strong support for station planning and site selection, asset evaluation, economic decision-making and optimization, thereby improving the prediction accuracy of new energy data.
[0007] In a possible implementation, the training and testing of the time series prediction model based on the multi-dimensional data to obtain the test results includes: Select and segment the multi-dimensional data to obtain a training data set and a test data set; Inputting the training data set into the time series prediction model for training to obtain a trained time series prediction model; The test data set is input into the trained time series prediction model to perform a model validation test to obtain a test result.
[0008] In a possible implementation, the historical electricity data, the historical electricity price data, the historical meteorological data, and the energy management information are associated with each other according to time series nodes, and the associated data information is selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes, including: Determine energy policy management data at different time points according to the energy management information; Creating a multidimensional data coordinate system, wherein the X-axis of the multidimensional data coordinate system is different time nodes, and the Y-axis of the multidimensional data coordinate system is data unit parameters of different dimensions; Importing the historical electricity quantity data, the historical electricity price data, the historical meteorological data and the energy policy management data into the multidimensional data coordinate system respectively, to obtain an electricity quantity change curve corresponding to the historical electricity quantity data, an electricity price change curve corresponding to the historical electricity price data, an environment change curve corresponding to the historical meteorological data and a management change curve corresponding to the energy policy management data; Performing change amplitude detection on the environment change curve and the management change curve to determine a first time point at which the environment change curve or the management change curve changes by a first preset amplitude; The first time node is defined as a starting time node, and amplitude detection is performed on the power change curve and the electricity price change curve to determine a second time node at which the power change curve and the electricity price change curve change by a second preset amplitude; According to the time correspondence between the first time node and the second time node, the historical electricity data, the historical electricity price data, the historical meteorological data and the energy management information are associated with each other to obtain a plurality of associated data groups; Performing key data group screening on the multiple associated data groups to obtain at least two representative data groups; The associated data in the at least two representative data groups are selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes.
[0009] In a possible implementation, the performing of key data group screening on the multiple associated data groups to obtain at least two representative data groups includes: Determine the data amplitude difference and amplitude change time interval corresponding to each associated data group according to the plurality of associated data groups; Calculate the ratio of the data amplitude difference and the amplitude change time interval to obtain the amplitude proportional coefficient corresponding to each associated data group; Collecting the initial data set of each associated data group at a time before the data amplitude occurs, and matching the initial data set corresponding to each associated data group to determine whether there is a situation where the initial data sets corresponding to at least two associated data groups match each other; if not, defining the associated data group as a first data group; if so, performing secondary matching on the at least two associated data groups according to the amplitude ratio coefficient and a preset coefficient matching condition to obtain a data group matching result; Determine, according to the data group matching result, whether there are at least two associated data groups whose amplitude ratio coefficients meet the preset coefficient matching condition; if so, determine the initial time node corresponding to the initial data set of the at least two associated data groups, and take the associated data group whose initial time node is close to the current time node as the second data group; If there are no at least two associated data groups whose corresponding amplitude ratio coefficients satisfy the preset coefficient matching condition, the associated data groups are defined as the third data group; The first data group, the second data group and the third data group are aggregated to obtain at least two representative data groups.
[0010] In a possible implementation manner, performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data includes: Performing data cleaning on the multi-dimensional data to obtain cleaned multi-dimensional data; The cleaned multi-dimensional data is subjected to data standardization processing to obtain processed multi-dimensional data.
[0011] In a second aspect, the present application provides a new energy data prediction system based on multi-factor modeling, which adopts the following technical solutions: A new energy data prediction system based on multi-factor modeling, comprising: A data acquisition module is used to acquire historical electricity data, historical electricity price data, historical meteorological data and energy management information of a new energy station, wherein the historical electricity data, the historical electricity price data and the historical meteorological data are all data generated in the same historical time period, and the energy management information is energy policy management data information of the area where the new energy station is located; A data selection module is used to associate the historical electricity data, the historical electricity price data, the historical meteorological data and the energy management information according to time series nodes, and select the associated data information according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes; A data processing module, used for performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data; A model training module is used to train and test the time series prediction model based on the multi-dimensional data to obtain test results; A data analysis module, used to determine whether the test result meets the preset test result standard. If so, real-time meteorological data and real-time energy management information are collected, and the real-time meteorological data and the real-time energy management information are input into the trained time series prediction model to obtain future electricity data and future electricity price data; The data matching module is used to match and analyze the future electricity data and the future electricity price data based on a preset economic evaluation standard to obtain the economic indicator value of the new energy station.
[0012] In a possible implementation, when the model training module performs training and testing on the time series prediction model based on the multi-dimensional data and obtains the test result, it is specifically used to: Select and segment the multi-dimensional data to obtain a training data set and a test data set; Inputting the training data set into the time series prediction model for training to obtain a trained time series prediction model; The test data set is input into the trained time series prediction model to perform model validation test and obtain the test result. In a possible implementation, the data selection module is specifically used to associate the historical electricity data, the historical electricity price data, the historical meteorological data and the energy management information according to the time series nodes, and select the associated data information according to the preset time interval to obtain the multi-dimensional data corresponding to different time nodes: Determine energy policy management data at different time points according to the energy management information; Creating a multidimensional data coordinate system, wherein the X-axis of the multidimensional data coordinate system is different time nodes, and the Y-axis of the multidimensional data coordinate system is data unit parameters of different dimensions; Importing the historical electricity quantity data, the historical electricity price data, the historical meteorological data and the energy policy management data into the multidimensional data coordinate system respectively, to obtain an electricity quantity change curve corresponding to the historical electricity quantity data, an electricity price change curve corresponding to the historical electricity price data, an environment change curve corresponding to the historical meteorological data and a management change curve corresponding to the energy policy management data; Performing change amplitude detection on the environment change curve and the management change curve to determine a first time point at which the environment change curve or the management change curve changes by a first preset amplitude; The first time node is defined as a starting time node, and amplitude detection is performed on the power change curve and the electricity price change curve to determine a second time node at which the power change curve and the electricity price change curve change by a second preset amplitude; According to the time correspondence between the first time node and the second time node, the historical electricity data, the historical electricity price data, the historical meteorological data and the energy management information are associated with each other to obtain a plurality of associated data groups; Performing key data group screening on the multiple associated data groups to obtain at least two representative data groups; The associated data in the at least two representative data groups are selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes.
[0013] In another possible implementation, when the data selection module performs key data group screening on the multiple related data groups to obtain at least two representative data groups, it is specifically used to: Determine the data amplitude difference and amplitude change time interval corresponding to each associated data group according to the plurality of associated data groups; Calculate the ratio of the data amplitude difference and the amplitude change time interval to obtain the amplitude proportional coefficient corresponding to each associated data group; Collecting the initial data set of each associated data group at a time before the data amplitude occurs, and matching the initial data set corresponding to each associated data group to determine whether there is a situation where the initial data sets corresponding to at least two associated data groups match each other; if not, defining the associated data group as a first data group; if so, performing secondary matching on the at least two associated data groups according to the amplitude ratio coefficient and a preset coefficient matching condition to obtain a data group matching result; Determine, according to the data group matching result, whether there are at least two associated data groups whose amplitude ratio coefficients meet the preset coefficient matching condition; if so, determine the initial time node corresponding to the initial data set of the at least two associated data groups, and take the associated data group whose initial time node is close to the current time node as the second data group; If there are no at least two associated data groups whose corresponding amplitude ratio coefficients satisfy the preset coefficient matching condition, the associated data groups are defined as the third data group; The first data group, the second data group and the third data group are aggregated to obtain at least two representative data groups.
[0014] In another possible implementation, when the data processing module performs data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data, it is specifically used to: Performing data cleaning on the multi-dimensional data to obtain cleaned multi-dimensional data; The cleaned multi-dimensional data is subjected to data standardization processing to obtain processed multi-dimensional data.
[0015] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one application is configured to: execute a new energy data prediction method based on multi-factor modeling as described in any one of the first aspects.
[0016] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute any of the new energy data prediction methods based on multi-factor modeling as described in the first aspect.
[0017] In summary, the present application includes at least one of the following beneficial technical effects: By adopting the above technical solution, the historical electricity data, historical electricity price data, historical meteorological data and energy management information of the new energy station in the same historical time period are obtained, ensuring the consistency and relevance of the data. These data, as the basis of multi-dimensional information, provide comprehensive and accurate input for subsequent data processing and model training. By constructing these data according to the time series node association, the changing trend of each factor over time can be clearly reflected, laying a solid foundation for subsequent analysis. By selecting the associated data information according to the preset time interval, the data redundancy is effectively reduced, while retaining the key information, making the obtained multi-dimensional data more streamlined and representative. Further data preprocessing improves the quality and availability of the data, providing reliable data support for the training of the time series prediction model. The time series prediction model is trained and tested based on the processed multi-dimensional data, and the accuracy and reliability of the model are ensured by judging whether the test results meet the preset standards. Subsequently, the real-time meteorological data and energy management information are input into the trained model, which can predict the future electricity and future electricity prices in real time, providing a scientific basis for the economic operation of the new energy station. By matching and analyzing future electricity volume and future electricity price data based on preset economic evaluation standards, the two key factors of electricity volume and electricity price are comprehensively considered, and the economic indicator values of new energy stations are evaluated more comprehensively and accurately, providing strong support for the economic decision-making and optimization of the stations, thereby improving the prediction accuracy of new energy data. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 A schematic flow chart of a new energy data prediction method based on multi-factor modeling provided in an embodiment of the present application.
[0019] Figure 2 A schematic diagram of the structure of a new energy data prediction system based on multi-factor modeling provided in an embodiment of the present application.
[0020] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0021] The following is combined with Figure 1-3 This application is described in further detail.
[0022] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, a person skilled in the art may make non-creative modifications to the present embodiment as needed, but such modifications are protected by the patent law as long as they are within the scope of the present application.
[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0024] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.
[0025] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.
[0026] The embodiment of the present application provides a method for predicting new energy data based on multi-factor modeling, which is executed by an electronic device, wherein the electronic device can be an independent physical electronic device, or an electronic device cluster or distributed system composed of multiple physical electronic devices, or a cloud electronic device that provides cloud computing services. The embodiment of the present application is not limited here, such as Figure 1 As shown, the method includes: Step S10: Obtain historical electricity data, historical electricity price data, historical meteorological data and energy management information of new energy stations.
[0027] Among them, historical electricity data, historical electricity price data and historical meteorological data are all data generated within the same historical time period, and energy management information is energy policy management data information in the area where the new energy station is located.
[0028] For the embodiments of the present application, a new energy station refers to a place or facility that uses renewable energy (such as solar energy, wind energy, etc.) to generate electricity. Historical electricity data refers to the record of electricity generated by the new energy station at a certain time or period in the past, which is used to evaluate its power generation capacity and efficiency. Historical electricity price data represents the electricity market price information related to the new energy station in the same time period, which is used to analyze economic benefits. Historical meteorological data refers to weather condition data in the same time period, such as temperature, wind speed, light intensity, etc., which have a direct impact on the efficiency of new energy power generation. Energy management information refers to energy policy management data information in the area where the new energy station is located, including but not limited to policy subsidies, tax incentives, equipment application status, power dispatching rules, etc., which have an important impact on the operating strategy of the new energy station.
[0029] Specifically, a special data collection system is established, which can automatically obtain relevant data from the power generation system of the new energy station, the power trading market, the meteorological monitoring station and other channels. Secondly, a data verification mechanism is set up to ensure the accuracy and completeness of the data. Finally, the collected data is stored in the database for subsequent analysis.
[0030] Step S11, historical electricity data, historical electricity price data, historical meteorological data and energy management information are associated and constructed according to time series nodes, and the associated data information is selected according to preset time intervals to obtain multi-dimensional data corresponding to different time nodes.
[0031] Specifically, energy policy management data at different time nodes are determined according to energy management information, and a multidimensional data coordinate system is created. The X-axis of the multidimensional data coordinate system is different time nodes, and the Y-axis of the multidimensional data coordinate system is data unit parameters of different dimensions. Historical electricity data, historical electricity price data, historical meteorological data, and energy policy management data are respectively imported into the multidimensional data coordinate system to obtain an electricity change curve corresponding to the historical electricity data, an electricity price change curve corresponding to the historical electricity price data, an environmental change curve corresponding to the historical meteorological data, and a management change curve corresponding to the energy policy management data. The environmental change curve and the management change curve are tested for change amplitudes to determine whether the environmental change curve or the management change curve has changed. A first time node at which a first preset amplitude change occurs, the first time node is defined as a starting time node, amplitude detection is performed on an electric quantity change curve and an electricity price change curve, and a second time node at which a second preset amplitude change occurs on the electric quantity change curve and the electricity price change curve is determined; according to a time correspondence between the first time node and the second time node, data information association is constructed for historical electric quantity data, historical electricity price data, historical meteorological data, and energy management information to obtain a plurality of associated data groups, key data groups are screened for the plurality of associated data groups to obtain at least two representative data groups, and associated data in the at least two representative data groups are selected at preset time intervals to obtain multi-dimensional data corresponding to different time nodes.
[0032] In an embodiment of the present application, the data amplitude difference and the amplitude change time interval corresponding to each associated data group are determined according to a plurality of associated data groups, the data amplitude difference and the amplitude change time interval are ratio-calculated to obtain the amplitude proportionality coefficient corresponding to each associated data group, the initial data set at a moment before the data amplitude occurs in each associated data group is collected, and the initial data set corresponding to each associated data group is matched to determine whether there is a situation where the initial data sets corresponding to at least two associated data groups match, if not, the associated data group is defined as the first data group, if so, the amplitude proportionality coefficient and the preset coefficient matching condition are matched to the initial data set corresponding to each associated data group. A secondary matching is performed on at least two associated data groups to obtain a data group matching result, and it is determined according to the data group matching result whether there are amplitude ratio coefficients corresponding to at least two associated data groups that meet a preset coefficient matching condition; if so, an initial time node corresponding to an initial data set of the at least two associated data groups is determined, and an associated data group whose initial time node is close to the current time node is taken as a second data group; if there are no amplitude ratio coefficients corresponding to at least two associated data groups that meet the preset coefficient matching condition, the associated data group is defined as a third data group, and the first data group, the second data group and the third data group are aggregated to obtain at least two representative data groups.
[0033] It is worth mentioning that the preset time interval and preset coefficient matching conditions are pre-set by the staff based on data extraction experience and are not limited here.
[0034] Step S12: preprocess the multi-dimensional data to obtain processed multi-dimensional data.
[0035] According to the embodiment of the present application, data cleaning is performed on the multi-dimensional data to obtain the cleaned multi-dimensional data, and data standardization is performed on the cleaned multi-dimensional data to obtain the processed multi-dimensional data.
[0036] In the embodiment of the present application, data cleaning processing refers to the process of identifying, correcting or deleting errors, duplications, missing or outliers in a data set. This step is intended to improve the quality of the data, ensure the accuracy and consistency of the data, and provide a reliable basis for subsequent data analysis and modeling. The multidimensional data after cleaning processing represents a data set that has been free of errors, duplications, missing or outliers after data cleaning processing, and the quality of these data has been significantly improved. Data standardization processing refers to converting data of different dimensions and distributions into a unified scale or range for subsequent data analysis and modeling. This step is intended to eliminate dimensional differences between data and improve the comparability and analyzability of data.
[0037] Step S13: training and testing the time series prediction model based on the multi-dimensional data to obtain test results.
[0038] In an embodiment of the present application, multi-dimensional data is selected and segmented to obtain a training data set and a test data set, the training data set is input into a time series prediction model for training to obtain a trained time series prediction model (the time series prediction model is a neural network model), and the test data set is input into the trained time series prediction model for model verification testing to obtain test results.
[0039] In the embodiments of the present application, a time series prediction model is taken as an example of a neural network model, including but not limited to one type of neural network model.
[0040] Step S14, determine whether the test result meets the preset test result standard. If yes, collect real-time meteorological data and real-time energy management information, and input the real-time meteorological data and real-time energy management information into the trained time series prediction model to obtain future electricity data and future electricity price data.
[0041] In the embodiment of the present application, the standard for predicting the test result is that the difference range between the test result and the standard result is not greater than the standard set value data.
[0042] Step S15: Based on the preset economic evaluation standard, the future electricity data and the future electricity price data are matched and analyzed to obtain the economic indicator value of the new energy station.
[0043] In the embodiment of the present application, the historical electricity data, historical electricity price data, historical meteorological data and energy management information of the new energy station in the same historical time period are obtained to ensure the consistency and relevance of the data. These data, as the basis of multi-dimensional information, provide comprehensive and accurate input for subsequent data processing and model training. By constructing these data according to the time series node association, the changing trend of each factor over time can be clearly reflected, laying a solid foundation for subsequent analysis. By selecting the associated data information according to the preset time interval, the data redundancy is effectively reduced, while retaining the key information, so that the obtained multi-dimensional data is more streamlined and representative. Further preprocessing of the data improves the quality and availability of the data, and provides reliable data support for the training of the time series prediction model. The time series prediction model is trained and tested based on the processed multi-dimensional data, and the accuracy and reliability of the model are ensured by judging whether the test results meet the preset standards. Subsequently, the real-time meteorological data and energy management information are input into the trained model, which can predict the future electricity and future electricity prices in real time, providing a scientific basis for the economic operation of the new energy station. By matching and analyzing future electricity volume and future electricity price data based on preset economic evaluation standards, the two key factors of electricity volume and electricity price are comprehensively considered, and the economic indicator values of new energy stations are evaluated more comprehensively and accurately, providing strong support for the economic decision-making and optimization of the stations, thereby improving the prediction accuracy of new energy data.
[0044] The following is an introduction to a new energy data prediction system based on multi-factor modeling provided in an embodiment of the present application. The new energy data prediction system based on multi-factor modeling described below and the new energy data prediction method based on multi-factor modeling described above can be referred to each other. Please refer to Figure 2 , Figure 2 : is a schematic diagram of a new energy data prediction system 20 based on multi-factor modeling provided in an embodiment of the present application, including: The data acquisition module 21 is used to acquire the historical electricity data, historical electricity price data, historical meteorological data and energy management information of the new energy station. The historical electricity data, historical electricity price data and historical meteorological data are all data generated in the same historical time period. The energy management information is the energy policy management data information of the area where the new energy station is located; The data selection module 22 is used to associate the historical electricity data, historical electricity price data, historical meteorological data and energy management information according to the time series nodes, and select the associated data information according to the preset time interval to obtain the multi-dimensional data corresponding to different time nodes; The data processing module 23 is used to perform data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data; The model training module 24 is used to train and test the time series prediction model based on multi-dimensional data to obtain test results; The data analysis module 25 is used to determine whether the test result meets the preset test result standard. If so, real-time meteorological data and real-time energy management information are collected and input into the trained time series prediction model to obtain future electricity data and future electricity price data. The data matching module 26 is used to match and analyze the future electricity data and the future electricity price data based on the preset economic evaluation standard to obtain the economic indicator value of the new energy station.
[0045] In a possible implementation of the embodiment of the present application, when the model training module 24 performs training and testing on the time series prediction model based on multi-dimensional data and obtains the test results, it is specifically used to: Select and segment the multi-dimensional data to obtain training data sets and test data sets; Input the training data set into the time series prediction model for training to obtain the trained time series prediction model; Input the test data set into the trained time series prediction model to perform model validation test and obtain the test results In another possible implementation of the embodiment of the present application, the data selection module 22 associates historical electricity data, historical electricity price data, historical meteorological data, and energy management information according to time series nodes, and selects the associated data information according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes, which is specifically used to: Determine energy policy management data at different time points based on energy management information; Create a multidimensional data coordinate system, the X-axis of the multidimensional data coordinate system is different time nodes, and the Y-axis of the multidimensional data coordinate system is the data unit parameters of different dimensions; Import historical electricity data, historical electricity price data, historical meteorological data and energy policy management data into the multidimensional data coordinate system respectively, and obtain an electricity change curve corresponding to the historical electricity data, an electricity price change curve corresponding to the historical electricity price data, an environment change curve corresponding to the historical meteorological data and a management change curve corresponding to the energy policy management data; Performing change amplitude detection on the environment change curve and the management change curve to determine a first time point at which the environment change curve or the management change curve changes by a first preset amplitude; The first time node is defined as the starting time node, and the amplitude of the power change curve and the electricity price change curve is detected to determine the second time node at which the power change curve and the electricity price change curve change by a second preset amplitude; According to the time correspondence between the first time node and the second time node, historical electricity data, historical electricity price data, historical meteorological data and energy management information are associated with each other to obtain multiple associated data groups; Performing key data group screening on multiple related data groups to obtain at least two representative data groups; The associated data in at least two representative data groups are selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes.
[0046] In another possible implementation of the embodiment of the present application, when the data selection module 22 performs key data group screening on multiple related data groups to obtain at least two representative data groups, it is specifically used to: Determine the data amplitude difference and amplitude change time interval corresponding to each associated data group according to the plurality of associated data groups; Calculate the ratio of the data amplitude difference and the amplitude change time interval to obtain the amplitude proportional coefficient corresponding to each associated data group; Collecting the initial data set of each associated data group at a time before the data amplitude occurs, and matching the initial data set corresponding to each associated data group to determine whether there is a match between at least two initial data sets corresponding to the associated data groups; if not, defining the associated data group as the first data group; if so, performing secondary matching on at least two associated data groups according to the amplitude ratio coefficient and the preset coefficient matching condition to obtain a data group matching result; Determine whether there are at least two associated data groups whose amplitude ratio coefficients meet the preset coefficient matching condition according to the data group matching result; if so, determine the initial time node corresponding to the initial data set of the at least two associated data groups, and take the associated data group whose initial time node is close to the current time node as the second data group; If there are no at least two associated data groups whose corresponding amplitude ratio coefficients satisfy the preset coefficient matching condition, the associated data group is defined as a third data group; The first data group, the second data group and the third data group are aggregated to obtain at least two representative data groups.
[0047] In another possible implementation of the embodiment of the present application, when the data processing module 23 performs data preprocessing on the multi-dimensional data to obtain the processed multi-dimensional data, it is specifically used to: Performing data cleaning on the multi-dimensional data to obtain cleaned multi-dimensional data; The cleaned multi-dimensional data is subjected to data standardization processing to obtain processed multi-dimensional data.
[0048] The present application embodiment provides an electronic device, such as Figure 3 As shown, Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.
[0049] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of the embodiments of the present application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.
[0050] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0051] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.
[0052] The memory 303 is used to store application code for executing the solution of the embodiment of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the above method embodiment.
[0053] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0054] A computer-readable storage medium provided in an embodiment of the present application is introduced below. The computer-readable storage medium described below and the method described above can be referenced to each other.
[0055] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the new energy data prediction method based on multi-factor modeling are implemented.
[0056] Since the embodiments of the computer-readable storage medium part and the embodiments of the method part correspond to each other, the embodiments of the computer-readable storage medium part refer to the description of the embodiments of the method part.
[0057] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.
[0058] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A new energy data prediction method based on multi-factor modeling, characterized in that: include: Acquire historical electricity data, historical electricity price data, historical meteorological data and energy management information of the new energy station, wherein the historical electricity data, the historical electricity price data and the historical meteorological data are all data generated in the same historical time period, and the energy management information is energy policy management data information of the area where the new energy station is located; The historical electricity data, the historical electricity price data, the historical meteorological data and the energy management information are associated with each other according to time series nodes, and the associated data information is selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes; Performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data; Performing training and testing on the time series prediction model based on the multi-dimensional data to obtain test results; Determine whether the test result meets the preset test result standard. If so, collect real-time meteorological data and real-time energy management information, and input the real-time meteorological data and the real-time energy management information into the trained time series prediction model to obtain future electricity data and future electricity price data; Based on the preset economic evaluation standard, the future electricity data and the future electricity price data are matched and analyzed to obtain the economic indicator value of the new energy station.
2. The new energy data prediction method based on multi-factor modeling according to claim 1 is characterized in that: The training and testing of the time series prediction model based on the multi-dimensional data to obtain the test results includes: Select and segment the multi-dimensional data to obtain a training data set and a test data set; Inputting the training data set into the time series prediction model for training to obtain a trained time series prediction model; The test data set is input into the trained time series prediction model to perform a model validation test to obtain a test result.
3. The new energy data prediction method based on multi-factor modeling according to claim 1 is characterized in that: The historical electricity data, the historical electricity price data, the historical meteorological data and the energy management information are associated with each other according to time series nodes, and the associated data information is selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes, including: Determine energy policy management data at different time points according to the energy management information; Creating a multidimensional data coordinate system, wherein the X-axis of the multidimensional data coordinate system is different time nodes, and the Y-axis of the multidimensional data coordinate system is data unit parameters of different dimensions; Importing the historical electricity quantity data, the historical electricity price data, the historical meteorological data and the energy policy management data into the multidimensional data coordinate system respectively, to obtain an electricity quantity change curve corresponding to the historical electricity quantity data, an electricity price change curve corresponding to the historical electricity price data, an environment change curve corresponding to the historical meteorological data and a management change curve corresponding to the energy policy management data; Performing change amplitude detection on the environment change curve and the management change curve to determine a first time point at which the environment change curve or the management change curve changes by a first preset amplitude; The first time node is defined as a starting time node, and amplitude detection is performed on the power change curve and the electricity price change curve to determine a second time node at which the power change curve and the electricity price change curve change by a second preset amplitude; According to the time correspondence between the first time node and the second time node, the historical electricity data, the historical electricity price data, the historical meteorological data and the energy management information are associated with each other to obtain a plurality of associated data groups; Performing key data group screening on the multiple associated data groups to obtain at least two representative data groups; The associated data in the at least two representative data groups are selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes.
4. The new energy data prediction method based on multi-factor modeling according to claim 3 is characterized in that: The step of screening the plurality of associated data groups for key data groups to obtain at least two representative data groups includes: Determine the data amplitude difference and amplitude change time interval corresponding to each associated data group according to the plurality of associated data groups; Calculate the ratio of the data amplitude difference and the amplitude change time interval to obtain the amplitude proportional coefficient corresponding to each associated data group; Collecting the initial data set of each associated data group at a time before the data amplitude occurs, and matching the initial data set corresponding to each associated data group to determine whether there is a situation where the initial data sets corresponding to at least two associated data groups match each other; if not, defining the associated data group as a first data group; if so, performing secondary matching on the at least two associated data groups according to the amplitude ratio coefficient and a preset coefficient matching condition to obtain a data group matching result; Determine, according to the data group matching result, whether there are at least two associated data groups whose amplitude ratio coefficients meet the preset coefficient matching condition; if so, determine the initial time node corresponding to the initial data set of the at least two associated data groups, and take the associated data group whose initial time node is close to the current time node as the second data group; If there are no at least two associated data groups whose corresponding amplitude ratio coefficients satisfy the preset coefficient matching condition, the associated data groups are defined as the third data group; The first data group, the second data group and the third data group are aggregated to obtain at least two representative data groups.
5. The new energy data prediction method based on multi-factor modeling according to claim 1 is characterized in that: The performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data includes: Performing data cleaning on the multi-dimensional data to obtain cleaned multi-dimensional data; The cleaned multi-dimensional data is subjected to data standardization processing to obtain processed multi-dimensional data.
6. A new energy data prediction system based on multi-factor modeling, characterized in that: include: A data acquisition module is used to acquire historical electricity data, historical electricity price data, historical meteorological data and energy management information of a new energy station, wherein the historical electricity data, the historical electricity price data and the historical meteorological data are all data generated in the same historical time period, and the energy management information is energy policy management data information of the area where the new energy station is located; A data selection module is used to associate the historical electricity data, the historical electricity price data, the historical meteorological data and the energy management information according to time series nodes, and select the associated data information according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes; A data processing module, used for performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data; A model training module is used to train and test the time series prediction model based on the multi-dimensional data to obtain test results; A data analysis module, used to determine whether the test result meets the preset test result standard. If so, real-time meteorological data and real-time energy management information are collected, and the real-time meteorological data and the real-time energy management information are input into the trained time series prediction model to obtain future electricity data and future electricity price data; The data matching module is used to match and analyze the future electricity data and the future electricity price data based on a preset economic evaluation standard to obtain the economic indicator value of the new energy station.
7. A new energy data prediction system based on multi-factor modeling according to claim 6, characterized in that: The data selection module is specifically used to associate and construct data information of the historical electricity data, the historical electricity price data, the historical meteorological data and the energy management information according to time series nodes, and select the associated data information according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes: Determine energy policy management data at different time points according to the energy management information; Creating a multidimensional data coordinate system, wherein the X-axis of the multidimensional data coordinate system is different time nodes, and the Y-axis of the multidimensional data coordinate system is data unit parameters of different dimensions; Importing the historical electricity quantity data, the historical electricity price data, the historical meteorological data and the energy policy management data into the multidimensional data coordinate system respectively, to obtain an electricity quantity change curve corresponding to the historical electricity quantity data, an electricity price change curve corresponding to the historical electricity price data, an environment change curve corresponding to the historical meteorological data and a management change curve corresponding to the energy policy management data; Performing change amplitude detection on the environment change curve and the management change curve to determine a first time point at which the environment change curve or the management change curve changes by a first preset amplitude; The first time node is defined as a starting time node, and amplitude detection is performed on the power change curve and the electricity price change curve to determine a second time node at which the power change curve and the electricity price change curve change by a second preset amplitude; According to the time correspondence between the first time node and the second time node, the historical electricity data, the historical electricity price data, the historical meteorological data and the energy management information are associated with each other to obtain a plurality of associated data groups; Performing key data group screening on the multiple associated data groups to obtain at least two representative data groups; The associated data in the at least two representative data groups are selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes.
8. The new energy data prediction method based on multi-factor modeling according to claim 7 is characterized in that: When the data selection module performs key data group screening on the multiple related data groups to obtain at least two representative data groups, it is specifically used to: Determine the data amplitude difference and amplitude change time interval corresponding to each associated data group according to the plurality of associated data groups; Calculate the ratio of the data amplitude difference and the amplitude change time interval to obtain the amplitude proportional coefficient corresponding to each associated data group; Collecting the initial data set of each associated data group at a time before the data amplitude occurs, and matching the initial data set corresponding to each associated data group to determine whether there is a situation where the initial data sets corresponding to at least two associated data groups match each other; if not, defining the associated data group as a first data group; if so, performing secondary matching on the at least two associated data groups according to the amplitude ratio coefficient and a preset coefficient matching condition to obtain a data group matching result; Determine, according to the data group matching result, whether there are at least two associated data groups whose amplitude ratio coefficients meet the preset coefficient matching condition; if so, determine the initial time node corresponding to the initial data set of the at least two associated data groups, and take the associated data group whose initial time node is close to the current time node as the second data group; If there are no at least two associated data groups whose corresponding amplitude ratio coefficients satisfy the preset coefficient matching condition, the associated data groups are defined as the third data group; The first data group, the second data group and the third data group are aggregated to obtain at least two representative data groups.
9. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a new energy data prediction method based on multi-factor modeling as described in any one of claims 1-5.
10. A computer-readable storage medium, characterized in that: include: A computer program is stored which can be loaded by a processor and execute a new energy data prediction method based on multi-factor modeling as described in any one of claims 1 to 5.