Power trading decision method, device, storage medium and electronic equipment

Abstract

The present disclosure relates to a method, device, storage medium and electronic device for power trading decision-making, which can improve the efficiency of power trading and the accuracy of decision-making. The method includes: obtaining real-time data of the power market, wherein the real-time data of the power market includes power trading data, new energy power generation data and meteorological data; preprocessing the real-time data of the power market to obtain target data; inputting the target data into a pre-trained machine learning model to obtain a power market price prediction result; and determining a target power trading strategy according to the power market price prediction result.

Description

Technical Field

[0001] The present disclosure relates to the technical field of power market data analysis and prediction, and in particular, to a power trading decision-making method, device, storage medium and electronic equipment. Background Art

[0002] In the electricity market, the electricity trading system is a key tool for electricity traders to conduct transactions. The system can help traders conduct effective transactions in an environment of fierce competition and volatile markets by providing real-time market data and executing trading instructions.

[0003] In the related technologies, the existing electricity trading system supports market participants through simple information disclosure and basic transaction execution functions, usually obtaining information from scattered data sources, and the prediction of market price fluctuations relies on basic statistical analysis and simple models of historical data, which makes the prediction accuracy of market price fluctuations low and cannot effectively respond to the rapidly changing market environment, thus affecting the efficiency of electricity trading and the accuracy of decision-making. Summary of the invention

[0004] The purpose of the present disclosure is to provide a power trading decision method, device, storage medium and electronic device to solve the problems in the related art.

[0005] In order to achieve the above objectives, in a first aspect, the present disclosure provides a method for power trading decision-making, the method comprising: Acquiring real-time data of the power market, wherein the real-time data of the power market includes power transaction data, new energy power generation data and meteorological data; Preprocessing the real-time data of the power market to obtain target data; Inputting the target data into a pre-trained machine learning model to obtain a power market price prediction result; According to the electricity market price forecast results, a target electricity trading strategy is determined.

[0006] Optionally, the preprocessing of the real-time data of the power market to obtain target data includes: The real-time data of the power market is cleaned, and feature recognition is performed on the cleaned real-time data of the power market to obtain the target data.

[0007] Optionally, the training of the machine learning model includes: Acquire a model training sample, wherein the model training sample includes sample data and a data label corresponding to the sample data; Divide the model training samples into a training set, a validation set and a test set, wherein the training set is used for learning model parameters, the validation set is used for model selection and tuning, and the test set is used to evaluate the performance of the final model; The machine learning model is trained according to the training set, the validation set and the test set to obtain a trained machine learning model.

[0008] Optionally, the data tag includes an actual electricity market price corresponding to the time series of the sample data.

[0009] Optionally, inputting the target data into a pre-trained machine learning model to obtain a power market price prediction result includes: Inputting the target data into a pre-trained machine learning model to obtain a predicted value of the electricity market price within the time period to be predicted; The electricity market price prediction result is obtained according to the electricity market price prediction value.

[0010] Optionally, the obtaining of real-time electricity market data includes: The real-time data of the electricity market is collected by using a preset web crawler algorithm.

[0011] In a second aspect, the present disclosure further provides an electric power trading decision-making device, the device comprising: An acquisition module is used to acquire real-time data of the power market, wherein the real-time data of the power market includes power transaction data, new energy power generation data and meteorological data; A preprocessing module, used for preprocessing the real-time data of the power market to obtain target data; A prediction module, used to input the target data into a pre-trained machine learning model to obtain a power market price prediction result; The determination module is used to determine the target power trading strategy according to the power market price prediction result.

[0012] Optionally, the preprocessing module is used to: The real-time data of the power market is cleaned, and feature recognition is performed on the cleaned real-time data of the power market to obtain the target data.

[0013] In a third aspect, the present disclosure provides a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0014] In a fourth aspect, the present disclosure provides an electronic device, including: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of any one of the methods in the first aspect.

[0015] Through the above technical solution, real-time data of the power market is obtained, wherein the real-time data of the power market includes power trading data, new energy power generation data and meteorological data, and the real-time data of the power market is pre-processed to obtain target data, and the target data is input into the pre-trained machine learning model to obtain the power market price forecast result, and the target power trading strategy is determined according to the power market price forecast result. Among them, multi-source data related to the power market is collected and integrated in real time, and the market price forecast based on machine learning is adopted for the pre-processed target data. By combining the optimized forecast model and real-time data analysis, it can provide intelligent decision support for traders, thereby improving the efficiency of power trading and the accuracy of decision-making.

[0016] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings: Figure 1 The figure is a flow chart of a method for making decisions on power trading according to an exemplary embodiment of the present disclosure.

[0018] Figure 2 The figure is a block diagram of a power trading decision-making device according to an exemplary embodiment of the present disclosure.

[0019] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0021] As mentioned in the background technology, in the relevant technology, the existing power trading system has several significant defects: First, the scattered data sources make it impossible for the system to fully obtain and integrate the multi-dimensional data required by the market, limiting the accurate understanding of the overall market situation. Secondly, the prediction of market price fluctuations relies on simple models of basic statistical analysis and historical data, which makes the prediction accuracy of market price fluctuations low and cannot effectively respond to the rapidly changing market environment. And it is limited to providing basic information disclosure and transaction execution functions, which affects the efficiency of power trading and the accuracy of decision-making.

[0022] In view of this, the embodiments of the present disclosure provide a method, device, storage medium and electronic device for making decisions on power trading, which can improve the efficiency of power trading and the accuracy of decision-making.

[0023] Figure 1 is a flow chart of a power trading decision method according to an exemplary embodiment of the present disclosure. Figure 1 As shown, the method may include the following steps: Step S101, obtaining real-time data of the power market, wherein the real-time data of the power market includes power transaction data, new energy power generation data and meteorological data.

[0024] It should be understood that It should be understood that real-time market data can be obtained from multiple data sources, including but not limited to information on electricity production, demand, price, weather conditions, etc. Data sources can cover various market quotations, supply and demand balances, and policy changes. Traders can use these market data for multi-dimensional analysis, including market price trend forecasting, risk assessment, and market opportunity identification.

[0025] For example, regarding real-time data on the electricity market, multi-dimensional information including power forecast, electricity production, demand, price, weather, etc. may be selected according to actual conditions.

[0026] Step S102, preprocessing the real-time data of the power market to obtain target data.

[0027] Step S103, inputting the target data into a pre-trained machine learning model to obtain a power market price prediction result.

[0028] Step S104, determining a target power trading strategy according to the power market price forecast result.

[0029] It should be understood that the use of technologies such as machine learning and data mining can be used to analyze and process large amounts of historical and real-time market data, extract patterns from complex market data, predict trends, and identify potential market opportunities and risks, and assist traders in formulating trading strategies and action plans based on the analysis results.

[0030] For example, the power trading system can provide a data visualization interface to display data in the form of charts, maps, etc., to help traders analyze market dynamics and thus determine target power trading strategies.

[0031] Through the above method, the real-time data of the power market is obtained, wherein the real-time data of the power market includes power trading data, new energy power generation data and meteorological data, the real-time data of the power market is pre-processed to obtain the target data, and the target data is input into the pre-trained machine learning model to obtain the power market price forecast result, and the target power trading strategy is determined according to the power market price forecast result. Among them, the multi-source data related to the power market is collected and integrated in real time, and the market price forecast based on machine learning is adopted for the pre-processed target data. By combining the optimized forecast model and real-time data analysis, it can provide intelligent decision support for traders, thereby improving the efficiency of power trading and the accuracy of decision-making.

[0032] In a possible implementation, preprocessing the real-time data of the power market to obtain target data may include: The real-time data of the power market is cleaned, and feature recognition is performed on the cleaned real-time data of the power market to obtain target data.

[0033] It should be understood that Python's Pandas library can be used for data cleaning, including data filtering, data conversion, and data sorting. By identifying and removing duplicate records in the real-time data set of the power market, the uniqueness and accuracy of the data are ensured, and the format of data obtained from different data sources is standardized, and the field naming, units, and data types are unified to facilitate subsequent data integration and analysis.

[0034] For example, after collecting raw data and cleaning it, the data can be classified and organized according to different categories (such as price data, load data, meteorological data, etc.), and missing values, outliers, and standardized / normalized can be processed.

[0035] For example, the processed data can be presented in a visual manner. Specifically, the data characteristics can be intuitively displayed in the form of charts, reports, etc., and the correlation between various types of data can be demonstrated. Power traders can select important influencing factors as model inputs based on actual trading experience, such as: historical transaction price ranges, load demand restrictions, power generation cost constraints, transmission channel capacity, seasonal factors, special event impacts, etc., which are not limited to the embodiments of the present disclosure.

[0036] For example, ETL (Extract, Transform, Load) tools (such as Apache NiFi, Talend) can be used for automated data cleaning and feature extraction according to actual conditions.

[0037] Through the above methods, data cleaning and feature recognition can improve data quality, ensure data integrity and accuracy, and multi-dimensional data association analysis can provide a basis for decision-making. By selecting key features, a reliable data foundation can be provided for subsequent model training, thereby improving the training effect and prediction accuracy of the market price prediction model.

[0038] In one possible implementation, the training of the machine learning model may include: Obtaining a model training sample, where the model training sample includes sample data and data labels corresponding to the sample data; The model training samples are divided into training set, validation set and test set. The training set is used to learn model parameters, the validation set is used for model selection and tuning, and the test set is used to evaluate the performance of the final model. The machine learning model is trained according to the training set, validation set and test set to obtain a trained machine learning model.

[0039] The data labels include the actual electricity market prices corresponding to the time series of the sample data.

[0040] It should be understood that clustering algorithms can be used to analyze the correlation between different data sources, calculate the degree of correlation between each data source and the price, and assign initial weights to different data sources based on the correlation. The weights are used to characterize the influence of different data on market price predictions. The weights are applied to the features of each data source to construct a weighted feature data set, which helps improve the prediction accuracy and adaptability of the model.

[0041] It should be understood that the prediction accuracy and practicality of the model can be evaluated by analyzing the results predicted by the model and comparing and verifying them with actual market conditions.

[0042] For example, the general platform of cloud services can be used to help train models to predict market prices according to actual conditions. The general machine learning and data analysis platform provided by cloud services can be used to conduct forecasting and decision support for the electricity market.

[0043] For example, unsupervised learning algorithms, such as Self-Organizing Maps (SOM), can be used to perform cluster analysis according to actual conditions to infer market trends.

[0044] For example, time series analysis models can be used according to actual conditions, such as the Autoregressive Integrated Moving Average model (AIMA) and the Seasonal Autoregressive Integrated Moving Average model (SARIMA) for predicting electricity market prices. Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) can be used to process more complex time series data.

[0045] For example, heuristic algorithms (such as genetic algorithms and ant colony algorithms) can be used to optimize the parameters of the machine learning model according to actual conditions.

[0046] For example, a Bayesian network may be used to perform probability analysis and data classification according to actual conditions.

[0047] In a possible implementation, inputting the target data into a pre-trained machine learning model to obtain a power market price prediction result may include: Input the target data into the pre-trained machine learning model to obtain the predicted value of the electricity market price within the time period to be predicted; According to the electricity market price forecast value, the electricity market price forecast result is obtained.

[0048] It should be understood that in practical applications, the pre-processed real-time data of the electricity market is input into the trained machine learning model, and the model can predict the price trend in the future based on the learned historical laws and current market conditions. And by continuously monitoring the performance of the prediction model and continuously optimizing the model based on actual market feedback, the accuracy and reliability of the prediction can be improved.

[0049] For example, a suitable supervised learning algorithm can be selected according to the actual situation, such as linear regression: finding the linear relationship between input features and prices; support vector machine (SVM): finding the optimal classification / regression boundary by mapping data into a high-dimensional space; random forest: integrating the results of multiple decision trees for prediction.

[0050] For example, market dynamics and electricity market price forecast results can be displayed through visualization methods such as charts and maps, helping traders to understand complex market information more intuitively.

[0051] For example, a user interaction interface can be set up according to actual conditions, allowing traders to interact with relevant systems, such as adjusting forecast parameters, viewing detailed analysis, etc.

[0052] Through the above methods, machine learning and data mining technologies can be used to establish electricity market price forecasting models to analyze historical data and real-time market dynamics, accurately predict market price fluctuation trends, and help traders capture market opportunities and reduce risks in a timely manner, thereby improving trading efficiency and decision-making accuracy.

[0053] In a possible implementation, obtaining real-time data of the electricity market may include: Real-time data of the electricity market is collected through the preset web crawler algorithm.

[0054] It should be understood that a web crawler algorithm refers to an automated program that can simulate human users accessing web pages and searching for information on the Internet, thereby crawling information and data from websites and storing them in a database. A web crawler algorithm can automatically traverse web pages and websites on the Internet according to specified rules and download the information content therein for data integration and analysis.

[0055] It should be understood that the web crawler algorithm can be developed by using the Python programming language and third-party libraries (such as Requests, BeautifulSoup, etc.) Specifically, the crawler obtains data from power market-related websites through HTTP requests, such as transaction data of power exchanges, price reports of energy markets, and real-time conditions of meteorological data, integrates with the API interfaces of various data sources, and obtains real-time data through API calls for subsequent processing and analysis.

[0056] It should also be understood that API interfaces are one of the important means of modern data collection. Through API interfaces, data can be obtained from third-party platforms or services. API interfaces usually provide structured data for subsequent processing and analysis. The advantage of API interfaces is that their data is updated in a timely manner and is easy to obtain. It is suitable for collecting real-time data or newer data.

[0057] For example, a rule engine or an expert system may be used to process multi-source data according to actual conditions, and weights may be manually assigned according to predefined rules.

[0058] For example, a data lake architecture can be adopted according to actual conditions to achieve data integration and query by integrating all data sources into a unified storage platform.

[0059] Through the above method, the real-time data of the power market is collected by using a preset web crawler algorithm, which can effectively integrate information, ensure the relevance and accuracy of the data, and help traders obtain comprehensive and accurate market information.

[0060] In summary, the power trading decision-making method has the following advantages: 1) Efficient integration and processing of multi-source data: Through clustering algorithms and data cleaning technology, various types of data in the power market can be effectively integrated and processed from multiple data sources. This multi-dimensional data integration improves the integrity and accuracy of the data, enabling traders to obtain comprehensive and reliable market information and avoid information silos and data fragmentation.

[0061] 2) Accurate market price prediction: By adopting supervised learning algorithms (such as random forests, support vector machines, etc.) combined with prediction models (such as time series analysis, deep learning models, etc.), the accuracy of market price prediction is significantly improved, allowing traders to more accurately grasp the changing trends of market prices, thereby optimizing trading decisions and reducing market risks.

[0062] 3) Real-time decision support: Through the analysis and processing of real-time data, the market forecast model can be dynamically updated, and the latest market intelligence and trading suggestions can be provided to traders in a timely manner. This real-time decision support can help traders respond quickly in the case of large market fluctuations, seize trading opportunities and avoid potential risks.

[0063] 4) Intelligent decision-making suggestions: Using machine learning and data mining technology, it not only provides basic information disclosure and transaction execution functions, but also can extract valuable patterns and trends from a large amount of historical and real-time data to provide intelligent decision-making suggestions. This intelligent support can effectively improve traders' decision-making efficiency and transaction success rate.

[0064] 5) Improve transaction efficiency and accuracy: By combining advanced forecasting models and real-time data analysis, the efficiency of power trading and the accuracy of decision-making are improved. Traders can process complex data and make wise decisions in a short time, thus gaining an advantage in the highly competitive market environment.

[0065] Figure 2 is a power trading decision-making device 200 according to an exemplary embodiment of the present disclosure, such as Figure 2 As shown, the power trading decision-making device 200 includes: An acquisition module 201 is used to acquire real-time data of the power market, wherein the real-time data of the power market includes power transaction data, new energy power generation data and meteorological data; The preprocessing module 202 is used to preprocess the real-time data of the power market to obtain target data; The prediction module 203 is used to input the target data into the pre-trained machine learning model to obtain the power market price prediction result; The determination module 204 is used to determine the target power trading strategy according to the power market price prediction result.

[0066] Through the above device, the real-time data of the power market is obtained, wherein the real-time data of the power market includes power trading data, new energy power generation data and meteorological data, the real-time data of the power market is pre-processed to obtain the target data, and the target data is input into the pre-trained machine learning model to obtain the power market price forecast result, and the target power trading strategy is determined according to the power market price forecast result. Among them, the multi-source data related to the power market is collected and integrated in real time, and the market price forecast based on machine learning is adopted for the pre-processed target data. By combining the optimized forecast model and real-time data analysis, it can provide intelligent decision support for traders, thereby improving the efficiency of power trading and the accuracy of decision-making.

[0067] Optionally, the preprocessing module 202 is used to: The real-time data of the power market is cleaned, and feature recognition is performed on the cleaned real-time data of the power market to obtain target data.

[0068] Optionally, the training of the machine learning model includes the following modules: A model training sample acquisition module is used to acquire model training samples, where the model training samples include sample data and data labels corresponding to the sample data; The model training sample division module is used to divide the model training samples into training set, validation set and test set. The training set is used to learn model parameters, the validation set is used for model selection and tuning, and the test set is used to evaluate the performance of the final model. The machine learning model training module is used to train the machine learning model according to the training set, validation set and test set to obtain a trained machine learning model.

[0069] Optionally, the data labels in the model training sample acquisition module include actual electricity market prices corresponding to the time series of the sample data.

[0070] Optionally, the prediction module 203 is used to: Input the target data into the pre-trained machine learning model to obtain the predicted value of the electricity market price within the time period to be predicted; According to the electricity market price forecast value, the electricity market price forecast result is obtained.

[0071] Optionally, the acquisition module 201 is used to: Real-time data of the electricity market is collected through the preset web crawler algorithm.

[0072] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0073] Figure 3 FIG. 1 is a block diagram of an electronic device 300 according to an exemplary embodiment. Figure 3 As shown, the electronic device 300 may include: a processor 301 , a memory 302 . The electronic device 300 may also include one or more of a multimedia component 303 , an input / output (I / O) interface 304 , and a communication component 305 .

[0074] The processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps in the above-mentioned power trading decision method. The memory 302 is used to store various types of data to support the operation of the electronic device 300, and these data may include, for example, instructions for any application or method for operating on the electronic device 300, and application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving an external audio signal. The received audio signal may be further stored in the memory 302 or sent through the communication component 305. The audio component also includes at least one speaker for outputting an audio signal. The I / O interface 304 provides an interface between the processor 301 and other interface modules, and the above-mentioned other interface modules may be a keyboard, a mouse, a button, etc. These buttons may be virtual buttons or physical buttons. The communication component 305 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 305 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0075] In an exemplary embodiment, the electronic device 300 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned power trading decision-making method.

[0076] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned power trading decision method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 302 including program instructions, and the above-mentioned program instructions can be executed by the processor 301 of the electronic device 300 to complete the above-mentioned power trading decision method.

[0077] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0078] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0079] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A power trading decision-making method, characterized in that: The method comprises: Acquiring real-time data of the power market, wherein the real-time data of the power market includes power transaction data, new energy power generation data and meteorological data; Preprocessing the real-time data of the power market to obtain target data; Inputting the target data into a pre-trained machine learning model to obtain a power market price prediction result; According to the electricity market price forecast results, a target electricity trading strategy is determined.

2. The method according to claim 1, characterized in that The preprocessing of the real-time data of the power market to obtain target data includes: The real-time data of the power market is cleaned, and feature recognition is performed on the cleaned real-time data of the power market to obtain the target data.

3. The method according to claim 1, characterized in that: The training of the machine learning model includes: Acquire a model training sample, wherein the model training sample includes sample data and a data label corresponding to the sample data; Divide the model training samples into a training set, a validation set and a test set, wherein the training set is used for learning model parameters, the validation set is used for model selection and tuning, and the test set is used to evaluate the performance of the final model; The machine learning model is trained according to the training set, the validation set and the test set to obtain a trained machine learning model.

4. The method according to claim 3, characterized in that The data tags include actual electricity market prices corresponding to the time series of the sample data.

5. The method according to claim 1, characterized in that The target data is input into a pre-trained machine learning model to obtain a power market price prediction result, including: Inputting the target data into a pre-trained machine learning model to obtain a predicted value of the electricity market price within the time period to be predicted; The electricity market price prediction result is obtained according to the electricity market price prediction value.

6. The method according to claim 1, characterized in that The obtaining of real-time data of the electricity market includes: The real-time data of the electricity market is collected by using a preset web crawler algorithm.

7. An electric power trading decision-making device, characterized in that: The device comprises: An acquisition module is used to acquire real-time data of the power market, wherein the real-time data of the power market includes power transaction data, new energy power generation data and meteorological data; A preprocessing module, used for preprocessing the real-time data of the power market to obtain target data; A prediction module, used to input the target data into a pre-trained machine learning model to obtain a power market price prediction result; The determination module is used to determine the target power trading strategy according to the power market price prediction result.

8. The device according to claim 7, characterized in that The pre-processing module is used for: The real-time data of the power market is cleaned, and feature recognition is performed on the cleaned real-time data of the power market to obtain the target data.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 6.

Images