Method and system for monitoring electric power marketing condition in real time

Abstract

The invention relates to a method and system for monitoring power marketing conditions in real time, and the method comprises the steps: obtaining power market data from data sources of different countries according to a preset time interval, and carrying out the standardization processing of the power market data, and obtaining structural data; performing statistical analysis on the structured data to obtain an analysis result; and carrying out visual display on the analysis result. And real-time acquisition and processing of transnational electricity market data are realized.

Description

Technical Field

[0001] This invention relates to the field of electricity, and more specifically, to a method and system for real-time monitoring of electricity marketing. Background Technology

[0002] Traditional electricity marketing management models suffer from numerous drawbacks. Data from various countries and projects is typically managed and analyzed manually using Excel spreadsheets. This method is not only inefficient but also prone to errors due to inconsistent data formats, making it difficult to support large-scale, multi-dimensional, and time-sensitive data processing needs. In contract management, documents are stored in a scattered manner on local disks, lacking a centralized and unified storage structure and standardized processing mechanisms, which hinders information retrieval, updates, and compliance reviews. Furthermore, the frequent fluctuations in electricity market prices mean that relying on manual data collection cannot achieve hourly or even real-time responses, impacting the company's ability to make rapid decisions. Existing commercial platforms often lack high customization capabilities, have limited functionality, and struggle to meet the complex management needs of multinational operating companies. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for real-time monitoring of electricity marketing, addressing the shortcomings of existing commercial platforms in the prior art, which have limited functionality and are unable to meet the complex management needs of multinational operating enterprises.

[0004] The technical solution adopted by this invention to solve its technical problem is: to provide a method for real-time monitoring of electricity marketing, comprising the following steps:

[0005] Step S1: Obtain electricity market data from data sources in different countries according to a preset time interval, and perform standardization processing on the electricity market data to obtain structured data;

[0006] Step S2: Perform statistical analysis on the structured data to obtain the analysis results;

[0007] Step S3: Visualize the analysis results.

[0008] In one embodiment, in step S1, the electricity market data includes electricity price data;

[0009] The standardization process of the electricity market data to obtain structured data includes:

[0010] The electricity price data is processed by currency unification, time zone conversion, and missing information completion to obtain the structured data.

[0011] In one embodiment, step S2 includes:

[0012] The structured data is categorized and summarized to obtain comparative data on electricity prices in different countries during the same time period.

[0013] In one embodiment, the method further includes:

[0014] Acquire electricity news data from different countries or regions, extract keywords from the electricity news data, and display the processed news data in a simplified form.

[0015] In one embodiment, step S3 includes:

[0016] Based on the analysis results, corresponding data charts are generated, and the data charts are visualized in an interactive manner.

[0017] The data chart types include at least one of the following: bar chart, line chart, heat map, map distribution map, and interactive dashboard.

[0018] In one embodiment, the method further includes:

[0019] Risk analysis is performed on the structured data and / or the analysis results, and risk warning information is generated and visualized.

[0020] In one embodiment, the risk analysis of the structured data and / or the analysis results includes:

[0021] Based on preset risk indicators, the structured data and / or the analysis results are assessed for risk level, and corresponding risk warning information is generated.

[0022] In one embodiment, the electricity market data further includes contract data; step S2 further includes:

[0023] The contract data is identified, and the identified data is standardized to obtain structured contract data.

[0024] In one embodiment, the method further includes:

[0025] The structured contract data that meets the preset query conditions is substituted into the preset standardized business calculation rules to obtain the standardized business calculation results and display them.

[0026] The present invention also provides a system for real-time monitoring of electricity marketing, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0027] The beneficial effects of this invention are that it relates to a method and system for real-time monitoring of electricity marketing, wherein the method includes: acquiring electricity market data from data sources in different countries according to preset time intervals; standardizing the electricity market data to obtain structured data; performing statistical analysis on the structured data to obtain analysis results; and visualizing the analysis results. This achieves real-time acquisition and processing of cross-border electricity market data. Attached Figure Description

[0028] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings:

[0029] Figure 1 This is a flowchart illustrating the method for real-time monitoring of electricity marketing according to the present invention;

[0030] Figure 2 This is a structural block diagram of the system for real-time monitoring of electricity marketing according to the present invention. Detailed Implementation

[0031] The present application will now be described in further detail with reference to the accompanying drawings and specific embodiments. Similar elements in different embodiments are referred to by related similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of the present application. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to the present application are not shown or described in the specification. This is to avoid obscuring the core parts of the present application with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0032] like Figure 1 As shown, Figure 1 A flowchart illustrating the method for real-time monitoring of electricity marketing in this invention.

[0033] The technical solution adopted by this invention to solve its technical problem is: to provide a method for real-time monitoring of electricity marketing, comprising the following steps:

[0034] Step S1: Obtain electricity market data from data sources in different countries according to a preset time interval, and perform standardization processing on the electricity market data to obtain structured data;

[0035] In this step, it should be noted that the system automatically retrieves electricity market data from multiple national electricity market data sources according to preset time intervals (such as hourly or daily). These data sources include, but are not limited to, national electricity exchanges, energy regulatory agencies, wind farm monitoring systems, and electricity price publication platforms.

[0036] The types of data acquired include electricity price data (such as spot electricity price and futures electricity price), trading volume, power generation capacity, load forecast, and weather data.

[0037] Step S2: Perform statistical analysis on the structured data to obtain the analysis results;

[0038] In this step, it's important to note that multi-dimensional statistical analysis is performed on the structured data to generate analysis results. This analysis includes, but is not limited to: electricity price trend analysis: statistical analysis of electricity price trends by country, time period, and electricity price type (spot / futures); capacity and sales comparison analysis: comparing actual power generation and sales volume of wind farms to identify discrepancies; market sensitivity analysis: analyzing the responsiveness of electricity prices to market events (such as weather changes and policy adjustments); risk indicator calculation: calculating key risk indicators (KRIs) such as P10 / P90 revenue, hedging ratio, and open interest; and predictive model output: predicting future electricity prices and sales volumes based on machine learning models. The analysis results are output in the form of data tables, indicator values, and trend charts for subsequent visualization.

[0039] Step S3: Visualize the analysis results. In this step, it should be noted that the system will visualize the analysis results using business intelligence (BI) tools. The visualization formats include...

[0040] Furthermore, in step S1, the electricity market data includes electricity price data; the standardization process of the electricity market data to obtain structured data includes: currency unification processing, time zone conversion processing, and missing information completion processing of the electricity price data to obtain the structured data.

[0041] It should be noted that in step S1, the system automatically obtains electricity market data from multiple countries' electricity market data sources at preset time intervals (e.g., hourly, daily, or weekly). These data sources include, but are not limited to, real-time electricity price data from electricity exchanges in various countries, market information released by energy regulatory agencies, real-time capacity data of power generation facilities such as wind farms and photovoltaic power plants, as well as futures electricity prices, load forecasts, and weather data provided by third-party energy data service platforms.

[0042] In this embodiment, the electricity market data includes at least electricity price data. Since the electricity price data of different countries differ in terms of currency, time format and data integrity, the system needs to standardize the original data to obtain structured data with unified structure and standardized format. Specifically, the following processing steps are included: (1) Currency unification processing: The system identifies the currency unit used in the electricity price data (such as RMB, Euro, USD, etc.) and performs exchange rate conversion according to the preset base currency (such as Euro) to unify all electricity price data into the same currency, ensuring the comparability and consistency of subsequent data analysis; (2) Time zone conversion processing: The system identifies the timestamp information contained in the electricity price data and performs unified conversion according to the international standard time (such as UTC) or the local time of the target market (such as CET) to eliminate the data misalignment problem caused by time zone differences and ensure the continuity and accuracy of time series data; (3) Missing information completion processing: For missing electricity price data caused by data source delay, interface abnormality, etc.

[0043] Specifically, one or more of the following methods are used for data completion: interpolation, which involves linear interpolation based on electricity price data at different time points; historical mean method, which involves filling in the missing data based on the average value of historical electricity price data for the same period; and prediction model method, which involves predicting missing data based on machine learning models (such as regression models or time series models). After the above standardization process, the system generates structured electricity price data and stores it in the database in a unified format for subsequent statistical analysis modules to access.

[0044] Furthermore, step S2 includes: classifying and summarizing the structured data to obtain electricity price comparison data for different countries in the same time period.

[0045] It should be noted that in step S2, the system performs classification and summarization processing on the structured data obtained in step S1 to generate electricity price comparison data for different countries within the same time period. The specific process includes the following sub-steps: (1) Data classification: The system groups the structured data according to preset classification dimensions. The classification dimensions include, but are not limited to, country dimension (classified according to the country of data source), time period dimension (divided by time granularity such as hour, day, week, etc.), electricity price type dimension (distinguishing between spot electricity price, futures electricity price, day-ahead electricity price, etc.), and market type dimension (distinguishing between different market types such as power exchange, over-the-counter trading, bilateral contracts, etc.); (2) Data summarization: Under each classification dimension, the electricity price data is summarized and statistically analyzed to generate representative electricity price indicators, including but not limited to average electricity price (average electricity price within a certain time period), highest / lowest electricity price (the highest / lowest electricity price within a certain time period), etc. (2) Electricity price extremes within a period, electricity price volatility (standard deviation or coefficient of variation reflecting the fluctuation range of electricity prices), electricity price median (used to measure the central trend of electricity price distribution), and electricity price distribution frequency (used to draw electricity price distribution histograms or heat maps); (3) Comparative analysis: Based on the summary results, the system generates electricity price comparison data between different countries within the same time period, specifically including electricity price difference analysis (calculating the electricity price difference and percentage difference between two or more countries), electricity price trend comparison (drawing electricity price trend curves of multiple countries to intuitively show the differences in electricity price trends), electricity price ranking analysis (sorting countries according to electricity price level to identify high-price and low-price markets) and electricity price correlation analysis (calculating the correlation coefficient between electricity prices in different countries to assess market linkage); The above comparison data can be used in subsequent visualization display modules, and can also be used as input for advanced analysis modules such as risk analysis and market forecasting.

[0046] Furthermore, the method also includes: acquiring power news data from different countries or regions, extracting keywords from the power news data, and displaying the processed news data in a simplified form.

[0047] It should be noted that by accessing multiple international news data sources or energy industry information platforms, the system automatically acquires news data related to the electricity market, including adjustments to energy policies in various countries, dynamics of electricity market reforms, electricity price fluctuations, the development of renewable energy, business dynamics such as mergers, acquisitions, cooperation, and investments by power companies, as well as information on the impact of extreme weather or natural disasters on electricity supply and demand. The news data can be multilingual text, which the system processes using natural language processing technology. First, it uses commercially available keyword extraction algorithms to perform semantic analysis on the news text, automatically extracting words or phrases that reflect the core content of the news, such as event type, countries or regions involved, names of companies or institutions, time information, and descriptions of the degree of impact. Then, the extracted keywords are structured and displayed in a simplified form in the user interface. The display methods include keyword tag clouds, news summary cards, timeline displays, and map-linked displays. Users can click on keywords or summary cards to view the original news article or related analysis content.

[0048] Furthermore, step S3 includes: generating corresponding data charts based on the analysis results, and visually displaying the data charts in an interactive manner; wherein the data chart type includes at least one of bar charts, line charts, heat maps, map distribution maps, and interactive dashboards.

[0049] Furthermore, the risk analysis of the structured data and / or the analysis results includes: assessing the risk level of the structured data and / or the analysis results according to preset risk indicators, identifying potential risk factors, and generating corresponding risk warning information.

[0050] It should be noted that 24 / 7 monitoring and dynamic early warning of various risks in the electricity marketing process will improve the risk management capabilities and operational efficiency of power companies. The system comprises a data acquisition module, a data processing module, a risk assessment module, and an early warning output module. The data acquisition module collects structured data in real time during the electricity marketing process, including but not limited to user electricity consumption data, electricity price information, contract performance status, market transaction data, and policy change information. The data processing module cleans, normalizes, and structures the collected data to create a standardized dataset suitable for analysis. The risk assessment module incorporates multiple key risk indicators (KRIs), such as the P10 / P90 income indicator (used to assess extreme cases of income distribution and identify income volatility risk), the hedging ratio indicator (used to measure the effectiveness of market risk hedging), the regulatory impact indicator (used to assess the potential impact of policy or regulatory changes on electricity marketing), and auxiliary indicators such as customer default rate and contract execution rate. Based on preset risk indicators, the system calculates these indicators in real time to assess the risk level of the current electricity marketing activity. The early warning output module automatically generates risk warning information when an indicator exceeds a set threshold or the risk level reaches a warning level, and notifies relevant management personnel through a visual interface, SMS, email, and other means.

[0051] Furthermore, the method also includes: performing risk analysis on the structured data and / or the analysis results, generating risk warning information, and visually displaying the risk warning information.

[0052] It should be noted that the system supports various chart types, including bar charts, line charts, heatmaps, map distribution maps, and interactive dashboards. The appropriate chart type can be selected based on user needs and data characteristics. For example: Electricity Price Trend Chart: A line chart shows the trend of electricity prices over time, helping users intuitively understand price fluctuations. Power Generation and Sales Comparison Chart: A bar chart compares power generation and sales in different countries or regions, facilitating quick comparison and analysis. Heatmap: Displays the density distribution of power generation and sales in different regions or time periods, helping users identify high-density areas or time periods. Map Distribution Map: Visually displays the geographical location and power generation of each power plant on a map, allowing users to understand geographical distribution. Interactive Dashboard: Comprehensively displays key indicators such as electricity prices, power generation, sales, and contract revenue. Users can use interactive functions to gain a deeper understanding of the detailed information for each indicator.

[0053] In one embodiment, the method further includes: analyzing the predicted data based on a number of preset key risk indicators to obtain and display risk warning information.

[0054] It should be noted that the system pre-sets several key risk indicators, such as P10 / P90 revenue forecasts, hedging ratios, and the impact of regulatory policies. These indicators reflect the main risk points in the electricity market, helping users comprehensively assess potential risks. Based on these key risk indicators, the system analyzes forecast data using predictive models (such as linear regression, multinomial regression, support vector machine (SVM), and time series analysis (ARIMA). When a risk indicator exceeds a preset threshold, the system automatically generates a risk warning and displays it through a visual interface. For example, if the predicted annual revenue of a contract's P10 is lower than the preset minimum acceptable value, the system will issue a warning, reminding the user that the contract carries a high risk of loss. Warning information can be displayed intuitively through color changes, flashing, and pop-ups, ensuring users notice potential risks promptly. In addition to providing risk warnings, the system also offers risk response suggestions. Depending on the type and severity of the risk, the system can recommend corresponding risk mitigation measures, such as adjusting hedging strategies, optimizing contract terms, and reassessing market strategies, helping users take timely and effective measures to reduce risk.

[0055] Specifically, the system incorporates several key risk indicators (KRIs), such as P10 / P90 revenue forecasts, hedging ratios, and the impact of regulatory policies. Based on a scheduled task mechanism, the system automatically updates the analysis results daily and displays early warning information through a visual dashboard. Users can quickly locate risk changes through interactive charts, improving the real-time nature and efficiency of risk response.

[0056] P10 and P90 are commonly used probability forecasting indicators: P90: indicates that at a 90% confidence level, actual income will not be lower than this value, often used for conservative estimation. P10: indicates that at a 10% confidence level, actual income will not be higher than this value, often used for risk warning or maximum loss estimation.

[0057] For example, if a contract's P90 predicts annual revenue of 8 million euros and P10 predicts 12 million euros, it means that in most cases, the company's revenue will be higher than 8 million euros; however, there is also a 10% chance that the revenue may be higher than 12 million euros. This indicator is often used to quantify the risk-return range under market volatility and is closely related to contract pricing and hedging strategies.

[0058] In one embodiment, the electricity market data further includes contract data; step S2 further includes: identifying the contract data and standardizing the identified data to obtain structured contract data.

[0059] It should be noted that key information in contract documents, such as contract number, contract start and end dates, electricity price type, output delivery type, related contracting parties, and subsidy prices, is automatically identified using Optical Character Recognition (OCR) or Natural Language Processing (NLP) technologies. The identified contract data undergoes standardization to ensure a consistent data format. For example, the electricity price unit is standardized to Euros per kilowatt-hour. This standardized contract data is stored in the system's database, providing a high-quality data foundation for subsequent analysis and applications.

[0060] In one embodiment, the platform features automated contract management, allowing users to input core contract elements via the front end, such as contract number, contract start and end dates, electricity price type, output delivery type, associated contract parties, and subsidy prices. The system backend identifies and standardizes this input contract data, transforming it into structured contract data, which is then uniformly stored in a database. Each contract is distinguished in the database by its contract number and version number. The backend generates daily business logic calculation rules matching the current time, such as contract revenue equaling contract unit price multiplied by output. The backend scheduler runs daily, querying which contracts, effective dates, and projects are "active" on the current system date (e.g., 2025-05-15). These active objects are bound to business calculation rule templates, generating SQL statements or business logic code in real time, executing and storing the daily calculation results for visualization or decision analysis, ensuring the timeliness and traceability of data in business analysis and revenue calculation.

[0061] In one embodiment, the method further includes: substituting the structured contract data that meets preset query conditions into preset standardized business calculation rules to obtain standardized business calculation results and display them.

[0062] It should be noted that contract data meeting preset query conditions from structured contract data is substituted into preset standardized business calculation rules for business calculations. For example, key business indicators such as contract revenue (contract unit price × output) and subsidy revenue (subsidy price × output) are calculated. These calculation rules can be customized and adjusted according to the specific business needs of the enterprise. The calculation results are displayed through a visual interface, and users can view detailed calculation results for different contracts through interactive functions. For example, users can choose to view information such as revenue forecasts, subsidy revenue, and cost analysis for specific contracts. The system also provides a comprehensive reporting function, summarizing and displaying the calculation results of multiple contracts to help users fully understand the overall situation of contract business.

[0063] In one embodiment, the electricity market data includes hydrogen data and natural gas data; step S1 includes: standardizing the hydrogen data and the natural gas data to obtain structured hydrogen data and structured natural gas data respectively.

[0064] It should be noted that the acquired hydrogen data includes hydrogen prices, production volume, sales volume, and transportation costs. The system standardizes this data, including unit unification (e.g., converting hydrogen prices from different countries to Euros / kg), timestamp unification (converting to Coordinated Universal Time, UTC), and missing data completion (using interpolation algorithms or estimation methods based on historical data), ultimately yielding structured hydrogen data. The acquired natural gas data includes natural gas prices, production volume, sales volume, and transportation costs. The system standardizes this data as well, including unit unification (e.g., converting natural gas prices from different countries to Euros / MMBtu), timestamp unification (converting to Coordinated Universal Time, UTC), and missing data completion (using interpolation algorithms or estimation methods based on historical data), ultimately yielding structured natural gas data. The above prediction and early warning processes are equally applicable to hydrogen and natural gas.

[0065] like Figure 2 As shown, this application also provides a system for real-time monitoring of electricity marketing, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0066] This system enables real-time monitoring of electricity marketing through automated data acquisition and cleaning processes, as well as data analysis and visualization using business intelligence (BI) tools. The system acquires raw data from various data sources (such as Excel spreadsheets and databases), which may include marketing data, customer data, and market data from the power company. Then, using Robotic Process Automation (RPA) technology, it automatically extracts data from these data sources. The RPA robot can simulate human user operations, automatically logging into the system, extracting data, and filling out forms, thereby reducing errors and time consumption from manual operations. The extracted data is transmitted to a database for storage and management. The database, as the core of data storage, can efficiently manage and retrieve large amounts of data. Before data is stored in the database, the system cleans the data, including removing duplicates, correcting errors, and filling in missing values, to ensure data accuracy and consistency. This step is crucial for subsequent data analysis.

[0067] The system analyzes cleaned data using business intelligence (BI) tools, generating various charts, reports, and dashboards to help users understand and utilize the data. Users can remotely access the dashboards generated by the BI tools to view electricity marketing data in real time. These dashboards can display key indicators, trend analysis, customer behavior analysis, and more, helping users make data-driven decisions. Users access the dashboards generated by the BI tools via computer to obtain real-time electricity marketing data and analysis results. Users can select different views and reports according to their needs for in-depth data analysis and exploration. In this way, the system not only improves the speed and quality of data processing but also reduces errors and costs associated with manual operations, thereby improving the efficiency and accuracy of decision-making.

[0068] It is understood that the above embodiments only illustrate preferred embodiments of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that for those skilled in the art, free combinations of the above technical features and various modifications and improvements can be made without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, all equivalent transformations and modifications made with respect to the scope of the claims of the present invention should fall within the scope of the claims of the present invention.

Claims

1. A method for real-time monitoring of electricity marketing, characterized in that, Includes the following steps: Step S1: Obtain electricity market data from data sources in different countries according to a preset time interval, and perform standardization processing on the electricity market data to obtain structured data; Step S2: Perform statistical analysis on the structured data to obtain the analysis results; Step S3: Visualize the analysis results.

2. The method for real-time monitoring of electricity marketing as described in claim 1, characterized in that, In step S1, the electricity market data includes electricity price data; The standardization process of the electricity market data to obtain structured data includes: The electricity price data is processed by currency unification, time zone conversion, and missing information completion to obtain the structured data.

3. The method for real-time monitoring of electricity marketing according to claim 2, characterized in that, Step S2 includes: The structured data is categorized and summarized to obtain comparative data on electricity prices in different countries during the same time period.

4. The method for real-time monitoring of electricity marketing according to claim 1, characterized in that, The method further includes: Acquire electricity news data from different countries or regions, extract keywords from the electricity news data, and display the processed news data in a simplified form.

5. The method for real-time monitoring of electricity marketing according to claim 1, characterized in that, Step S3 includes: Based on the analysis results, corresponding data charts are generated, and the data charts are visualized in an interactive manner. The data chart types include at least one of the following: bar chart, line chart, heat map, map distribution map, and interactive dashboard.

6. The method for real-time monitoring of electricity marketing according to claim 1, characterized in that, The method further includes: Risk analysis is performed on the structured data and / or the analysis results, and risk warning information is generated and visualized.

7. The method for real-time monitoring of electricity marketing according to claim 6, characterized in that, The risk analysis of the structured data and / or the analysis results includes: Based on preset risk indicators, the structured data and / or the analysis results are assessed for risk level, and corresponding risk warning information is generated.

8. The method for real-time monitoring of electricity marketing according to claim 1, characterized in that, The electricity market data also includes contract data; step S2 further includes: The contract data is identified, and the identified data is standardized to obtain structured contract data.

9. The method for real-time monitoring of electricity marketing according to claim 8, characterized in that, The method further includes: The structured contract data that meets the preset query conditions is substituted into the preset standardized business calculation rules to obtain the standardized business calculation results and display them.

10. A system for real-time monitoring of electricity marketing, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-9.

Images