Electricity price prediction processing management method and system based on electricity price big data

Through the electricity price prediction and management system based on electricity price big data, the combination of reference modules, optimization modules and electricity price prediction modules is used to solve the problem that traditional electricity price prediction methods ignore complex factors, and the accuracy and real-time improvement of electricity price prediction is achieved. The complexity of the electricity market is required.

CN119027196AInactive Publication Date: 2024-11-26XINJIANG BRANCH OF NATIONAL ENERGY GROUP GUOYUAN ELECTRIC POWER CO LTD +1
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411121565.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing electricity price prediction method is based on traditional statistical models or economic models, and ignores complex factors such as nonlinear relationships, seasonal changes, weather factors, renewable energy supply fluctuations and policy adjustments in the power market, resulting in the accuracy of the prediction results. and real-time is difficult to meet actual needs.

Method used

Adopt the electricity price prediction and management system based on electricity price big data, including reference modules, optimization modules and electricity price prediction modules. Through the analysis, feature extraction, classification, model establishment and real-time monitoring of the electricity price prediction system, accurate prediction and dynamics of electricity price are achieved. Adjustment.

Benefits of technology

It improves the accuracy and real-time nature of electricity price prediction, overcomes possible abnormal causes in the target area, realizes timely monitoring and optimization adjustment of electricity price changes, and meets the complexity and uncertainty needs of the power market.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119027196A_ABST
    Figure CN119027196A_ABST
Patent Text Reader

Abstract

The invention discloses an electricity price prediction processing management method and system based on electricity price big data, and belongs to the technical field of electricity price prediction, and the method comprises the steps: analyzing each material target, and determining an electricity price prediction analysis chart corresponding to each material target; obtaining target electricity price analysis data corresponding to the target area; performing feature extraction on the target electricity price analysis data to obtain a target analysis range; determining a reference target based on the target analysis range and the electricity price prediction analysis chart; cutting the electricity price prediction analysis chart to obtain a contrast analysis chart; determining abnormal parameters based on the contrast analysis chart; determining an initial optimization mode according to each abnormal parameter; verifying and adjusting the initial optimization mode to obtain a target optimization mode, and establishing an electricity price prediction model based on the target optimization mode and a reference target; analyzing the electricity price analysis data corresponding to the target area through an electricity price prediction model to obtain a predicted electricity price; and displaying the predicted electricity price in real time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of electricity price prediction, and specifically relates to an electricity price prediction processing management method and system based on electricity price big data. Background Art

[0002] With the rapid development of society and the growing demand for energy, the importance of the power market has become increasingly prominent. In the power market, electricity prices are the core element of transactions between supply and demand, and their volatility and uncertainty have brought huge challenges to market participants. Accurate electricity price forecasts are of great significance for market parties such as power producers, suppliers, large users and regulatory agencies to formulate effective market strategies, optimize resource allocation and reduce operating risks.

[0003] However, most of the existing electricity price forecasting methods are based on traditional statistical models or economic models. These methods usually assume that the electricity market is stable and ignore the impact of various complex factors such as nonlinear relationships, seasonal changes, weather factors, fluctuations in renewable energy supply, policy adjustments, and economic fluctuations in the market. Therefore, when faced with the complexity and uncertainty of the electricity market, the accuracy and real-time nature of the forecast results of these traditional methods often cannot meet actual needs.

[0004] Based on this, in order to solve the problem of electricity price prediction, the present invention provides an electricity price prediction processing management method and system based on electricity price big data. Summary of the invention

[0005] In order to solve the problems existing in the above-mentioned solutions, the present invention provides an electricity price prediction, processing and management method and system based on electricity price big data.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An electricity price forecasting and processing management system based on electricity price big data, including a reference module, an optimization module and an electricity price forecasting module;

[0008] The reference module is used to analyze each material target and determine the electricity price forecast analysis chart corresponding to each material target; the material target is an existing electricity price forecast system;

[0009] Determine the target area, collect data on the target area according to the various influencing factors of electricity price forecast, and obtain the target electricity price analysis data corresponding to the target area; extract features from the target electricity price analysis data to obtain the target analysis range;

[0010] Mark the target analysis range in each electricity price forecast analysis diagram, identify each unit class corresponding to the target analysis range, and mark each corresponding unit class as a control class; identify the historical unit value corresponding to the control class;

[0011] According to the formula Calculate the material value of each material target;

[0012] Where: PU is the material value; j represents the corresponding control class in the electricity price forecast analysis diagram, j = 1, 2, ..., m, m is a positive integer; DYj is the historical unit value of the corresponding control class; λj is the weight coefficient of the corresponding control class;

[0013] Select the material target with the highest material value as the reference target.

[0014] Furthermore, the method for setting the electricity price forecast analysis chart of the material target includes:

[0015] Obtain historical electricity price forecast data for each material target, which includes electricity price analysis data and historical forecast results;

[0016] Extracting features from the historical electricity price forecast data according to various influencing factors of electricity price forecast to obtain various influencing analysis feature data;

[0017] Classify the historical electricity price forecast data according to each impact analysis feature data to obtain a number of unit class data; integrate each impact analysis feature data corresponding to the unit class into a unit range;

[0018] Mark each historical electricity price forecast data within the unit class as historical unit data; calculate the historical unit value corresponding to each unit class;

[0019] An electricity price forecast analysis chart for the material target is generated according to the unit range and historical unit values ​​corresponding to each unit class.

[0020] Furthermore, the method for classifying the historical electricity price forecast data according to each impact analysis feature data includes:

[0021] A unit class judgment model is established, and the expression of the unit class judgment model is:

[0022]

[0023] Where: s is the input data, which is the two impact analysis feature data for the same impact analysis; the output data is the unit class judgment value DP(s);

[0024] The impact analysis feature data corresponding to the historical electricity price forecast data are analyzed through the unit class judgment model to determine the unit class judgment value between each impact analysis feature data; the historical electricity price forecast data are classified according to the obtained unit class judgment value to obtain each unit class.

[0025] Furthermore, the method for calculating the historical unit value of each unit class includes:

[0026] A prediction and judgment model is established. The expression of the prediction and judgment model is:

[0027]

[0028] Where: q is the input data, the input data is the historical unit data, and the output data is the predicted judgment value SP(q);

[0029] Analyze each historical unit data in the unit class through the prediction judgment model to obtain the prediction judgment value corresponding to each historical unit data;

[0030] Each prediction judgment value corresponding to the unit class is marked as SP(q)i, i represents the corresponding historical unit data, i=1, 2, ..., n, n is a positive integer;

[0031] According to the formula Calculate the historical unit values ​​for each unit class;

[0032] Where: DY is the historical unit value.

[0033] The optimization module is used to optimize the reference target, obtain the electricity price forecast analysis chart corresponding to the reference target, cut the electricity price forecast analysis chart according to each control class, and obtain the control analysis chart; identify the historical unit value corresponding to each control class in the control analysis chart; mark the control class whose historical unit value is lower than the threshold value X1 as an abnormal class; determine the abnormal parameter according to the unit range corresponding to the abnormal class;

[0034] Determine the initial optimization method according to each abnormal parameter; set the electricity price simulation data; verify and adjust the initial optimization method through the electricity price simulation data to obtain the target optimization method, and establish the electricity price prediction model based on the target optimization method and the reference target.

[0035] Furthermore, the method for verifying and adjusting the initial optimization method through electricity price simulation data includes:

[0036] Step SA1: forecasting electricity prices for electricity price simulation data by initial optimization to obtain corresponding forecasted electricity prices, comparing each forecasted electricity price with the corresponding actual electricity price, and calculating the corresponding forecast accuracy;

[0037] Step SA2: When the prediction accuracy is greater than the threshold X2, the initial optimization method is marked as the target optimization method;

[0038] When the prediction accuracy is not greater than the threshold value X2, the initial optimization method is adjusted to obtain a new initial optimization method;

[0039] Step SA3: loop step SA1 to step SA2 until the target optimization method is determined.

[0040] The electricity price prediction module is used to predict electricity prices, obtain electricity price analysis data of the target area in real time, analyze the electricity price analysis data through the electricity price prediction model, and obtain the corresponding predicted electricity price; and display the obtained predicted electricity price in real time.

[0041] Furthermore, after obtaining the predicted electricity price, the actual electricity price corresponding to the predicted electricity price is collected, and the control class corresponding to the predicted electricity price is identified; the prediction accuracy of each control class is calculated in real time according to the predicted electricity price and the actual electricity price, and a prediction accuracy curve is generated, and prediction monitoring is performed based on the prediction accuracy curve of each control class.

[0042] Furthermore, the method for performing prediction monitoring based on the prediction accuracy curve includes:

[0043] Identify in real time the curve slope and the corresponding prediction accuracy rate corresponding to the current time in the prediction accuracy curve; integrate the obtained curve slope and prediction accuracy rate into monitoring and analysis data;

[0044] A monitoring judgment model is established. The expression of the monitoring judgment model is:

[0045]

[0046] Where: p is the input data, the input data is the monitoring analysis data, and the output data is the monitoring judgment value HK(p);

[0047] Predictive monitoring is performed based on the obtained monitoring judgment values.

[0048] The electricity price forecasting processing and management method based on electricity price big data includes:

[0049] Analyze each material target and determine the electricity price forecast analysis chart corresponding to each material target;

[0050] Obtain target electricity price analysis data corresponding to the target area; perform feature extraction on the target electricity price analysis data to obtain the target analysis range;

[0051] Determine the reference target based on the target analysis scope and the electricity price forecast analysis chart;

[0052] The electricity price forecast analysis chart is cropped to obtain a control analysis chart; abnormal parameters are determined based on the control analysis chart;

[0053] Determine the initial optimization method based on each abnormal parameter; verify and adjust the initial optimization method to obtain the target optimization method.

[0054] Establish an electricity price prediction model based on the target optimization method and reference target;

[0055] The electricity price analysis data corresponding to the target area is analyzed through the electricity price prediction model to obtain the predicted electricity price; the predicted electricity price is displayed in real time.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] Through the mutual cooperation among the reference module, optimization module and electricity price forecasting module, accurate prediction of electricity prices can be achieved; in particular, full use is made of various existing electricity price forecasting systems to set the electricity price forecasting method that best suits the target area, overcome possible abnormal reasons in the target area, and improve the accuracy of electricity price forecasting; and dynamic monitoring is carried out based on each control class to understand the changes in electricity price forecasts in real time, and make timely adjustments with users, which also facilitates block-based optimization and adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0060] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] like Figure 1 As shown, the electricity price forecasting processing and management system based on electricity price big data includes a reference module, an optimization module and an electricity price forecasting module;

[0062] The reference module is used to analyze the existing electricity price forecasting systems, determine the electricity price forecasting systems that have reference or reference functions, mark the existing electricity price forecasting systems as material targets, and mark the determined reference electricity price forecasting systems as reference targets. The specific process is as follows:

[0063] Identify each material target, and obtain historical electricity price forecast data for each material target, including previous electricity price related data and corresponding historical forecast results, the historical forecast results include predicted electricity prices and actual electricity prices; previous electricity price related data are the relevant data required for electricity price forecasting, such as historical electricity price data, weather data, market load data and other related factor data that may affect electricity price fluctuations. For the sake of ease of description, previous electricity price related data are marked as electricity price analysis data, because they are historical electricity price forecast data, they are therefore marked as historical electricity price forecast data; preset various influencing factors that have an impact on electricity price forecasting, perform feature extraction on historical electricity price forecast data according to various influencing factors, and obtain impact analysis feature data, which are specific data of various influencing factors.

[0064] The historical electricity price forecast data are classified according to each impact analysis feature data to obtain a number of unit class data. The unit class is defined as the impact analysis feature data within the classification can be considered to have the same impact on the electricity price forecast; a unit class judgment model is established based on a large amount of historical electricity price data to judge whether the corresponding impact analysis feature data have the same impact on the electricity price forecast. Based on a large amount of historical electricity price data, it is possible to statistically analyze which impact analysis feature data have the same impact on the electricity price forecast; the expression of the unit class judgment model is: Wherein: s is the input data, and the input data is two impact analysis feature data for the same impact analysis; the output data is the unit class judgment value DP(s); the impact analysis feature data corresponding to the historical electricity price forecast data are analyzed by the unit class judgment model to determine the unit class judgment value between each impact analysis feature data; the historical electricity price forecast data are classified according to the obtained unit class judgment value to obtain each unit class.

[0065] Each historical electricity price forecast data in the unit class is marked as historical unit data; a forecast judgment model is established. The forecast judgment model is used to judge whether the forecast meets the forecast requirements based on the historical forecast results corresponding to the historical unit data. The forecast requirements are set according to user needs, such as allowing forecast deviation, that is, whether the forecast electricity price is accurate, which is not the forecast standard defined by the original electricity price forecast system; the expression of the forecast judgment model is Where: q is the input data, the input data is the historical unit data, and the output data is the predicted judgment value SP(q);

[0066] Analyze each historical unit data in the unit class through the prediction judgment model to obtain the prediction judgment value corresponding to each historical unit data; mark each prediction judgment value corresponding to the unit class as SP(q)i, i represents the corresponding historical unit data, i=1, 2, ..., n, n is a positive integer;

[0067] According to the formula Calculate the historical unit value of each unit type; where: DY is the historical unit value;

[0068] Integrate the impact analysis feature data corresponding to the unit class into a unit range, that is, the electricity price analysis data range corresponding to the unit class;

[0069] The electricity price forecast analysis chart of the material target is generated according to the unit range and historical unit values ​​corresponding to each unit class; the electricity price forecast analysis chart uses each influencing analysis characteristic data as the independent variable and the historical unit value as the covariate. Specifically, each influencing factor is set as the independent variable coordinate axis according to the size of the influence. As the influencing factors change, the area range corresponding to each unit class is determined, marked as the unit area, and the historical unit value corresponding to the unit area is set.

[0070] Mark the area where the user needs to conduct electricity price forecast as the target area, collect data for the target area according to various influencing factors, determine the electricity price analysis data that the target area may have, and mark it as the target electricity price analysis data; extract features from the target electricity price analysis data according to various influencing factors, obtain the characteristic data of each target impact analysis, and integrate them into the target analysis range;

[0071] Mark the target analysis range in each electricity price forecast analysis diagram, identify each unit class corresponding to the target analysis range, and mark each corresponding unit class as a control class; identify the historical unit value corresponding to the control class;

[0072] According to the formula Calculate the material value of each material target;

[0073] Where: PU is the material value; j represents the corresponding control class in the electricity price forecast analysis diagram, j = 1, 2, ..., m, m is a positive integer; DYj is the historical unit value of the corresponding control class; λj is the weight coefficient of the corresponding control class, and the weight coefficient is set according to the probability of occurrence of the target electricity price analysis data corresponding to the control class in the target area;

[0074] Select the material target with the highest material value as the reference target.

[0075] The optimization module is used to optimize the reference target, obtain the electricity price forecast analysis diagram corresponding to the reference target, and cut the electricity price forecast analysis diagram according to each control class to obtain the control analysis diagram; identify the historical unit value corresponding to each control class in the control analysis diagram; mark the control class whose historical unit value is lower than the threshold value X1 as an abnormal class, that is, the overall accuracy of the electricity price forecast does not meet the requirements; determine the abnormal parameters according to the unit range corresponding to the abnormal class, and the abnormal parameters are the impact analysis feature data under which the electricity price forecast will be unqualified;

[0076] Determine the initial optimization method according to each abnormal parameter, that is, determine how to overcome the abnormal electricity price forecast corresponding to the abnormal parameter by manual means, and form an optimization method, which is marked as the initial optimization method;

[0077] Based on the historical electricity price data of the control class corresponding to the abnormal parameters, corresponding electricity price simulation data is set, namely, including electricity price analysis data and real electricity price data, for simulation verification; the initial optimization method is verified and adjusted through the electricity price simulation data to obtain the target optimization method, and an electricity price prediction model is established based on the target optimization method and the reference target; the electricity price prediction model is used to predict the corresponding electricity price based on the electricity price analysis data.

[0078] Methods for verifying and adjusting the initial optimization method through electricity price simulation data include:

[0079] Step SA1: forecasting electricity prices for electricity price simulation data by initial optimization to obtain corresponding forecasted electricity prices, comparing each forecasted electricity price with the corresponding actual electricity price, and calculating the corresponding forecast accuracy;

[0080] Step SA2: When the prediction accuracy is greater than the threshold X2, the initial optimization method is marked as the target optimization method;

[0081] When the prediction accuracy is not greater than the threshold value X2, the initial optimization method is adjusted to obtain a new initial optimization method;

[0082] Step SA3: loop step SA1 to step SA2 until the target optimization method is determined.

[0083] The electricity price prediction module is used to predict electricity prices, obtain electricity price analysis data of the target area in real time, analyze the electricity price analysis data through the electricity price prediction model, and obtain the corresponding predicted electricity price; and display the obtained predicted electricity price in real time.

[0084] In one embodiment, after obtaining the predicted electricity price, the actual electricity price corresponding to the predicted electricity price is collected, and the control class corresponding to the predicted electricity price is identified; the prediction accuracy of each control class is calculated in real time based on the predicted electricity price and the actual electricity price, and a prediction accuracy curve is generated, with the horizontal axis being time and the vertical axis being the warning accuracy; prediction monitoring is performed based on the prediction accuracy curve of each control class.

[0085] Methods for predictive monitoring based on prediction accuracy curves include:

[0086] Identify in real time the curve slope and the corresponding prediction accuracy rate corresponding to the current time in the prediction accuracy curve; integrate the obtained curve slope and prediction accuracy rate into monitoring and analysis data;

[0087] A monitoring judgment model is established. The monitoring judgment model is used to analyze the monitoring analysis data. The slope of the curve and the prediction accuracy in the monitoring analysis data are determined to see whether they exceed the corresponding preset values. That is, a slope decline warning value and an accuracy warning value are preset. If any of them does not meet the standard, the monitoring is considered unqualified. The expression of the monitoring judgment model is: Where: p is the input data, the input data is the monitoring analysis data, and the output data is the monitoring judgment value HK(p);

[0088] Predictive monitoring is performed based on the obtained monitoring judgment values.

[0089] The electricity price forecasting processing and management method based on electricity price big data includes:

[0090] Analyze each material target and determine the electricity price forecast analysis chart corresponding to each material target;

[0091] Obtain target electricity price analysis data corresponding to the target area; perform feature extraction on the target electricity price analysis data to obtain the target analysis range;

[0092] Determine the reference target based on the target analysis scope and the electricity price forecast analysis chart;

[0093] The electricity price forecast analysis chart is cropped to obtain a control analysis chart; abnormal parameters are determined based on the control analysis chart;

[0094] Determine the initial optimization method based on each abnormal parameter; verify and adjust the initial optimization method to obtain the target optimization method.

[0095] Establish an electricity price prediction model based on the target optimization method and reference target;

[0096] The electricity price analysis data corresponding to the target area is analyzed through the electricity price prediction model to obtain the predicted electricity price; the predicted electricity price is displayed in real time.

[0097] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0098] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. The electricity price forecasting and processing management system based on electricity price big data is characterized by: Including reference module, optimization module and electricity price prediction module; The reference module is used to analyze each material target and determine the electricity price forecast analysis chart corresponding to each material target; the material target is an existing electricity price forecast system; Determine the target area, collect data on the target area based on various influencing factors of electricity price forecast, and obtain target electricity price analysis data corresponding to the target area; Extract features from the target electricity price analysis data to obtain the target analysis range; mark the target analysis range in each electricity price forecast analysis diagram, identify each unit class corresponding to the target analysis range, and mark each corresponding unit class as a control class; identify the historical unit value corresponding to the control class; According to the formula Calculate the material value of each material target; Where: PU is the material value; j represents the corresponding control class in the electricity price forecast analysis diagram, j = 1, 2, ..., m, m is a positive integer; DYj is the historical unit value of the corresponding control class; λj is the weight coefficient of the corresponding control class; Select the material target with the highest material value as the reference target; The optimization module is used to optimize the reference target, obtain the electricity price forecast analysis chart corresponding to the reference target, cut the electricity price forecast analysis chart according to each control class, and obtain the control analysis chart; identify the historical unit value corresponding to each control class in the control analysis chart; mark the control class whose historical unit value is lower than the threshold value X1 as an abnormal class; determine the abnormal parameter according to the unit range corresponding to the abnormal class; Determine the initial optimization method according to each abnormal parameter; set the electricity price simulation data; verify and adjust the initial optimization method through the electricity price simulation data, obtain the target optimization method, and establish the electricity price prediction model based on the target optimization method and the reference target; The electricity price prediction module is used to predict electricity prices, obtain electricity price analysis data of the target area in real time, analyze the electricity price analysis data through the electricity price prediction model, and obtain the corresponding predicted electricity price; and display the obtained predicted electricity price in real time.

2. The electricity price forecasting and processing management system based on electricity price big data according to claim 1 is characterized in that: The method of setting the electricity price forecast analysis chart of the material target includes: Obtain historical electricity price forecast data for each material target, which includes electricity price analysis data and historical forecast results; Extracting features from the historical electricity price forecast data according to various influencing factors of electricity price forecast to obtain various influencing analysis feature data; Classify the historical electricity price forecast data according to each impact analysis feature data to obtain a number of unit class data; integrate each impact analysis feature data corresponding to the unit class into a unit range; Mark each historical electricity price forecast data within the unit class as historical unit data; calculate the historical unit value corresponding to each unit class; An electricity price forecast analysis chart for the material target is generated according to the unit range and historical unit values ​​corresponding to each unit class.

3. The electricity price forecasting and processing management system based on electricity price big data according to claim 2 is characterized in that: Methods for classifying historical electricity price forecast data according to various impact analysis feature data include: A unit class judgment model is established, and the expression of the unit class judgment model is: Where: s is the input data, which is the two impact analysis feature data for the same impact analysis; the output data is the unit class judgment value DP(s); The impact analysis feature data corresponding to the historical electricity price forecast data are analyzed through the unit class judgment model to determine the unit class judgment value between each impact analysis feature data; the historical electricity price forecast data are classified according to the obtained unit class judgment value to obtain each unit class.

4. The electricity price forecasting and processing management system based on electricity price big data according to claim 2, characterized in that: Methods for calculating historical unit values ​​for each unit class include: A prediction and judgment model is established. The expression of the prediction and judgment model is: Where: q is the input data, the input data is the historical unit data, and the output data is the predicted judgment value SP(q); Analyze each historical unit data in the unit class through the prediction judgment model to obtain the prediction judgment value corresponding to each historical unit data; Each prediction judgment value corresponding to the unit class is marked as SP(q)i, i represents the corresponding historical unit data, i=1, 2, ..., n, n is a positive integer; According to the formula Calculate the historical unit values ​​for each unit class; Where: DY is the historical unit value.

5. The electricity price forecasting and processing management system based on electricity price big data according to claim 1, characterized in that: Methods for verifying and adjusting the initial optimization method through electricity price simulation data include: Step SA1: forecasting electricity prices for electricity price simulation data by initial optimization to obtain corresponding forecasted electricity prices, comparing each forecasted electricity price with the corresponding actual electricity price, and calculating the corresponding forecast accuracy; Step SA2: When the prediction accuracy is greater than the threshold X2, the initial optimization method is marked as the target optimization method; When the prediction accuracy is not greater than the threshold value X2, the initial optimization method is adjusted to obtain a new initial optimization method; Step SA3: loop step SA1 to step SA2 until the target optimization method is determined.

6. The electricity price forecasting and processing management system based on electricity price big data according to claim 1, characterized in that: After obtaining the predicted electricity price through the electricity price prediction model, the actual electricity price corresponding to the predicted electricity price is collected, and the control class corresponding to the predicted electricity price is identified; the prediction accuracy of each control class is calculated in real time according to the predicted electricity price and the actual electricity price, and a prediction accuracy curve is generated, and prediction monitoring is performed based on the prediction accuracy curve of each control class.

7. The electricity price forecasting and processing management system based on electricity price big data according to claim 6, characterized in that: Methods for predictive monitoring based on prediction accuracy curves include: Identify in real time the curve slope and the corresponding prediction accuracy rate corresponding to the current time in the prediction accuracy curve; integrate the obtained curve slope and prediction accuracy rate into monitoring and analysis data; A monitoring judgment model is established. The expression of the monitoring judgment model is: Where: p is the input data, the input data is the monitoring analysis data, and the output data is the monitoring judgment value HK(p); Predictive monitoring is performed based on the obtained monitoring judgment values.

8. A method for electricity price forecasting, processing and management based on electricity price big data, characterized in that: Applied to the electricity price forecasting processing and management system based on electricity price big data as described in any one of claims 1 to 7, the method comprises: Analyze each material target and determine the electricity price forecast analysis chart corresponding to each material target; Obtain target electricity price analysis data corresponding to the target area; perform feature extraction on the target electricity price analysis data to obtain the target analysis range; Determine the reference target based on the target analysis scope and the electricity price forecast analysis chart; The electricity price forecast analysis chart is cropped to obtain a control analysis chart; abnormal parameters are determined based on the control analysis chart; Determine the initial optimization method based on each abnormal parameter; verify and adjust the initial optimization method to obtain the target optimization method. Establish an electricity price prediction model based on the target optimization method and reference target; The electricity price analysis data corresponding to the target area is analyzed through the electricity price prediction model to obtain the predicted electricity price; the predicted electricity price is displayed in real time.

Citation Information

Patent Citations

  • Electric power spot market price information prediction optimization method and system

    CN116485443A

  • Supplier capacity early warning system and method thereof

    CN117078205A

  • Power market price risk evolution analysis method based on optimization algorithm

    CN117541284A

  • Micro-module power environment monitoring system

    CN118070193A

  • Electrical fault position confirmation method based on big data

    CN118150933A