Day-ahead clearing electricity price data processing method, device, storage medium and program product

By obtaining and processing spot boundary conditions and load data before the operation date, determining the thermal power load rate and inputting the pre-trained model, the problem of low prediction accuracy of electricity price clearance in the existing technology has been solved, and higher prediction accuracy has been achieved .

CN118710321BActive Publication Date: 2024-12-03CHINA THREE GORGES RENEWABLES (GRP) CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411186638.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-12-03
Estimated Expiration
2044-08-28

AI Technical Summary

Technical Problem

The current method of clearing electricity price prediction recently requires a large amount of historical data training, resulting in low prediction accuracy and historical data within a week or even further cannot accurately reflect the supply and demand relationship.

Method used

By obtaining the spot boundary conditions before the operation date, extracting the entire network predicted load, determining the previous prediction of the entire network and thermal power load rate, and inputting the pre-trained pre-clearing electricity price prediction model to obtain the previous pre-clearing electricity price data.

Benefits of technology

While avoiding training large batches of data, it improves the prediction accuracy of electricity price data recently issued.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118710321B_ABST
    Figure CN118710321B_ABST
Patent Text Reader

Abstract

The embodiment of the present application provides a method, device, storage medium and program product for processing day-ahead clearing electricity price data. The method includes: obtaining spot boundary conditions within a preset time period before the operation day; extracting the corresponding network-wide forecast load within the preset time period from the spot boundary conditions; determining the day-ahead forecast network-wide load of the operation day according to the corresponding network-wide forecast load within the preset time period; determining the thermal power load rate of the operation day according to the day-ahead forecast network-wide load of the operation day and the spot boundary conditions one day before the operation day; inputting the thermal power load rate of the operation day into the pre-trained day-ahead clearing electricity price prediction model to obtain the day-ahead clearing electricity price data of the operation day. The method is used to achieve the effect of improving the prediction accuracy of the day-ahead clearing electricity price data while avoiding the computer from training large quantities of data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method, device, storage medium and program product for processing day-ahead clearing electricity price data. Background Art

[0002] The electricity spot market clearing price is calculated based on supply and demand quotations and system network constraints to obtain the transaction price of electricity at each time and at a certain node. The spot real-time market price has great uncertainty, and the accuracy of the day-ahead clearing price is a key factor in the medium- and long-term daily rolling time-sharing transactions and day-ahead spot transaction declaration strategies of power generation companies.

[0003] The existing method for predicting the day-ahead clearing price is to use a computer to learn a large amount of selected or processed historical data using a big data processing algorithm such as a neural network, and to establish a prediction model to predict the day-ahead clearing electricity price.

[0004] However, big data processing algorithms require a large number of training samples, and historical data from a week or even further back cannot accurately reflect the supply and demand relationship of the day before. As a result, computers need to undergo a large amount of data training and the prediction accuracy is low. Summary of the invention

[0005] The embodiments of the present application provide a method, device, storage medium and program product for processing day-ahead clearing electricity price data, so as to achieve the effect of improving the prediction accuracy of day-ahead clearing electricity price data while avoiding the computer from training large batches of data.

[0006] In a first aspect, an embodiment of the present application provides a method for processing day-ahead clearing electricity price data, comprising:

[0007] Get the spot boundary conditions within the preset time period before the operation date.

[0008] The corresponding network-wide forecast load within a preset time period is extracted from the spot boundary conditions.

[0009] According to the corresponding network-wide predicted load within the preset time period, the predicted network-wide load on the day before the operation day is determined.

[0010] The thermal power load rate on the operation day is determined based on the day-ahead forecast of the entire network load and the spot boundary conditions one day before the operation day.

[0011] The thermal power load rate on the operation day is input into the pre-trained day-ahead clearing electricity price prediction model to obtain the day-ahead clearing electricity price data on the operation day.

[0012] In one possible implementation, the predicted network load before the day of the operation day is determined according to the corresponding network-wide predicted load within a preset time period, including: obtaining the temperature coefficient and holiday coefficient of the operation day; obtaining the predicted network load one day before the operation day; if the sum of the temperature coefficient and the holiday coefficient is not less than 0, obtaining the maximum value of the corresponding network-wide predicted load within the preset time period; determining the predicted network load before the day of the operation day according to the sum of the temperature coefficient and the holiday coefficient, the predicted network load one day before the operation day, and the maximum value of the corresponding network-wide predicted load within the preset time period; if the sum of the temperature coefficient and the holiday coefficient is less than 0, obtaining the minimum value of the corresponding network-wide predicted load within the preset time period; determining the predicted network load before the day of the operation day according to the sum of the temperature coefficient and the holiday coefficient, the predicted network load one day before the operation day, and the minimum value of the corresponding network-wide predicted load within the preset time period.

[0013] In a possible implementation, the predicted network load on the day before the operation day is determined according to the sum of the temperature coefficient and the holiday coefficient, the predicted network load on the day before the operation day, and the maximum value of the corresponding predicted network load in a preset time period. The formula is:

[0014]

[0015] In the formula, C n Forecast the network load for the day before the operation day. C n-1 The forecast load of the entire network one day before the operation day, a is the temperature coefficient, b is the holiday coefficient, Max(C) is the maximum value of the predicted load of the entire network corresponding to the preset time period, a The value ranges from -1 to 1. b The value range is -1 to 1.

[0016] In a possible implementation, the predicted network load on the day before the operation day is determined according to the sum of the temperature coefficient and the holiday coefficient, the predicted network load on the day before the operation day, and the minimum value of the corresponding predicted network load in the preset time period. The formula is:

[0017]

[0018] In the formula, C n Forecast the network load for the day before the operation day. C n-1 The forecast load of the entire network one day before the operation day, a is the temperature coefficient, b is the holiday coefficient, Min(C) is the minimum value of the predicted load of the entire network corresponding to the preset time period,a The value ranges from -1 to 1. b The value range is -1 to 1.

[0019] In a possible implementation, the thermal power load rate on the operation day is determined according to the forecast of the entire grid load on the operation day and the spot boundary conditions one day before the operation day. The formula is:

[0020]

[0021] In the formula, R n is the thermal power load rate on the operating day, C n Forecast the network load for the day before the operation day. P n-1 is the inter-provincial liaison line plan data extracted from the spot boundary conditions one day before the operation day, E n-1 It is the predicted output data of new energy extracted from the spot boundary conditions one day before the operation day. A n-1 is the positive reserve capacity data extracted from the spot boundary conditions one day before the operation day, B n-1 In order to collect the latest installed capacity data of thermal power plants entering the market from the disclosed information, O n-1 It is the maintenance unit capacity data extracted from the spot boundary conditions one day before the operation day.

[0022] In a second aspect, an embodiment of the present application provides a device for processing day-ahead clearing electricity price data, comprising:

[0023] The spot boundary condition acquisition module is used to obtain the spot boundary conditions within a preset time period before the operation day.

[0024] The whole network forecast load extraction module is used to extract the whole network forecast load corresponding to the preset time period from the spot boundary conditions.

[0025] The module for determining the network load predicted by the day-ahead is used to determine the network load predicted by the day-ahead on the operation day according to the corresponding network load predicted within a preset time period.

[0026] The thermal power load rate determination module is used to determine the thermal power load rate on the operation day based on the day-ahead forecast of the entire network load and the spot boundary conditions one day before the operation day.

[0027] The day-ahead clearing electricity price determination module is used to input the thermal power load rate on the operation day into the pre-trained day-ahead clearing electricity price prediction model to obtain the day-ahead clearing electricity price data on the operation day.

[0028] In a third aspect, an embodiment of the present application provides a computer device, including: a memory, a processor;

[0029] Memory stores computer-executable instructions;

[0030] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0032] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0033] The day-ahead-clearing electricity price data processing method, device, storage medium and program product provided in the embodiments of the present application determine the day-ahead-predicted total network load on the operating day by using the total network forecast load corresponding to the spot boundary conditions in the preset time period before the operating day, determine the thermal power load rate on the operating day according to the day-ahead-predicted total network load on the operating day and the spot boundary conditions one day before the operating day, input the thermal power load rate on the operating day into the pre-trained day-ahead-clearing electricity price forecast model, and obtain the day-ahead-clearing electricity price data on the operating day, thereby achieving the effect of improving the forecast accuracy of the day-ahead-clearing electricity price data while avoiding the computer from training large quantities of data. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0035] Figure 1 A schematic diagram of a scenario for a method for processing day-ahead clearing electricity price data provided in this application;

[0036] Figure 2 Schematic diagram of the process of processing the day-ahead clearing electricity price data provided for this application Figure 1 ;

[0037] Figure 3 Schematic diagram of the process of processing the day-ahead clearing electricity price data provided for this application Figure 2 ;

[0038] Figure 4 A schematic diagram of the structure of the day-ahead clearing electricity price data processing device provided in this application;

[0039] Figure 5 A schematic diagram of the structure of the computer device provided for this application.

[0040] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0041] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0042] The clearing price of the electricity spot market is calculated based on algorithms such as supply and demand quotations and system network constraints to obtain the transaction price of electricity energy at each time and at a certain node (region or system). The spot real-time market has great uncertainty, and the accuracy of the day-ahead price forecast becomes a key factor affecting the medium- and long-term daily rolling time-sharing transactions and day-ahead spot transaction declaration strategies of power generation companies. Existing day-ahead price budgeting methods all use big data algorithms such as neural networks, integrated learning, multi-layer perceptrons, gated recurrent units, etc. to learn a large amount of selected or processed historical data, such as the province's load, new energy output, interconnection line plans, and clearing electricity prices, and establish a prediction model. However, the provincial load, interconnection line plans, generator installation scale, and new energy output are all changing over time. Historical data for a week or even further back cannot accurately reflect the day-ahead supply and demand relationship, and the larger the sample size, the more likely it is to overfit. With a small sample size, big data algorithms such as neural networks cannot dig out the potential relationship between the variables.

[0043] In order to solve the above technical problems, the embodiments of the present application propose the following technical ideas: Taking into account that historical data from a week ago or even further ago cannot reflect the day-ahead supply and demand relationship, the inventor thinks that thermal power units account for the majority of variable costs. As the load rate increases, the variable cost curve of thermal power units has a very close relationship with the day-ahead clearing electricity price. Therefore, the key feature of the thermal power load rate is extracted, and the day-ahead predicted full-network load on the operating day is determined by the corresponding full-network predicted load in the spot boundary bar within the preset time period before the operating day. The thermal power load rate on the operating day is determined according to the day-ahead predicted full-network load on the operating day and the spot boundary conditions one day before the operating day, and the pre-trained day-ahead clearing electricity price prediction model is input to obtain the day-ahead clearing electricity price data on the operating day, thereby avoiding training large quantities of data while improving the prediction accuracy of the day-ahead clearing electricity price data.

[0044] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0045] Figure 1 A schematic diagram of the scenario of the method for processing the day-ahead clearing electricity price data provided for this application, such as Figure 1 As shown, the specific scenario of the present application includes: a receiving device 101, a processor 102 and a display device 103. It is understandable that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the object identification method. In other feasible implementations of the present application, the above architecture may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently, which can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown may be implemented in hardware, software, or a combination of software and hardware.

[0046] In the specific implementation process, the receiving device 101 can be an input / output interface or a communication interface, and can obtain the spot boundary conditions within a preset time period before the operation day.

[0047] Processor 102 can extract the corresponding network-wide predicted load within a preset time period from the spot boundary conditions; determine the day-ahead predicted network-wide load on the operating day based on the corresponding network-wide predicted load within the preset time period; determine the thermal power load rate on the operating day based on the day-ahead predicted network-wide load on the operating day and the spot boundary conditions one day before the operating day; input the thermal power load rate on the operating day into a pre-trained day-ahead clearing electricity price prediction model to obtain the day-ahead clearing electricity price data on the operating day.

[0048] The display device 103 can be used to display the day-ahead clearing electricity price data of the operation day.

[0049] The display device may also be a touch display screen, which is used to receive user instructions while displaying the above content to achieve operational interaction with the user.

[0050] It should be understood that the above-mentioned processor can be implemented by the processor reading instructions in the memory and executing the instructions, or it can be implemented by a chip circuit.

[0051] In addition, the network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0052] Figure 2 Schematic diagram of the process of processing the day-ahead clearing electricity price data provided for this application Figure 1 ,like Figure 2 As shown, the method includes:

[0053] S201: Obtain spot boundary conditions within a preset time period before the operation day.

[0054] The preset time period is 6 days before the operation date. The spot boundary conditions include the load forecast of the entire network, the planned data of the inter-provincial interconnection lines, the data of the overhauled units and the forecast data of the output of new energy sources, etc. The day-ahead clearing electricity price of D-day is predicted on D-2, and the spot boundary conditions of D-day have not yet been disclosed.

[0055] For example, if the operation day is the 30th, the spot boundary conditions for the preset time period of the 25th to 29th are obtained, wherein the spot boundary conditions for the 25th to 29th are disclosed one day in advance, that is, the 24th to 28th.

[0056] S202: Extracting the corresponding network-wide forecast load within a preset time period from the spot boundary conditions.

[0057] S203: Determine the predicted network load before the operation day according to the corresponding network predicted load in the preset time period.

[0058] Specifically, the day-ahead forecast of the entire network load on D-day is estimated based on the forecast load of the entire network from D-5 to D-1, including steps Sa1 to Sa6:

[0059] Sa1: Get the temperature coefficient and holiday coefficient of the operating day.

[0060] Among them, the short-term day-ahead forecast of the entire network load is mainly affected by temperature and holidays. Therefore, the temperature coefficient a and holiday coefficient b are set to represent the impact on the day-ahead forecast of the entire network load, and the temperature coefficient and holiday coefficient are determined by trading personnel based on experience.

[0061] Sa2: Get the forecast load of the entire network one day before the operation day.

[0062] Specifically, the network-wide forecast load on the day before operation day D is used as a benchmark and is adjusted within the range of the maximum and minimum values ​​at the same time point within 5 days.

[0063] Sa3: If the sum of the temperature coefficient and the holiday coefficient is not less than 0, the maximum value of the predicted load of the entire network corresponding to the preset time period is obtained.

[0064] Sa4: Determine the predicted network load on the day before the operation day based on the sum of the temperature coefficient and the holiday coefficient, the predicted network load on the day before the operation day, and the maximum value of the corresponding predicted network load in the preset time period.

[0065] Specifically, the formula for determining the day-ahead forecast of the entire network load on the operation day (D-day) is:

[0066]

[0067] In the formula, C n The day-ahead forecast of the entire network load for the operation day D is: C n-1 The forecast load of the entire network one day before the operation day (D-1), a is the temperature coefficient, b is the holiday coefficient, Max(C) is the maximum value of the predicted load of the entire network corresponding to the preset time period, a The value ranges from -1 to 1. b The value range is -1 to 1.

[0068] Sa5: If the sum of the temperature coefficient and the holiday coefficient is less than 0, the minimum value of the corresponding network-wide predicted load within the preset time period is obtained.

[0069] Sa6: Determine the predicted network load on the day before the operation day based on the sum of the temperature coefficient and the holiday coefficient, the predicted network load on the day before the operation day, and the minimum value of the corresponding predicted network load in the preset time period.

[0070] Specifically, the formula for determining the day-ahead forecast of the entire network load on the operation day (D-day) is:

[0071]

[0072] In the formula, C n The day-ahead forecast of the entire network load on the operation day (D-day) is: C n-1 The forecast load of the entire network one day before the operation day (D-1), a is the temperature coefficient, b is the holiday coefficient, Min(C) is the minimum value of the predicted load of the entire network corresponding to the preset time period, a The value ranges from -1 to 1. b The value range is -1 to 1.

[0073] S204: Determine the thermal power load rate on the operation day based on the day-ahead forecast of the entire grid load on the operation day and the spot boundary conditions one day before the operation day.

[0074] Among them, the spot boundary conditions on the operation day (D-day), such as inter-provincial interconnection line planning data, maintenance unit data and new energy output forecast data, have not yet been disclosed.

[0075] Specifically, the planned data of inter-provincial interconnection lines, the data of positive and standby capacity, and the data of maintenance unit capacity are unpredictable, but they are basically unchanged or change slightly on two consecutive days. Therefore, the spot boundary conditions of the day before the operation day (D-1 day) are used instead of the data of the operation day (D day).

[0076] Specifically, when the new energy forecast output data discloses the spot boundary conditions of D-1 on D-2, the information includes data for three days, D-1, D, and D+1. The forecast output data for D-1 is selected here instead.

[0077] Specifically, the data on the scale of installed capacity of thermal power units entering the market is disclosed by the provincial power trading center. When the provincial power trading center updates the list of trading entities, the data on the scale of installed capacity of thermal power units entering the market will be updated at any time.

[0078] Specifically, the formula for determining the thermal power load rate on the operating day is:

[0079]

[0080] In the formula, R n is the thermal power load rate on the operation day (D day), C n The day-ahead forecast of the entire network load on the operation day (D-day) is: P n-1 The inter-provincial liaison line plan data is extracted from the spot boundary conditions one day before the operation day (D-1 day). E n-1 It is the predicted output data of new energy extracted from the spot boundary conditions one day before the operation day (D-1 day). A n-1 is the positive reserve capacity data extracted from the spot boundary conditions one day before the operation day (D-1 day), B n-1 In order to collect the latest installed capacity data of thermal power plants entering the market from the disclosed information, O n-1 It is the maintenance unit capacity data extracted from the spot boundary conditions one day before the operation day (D-1).

[0081] S205: Input the thermal power load rate on the operation day into the pre-trained day-ahead clearing electricity price prediction model to obtain the day-ahead clearing electricity price data on the operation day.

[0082] Among them, the pre-trained day-ahead clearing electricity price prediction model is trained based on the corresponding thermal power load rate and clearing electricity price in a preset time period.

[0083] Specifically, the mapping relationship between the thermal power load rate and the day-ahead clearing electricity price is also affected by factors that change over time, such as coal prices, months, and the forecast load curve of the entire network. In order to eliminate the interference of these factors as much as possible, a training set with a short time span is used to build a model. The thermal power load rate from D-6 to D-2 is selected, that is, the thermal power load rate calculated based on the information disclosed one day in advance from D-7 to D-3 and the day-ahead clearing electricity price of the corresponding day are substituted into the initial day-ahead clearing electricity price prediction model for training to obtain the pre-trained day-ahead clearing electricity price prediction model. The thermal power load rate on the operation day (D-day) is input into the pre-trained day-ahead clearing electricity price prediction model to obtain the day-ahead clearing electricity price data on the operation day.

[0084] The method for processing day-ahead clearing electricity price data provided in the embodiment of the present application determines the day-ahead predicted total network load on the operating day through the corresponding total network predicted load in the spot boundary conditions within a preset time period before the operating day, determines the thermal power load rate on the operating day according to the day-ahead predicted total network load on the operating day and the spot boundary conditions one day before the operating day, inputs the thermal power load rate on the operating day into a pre-trained day-ahead clearing electricity price prediction model, and obtains the day-ahead clearing electricity price data on the operating day, thereby achieving the effect of avoiding training large quantities of data while improving the prediction accuracy of the day-ahead clearing electricity price data.

[0085] Figure 3 Schematic diagram of the process of processing the day-ahead clearing electricity price data provided for this application Figure 2 ,like Figure 3 As shown, in this embodiment Figure 2 Based on the illustrated embodiment, the training process of the day-ahead clearing electricity price prediction model is described in detail. The method includes:

[0086] S301: Obtain spot boundary conditions within a preset time period before the operation day, and determine the corresponding thermal power load rate within the preset time period based on the spot boundary conditions within the preset time period.

[0087] The preset time period is 5 days in total, from 6 days before the operation date to 2 days before the operation date.

[0088] Specifically, the formula for determining the thermal power load rate corresponding to the preset time period is:

[0089]

[0090] In the formula, R i For the first i The thermal power load rate extracted from the daily spot boundary conditions,C i For the first i The network-wide forecast load extracted from the spot boundary conditions of the day, P i For the first i Technical data of inter-provincial liaison lines extracted from the daily spot boundary conditions, E i For the first i The predicted output data of new energy extracted from the daily spot boundary conditions, A i For the first i The positive reserve capacity data extracted from the spot boundary conditions of the day, B i In order to collect the latest installed capacity data of thermal power plants entering the market from the disclosed information, O i For the first i The capacity data of the maintenance units extracted from the spot boundary conditions of the day.

[0091] Among them, the new energy forecast output data is i-2 Day 1 Disclosure i-1 When the spot boundary conditions are met, the information includes the i-1 Day, i Tianhedi i+1 There are three days of data in total. Here we select the i-1 The forecast output data for the day.

[0092] S302: Determine the thermal power load change rate at each time node within the preset time period according to the corresponding thermal power load rate within the preset time period.

[0093] Among them, since the predicted load of the entire network of actual thermal power units cannot change suddenly, in addition to the thermal power load rate, a feature that reflects the change of the thermal power load rate is also added: the thermal power load change rate.

[0094] Specifically, the formula for determining the thermal power load change rate at each time node within the preset time period is:

[0095]

[0096] In the formula, θ k for k The thermal power load change rate at the moment, R k for k The thermal power load rate at the moment, R k-3 for k-3 The thermal power load rate at the moment.

[0097] S303: Construct an initial random forest model.

[0098] Among them, according to the relationship between the historical thermal power load rate and the day-ahead clearing electricity price, it can be obtained that the two are in an obvious nonlinear relationship. Under this relationship, the random forest machine learning algorithm can well explore the relationship between the two.

[0099] S304: Inputting the thermal power load rate, thermal power load change rate and day-ahead clearing electricity price corresponding to the preset time period into the initial random forest model for training, and obtaining a pre-trained day-ahead clearing electricity price prediction model.

[0100] Specifically, the thermal power load rate and thermal power load change rate in the preset time period (D-6 to D-2) before the operation day (D-day) are used as the training set to establish a day-ahead clearing electricity price prediction model, and the thermal power load rate on the operation day (D-day) is input into the pre-trained day-ahead clearing electricity price prediction model to obtain the day-ahead clearing electricity price data on the operation day (D-day).

[0101] The method for processing day-ahead clearing electricity price data provided in the embodiment of the present application selects a random forest learning algorithm based on the nonlinear relationship between the thermal power load rate and the day-ahead clearing electricity price, and uses the thermal power load rate within a preset time period as a training set for training, thereby avoiding the effect of training large quantities of data.

[0102] Figure 4 The schematic diagram of the structure of the day-ahead clearing electricity price data processing device provided in this application is as follows: Figure 4 As shown, the day-ahead clearing electricity price data processing device 40 provided in this embodiment includes:

[0103] The spot boundary condition acquisition module 401 is used to acquire the spot boundary conditions within a preset time period before the operation date.

[0104] The network-wide forecast load extraction module 402 is used to extract the network-wide forecast load corresponding to a preset time period from the spot boundary conditions.

[0105] The module 403 for determining the predicted network load the day before is used to determine the predicted network load the day before on the operation day according to the corresponding predicted network load in a preset time period.

[0106] The thermal power load rate determination module 404 is used to determine the thermal power load rate on the operation day according to the day-ahead forecast of the entire network load on the operation day and the spot boundary conditions one day before the operation day.

[0107] The day-ahead clearing electricity price determination module 405 is used to input the thermal power load rate on the operation day into the pre-trained day-ahead clearing electricity price prediction model to obtain the day-ahead clearing electricity price data on the operation day.

[0108] In one possible implementation, the module 403 for determining the predicted network load on the day before the operation is specifically used to obtain the temperature coefficient and the holiday coefficient of the operation day; obtain the predicted network load on the day before the operation day; if the sum of the temperature coefficient and the holiday coefficient is not less than 0, obtain the maximum value of the corresponding predicted network load within the preset time period; determine the predicted network load on the day before the operation day based on the sum of the temperature coefficient and the holiday coefficient, the predicted network load on the day before the operation day, and the maximum value of the corresponding predicted network load within the preset time period; if the sum of the temperature coefficient and the holiday coefficient is less than 0, obtain the minimum value of the corresponding predicted network load within the preset time period; determine the predicted network load on the day before the operation day based on the sum of the temperature coefficient and the holiday coefficient, the predicted network load on the day before the operation day, and the minimum value of the corresponding predicted network load within the preset time period.

[0109] In a possible implementation, the module 403 for determining the day-ahead predicted network load is specifically used to determine the day-ahead predicted network load of the operation day using the formula:

[0110]

[0111] In the formula, C n Forecast the network load for the day before the operation day. C n-1 The forecast load of the entire network one day before the operation day, a is the temperature coefficient, b is the holiday coefficient, Max(C) is the maximum value of the predicted load of the entire network corresponding to the preset time period, a The value ranges from -1 to 1. b The value range is -1 to 1.

[0112] In a possible implementation, the module 403 for determining the day-ahead predicted network load is specifically used to determine the day-ahead predicted network load of the operation day using the formula:

[0113]

[0114] In the formula, C n Forecast the network load for the day before the operation day. C n-1 The forecast load of the entire network one day before the operation day, a is the temperature coefficient, b is the holiday coefficient, Min(C) is the minimum value of the predicted load of the entire network corresponding to the preset time period, a The value ranges from -1 to 1. b The value range is -1 to 1.

[0115] In a possible implementation, the thermal power load rate determination module 404 is specifically used to determine the thermal power load rate on the operation day, using the formula:

[0116]

[0117] In the formula, R n is the thermal power load rate on the operating day, C n Forecast the network load for the day before the operation day. P n-1 is the inter-provincial liaison line plan data extracted from the spot boundary conditions one day before the operation day, E n-1 It is the predicted output data of new energy extracted from the spot boundary conditions one day before the operation day. A n-1 is the positive reserve capacity data extracted from the spot boundary conditions one day before the operation day, B n-1 The installed capacity data of thermal power plants entering the market are collected from the disclosed information. O n-1 It is the maintenance unit capacity data extracted from the spot boundary conditions one day before the operation day.

[0118] The day-ahead electricity price data processing device provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.

[0119] Figure 5 This is a schematic diagram of the structure of the computer device provided in this application. Figure 5 As shown, the computer device 50 provided in this embodiment includes: at least one processor 501 and a memory 502 .

[0120] Optionally, the device 50 further includes a communication component 503 . The processor 501 , the memory 502 and the communication component 503 are connected via a bus 504 .

[0121] In a specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that at least one processor 501 executes the above method.

[0122] The specific implementation process of the processor 501 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0123] The embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the day-ahead clearing electricity price data processing method shown in the above embodiments.

[0124] The embodiments of the present application also provide a computer program product, including a computer program, which, when executed by a processor, implements the day-ahead clearing electricity price data processing method shown in each embodiment.

[0125] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0126] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0127] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0128] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0129] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0130] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0131] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0132] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0133] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0135] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0136] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0137] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for processing day-ahead clearing electricity price data, characterized in that: Applicable to computer equipment, including: Obtain spot boundary conditions within a preset time period before the operation date; Extracting the corresponding network-wide forecast load within the preset time period from the spot boundary conditions; Determine the predicted total network load on the day before the operation day according to the corresponding total network predicted load in the preset time period; Wherein, the method of determining the predicted network load of the day before the operation day according to the corresponding network predicted load within the preset time period includes: obtaining the temperature coefficient and holiday coefficient of the operation day; obtaining the predicted network load of the day before the operation day; if the sum of the temperature coefficient and the holiday coefficient is not less than 0, obtaining the maximum value of the corresponding network predicted load within the preset time period; determining the predicted network load of the day before the operation day according to the sum of the temperature coefficient and the holiday coefficient, the predicted network load of the day before the operation day, and the maximum value of the corresponding network predicted load within the preset time period; wherein, the method of determining the predicted network load of the day before the operation day according to the sum of the temperature coefficient and the holiday coefficient, the predicted network load of the day before the operation day, and the maximum value of the corresponding network predicted load within the preset time period is as follows: In the formula, C n The whole network load is predicted for the day before the operation day. C n-1 is the forecast load of the entire network one day before the operation day, a is the temperature coefficient, b is the holiday coefficient, Max(C) is the maximum value of the predicted load of the entire network corresponding to the preset time period, a The value ranges from -1 to 1. b The value ranges from -1 to 1; If the sum of the temperature coefficient and the holiday coefficient is less than 0, the minimum value of the corresponding network-wide predicted load within the preset time period is obtained; the predicted network-wide load on the day before the operation day is determined according to the sum of the temperature coefficient and the holiday coefficient, the predicted network-wide load on the day before the operation day, and the minimum value of the corresponding network-wide predicted load within the preset time period; wherein, the formula for determining the predicted network-wide load on the day before the operation day according to the sum of the temperature coefficient and the holiday coefficient, the predicted network-wide load on the day before the operation day, and the minimum value of the corresponding network-wide predicted load within the preset time period is: In the formula, C n The whole network load is predicted for the day before the operation day. C n-1 is the forecast load of the entire network one day before the operation day, a is the temperature coefficient, b is the holiday coefficient, Min(C) is the minimum value of the predicted load of the entire network corresponding to the preset time period, a The value ranges from -1 to 1. b The value ranges from -1 to 1; Determine the thermal power load rate on the operation day according to the day-ahead forecast of the entire grid load on the operation day and the spot boundary conditions one day before the operation day; The thermal power load rate on the operation day is input into a pre-trained day-ahead clearing electricity price prediction model to obtain day-ahead clearing electricity price data on the operation day.

2. The method according to claim 1, characterized in that The formula for determining the thermal power load rate on the operation day according to the predicted grid load on the operation day and the spot boundary conditions one day before the operation day is: In the formula, R n is the thermal power load rate on the operation day, C n The whole network load is predicted for the day before the operation day. P n-1 is the inter-provincial liaison line plan data extracted from the spot boundary conditions one day before the operation day, E n-1 is the predicted output data of new energy extracted from the spot boundary conditions one day before the operation day, A n-1 is the positive reserve capacity data extracted from the spot boundary conditions one day before the operation day, B n-1 In order to collect the latest installed capacity data of thermal power plants entering the market from the disclosed information, O n-1 is the maintenance unit capacity data extracted from the spot boundary conditions one day before the operation day.

3. A device for processing day-ahead clearing electricity price data, characterized in that: include: The spot boundary condition acquisition module is used to obtain the spot boundary conditions within a preset time period before the operation date; A network-wide forecast load extraction module, used to extract the network-wide forecast load corresponding to the preset time period from the spot boundary conditions; A module for determining the predicted network load on the day before the operation date, configured to determine the predicted network load on the day before the operation date according to the predicted network load corresponding to the preset time period; A thermal power load rate determination module, used to determine the thermal power load rate on the operation day according to the day-ahead forecast of the entire network load on the operation day and the spot boundary conditions one day before the operation day; A day-ahead clearing electricity price determination module, used for inputting the thermal power load rate of the operation day into the pre-trained day-ahead clearing electricity price prediction model to obtain the day-ahead clearing electricity price data of the operation day; The module for determining the predicted network load on the day before the operation is specifically used to: obtain the temperature coefficient and the holiday coefficient of the operation day; obtain the predicted network load on the day before the operation day; if the sum of the temperature coefficient and the holiday coefficient is not less than 0, obtain the maximum value of the predicted network load corresponding to the preset time period; determine the predicted network load on the day before the operation day according to the sum of the temperature coefficient and the holiday coefficient, the predicted network load on the day before the operation day, and the maximum value of the predicted network load corresponding to the preset time period; Among them, the formula for determining the predicted total network load on the day before the operation day according to the sum of the temperature coefficient and the holiday coefficient, the total network predicted load on the day before the operation day, and the maximum value of the corresponding total network predicted load within the preset time period is: In the formula, C n The whole network load is predicted for the day before the operation day. C n-1 is the forecast load of the entire network one day before the operation day, a is the temperature coefficient, b is the holiday coefficient, Max(C) is the maximum value of the predicted load of the entire network corresponding to the preset time period, a The value ranges from -1 to 1. b The value ranges from -1 to 1; If the sum of the temperature coefficient and the holiday coefficient is less than 0, the minimum value of the corresponding network-wide predicted load within the preset time period is obtained; the predicted network-wide load on the day before the operation day is determined according to the sum of the temperature coefficient and the holiday coefficient, the predicted network-wide load on the day before the operation day, and the minimum value of the corresponding network-wide predicted load within the preset time period; Among them, the formula for determining the predicted total network load on the day before the operation day according to the sum of the temperature coefficient and the holiday coefficient, the total network predicted load on the day before the operation day, and the minimum value of the corresponding total network predicted load in the preset time period is: In the formula, C n The whole network load is predicted for the day before the operation day. C n-1 is the forecast load of the entire network one day before the operation day, a is the temperature coefficient, b is the holiday coefficient, Min(C) is the minimum value of the predicted load of the entire network corresponding to the preset time period, a The value ranges from -1 to 1. b The value range is -1 to 1.

4. A computer device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 2 when executed by a processor.

6. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 2 is implemented.