CN117217822B - Method, device, terminal equipment and storage medium for predicting power transaction index - Google Patents
Method, device, terminal equipment and storage medium for predicting power transaction index Download PDFInfo
- Publication number
- CN117217822B CN117217822B CN202311478430.XA CN202311478430A CN117217822B CN 117217822 B CN117217822 B CN 117217822B CN 202311478430 A CN202311478430 A CN 202311478430A CN 117217822 B CN117217822 B CN 117217822B
- Authority
- CN
- China
- Prior art keywords
- index
- prediction
- target
- data
- equalization
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 7
- 230000005611 electricity Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The embodiment of the invention provides a method, a device, terminal equipment and a storage medium for predicting an electric power transaction index, and belongs to the field of data processing. The method comprises the following steps: acquiring target characteristic data; calculating the similarity between the target feature data and the historical feature data to obtain a first similarity value, and determining the similar feature data according to the first similarity value; performing data fitting according to the similar characteristic data to obtain a first prediction equilibrium index of a target prediction day; predicting the target prediction day through a regression prediction model to obtain a second prediction equilibrium index of the target prediction day; determining a first weight parameter corresponding to the first prediction equilibrium index and the second prediction equilibrium index according to the similar characteristic data; and determining a target prediction equilibrium index corresponding to the target prediction day according to the first weight parameter, the first prediction equilibrium index and the second prediction equilibrium index. The method solves the problems of larger deviation between the equalization index prediction result and the actual equalization index and lower accuracy, and improves the accuracy of power equalization index prediction.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a terminal device, and a storage medium for predicting an electric power transaction index.
Background
The main power output of the market is the day-ahead power output and the real-time power output. The power output and clearing is the achievable power quantity and the supply and demand balance power quantity determined according to the market supply and demand conditions under the condition that the complete constraint condition of the power grid is considered or the safety constraint condition of the power grid is not considered. Therefore, the power spot market power output is one of important influencing factors reflecting the power balance index of the power market for achieving the supply and demand balance, namely, the trading index capable of reflecting the supply and demand relation and the achievable amount of electricity in the power trade.
There are various factors that affect the market equilibrium index of the electric power market, such as market supply and demand relationship, electric power supply mode, electric power market structure, and market rules. The electric power spot market has complex forming mechanism, more influence factors on clear electric power, frequent fluctuation and difficult control in the process of making the balance index.
In the prior art, the power market equilibrium index is predicted in a model prediction mode, but the prediction result obtained by the method depends on factors such as power supply and demand relation, so that the deviation between the equilibrium index prediction result and an actual equilibrium index is larger, the accuracy is lower, and therefore, the power equilibrium index prediction result cannot be accurately and effectively utilized in actual production to realize making an effective decision scheme for the market.
Disclosure of Invention
The embodiment of the invention mainly aims to provide a method, a device, terminal equipment and a storage medium for predicting an electric power transaction index, and aims to solve the problems that in the prior art, a predicted result obtained depends on factors such as an electric power supply and demand relation, so that a deviation between an equilibrium index predicted result and an actual equilibrium index is larger and the accuracy is lower.
In a first aspect, an embodiment of the present invention provides a method for predicting an electric power trading index, including:
acquiring target characteristic data in a current preset time period, wherein the target characteristic data refer to characteristic data influencing an electric power balance index, and the electric power balance index comprises balanced supply and demand electric quantity and achievable electric quantity;
calculating the similarity between the target feature data and the historical feature data to obtain a first similarity value, and determining similar feature data corresponding to the target feature data according to the first similarity value;
performing data fitting according to the similar characteristic data to obtain a first prediction equilibrium index corresponding to the target prediction day;
carrying out equalization index prediction on the target prediction day through a regression prediction model to obtain a second prediction equalization index corresponding to the target prediction day;
Determining a first weight parameter corresponding to the first prediction equalization index and the second prediction equalization index according to the similar characteristic data, wherein the first weight parameter is related to meteorological data in the similar characteristic data;
and determining a target prediction equilibrium index corresponding to the target prediction day according to the first weight parameter, the first prediction equilibrium index and the second prediction equilibrium index.
In a second aspect, an embodiment of the present invention provides an apparatus for predicting an electric power trading index, including:
the data acquisition module is used for acquiring target characteristic data in a current preset time period, wherein the target characteristic data refer to characteristic data affecting an electric power balance index;
the data processing module is used for calculating the similarity between the target feature data and the historical feature data to obtain a first similarity value, and determining similar feature data corresponding to the target feature data according to the first similarity value;
the first equalization index prediction module is used for carrying out data fitting according to the similar characteristic data to obtain a first prediction equalization index corresponding to the target prediction day;
the second equalization index prediction module is used for carrying out equalization index prediction on the target prediction day through a regression prediction model to obtain a second prediction equalization index corresponding to the target prediction day;
The weight calculation module is used for determining first weight parameters corresponding to the first prediction equilibrium index and the second prediction equilibrium index according to the similar characteristic data, and the first weight parameters are related to meteorological data in the similar characteristic data;
and the equalization index output module is used for determining a target prediction equalization index corresponding to a target prediction day according to the first weight parameter, the first prediction equalization index and the second prediction equalization index.
In a third aspect, embodiments of the present invention also provide a terminal device comprising a processor, a memory, a computer program stored on the memory and executable by the processor, and a data bus for enabling a connection communication between the processor and the memory, wherein the computer program, when executed by the processor, implements the steps of a method of any one of the power transaction index predictions as provided in the present specification.
In a fourth aspect, embodiments of the present invention also provide a storage medium for computer readable storage, wherein the storage medium stores one or more programs executable by one or more processors to implement the steps of a method of any one of the power transaction index predictions as provided in the present specification.
The embodiment of the invention provides a method, a device, terminal equipment and a storage medium for predicting an electric power transaction index, wherein the method comprises the steps of obtaining target characteristic data in a current preset time period, wherein the target characteristic data refer to characteristic data affecting an electric power balance index; calculating the similarity between the target feature data and the historical feature data to obtain a first similarity value, and determining similar feature data corresponding to the target feature data according to the first similarity value; performing data fitting according to the similar characteristic data to obtain a first prediction equilibrium index corresponding to the target prediction day; carrying out equilibrium index prediction on the target prediction day through a regression prediction model to obtain a second prediction equilibrium index corresponding to the target prediction day; determining a first weight parameter corresponding to the first prediction equilibrium index and the second prediction equilibrium index according to the similar characteristic data, wherein the first weight parameter is related to meteorological data in the similar characteristic data; and determining a target prediction equilibrium index corresponding to the target prediction day according to the first weight parameter, the first prediction equilibrium index and the second prediction equilibrium index. The method solves the problems of larger deviation between the equilibrium index prediction result and the actual equilibrium index and lower accuracy caused by the fact that the prediction result obtained in the prior art depends on factors such as the power supply and demand relation, thereby improving the accuracy of the equilibrium index prediction result and providing support for making an effective decision scheme for the market by using the power equilibrium index prediction result subsequently.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for predicting an electric power trading index according to an embodiment of the invention;
FIG. 2 is a flow chart of substep S103 of the method of power trading index prediction in FIG. 1;
FIG. 3 is a schematic diagram of a scenario in which the method for predicting the power trading index according to the present embodiment is implemented;
fig. 4 is a schematic block diagram of a device for predicting an electric power trading index according to an embodiment of the invention;
fig. 5 is a schematic block diagram of a structure of a terminal device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The embodiment of the invention provides a method, a device, terminal equipment and a storage medium for predicting an electric power transaction index. The method for predicting the power transaction index can be applied to terminal equipment, and the terminal equipment can be electronic equipment such as tablet computers, notebook computers, desktop computers, personal digital assistants, wearable equipment and the like. The terminal device may be a server or a server cluster.
In this embodiment, the power balance index is a trade index generated by sellers and buyers corresponding to the amount of available power or the amount of balanced power at the point where the actual supply amount and the actual demand amount of power reach balance, so as to reflect the current power trade heat.
Some embodiments of the invention are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for predicting an electric power trading index according to an embodiment of the invention.
As shown in fig. 1, the method for predicting the power trading index includes steps S101 to S106.
Step S101, obtaining target characteristic data in a current preset time period, wherein the target characteristic data refer to characteristic data affecting a power balance index, and the power balance index comprises supply and demand balance electric quantity and achievable electric quantity.
Illustratively, target characteristic data within a preset time period adjacent to a target prediction day is selected, wherein the target characteristic data refers to characteristic data affecting a power balance index.
Optionally, the target characteristic data includes, but is not limited to, load data, contribution data, bid space, price data, weather data.
For example, if the preset time period is 30 days, historical data within 30 days from the target prediction day is obtained as target feature data.
In some embodiments, the acquiring the target feature data within the current preset time period includes: acquiring initial characteristic data in a current preset time period; detecting the missing value of the initial characteristic data, and when the missing value exists in the initial characteristic data, obtaining nearest neighbor data corresponding to the missing value; fitting the nearest neighbor data to obtain a target value corresponding to the missing value; and determining target characteristic data according to the target value and the initial characteristic data.
The method includes the steps of obtaining corresponding initial feature data from historical feature data according to a preset time period, detecting missing values of the initial feature data, obtaining data adjacent to the missing values as nearest neighbor data when the missing values exist in the initial feature data, averaging the nearest neighbor data, taking the average value as a target value, filling the target value to the position of the missing values in the initial feature data, and obtaining target feature data.
Or, performing data fitting on nearest neighbor data on the left side of the missing value, further predicting data of the position where the missing value is located to obtain a first prediction result, performing data fitting on nearest neighbor data on the right side of the missing value, further predicting data of the position where the missing value is located to obtain a second prediction result, and further averaging the first prediction result and the second prediction result to obtain a target value corresponding to the missing value.
For example, the target feature data are arranged according to the time sequence, after the position of the missing value is determined, the nearest neighbor data fitting interpolation method is adopted for filling, namely the Euclidean distance is used for judging the distance, and the average value of n nearest points from the time point of the missing value is used for filling. If there is a missing value at time t1, the missing value at time t1 is filled with an average value of the corresponding features at times t1-1, t 1-2.
Step S102, calculating the similarity between the target feature data and the historical feature data to obtain a first similarity value, and determining similar feature data corresponding to the target feature data according to the first similarity value.
Illustratively, the first similarity value is obtained by calculating the similarity between the target feature data and the history feature data using the cosine similarity, and the first similarity values are arranged in the order from high to low, so that the first n data in the arrangement result are regarded as the similar feature data.
Or taking the historical characteristic data corresponding to the first similarity value which is larger than a preset threshold value as the similar characteristic data corresponding to the target characteristic data.
Optionally, the similarity algorithm between the target feature data and the historical feature data is calculated, and the similarity algorithm is not particularly limited and can be selected according to actual requirements.
And step S103, performing data fitting according to the similar characteristic data to obtain a first prediction equilibrium index corresponding to the target prediction day.
The method includes the steps of obtaining equalization index information in similar characteristic data, arranging the equalization index information according to a time sequence, performing data fitting on the equalization index information to obtain a fitting curve, establishing an association relationship between time and the equalization index information, and inputting a target prediction day into the fitting curve to obtain a first prediction equalization index corresponding to the target prediction day.
In some embodiments, the performing data fitting according to the similar feature data to obtain a first predicted balance index corresponding to the target predicted day, specifically referring to fig. 2, step S103 includes: substep S1031 to substep S1032. Comprising the following steps:
and step S1031, normalizing the first similar value corresponding to the similar characteristic data to obtain a second similar value corresponding to the similar characteristic data.
Illustratively, the first similarity value is normalized to obtain a second similarity value corresponding to the similar feature data, and a sum of the second similarity values is equal to a preset value (i.e., arabic numeral 1). And the second similarity value is used for representing the importance degree of similar characteristic data in the process of carrying out equilibrium index prediction on the target prediction day.
And S1032, determining a first prediction balance index corresponding to the target prediction day according to the second similarity value and the balance index information in the similar characteristic data.
Illustratively, equalization index information in the similar characteristic data is obtained, and the equalization index information and the second similarity value are weighted and summed, so that a first predicted equalization index corresponding to the target prediction day is obtained.
In some embodiments, after determining the first predicted balance index corresponding to the target prediction day according to the second similarity value and the balance index information in the similar feature data, the method further includes: determining a second weight parameter corresponding to the first predictive equalization index according to the second similarity value and the similar characteristic data; and multiplying the second weight parameter by the first prediction equalization index to obtain a multiplication result, and updating the first prediction equalization index by using the multiplication result.
The similar feature data contains bidding space information, the bidding space information is weighted and summed by using a second similar value to obtain similar bidding space, the bidding space information in the similar feature data is obtained, the bidding space information is arranged according to time sequence, so that the bidding space information is subjected to data fitting to obtain a fitting curve, the association relationship between time and the bidding space information is built, and then the target prediction date is input into the fitting curve, so that the predicted bidding space information corresponding to the target prediction date is obtained. Dividing the similar bidding space by the predicted bidding space information to obtain a second weight parameter, multiplying the second weight parameter by the first predicted equilibrium index to obtain a multiplication result, and updating the first predicted equilibrium index by using the multiplication result.
And step S104, carrying out equilibrium index prediction on the target prediction day through a regression prediction model to obtain a second prediction equilibrium index corresponding to the target prediction day.
The model training is performed by using feature information in the historical feature data to obtain a regression prediction model, and then the target prediction date is input into the regression prediction model to obtain a second prediction equilibrium index corresponding to the target prediction date.
For example, the historical characteristic data includes load data, output data, bid space, electricity price data and weather data, wherein the electricity price data is output by a model, and characteristics such as time information, load data, output data, bid space and weather data are input by the model, and then a relationship among the time information, the load data, the output data, the bid space, the weather data and the electricity price data is established according to a neural network model, model training is performed through the historical characteristic data, so that a regression prediction model is obtained, and then information such as a target prediction day and the load data, the output data, the bid space and the weather data corresponding to the target prediction day are input into the regression prediction model, so that a second prediction equilibrium index corresponding to the target prediction day is obtained.
Or, for example, performing data fitting on electricity price data in the historical characteristic data by using a least square method to obtain a regression prediction model, inputting the regression prediction model as time information, and outputting equalization index information corresponding to the time information, so that a target prediction day is input into the regression prediction model, and a second prediction equalization index corresponding to the target prediction day is obtained.
Step S105, determining a first weight parameter corresponding to the first predicted equalization index and the second predicted equalization index according to the similar characteristic data, where the first weight parameter is related to meteorological data in the similar characteristic data.
For example, when the power balance index is predicted, the weather data is influenced by the weather data, the weather data changes along with the time, but when the first predicted balance index and the second predicted balance index are subjected to balance index prediction, the weather data are influenced by the weather data, and for this purpose, the first weight parameters corresponding to the first predicted balance index and the second predicted balance index are determined according to the similarity between the weather data in the similar characteristic data and the weather data of the target prediction day published by the weather bureau in real time.
For example, the greater the similarity between the weather data in the similar characteristic data and the weather data of the target prediction day published in real time by the weather bureau, the greater the first weight parameter; the higher the confidence that the first predictive equalization index and the second predictive equalization index result are. When the similarity between the meteorological data in the similar characteristic data and the meteorological data of the target prediction day published in real time by the meteorological bureau is smaller, the first weight parameter is smaller; the lower the confidence that the first predictive equalization index and the second predictive equalization index result are.
In some embodiments, the similar characteristic data includes first meteorological data, and the determining, according to the similar characteristic data, a first weight parameter corresponding to the first predicted equalization index and the second predicted equalization index includes: obtaining second meteorological data corresponding to a target prediction day; and obtaining a first weight parameter corresponding to the first predicted balance index and the second predicted balance index according to the ratio between the first meteorological data and the second meteorological data.
Illustratively, the similar characteristic data includes first weather data, and second weather data corresponding to the target prediction day is obtained, wherein the second weather data changes according to data publication of the weather bureau. Meteorological data includes, but is not limited to, irradiance, wind force values.
Illustratively, the first weather data and the second weather data are compared to obtain a first value, and the first value is subtracted from a preset value (i.e., arabic number 1) to obtain a second value, so that the first value and the second value together form a first weight parameter.
Illustratively, the second weather data is dynamically changing, so the first weight parameter is also dynamically changing.
And S106, determining a target prediction equilibrium index corresponding to a target prediction day according to the first weight parameter, the first prediction equilibrium index and the second prediction equilibrium index.
Illustratively, the first predicted equalization index and the second predicted equalization index are weighted and summed with a first weight parameter to obtain a target predicted equalization index corresponding to the target prediction day.
In some embodiments, after the determining the target predicted equalization index corresponding to the target predicted day according to the first weight parameter, the first predicted equalization index, and the second predicted equalization index, the method further includes: obtaining a target equilibrium index interval corresponding to a target prediction day; and adjusting the target predictive equilibrium index according to the target equilibrium index interval to obtain an adjusted target predictive equilibrium index.
In an exemplary embodiment, a target balance index interval corresponding to the target prediction day is obtained, and when the target prediction balance index is not in the target balance index interval, the target prediction balance index is adjusted to be in the target balance index interval.
For example, the target equalization index interval is [ a, b ], and the target predicted equalization index is c, and when the target predicted equalization index c is greater than b, the target predicted equalization index is adjusted to b; and when the target prediction equilibrium index c is smaller than a, adjusting the target prediction equilibrium index to a.
In some embodiments, the obtaining the target equalization index interval corresponding to the target prediction day includes: obtaining an equilibrium index upper limit proportion and an equilibrium index lower limit proportion corresponding to a target prediction day; determining the confidence coefficient corresponding to the target feature data, and determining a confidence interval corresponding to the target prediction day according to the confidence coefficient; and determining a target balance index interval corresponding to the target prediction day according to the confidence interval, the balance index upper limit proportion and the balance index lower limit proportion.
Illustratively, based on the m-day target feature data, a confidence interval is calculated through the confidence k, and a target equilibrium index interval corresponding to the target prediction day is determined through the confidence interval, the equilibrium index upper limit proportion and the equilibrium index lower limit proportion.
Optionally, the balance index upper limit proportion may further include a market balance index upper limit, and the balance index lower limit proportion may further include a market balance index lower limit.
Optionally, a parameter configuration table is established through the database, and the confidence coefficient, the upper limit proportion of the balance index and the lower limit proportion of the balance index are flexibly configured through setting the parameter configuration table, so that the upper limit proportion of the balance index and the lower limit proportion of the balance index corresponding to the target prediction day and the confidence coefficient corresponding to the target feature data are obtained from the parameter configuration table.
Alternatively, the corresponding number information of the target feature data, the corresponding number information of the similar feature data may be also configured by the parameter configuration table, and the like.
The input information corresponding to the power balance index prediction can be flexibly adjusted through the parameter configuration table, so that the target prediction balance index corresponding to the target prediction day can be quickly obtained through adjusting the parameter configuration table.
Referring to fig. 3, fig. 3 is a schematic diagram of a scenario for implementing the method for predicting the power transaction index according to the present embodiment, as shown in fig. 3, a database parameter configuration table is established and required parameters are configured, initial feature data of a target number is obtained according to the parameter configuration table, missing values of the initial feature data are detected, and when the missing values of the initial feature data exist, the missing values are filled by using a nearest neighbor data fitting interpolation method, so as to obtain target feature data. Obtaining quantity information corresponding to similar feature data from a database parameter configuration table, obtaining similar feature data under the corresponding quantity information from historical feature data by using a similarity algorithm, and performing weighted fitting according to the similarity corresponding to the similar feature data to obtain a first prediction equilibrium index; predicting a target prediction day by using a regression prediction model to obtain a second prediction equilibrium index; and calculating weather data of the target prediction date and similar characteristic data to obtain first parameter information, updating the first prediction equilibrium index by using bid space information of the target prediction date and similar characteristic data to obtain an updated first prediction equilibrium index, and finally carrying out weighted summation on the updated first prediction equilibrium index and the updated second prediction equilibrium index by using the first parameter information to obtain a target prediction equilibrium index corresponding to the target prediction date. Obtaining an equalization index upper limit proportion and an equalization index lower limit proportion corresponding to a target prediction day from a database parameter configuration table, and confidence coefficient corresponding to target feature data, and determining a confidence interval corresponding to the target prediction day according to the confidence coefficient; and determining a target balance index interval corresponding to the target prediction day according to the confidence interval, the balance index upper limit proportion and the balance index lower limit proportion, and adjusting the target prediction balance index according to the target balance index interval to obtain an adjusted target prediction balance index. The method solves the problems that the predicted result obtained in the prior art depends on factors such as power supply and demand relation, and the like, so that the deviation between the equilibrium index predicted result and an actual equilibrium index is larger, and the accuracy is lower, thereby improving the accuracy of the equilibrium index predicted result, and providing support for making an effective decision scheme for the market by using the power equilibrium index predicted result subsequently.
Referring to fig. 4, fig. 4 is a device 200 for predicting a power trading index according to an embodiment of the present application, where the device 200 for predicting a power trading index includes a data acquisition module 201, a data processing module 202, a first equalization index prediction module 203, a second equalization index prediction module 204, a weight calculation module 205, and an equalization index output module 206, where the data acquisition module 201 is configured to acquire target feature data in a current preset time period, where the target feature data refers to feature data affecting a power equalization index; the data processing module 202 is configured to calculate a similarity between the target feature data and the historical feature data to obtain a first similarity value, and determine similar feature data corresponding to the target feature data according to the first similarity value; the first equalization index prediction module 203 is configured to perform data fitting according to the similar feature data to obtain a first predicted equalization index corresponding to a target prediction day; a second equalization index prediction module 204, configured to perform equalization index prediction on the target prediction day through a regression prediction model, so as to obtain a second predicted equalization index corresponding to the target prediction day; the weight calculation module 205 is configured to determine, according to the similar characteristic data, a first weight parameter corresponding to the first predicted equalization index and the second predicted equalization index, where the first weight parameter is related to meteorological data in the similar characteristic data; and the equalization index output module 206 is configured to determine a target predicted equalization index corresponding to the target prediction day according to the first weight parameter, the first predicted equalization index, and the second predicted equalization index.
In some embodiments, the data obtaining module 201 performs, in the process of obtaining the target feature data within the current preset time period:
acquiring initial characteristic data in a current preset time period;
detecting the missing value of the initial characteristic data, and when the missing value exists in the initial characteristic data, obtaining nearest neighbor data corresponding to the missing value;
fitting the nearest neighbor data to obtain a target value corresponding to the missing value;
and determining target characteristic data according to the target value and the initial characteristic data.
In some embodiments, the first equalization index prediction module 203 performs, in the process of performing data fitting according to the similar feature data to obtain the first predicted equalization index corresponding to the target prediction day:
normalizing the first similar value corresponding to the similar characteristic data to obtain a second similar value corresponding to the similar characteristic data;
and determining a first prediction equilibrium index corresponding to the target prediction day according to the second similarity value and the equilibrium index information in the similar characteristic data.
In some embodiments, the first equalization index prediction module 203 further performs, in a process after determining the first predicted equalization index corresponding to the target prediction day according to the second similarity value and the equalization index information in the similar feature data:
Determining a second weight parameter corresponding to the first predictive equalization index according to the second similarity value and the similar characteristic data;
and multiplying the second weight parameter by the first prediction equalization index to obtain a multiplication result, and updating the first prediction equalization index by using the multiplication result.
In some embodiments, the similar feature data includes first meteorological data, and the weight calculation module 205 performs, in the determining, according to the similar feature data, a first weight parameter corresponding to the first predicted equalization index and the second predicted equalization index:
obtaining second meteorological data corresponding to a target prediction day;
and obtaining a first weight parameter corresponding to the first predicted balance index and the second predicted balance index according to the ratio between the first meteorological data and the second meteorological data.
In some embodiments, the equalization index output module 206 further performs, in the process after determining the target predicted equalization index corresponding to the target prediction day according to the first weight parameter, the first predicted equalization index, and the second predicted equalization index:
obtaining a target equilibrium index interval corresponding to a target prediction day;
And adjusting the target predictive equilibrium index according to the target equilibrium index interval to obtain an adjusted target predictive equilibrium index.
In some embodiments, the equalization index output module 206 performs, during the target equalization index interval corresponding to the obtained target prediction day:
obtaining an equilibrium index upper limit proportion and an equilibrium index lower limit proportion corresponding to a target prediction day;
determining the confidence coefficient corresponding to the target feature data, and determining a confidence interval corresponding to the target prediction day according to the confidence coefficient;
and determining a target balance index interval corresponding to the target prediction day according to the confidence interval, the balance index upper limit proportion and the balance index lower limit proportion.
In some embodiments, the apparatus 200 for power trade index prediction may also be used for terminal devices.
It should be noted that, for convenience and brevity of description, the specific working process of the apparatus 200 for predicting the power balance index described above may refer to the corresponding process in the foregoing method embodiment for predicting the power transaction index, which is not described herein again.
Referring to fig. 5, fig. 5 is a schematic block diagram of a structure of a terminal device according to an embodiment of the present invention.
As shown in fig. 5, the terminal device 300 includes a processor 301 and a memory 302, the processor 301 and the memory 302 being connected by a bus 303, such as an I2C (Inter-integrated Circuit) bus.
In particular, the processor 301 is used to provide computing and control capabilities, supporting the operation of the entire terminal device. The processor 301 may be a central processing unit (Central Processing Unit, CPU), the processor 301 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Specifically, the Memory 302 may be a Flash chip, a Read-Only Memory (ROM) disk, an optical disk, a U-disk, a removable hard disk, or the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of a portion of the structure related to the embodiment of the present invention, and does not constitute a limitation of the terminal device to which the embodiment of the present invention is applied, and that a specific server may include more or less components than those shown in the drawings, or may combine some components, or have a different arrangement of components.
The processor is used for running a computer program stored in the memory, and implementing any one of the power transaction index prediction methods provided by the embodiment of the invention when the computer program is executed.
In an embodiment, the processor is configured to run a computer program stored in a memory and to implement the following steps when executing the computer program:
acquiring target characteristic data in a current preset time period, wherein the target characteristic data refer to characteristic data affecting an electric power balance index;
calculating the similarity between the target feature data and the historical feature data to obtain a first similarity value, and determining similar feature data corresponding to the target feature data according to the first similarity value;
performing data fitting according to the similar characteristic data to obtain a first prediction equilibrium index corresponding to the target prediction day;
carrying out equalization index prediction on the target prediction day through a regression prediction model to obtain a second prediction equalization index corresponding to the target prediction day;
determining a first weight parameter corresponding to the first prediction equalization index and the second prediction equalization index according to the similar characteristic data, wherein the first weight parameter is related to meteorological data in the similar characteristic data;
And determining a target prediction equilibrium index corresponding to the target prediction day according to the first weight parameter, the first prediction equilibrium index and the second prediction equilibrium index.
In some embodiments, the processor 301 performs, in acquiring the target feature data within the current preset time period:
acquiring initial characteristic data in a current preset time period;
detecting the missing value of the initial characteristic data, and when the missing value exists in the initial characteristic data, obtaining nearest neighbor data corresponding to the missing value;
fitting the nearest neighbor data to obtain a target value corresponding to the missing value;
and determining target characteristic data according to the target value and the initial characteristic data.
In some embodiments, the processor 301 performs, in a process of obtaining the first prediction equalization index corresponding to the target prediction day according to the data fitting of the similar feature data:
normalizing the first similar value corresponding to the similar characteristic data to obtain a second similar value corresponding to the similar characteristic data;
and determining a first prediction equilibrium index corresponding to the target prediction day according to the second similarity value and the equilibrium index information in the similar characteristic data.
In some embodiments, the processor 301 further performs, in a process after determining the first predicted balance index corresponding to the target prediction day according to the second similarity value and the balance index information in the similar feature data:
determining a second weight parameter corresponding to the first predictive equalization index according to the second similarity value and the similar characteristic data;
and multiplying the second weight parameter by the first prediction equalization index to obtain a multiplication result, and updating the first prediction equalization index by using the multiplication result.
In some embodiments, the similar characteristic data includes first meteorological data, and the processor 301 performs, in the determining, according to the similar characteristic data, a first weight parameter corresponding to the first predicted equalization index and the second predicted equalization index:
obtaining second meteorological data corresponding to a target prediction day;
and obtaining a first weight parameter corresponding to the first predicted balance index and the second predicted balance index according to the ratio between the first meteorological data and the second meteorological data.
In some embodiments, the processor 301 further performs, in the process after determining the target predicted equalization index corresponding to the target predicted day according to the first weight parameter, the first predicted equalization index, and the second predicted equalization index:
Obtaining a target equilibrium index interval corresponding to a target prediction day;
and adjusting the target predictive equilibrium index according to the target equilibrium index interval to obtain an adjusted target predictive equilibrium index.
In some embodiments, the processor 301 performs, in obtaining the target equalization index interval corresponding to the target prediction day:
obtaining an equilibrium index upper limit proportion and an equilibrium index lower limit proportion corresponding to a target prediction day;
determining the confidence coefficient corresponding to the target feature data, and determining a confidence interval corresponding to the target prediction day according to the confidence coefficient;
and determining a target balance index interval corresponding to the target prediction day according to the confidence interval, the balance index upper limit proportion and the balance index lower limit proportion.
It should be noted that, for convenience and brevity of description, specific working processes of the terminal device described above may refer to corresponding processes in the foregoing power transaction index prediction method embodiment, and are not described herein again.
Embodiments of the present invention also provide a storage medium for computer readable storage storing one or more programs executable by one or more processors to implement the steps of any of the methods of power transaction index prediction as provided in the description of embodiments of the present invention.
The storage medium may be an internal storage unit of the terminal device according to the foregoing embodiment, for example, a hard disk or a memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal device.
Those of ordinary skill in the art will appreciate that all or some of the steps, systems, functional modules/units in the apparatus, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware embodiment, the division between the functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
It should be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments. While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (9)
1. A method of power trading index prediction, the method comprising:
acquiring target characteristic data in a current preset time period, wherein the target characteristic data refer to characteristic data influencing an electric power balance index, and the electric power balance index comprises balanced supply and demand electric quantity and achievable electric quantity;
calculating the similarity between the target feature data and the historical feature data to obtain a first similarity value, and determining similar feature data corresponding to the target feature data according to the first similarity value;
performing data fitting according to the similar characteristic data to obtain a first prediction equilibrium index corresponding to the target prediction day;
carrying out equalization index prediction on the target prediction day through a regression prediction model to obtain a second prediction equalization index corresponding to the target prediction day;
determining a first weight parameter corresponding to the first prediction equalization index and the second prediction equalization index according to the similar characteristic data, wherein the first weight parameter is related to meteorological data in the similar characteristic data;
the similar characteristic data includes first meteorological data, and the determining, according to the similar characteristic data, a first weight parameter corresponding to the first predicted equalization index and the second predicted equalization index includes:
Obtaining second meteorological data corresponding to a target prediction day;
the first meteorological data and the second meteorological data are subjected to ratio to obtain a first numerical value, and the first numerical value is subtracted from 1 to obtain a second numerical value, so that a first weight parameter is formed by the first numerical value and the second numerical value together;
and determining a target prediction equilibrium index corresponding to the target prediction day according to the first weight parameter, the first prediction equilibrium index and the second prediction equilibrium index.
2. The method of claim 1, wherein the obtaining target feature data for a current preset time period comprises:
acquiring initial characteristic data in a current preset time period;
detecting the missing value of the initial characteristic data, and when the missing value exists in the initial characteristic data, obtaining nearest neighbor data corresponding to the missing value;
fitting the nearest neighbor data to obtain a target value corresponding to the missing value;
and determining target characteristic data according to the target value and the initial characteristic data.
3. The method of claim 1, wherein the performing data fitting according to the similar feature data to obtain a first prediction equalization index corresponding to a target prediction day comprises:
Normalizing the first similar value corresponding to the similar characteristic data to obtain a second similar value corresponding to the similar characteristic data;
and determining a first prediction equilibrium index corresponding to the target prediction day according to the second similarity value and the equilibrium index information in the similar characteristic data.
4. The method of claim 3, further comprising, after determining a first predicted equalization index corresponding to a target prediction day based on the second similarity value and equalization index information in the similar characteristic data:
determining a second weight parameter corresponding to the first predictive equalization index according to the second similarity value and the similar characteristic data;
and multiplying the second weight parameter by the first prediction equalization index to obtain a multiplication result, and updating the first prediction equalization index by using the multiplication result.
5. The method of claim 1, wherein after the determining the target predicted equalization index corresponding to the target prediction day based on the first weight parameter, the first predicted equalization index, and the second predicted equalization index, the method further comprises:
obtaining a target equilibrium index interval corresponding to a target prediction day;
And adjusting the target predictive equilibrium index according to the target equilibrium index interval to obtain an adjusted target predictive equilibrium index.
6. The method of claim 5, wherein obtaining a target equalization index interval corresponding to a target prediction day comprises:
obtaining an equilibrium index upper limit proportion and an equilibrium index lower limit proportion corresponding to a target prediction day;
determining the confidence coefficient corresponding to the target feature data, and determining a confidence interval corresponding to the target prediction day according to the confidence coefficient;
and determining a target balance index interval corresponding to the target prediction day according to the confidence interval, the balance index upper limit proportion and the balance index lower limit proportion.
7. An apparatus for predicting an electrical power trading index, comprising:
the system comprises a data acquisition module, a power balance index generation module and a power balance module, wherein the data acquisition module is used for acquiring target characteristic data in a current preset time period, the target characteristic data refer to characteristic data affecting the power balance index, and the power balance index comprises supply and demand balance electric quantity and achievable traffic electric quantity;
the data processing module is used for calculating the similarity between the target feature data and the historical feature data to obtain a first similarity value, and determining similar feature data corresponding to the target feature data according to the first similarity value;
The first equalization index prediction module is used for carrying out data fitting according to the similar characteristic data to obtain a first prediction equalization index corresponding to the target prediction day;
the second equalization index prediction module is used for carrying out equalization index prediction on the target prediction day through a regression prediction model to obtain a second prediction equalization index corresponding to the target prediction day;
the weight calculation module is used for determining first weight parameters corresponding to the first prediction equilibrium index and the second prediction equilibrium index according to the similar characteristic data, and the first weight parameters are related to meteorological data in the similar characteristic data;
the similar characteristic data comprise first meteorological data, and the weight calculation module is further used for obtaining second meteorological data corresponding to a target prediction day; the first meteorological data and the second meteorological data are subjected to ratio to obtain a first numerical value, and the first numerical value is subtracted from 1 to obtain a second numerical value, so that a first weight parameter is formed by the first numerical value and the second numerical value together;
and the equalization index output module is used for determining a target prediction equalization index corresponding to a target prediction day according to the first weight parameter, the first prediction equalization index and the second prediction equalization index.
8. A terminal device, characterized in that the terminal device comprises a processor and a memory;
the memory is used for storing a computer program;
the processor is configured to execute the computer program and to implement the method of power trading index prediction according to any one of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium, which when executed by one or more processors, causes the one or more processors to perform the method steps of power transaction index prediction as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311478430.XA CN117217822B (en) | 2023-11-08 | 2023-11-08 | Method, device, terminal equipment and storage medium for predicting power transaction index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311478430.XA CN117217822B (en) | 2023-11-08 | 2023-11-08 | Method, device, terminal equipment and storage medium for predicting power transaction index |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117217822A CN117217822A (en) | 2023-12-12 |
| CN117217822B true CN117217822B (en) | 2024-02-13 |
Family
ID=89051532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311478430.XA Active CN117217822B (en) | 2023-11-08 | 2023-11-08 | Method, device, terminal equipment and storage medium for predicting power transaction index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117217822B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226736A (en) * | 2013-03-27 | 2013-07-31 | 东北电力大学 | Method for predicting medium and long term power load based on cluster analysis and target theory |
| CN109308634A (en) * | 2018-08-28 | 2019-02-05 | 贵州电力交易中心有限公司 | A kind of electricity transaction index calculation method applied to electric power medium and long-term transaction |
| CN110867904A (en) * | 2019-11-27 | 2020-03-06 | 广西电网有限责任公司 | Electric quantity clearing method and device |
| CN112001581A (en) * | 2020-07-07 | 2020-11-27 | 国网重庆市电力公司 | Power grid electric power quantity balancing method |
| US11070056B1 (en) * | 2020-03-13 | 2021-07-20 | Dalian University Of Technology | Short-term interval prediction method for photovoltaic power output |
| CN113689068A (en) * | 2021-07-09 | 2021-11-23 | 国网河北省电力有限公司经济技术研究院 | Electric power and electric quantity balance planning method and device and terminal equipment |
-
2023
- 2023-11-08 CN CN202311478430.XA patent/CN117217822B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226736A (en) * | 2013-03-27 | 2013-07-31 | 东北电力大学 | Method for predicting medium and long term power load based on cluster analysis and target theory |
| CN109308634A (en) * | 2018-08-28 | 2019-02-05 | 贵州电力交易中心有限公司 | A kind of electricity transaction index calculation method applied to electric power medium and long-term transaction |
| CN110867904A (en) * | 2019-11-27 | 2020-03-06 | 广西电网有限责任公司 | Electric quantity clearing method and device |
| US11070056B1 (en) * | 2020-03-13 | 2021-07-20 | Dalian University Of Technology | Short-term interval prediction method for photovoltaic power output |
| CN112001581A (en) * | 2020-07-07 | 2020-11-27 | 国网重庆市电力公司 | Power grid electric power quantity balancing method |
| CN113689068A (en) * | 2021-07-09 | 2021-11-23 | 国网河北省电力有限公司经济技术研究院 | Electric power and electric quantity balance planning method and device and terminal equipment |
Non-Patent Citations (2)
| Title |
|---|
| 以工业用户为典型对象的生产电力指数分析与应用;黄艳;陈武;张朋志;程韦;李潇;;农电管理(第08期);45-46 * |
| 自回归误差下的改进Lyapounov最大指数法在短期负荷预测中的应用研究;苏丽;吴舰;吴楠;乔玉鹏;;贵州师范大学学报(自然科学版)(第01期);79-84 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117217822A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2017142781A (en) | Random quotation and sudden change prediction | |
| CN113657668A (en) | Power load prediction method and system based on LSTM network | |
| CN108736474B (en) | Power load prediction method and device | |
| CN110688620A (en) | Short-term load prediction method and device | |
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| JP7062144B1 (en) | Power demand forecasting device and power demand forecasting method | |
| CN116091118A (en) | Electricity price prediction method, device, equipment, medium and product | |
| CN114943565A (en) | Electric power spot price prediction method and device based on intelligent algorithm | |
| CN113962874A (en) | Bus load model training method, device, equipment and storage medium | |
| CN117217822B (en) | Method, device, terminal equipment and storage medium for predicting power transaction index | |
| CN110705738B (en) | Intelligent electricity utilization stimulation demand response method and system based on artificial intelligence | |
| Chaweewat et al. | An electricity price interval forecasting by using residual neural network | |
| CN111144634A (en) | Method and device for predicting power price | |
| CN116452242A (en) | Game profit prediction method, device and equipment based on fitting regression | |
| JP2019046467A (en) | Power transaction support device and power transaction support method | |
| CN115564152A (en) | Carbon emission prediction method and device based on STIRPAT model | |
| CN112633771B (en) | Power resource numerical value calculation method, device, computer equipment and storage medium | |
| JP7342369B2 (en) | Prediction system, prediction method | |
| US20160093002A1 (en) | Optimal Battery Pricing and Energy Management for Localized Energy Resources | |
| CN113947007A (en) | Energy load prediction method, device and equipment | |
| CN113205257A (en) | House property index data analysis method, apparatus, device and storage medium | |
| CN112906757A (en) | Model training method, optical power prediction method, device, equipment and storage medium | |
| CN111178637A (en) | Power grid short-term load prediction method and device | |
| JP2020115276A (en) | Information processing method, information processing device, program, and generation method of learned model | |
| CN109409596B (en) | Processing method, device, equipment and computer-readable storage medium for predicting wind speed |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |