CN113763047A - Load prediction information value rate evaluation method and system based on kernel density estimation - Google Patents

Load prediction information value rate evaluation method and system based on kernel density estimation Download PDF

Info

Publication number
CN113763047A
CN113763047A CN202111045387.9A CN202111045387A CN113763047A CN 113763047 A CN113763047 A CN 113763047A CN 202111045387 A CN202111045387 A CN 202111045387A CN 113763047 A CN113763047 A CN 113763047A
Authority
CN
China
Prior art keywords
real
electric power
market
profit
retailer
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.)
Pending
Application number
CN202111045387.9A
Other languages
Chinese (zh)
Inventor
冯歆尧
彭泽武
谢瀚阳
梁盈威
苏华权
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Power Grid Co Ltd
Original Assignee
Guangdong Power Grid Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Power Grid Co Ltd filed Critical Guangdong Power Grid Co Ltd
Priority to CN202111045387.9A priority Critical patent/CN113763047A/en
Publication of CN113763047A publication Critical patent/CN113763047A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0206—Price or cost determination based on market factors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • 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
    • 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
    • Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
    • Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards

Abstract

The invention provides a load prediction information value rate evaluation method and system based on kernel density estimation, wherein a double-calculation market system which is generally applied in electric power market transaction is modeled; secondly, considering that the electric power retailer needs to predict and bid the predicted real-time electricity consumption of the proxied user, the uncertainty of the part of the electricity is modeled into the probability density distribution of random variables; and finally, fitting the distribution of the uncertainty variable through kernel density estimation, and obtaining the value rate measurement of the load prediction information according to the fitted approximate distribution. The method is characterized in that uncertainty is depicted and fitted based on kernel density estimation, and the influence of the uncertainty of the power resource on the profit of the electricity purchasing and selling transaction of the power retailer is measured according to the kernel function and the fitting distribution of the kernel function, so that the information value rate is evaluated, the accuracy can reach 95%, and the power retailer can be effectively guided to participate in the information transaction.

Description

Load prediction information value rate evaluation method and system based on kernel density estimation
Technical Field
The invention relates to the technical field of electric power market trading, in particular to a load prediction information value rate evaluation method and system based on kernel density estimation.
Background
The development of smart grids has enabled power resources from various sources to be closely tied together through information networks, thereby enabling coupling between power and information. On the other hand, with the development of data processing technologies such as big data and cloud computing, the capability of people to collect, process and analyze information is improved, and the value of the information is receiving more and more attention. However, in the power system, protection of privacy and commercial interests among different subjects makes it difficult to achieve collaborative sharing of information, severely limits the ability of information to be converted into economic value, and also restricts the effective use of power resources.
Disclosure of Invention
The invention provides a load prediction information value rate evaluation method and system based on kernel density estimation, which can be applied to information transaction based on electric power market transaction, and the kernel density estimation-based method is used for measuring the effect of eliminating uncertainty of information, so that the evaluation precision of the information value rate is improved, and the information value rate data with the precision as high as 95% is obtained.
The invention provides a load prediction information value rate evaluation method based on kernel density estimation, which comprises the following steps:
respectively establishing a day-ahead market electric power transaction cost model and a real-time market electric power transaction profit model according to day-ahead market data and real-time market data;
establishing a profit model of the electric power retailer according to the day-ahead market electric power transaction cost model and the real-time market electric power transaction profit model;
fitting to obtain a real-time user load demand distribution function based on the real-time user load demand;
calculating to obtain a profit expectation function of the electric power retailer and a profit target expectation value of the electric power retailer according to the real-time user load demand distribution function and the profit model of the electric power retailer;
calculating to obtain a load prediction information value rate by a kernel density estimation method in combination with the profit expectation function of the electric power retailer and the profit target expectation value of the electric power retailer;
and measuring and calculating according to the load prediction information value rate and the information value rate of the electric power retailer, so that the load prediction information value rate meets a preset threshold value.
Further, the day-ahead market electricity trading cost model is expressed by the following formula:
CDA＝πXDA；
wherein, CDAFor the cost of the power trade in the day-ahead market, pi is the price information of the day-ahead market, XDAThe electric power trading volume cleared for the market in the day ahead;
the real-time market electric power trading profit model is expressed by the following formula:
Figure BDA0003250968740000021
wherein, PRTProfit for real-time market electricity trade, p is price information for retail of electricity retailers, xRTElectric power trade volume, X, cleared for real-time marketDAElectric power trade volume, lambda, cleared for the day-ahead market+Maximum price, lambda, for a real-time market-Minimum price for real-time market, XminFor minimum real-time user load demand, XmaxThe maximum real-time user load demand.
Further, the profit model of the electricity retailer is expressed by the following formula:
Figure BDA0003250968740000022
where P is the profit of the electricity retailer, PRTTo a real-time marketProfit from field power trade, CDAFor the cost of the power trade in the market at the day-ahead, p is the price information for the retail sale of the power retailer, xRTClearing the electric power trade volume for the real-time market, wherein pi is the price information of the day-ahead market, XDAElectric power trade volume, lambda, cleared for the day-ahead market+Maximum price, lambda, for a real-time market-Minimum price for real-time market, XDAElectric power trade volume, X, cleared for the day-ahead marketminFor minimum real-time user load demand, XmaxThe maximum real-time user load demand.
Further, the electric retailer profit expectation function is expressed by the following formula:
Figure BDA0003250968740000031
wherein EP is the profit of the Power retailer, XminFor minimum real-time user load demand, XmaxFor maximum real-time customer load demand, P is the profit of the electricity retailer, xRTFor the real-time market clearing of the electricity transaction amount,
Figure BDA0003250968740000032
a distribution function for real-time user load demand;
the electricity retailer profit objective desired value is calculated by the following formula:
EP*＝(p-π)EXRT-Vσ·σ；
among them, EP*For the profit target expectation of the power retailer, p is the retail price information of the power retailer, pi is the price information of the day-ahead market, EXRTFor real-time electricity retailer profits, Vσσ is the weight, which is the information value rate.
The second aspect of the present invention provides a load prediction information value rate evaluation system based on kernel density estimation, including:
the double-model establishing module is used for respectively establishing a day-ahead market electric power transaction cost model and a real-time market electric power transaction profit model according to day-ahead market data and real-time market data;
the profit model establishing module of the electric power retailer is used for establishing a profit model of the electric power retailer according to the electric power trading cost model of the day-ahead market and the electric power trading profit model of the real-time market;
the real-time user load demand distribution function calculation module is used for fitting to obtain a real-time user load demand distribution function based on the real-time user load demand;
the profit expectation calculation module is used for calculating a profit expectation function of the electric power retailer and a profit target expectation value of the electric power retailer according to the real-time user load demand distribution function and the profit model of the electric power retailer;
the load prediction information value rate calculation module is used for calculating and obtaining the load prediction information value rate by combining the profit expectation function of the electric power retailer and the profit target expectation value of the electric power retailer through a kernel density estimation method;
and the judging module is used for measuring and calculating according to the load prediction information value rate and the information value rate of the electric power retailer, so that the load prediction information value rate meets a preset threshold value.
Further, the day-ahead market electricity trading cost model is expressed by the following formula:
CDA＝πXDA；
wherein, CDAFor the cost of the power trade in the day-ahead market, pi is the price information of the day-ahead market, XDAThe electric power trading volume cleared for the market in the day ahead;
the real-time market electric power trading profit model is expressed by the following formula:
Figure BDA0003250968740000041
wherein, PRTProfit for real-time market electricity trade, p is price information for retail of electricity retailers, xRTElectric power trade volume, X, cleared for real-time marketDAElectric power trade volume, lambda, cleared for the day-ahead market+Maximum price, lambda, for a real-time market-Minimum price for real-time market, XminFor minimum real-time user load demand, XmaxThe maximum real-time user load demand.
Further, the profit model of the electricity retailer is expressed by the following formula:
Figure BDA0003250968740000042
where P is the profit of the electricity retailer, PRTProfit for real-time market power trading, CDAFor the cost of the power trade in the market at the day-ahead, p is the price information for the retail sale of the power retailer, xRTClearing the electric power trade volume for the real-time market, wherein pi is the price information of the day-ahead market, XDAElectric power trade volume, lambda, cleared for the day-ahead market+Maximum price, lambda, for a real-time market-Minimum price for real-time market, XDAElectric power trade volume, X, cleared for the day-ahead marketminFor minimum real-time user load demand, XmaxThe maximum real-time user load demand.
Further, the electric retailer profit expectation function is expressed by the following formula:
Figure BDA0003250968740000051
wherein EP is the profit of the Power retailer, XminFor minimum real-time user load demand, XmaxFor maximum real-time customer load demand, P is the profit of the electricity retailer, xRTFor the real-time market clearing of the electricity transaction amount,
Figure BDA0003250968740000052
a distribution function for real-time user load demand;
the electricity retailer profit objective desired value is calculated by the following formula:
EP*＝(p-π)EXRT-Vσ·σ；
among them, EP*For the profit target expectation of the power retailer, p is the retail price information of the power retailer, pi is the price information of the day-ahead market, EXRTFor real-time electricity retailer profits, Vσσ is the weight, which is the information value rate.
A third aspect of the present invention provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the load prediction information value rate evaluation method based on kernel density estimation according to any one of the first aspect.
A fourth aspect of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, where when the computer program runs, a device in which the computer-readable storage medium is located is controlled to execute the load prediction information value rate evaluation method based on kernel density estimation according to any one of the first aspects.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
the invention provides a load prediction information value rate evaluation method and system based on kernel density estimation, wherein the method comprises the following steps: respectively establishing a day-ahead market electric power transaction cost model and a real-time market electric power transaction profit model according to day-ahead market data and real-time market data; establishing a profit model of the electric power retailer according to the day-ahead market electric power transaction cost model and the real-time market electric power transaction profit model; fitting to obtain a real-time user load demand distribution function based on the real-time user load demand; calculating to obtain a profit expectation function of the electric power retailer and a profit target expectation value of the electric power retailer according to the real-time user load demand distribution function and the profit model of the electric power retailer; calculating to obtain a load prediction information value rate by a kernel density estimation method in combination with the profit expectation function of the electric power retailer and the profit target expectation value of the electric power retailer; and measuring and calculating according to the load prediction information value rate and the information value rate of the electric power retailer, so that the load prediction information value rate meets a preset threshold value. The method can be applied to information transaction based on electric power market transaction, uncertainty is depicted and fitted based on kernel density estimation, and the influence of the uncertainty of electric power resources on the electric power retailer electricity purchasing and selling transaction profits is measured according to kernel functions and fitting distribution of the kernel functions, so that the information value rate is estimated, the accuracy can reach 95% when the calculated information value rate is compared with the actual information value rate, and the electric power retailer can be effectively guided to participate in the information transaction.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a load prediction information value rate evaluation method based on kernel density estimation according to an embodiment of the present invention;
FIG. 2 is a diagram of an apparatus of a system for load forecasting worth of information rate assessment based on kernel density estimation according to an embodiment of the present invention;
fig. 3 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be understood that the step numbers used herein are for convenience of description only and are not intended as limitations on the order in which the steps are performed.
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 the specification of the present invention 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 terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to and includes any and all possible combinations of one or more of the associated listed items.
A first aspect.
Referring to fig. 1, an embodiment of the present invention provides a method for evaluating load prediction information value rate based on kernel density estimation, including:
and S10, respectively establishing a day-ahead market electric power trading cost model and a real-time market electric power trading profit model according to the day-ahead market data and the real-time market data.
Preferably, the day-ahead market electricity trading cost model is expressed by the following formula:
CDA＝πXDA；
wherein, CDAFor the cost of the power trade in the day-ahead market, pi is the price information of the day-ahead market, XDAThe electric power trading volume cleared for the market in the day ahead;
the real-time market electric power trading profit model is expressed by the following formula:
Figure BDA0003250968740000081
wherein, PRTFor real-time market power trade profit, p is the power retailerRetail price information, xRTElectric power trade volume, X, cleared for real-time marketDAElectric power trade volume, lambda, cleared for the day-ahead market+Maximum price, lambda, for a real-time market-Minimum price for real-time market, XminFor minimum real-time user load demand, XmaxThe maximum real-time user load demand.
And S20, establishing a profit model of the electric power retailer according to the day-ahead market electric power transaction cost model and the real-time market electric power transaction profit model.
Preferably, the profit model of the electricity retailer is expressed by the following formula:
Figure BDA0003250968740000082
where P is the profit of the electricity retailer, PRTProfit for real-time market power trading, CDAFor the cost of the power trade in the market at the day-ahead, p is the price information for the retail sale of the power retailer, xRTClearing the electric power trade volume for the real-time market, wherein pi is the price information of the day-ahead market, XDAElectric power trade volume, lambda, cleared for the day-ahead market+Maximum price, lambda, for a real-time market-Minimum price for real-time market, XDAElectric power trade volume, X, cleared for the day-ahead marketminFor minimum real-time user load demand, XmaxThe maximum real-time user load demand.
And S30, fitting to obtain a distribution function of the real-time user load demand based on the real-time user load demand.
And S40, calculating to obtain a profit expectation function of the electric power retailer and a profit target expectation value of the electric power retailer according to the real-time user load demand distribution function and the profit model of the electric power retailer.
Preferably, the electric power retailer profit expectation function is expressed by the following formula:
Figure BDA0003250968740000083
wherein EP is the profit of the Power retailer, XminFor minimum real-time user load demand, XmaxFor maximum real-time customer load demand, P is the profit of the electricity retailer, xRTFor the real-time market clearing of the electricity transaction amount,
Figure BDA0003250968740000091
a distribution function for real-time user load demand;
the electricity retailer profit objective desired value is calculated by the following formula:
EP*＝(p-π)EXRT-Vσ·σ；
among them, EP*For the profit target expectation of the power retailer, p is the retail price information of the power retailer, pi is the price information of the day-ahead market, EXRTFor real-time electricity retailer profits, Vσσ is the weight, which is the information value rate.
And S50, calculating to obtain the load prediction information value rate by a kernel density estimation method and combining the profit expectation function of the electric power retailer and the profit target expectation value of the electric power retailer.
And S60, calculating according to the load prediction information value rate and the information value rate of the electric power retailer, so that the load prediction information value rate meets a preset threshold value.
The method can be applied to information transaction based on electric power market transaction, uncertainty is depicted and fitted based on kernel density estimation, and the influence of the uncertainty of electric power resources on the electric power retailer electricity purchasing and selling transaction profits is measured according to kernel functions and fitting distribution of the kernel functions, so that the information value rate is estimated, the accuracy can reach 95% when the calculated information value rate is compared with the actual information value rate, and the electric power retailer can be effectively guided to participate in the information transaction.
In another specific embodiment of the invention, the invention provides a load prediction information value rate evaluation method based on nuclear density estimation, which is based on the scene that an electric power retailer participates in wholesale and retail electric power market for purchasing and selling electricity, and firstly, a double-settlement market system generally applied in electric power market transaction is modeled; secondly, considering that the electric power retailer needs to predict and bid the predicted real-time electricity consumption of the proxied user, the uncertainty of the part of the electricity is modeled into the probability density distribution of random variables; and finally, fitting the distribution of the uncertainty variable through kernel density estimation, and obtaining the value rate measurement of the load prediction information according to the fitted approximate distribution. The method can be applied to information transaction based on electric power market transaction, and helps electric power retailers to obtain information value rate data with the accuracy of 95% obtained through standardized information value evaluation. The method specifically comprises the following steps:
1) the method comprises the following steps of establishing profit models of electric power retailers in the electric power market double-settlement system, wherein the profit models respectively comprise:
1.1) the cost of electricity retailers to participate in the purchase of electricity in the market at the present day;
according to price information pi of the day-ahead market and the cleared electric power transaction amount X of the day-ahead marketDACalculating the electricity transaction cost in the market in the day ahead:
CDA＝πXDA (1)
1.2) the profit of the electricity retailer participating in the real-time market electricity purchase and sale;
according to the retail price information p of the electric power retailer, the price information lambda of the real-time market and the cleared electric power transaction amount X of the day-ahead marketDAElectric power trading volume x cleared from real-time marketRTThe difference, calculate the power trading profit in the real-time market:
Figure BDA0003250968740000101
wherein, XminFor the smallest possible real-time user load demand, XmaxThe maximum possible real-time user load demand. In addition, to ensure power system power balance, if xRT<XDAThen the electricity trading entity needs to be in the equilibrium market at a lower priceLattice lambda+Selling excessive predetermined quantity of electricity XDA-xRT(ii) a If xRT>XDAThen the electricity trading entity needs to be in the equilibrium market at a higher price λ-Buying the shortage of actual quantity of electricity xRT-XDA。
2) Modeling and distribution fitting the uncertainty of the power resource:
for power retailers, power resources primarily include real-time customer load demand with uncertainty, etc. Assume a value x of real-time user load demandRTObey a distribution, which is noted
Figure BDA0003250968740000102
The cumulative distribution function and its inverse of the distribution are noted
Figure BDA0003250968740000103
And
Figure BDA0003250968740000104
however, since the electric retailer can only obtain a sample of the distribution, to more accurately fit the distribution, an appropriate kernel function is selected, and thus the fitted distribution f is obtained by means of kernel density estimation0(xRT) The cumulative distribution function of the distribution and its inverse are denoted F0(xRT) And
Figure BDA0003250968740000111
3) calculating the information value rate corresponding to the kernel function:
according to the model of electricity purchasing and selling transactions of electricity retailers participating in wholesale and retail electricity markets, the profits of the electricity retailers can be obtained as follows:
Figure BDA0003250968740000112
given the uncertainty in the real-time customer load demand faced by the power retailer, the power retailer's profit should be measured in terms of the expected value, namely:
Figure BDA0003250968740000113
overcoming uncertainty to achieve optimal electricity purchases in the day-ahead electricity trading market is a primary task for electricity retailers. With no change in the uncertainty distribution shape of the real-time customer load demand, the optimal expected profit for the electricity retailer can be expressed as:
Figure BDA0003250968740000114
wherein, VσThat is, the information value rate, which represents a decrease in the standard deviation of the distribution per unit uncertainty can be calculated as an increase in the expected profit to the electricity retailer, by the following equation.
Figure BDA0003250968740000115
We select Box kernel function, Gaussian kernel function, Epanechnikov kernel function as the alternatives of kernel function, and calculate the corresponding information value rate expressions of various kernel functions according to the above formulas, as shown in Table 1:
TABLE 1
Figure BDA0003250968740000116
Figure BDA0003250968740000121
Wherein x issFor the location parameter of the kernel function, h is the bandwidth of the kernel function, i.e. the shape parameter of the kernel function, and the optimal value is usually determined in the process of kernel density estimation using the kernel function.
4) Calculating the information value rate corresponding to the distribution obtained by the kernel density estimation fitting:
the distribution obtained by fitting the kernel density estimate is obtained by adding several kernel functions, namely:
Figure BDA0003250968740000122
wherein the content of the first and second substances,
Figure BDA0003250968740000123
for kernel functions of the same type, different location parameters and the same bandwidth, h*Is the optimum bandwidth of the kernel function.
The information value rate corresponding to the distribution obtained by kernel density estimation fitting can also be obtained by properly adding the information value rates corresponding to each kernel function, that is:
Figure BDA0003250968740000124
thus, for an uncertainty distribution of real-time customer load demand by an electricity retailer, if the information obtained by the electricity retailer can eliminate a standard deviation of a certain amount of uncertainty distribution, then the improvement in the optimal expected profit can be obtained directly from the above-described information value rate.
5) Based on the calculated load prediction information value rate, the electric power retailer can obtain approximate information value rate, and according to the measurement and calculation of actual data, the accuracy of the information value rate calculated by applying the model of the electric power retailer in the electric power market transaction and the load prediction error fitting analysis method can reach 95%, so that the guidance effect of information transaction of the electric power retailer can be achieved.
The method can be applied to information transaction based on electric power market transaction, uncertainty is depicted and fitted based on kernel density estimation, and influence of uncertainty of electric power resources on electric power retailer electricity purchasing and selling transaction profits is measured according to kernel functions and fitting distribution of the kernel functions, so that evaluation of information value rate is achieved. Compared with the actual information value rate, the accuracy of the calculated information value rate can reach 95%, so that the electric power retailer can be effectively guided to participate in information transaction.
A second aspect.
Referring to fig. 2, an embodiment of the present invention provides a system for evaluating load forecast information value rate based on kernel density estimation, including:
the double model establishing module 10 is used for respectively establishing a day-ahead market electric power trading cost model and a real-time market electric power trading profit model according to day-ahead market data and real-time market data.
Preferably, the day-ahead market electricity trading cost model is expressed by the following formula:
CDA＝πXDA；
wherein, CDAFor the cost of the power trade in the day-ahead market, pi is the price information of the day-ahead market, XDAThe electric power trading volume cleared for the market in the day ahead;
the real-time market electric power trading profit model is expressed by the following formula:
Figure BDA0003250968740000131
wherein, PRTProfit for real-time market electricity trade, p is price information for retail of electricity retailers, xRTElectric power trade volume, X, cleared for real-time marketDAElectric power trade volume, lambda, cleared for the day-ahead market+Maximum price, lambda, for a real-time market-Minimum price for real-time market, XminFor minimum real-time user load demand, XmaxThe maximum real-time user load demand.
And the profit model establishing module 20 of the electric power retailer is used for establishing a profit model of the electric power retailer according to the electric power trading cost model of the day-ahead market and the electric power trading profit model of the real-time market.
Preferably, the profit model of the electricity retailer is expressed by the following formula:
Figure BDA0003250968740000141
where P is the profit of the electricity retailer, PRTProfit for real-time market power trading, CDAFor the cost of the power trade in the market at the day-ahead, p is the price information for the retail sale of the power retailer, xRTClearing the electric power trade volume for the real-time market, wherein pi is the price information of the day-ahead market, XDAElectric power trade volume, lambda, cleared for the day-ahead market+Maximum price, lambda, for a real-time market-Minimum price for real-time market, XDAElectric power trade volume, X, cleared for the day-ahead marketminFor minimum real-time user load demand, XmaxThe maximum real-time user load demand.
And the real-time user load demand distribution function calculation module 30 is configured to fit to obtain a real-time user load demand distribution function based on the real-time user load demand.
And the profit expectation calculation module 40 is used for calculating a profit expectation function of the electric power retailer and a profit target expectation value of the electric power retailer according to the real-time user load demand distribution function and the profit model of the electric power retailer.
Preferably, the electric power retailer profit expectation function is expressed by the following formula:
Figure BDA0003250968740000142
wherein EP is the profit of the Power retailer, XminFor minimum real-time user load demand, XmaxFor maximum real-time customer load demand, P is the profit of the electricity retailer, xRTFor the real-time market clearing of the electricity transaction amount,
Figure BDA0003250968740000143
a distribution function for real-time user load demand;
the electricity retailer profit objective desired value is calculated by the following formula:
EP*＝(p-π)EXRT-Vσ·σ；
among them, EP*For the profit target expectation of the power retailer, p is the retail price information of the power retailer, pi is the price information of the day-ahead market, EXRTFor real-time electricity retailer profits, Vσσ is the weight, which is the information value rate.
And the load prediction information value rate calculation module 50 is used for calculating the load prediction information value rate by combining the profit expectation function of the electric power retailer and the profit target expectation value of the electric power retailer through a kernel density estimation method.
And the judging module 60 is configured to measure and calculate according to the load prediction information value rate and the information value rate of the electric power retailer, so that the load prediction information value rate meets a preset threshold.
The method can be applied to information transaction based on electric power market transaction, uncertainty is depicted and fitted based on kernel density estimation, and the influence of the uncertainty of electric power resources on the electric power retailer electricity purchasing and selling transaction profits is measured according to kernel functions and fitting distribution of the kernel functions, so that the information value rate is estimated, the accuracy can reach 95% when the calculated information value rate is compared with the actual information value rate, and the electric power retailer can be effectively guided to participate in the information transaction.
In a third aspect.
The present invention provides an electronic device, including:
a processor, a memory, and a bus;
the bus is used for connecting the processor and the memory;
the memory is used for storing operation instructions;
the processor is configured to invoke the operation instruction, and the executable instruction enables the processor to perform an operation corresponding to the load prediction information value rate evaluation method based on kernel density estimation as shown in the first aspect of the present application.
In an alternative embodiment, an electronic device is provided, as shown in fig. 3, the electronic device 5000 shown in fig. 3 includes: a processor 5001 and a memory 5003. The processor 5001 and the memory 5003 are coupled, such as via a bus 5002. Optionally, the electronic device 5000 may also include a transceiver 5004. It should be noted that the transceiver 5004 is not limited to one in practical application, and the structure of the electronic device 5000 is not limited to the embodiment of the present application.
The processor 5001 may be a CPU, general purpose processor, DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 5001 may also be a combination of processors implementing computing functionality, e.g., a combination comprising one or more microprocessors, a combination of DSPs and microprocessors, or the like.
Bus 5002 can include a path that conveys information between the aforementioned components. The bus 5002 may be a PCI bus or EISA bus, etc. The bus 5002 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 3, but this does not mean only one bus or one type of bus.
The memory 5003 may be, but is not limited to, a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, an EEPROM, a CD-ROM or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 5003 is used for storing application program codes for executing the present solution, and the execution is controlled by the processor 5001. The processor 5001 is configured to execute application program code stored in the memory 5003 to implement the teachings of any of the foregoing method embodiments.
Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like.
A fourth aspect.
The invention provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements a load prediction information value rate evaluation method based on kernel density estimation as shown in the first aspect of the present application.
Yet another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, which, when run on a computer, enables the computer to perform the corresponding content in the aforementioned method embodiments.

Claims (10)

1. A load prediction information value rate evaluation method based on kernel density estimation is characterized by comprising the following steps:
respectively establishing a day-ahead market electric power transaction cost model and a real-time market electric power transaction profit model according to day-ahead market data and real-time market data;
establishing a profit model of the electric power retailer according to the day-ahead market electric power transaction cost model and the real-time market electric power transaction profit model;
fitting to obtain a real-time user load demand distribution function based on the real-time user load demand;
calculating to obtain a profit expectation function of the electric power retailer and a profit target expectation value of the electric power retailer according to the real-time user load demand distribution function and the profit model of the electric power retailer;
calculating to obtain a load prediction information value rate by a kernel density estimation method in combination with the profit expectation function of the electric power retailer and the profit target expectation value of the electric power retailer;
and measuring and calculating according to the load prediction information value rate and the information value rate of the electric power retailer, so that the load prediction information value rate meets a preset threshold value.
2. The method of claim 1, wherein the load forecast information value rate evaluation method based on kernel density estimation,
the day-ahead market electricity trading cost model is expressed by the following formula:
CDA＝πXDA；
wherein, CDAFor the cost of the power trade in the day-ahead market, pi is the price information of the day-ahead market, XDAThe electric power trading volume cleared for the market in the day ahead;
the real-time market electric power trading profit model is expressed by the following formula:
Figure FDA0003250968730000011
wherein, PRTProfit for real-time market electricity trade, p is price information for retail of electricity retailers, xRTElectric power trade volume, X, cleared for real-time marketDAElectric power trade volume, lambda, cleared for the day-ahead market+Maximum price, lambda, for a real-time market-Minimum price for real-time market, XminFor minimum real-time user load demand, XmaxThe maximum real-time user load demand.
3. The load forecast information value rate assessment method based on kernel density estimation as claimed in claim 1, wherein said electricity retailer profit model is expressed by the following formula:
Figure FDA0003250968730000021
where P is the profit of the electricity retailer, PRTIn real timeProfit of market Power trade, CDAFor the cost of the power trade in the market at the day-ahead, p is the price information for the retail sale of the power retailer, xRTClearing the electric power trade volume for the real-time market, wherein pi is the price information of the day-ahead market, XDAElectric power trade volume, lambda, cleared for the day-ahead market+Maximum price, lambda, for a real-time market-Minimum price for real-time market, XDAElectric power trade volume, X, cleared for the day-ahead marketminFor minimum real-time user load demand, XmaxThe maximum real-time user load demand.
4. The load forecast information value rate assessment method based on kernel density estimation as claimed in claim 1, wherein said electricity retailer profit expectation function is expressed by the following formula:
Figure FDA0003250968730000022
wherein EP is the profit of the Power retailer, XminFor minimum real-time user load demand, XmaxFor maximum real-time customer load demand, P is the profit of the electricity retailer, xRTAmount of electric power trade cleared for real-time market, fX RT(xRT) A distribution function for real-time user load demand;
the electricity retailer profit objective desired value is calculated by the following formula:
EP*＝(p-π)EXRT-Vσ·σ；
among them, EP*For the profit target expectation of the power retailer, p is the retail price information of the power retailer, pi is the price information of the day-ahead market, EXRTFor real-time electricity retailer profits, Vσσ is the weight, which is the information value rate.
5. A load prediction information value rate evaluation system based on kernel density estimation is characterized by comprising:
the double-model establishing module is used for respectively establishing a day-ahead market electric power transaction cost model and a real-time market electric power transaction profit model according to day-ahead market data and real-time market data;
the profit model establishing module of the electric power retailer is used for establishing a profit model of the electric power retailer according to the electric power trading cost model of the day-ahead market and the electric power trading profit model of the real-time market;
the real-time user load demand distribution function calculation module is used for fitting to obtain a real-time user load demand distribution function based on the real-time user load demand;
the profit expectation calculation module is used for calculating a profit expectation function of the electric power retailer and a profit target expectation value of the electric power retailer according to the real-time user load demand distribution function and the profit model of the electric power retailer;
the load prediction information value rate calculation module is used for calculating and obtaining the load prediction information value rate by combining the profit expectation function of the electric power retailer and the profit target expectation value of the electric power retailer through a kernel density estimation method;
and the judging module is used for measuring and calculating according to the load prediction information value rate and the information value rate of the electric power retailer, so that the load prediction information value rate meets a preset threshold value.
6. The load prediction information value rate assessment system based on kernel density estimation as claimed in claim 5,
the day-ahead market electricity trading cost model is expressed by the following formula:
CDA＝πXDA；
wherein, CDAFor the cost of the power trade in the day-ahead market, pi is the price information of the day-ahead market, XDAThe electric power trading volume cleared for the market in the day ahead;
the real-time market electric power trading profit model is expressed by the following formula:
Figure FDA0003250968730000041
wherein, PRTProfit for real-time market electricity trade, p is price information for retail of electricity retailers, xRTElectric power trade volume, X, cleared for real-time marketDAElectric power trade volume, lambda, cleared for the day-ahead market+Maximum price, lambda, for a real-time market-Minimum price for real-time market, XminFor minimum real-time user load demand, XmaxThe maximum real-time user load demand.
7. The load forecast information value rate evaluation system based on kernel density estimation of claim 5, wherein said electricity retailer profit model is expressed by the following formula:
Figure FDA0003250968730000042
where P is the profit of the electricity retailer, PRTProfit for real-time market power trading, CDAFor the cost of the power trade in the market at the day-ahead, p is the price information for the retail sale of the power retailer, xRTClearing the electric power trade volume for the real-time market, wherein pi is the price information of the day-ahead market, XDAElectric power trade volume, lambda, cleared for the day-ahead market+Maximum price, lambda, for a real-time market-Minimum price for real-time market, XDAElectric power trade volume, X, cleared for the day-ahead marketminFor minimum real-time user load demand, XmaxThe maximum real-time user load demand.
8. The load forecast information value rate evaluation system based on kernel density estimation of claim 5, wherein said electricity retailer profit expectation function is expressed by the following formula:
Figure FDA0003250968730000051
wherein EP is the profit of the Power retailer, XminFor minimum real-time user load demand, XmaxFor maximum real-time customer load demand, P is the profit of the electricity retailer, xRTAmount of electric power trade cleared for real-time market, fX RT(xRT) A distribution function for real-time user load demand;
the electricity retailer profit objective desired value is calculated by the following formula:
EP*＝(p-π)EXRT-Vσ·σ；
among them, EP*For the profit target expectation of the power retailer, p is the retail price information of the power retailer, pi is the price information of the day-ahead market, EXRTFor real-time electricity retailer profits, Vσσ is the weight, which is the information value rate.
9. An electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the method for load prediction information value rate assessment based on kernel density estimation according to any one of claims 1 to 4.
10. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program runs, the computer-readable storage medium controls a device to execute the load prediction information value rate assessment method based on kernel density estimation according to any one of claims 1 to 4.
CN202111045387.9A 2021-09-07 2021-09-07 Load prediction information value rate evaluation method and system based on kernel density estimation Pending CN113763047A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111045387.9A CN113763047A (en) 2021-09-07 2021-09-07 Load prediction information value rate evaluation method and system based on kernel density estimation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111045387.9A CN113763047A (en) 2021-09-07 2021-09-07 Load prediction information value rate evaluation method and system based on kernel density estimation

Publications (1)

Publication Number Publication Date
CN113763047A true CN113763047A (en) 2021-12-07

Family

ID=78793661

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111045387.9A Pending CN113763047A (en) 2021-09-07 2021-09-07 Load prediction information value rate evaluation method and system based on kernel density estimation

Country Status (1)

Country Link
CN (1) CN113763047A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106875211A (en) * 2017-01-06 2017-06-20 华东师范大学 Optimal service pricing method based on user's perceived value in a kind of cloud computing environment
US20190265768A1 (en) * 2018-02-24 2019-08-29 Hefei University Of Technology Method, system and storage medium for predicting power load probability density based on deep learning
CN111553750A (en) * 2020-05-12 2020-08-18 太原理工大学 Energy storage bidding strategy method considering power price uncertainty and loss cost

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106875211A (en) * 2017-01-06 2017-06-20 华东师范大学 Optimal service pricing method based on user's perceived value in a kind of cloud computing environment
US20190265768A1 (en) * 2018-02-24 2019-08-29 Hefei University Of Technology Method, system and storage medium for predicting power load probability density based on deep learning
CN111553750A (en) * 2020-05-12 2020-08-18 太原理工大学 Energy storage bidding strategy method considering power price uncertainty and loss cost

Similar Documents

Publication Publication Date Title
Krippner Measuring the stance of monetary policy in zero lower bound environments
Calza et al. Sectoral money demand and the great disinflation in the United States
Gerakos et al. Audit firms face downward-sloping demand curves and the audit market is far from perfectly competitive
JP2006331229A (en) Power transaction support system, method thereof, and program thereof
US20080208788A1 (en) Method and system for predicting customer wallets
Chen Policy failure or success? Detecting market failure in China's housing market
CN109191205A (en) A kind of price calculation method and terminal device based on prediction model
Chen et al. Herding and capitalization size in the Chinese stock market: a micro-foundation evidence
JP5084968B1 (en) Market risk prediction apparatus, market risk prediction method, and market risk prediction program
Simaitis et al. Smile and default: the role of stochastic volatility and interest rates in counterparty credit risk
CN113344689A (en) Financial data processing method, device and equipment
US20090240557A1 (en) Method, apparatus and computer program product for valuing a technological innovation
CN113763047A (en) Load prediction information value rate evaluation method and system based on kernel density estimation
Bai et al. Automated triangular arbitrage:: A trading algorithm for foreign exchange on a cryptocurrency market
KR102589568B1 (en) Apparatus and method for automated peer to peer energy trading brokerage
JP2016170468A (en) Electric power transaction amount determination system, electric power transaction amount determination method and program
CN113592263A (en) Resource return increment prediction method and device based on dynamic resource return increase ratio
Issa et al. Graphics performance analysis using Amdahl's law
JP5105653B1 (en) Market risk prediction device, hedge quantity calculation method, and hedge quantity calculation program
Coey et al. The simple empirics of optimal online auctions
CN113743787B (en) Information importance assessment method and system based on distribution standard deviation
Yin et al. Multi-agent based simulation of negotiate pricing process in B2C
Lai et al. International protection of intellectual property: An empirical investigation
KR102569395B1 (en) Data broker device of competitive data trading system and operating method thereof
KR102569394B1 (en) Service providing device of competitive data trading system and operating method thereof

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