CN112308337A - Prediction method, prediction device and processor for probabilistic short-term load of power system - Google Patents
Prediction method, prediction device and processor for probabilistic short-term load of power system Download PDFInfo
- Publication number
- CN112308337A CN112308337A CN202011308426.5A CN202011308426A CN112308337A CN 112308337 A CN112308337 A CN 112308337A CN 202011308426 A CN202011308426 A CN 202011308426A CN 112308337 A CN112308337 A CN 112308337A
- Authority
- CN
- China
- Prior art keywords
- probabilistic
- quantile
- power system
- prediction
- load
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000003860 storage Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 9
- 239000000126 substance Substances 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000012935 Averaging Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000001308 synthesis method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a prediction method, a prediction device and a processor of a probabilistic short-term load of a power system. The method includes constructing a plurality of probabilistic load prediction models based on the power system, each probabilistic load prediction model corresponding to a plurality of quantiles; determining the weight of each quantile; obtaining a comprehensive prediction model according to the weight of each quantile and each probabilistic load prediction model; and predicting the short-term load of the power system according to the comprehensive prediction model. The comprehensive prediction model can realize accurate prediction of the short-term load of the power system, and is not only suitable for the power system under the influence of extreme factors, but also suitable for the power system under the influence of non-extreme factors. The problems that the application range of the load prediction method is small and the prediction precision is low are solved.
Description
Technical Field
The present application relates to the field of power load prediction, and in particular, to a method, a device, a computer-readable storage medium, and a processor for predicting a probabilistic short-term load of a power system.
Background
At present, the accuracy of weather prediction is reduced due to sudden climate change, the accuracy of power grid load prediction is further influenced, the power grid load characteristic change which is difficult to predict and is caused by rapidly-increased distributed photovoltaic output, coal-to-electricity and other loads are overlapped with various interference factors influencing the day-ahead load prediction accuracy, and the traditional load prediction methods such as 'regression/extrapolation' and 'neural network' are more and more difficult to be applied to the existing day-ahead load prediction work.
At home, the current load prediction research work mainly focuses on prediction methods, including a grey prediction method, a regression analysis method, a time series method, an artificial intelligence method and the like. However, the conventional load prediction method has a small application range and low prediction accuracy.
Disclosure of Invention
The present application mainly aims to provide a method, a device, a computer-readable storage medium, and a processor for predicting a probabilistic short-term load of a power system, so as to solve the problems of a small application range and a low prediction accuracy of the conventional load prediction method in the prior art.
In order to achieve the above object, according to an aspect of the present application, there is provided a method for predicting a probabilistic short-term load of a power system, including: constructing a plurality of probabilistic load prediction models based on a power system, each of the probabilistic load prediction models corresponding to a plurality of quantiles; determining the weight of each quantile; obtaining a comprehensive prediction model according to the weight of each quantile and each probabilistic load prediction model; and predicting the short-term load of the power system according to the comprehensive prediction model.
Further, in case each single probabilistic load prediction model has the same weight for all quantiles, the comprehensive prediction model for quantile q is represented as:
wherein f isn,qRepresenting the nth said probabilistic load prediction model for quantile q, Xn,tInputs representing the regression model at time t, including historical load data, day of work variables and weather conditions, Wn,qParameter, ω, of the nth regression model representing the quantile qnRepresenting weights of an nth one of the probabilistic load prediction models.
Further, in case each single probabilistic load prediction model is not weighted equally for all quantiles, the comprehensive prediction model for quantile q is represented as:
wherein f isn,qRepresenting the nth said probabilistic load prediction model for quantile q, Xn,tInputs representing regression models at time t, including historical load data, and working diurnal variationsVolume and weather conditions, Wn,qParameter, ω, of the nth regression model representing the quantile qn,qA weight representing the nth probabilistic load prediction model quantile q.
Further, for ωnThe estimation method is expressed by a formula I, wherein the formula I is as follows:
wherein the content of the first and second substances,represents omeganEstimated value of, Ln,t,qRepresenting the quantile loss.
Further, for ωn,qThe estimation method of (2) is expressed by a formula two, which is:
wherein the content of the first and second substances,shows omegan,qEstimated value of, Ln,t,qRepresenting the quantile loss.
Further, optimizing the formula one to obtain a formula three, wherein the formula three is expressed as:
wherein, ytRepresenting the time t, the true value of the short-term load of the power system,a predicted value of the short-term load of the power system corresponding to the quantile q at time t,are aid decision variables.
Further, optimizing the formula three to obtain a formula four, wherein the formula four is expressed as:
according to another aspect of the present application, there is provided a prediction apparatus of a probabilistic short-term load of a power system, comprising: a construction unit configured to construct a plurality of probabilistic load prediction models based on a power system, each of the probabilistic load prediction models corresponding to a plurality of quantiles; a determining unit configured to determine a weight of each of the quantiles; the processing unit is used for obtaining a comprehensive prediction model according to the weight of each quantile and each probabilistic load prediction model; and the prediction unit is used for predicting the short-term load of the power system according to the comprehensive prediction model.
According to yet another aspect of the application, a computer-readable storage medium is provided, comprising a stored program, wherein the program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform any one of the methods for predicting probabilistic short-term load of an electric power system.
According to yet another aspect of the application, a processor is provided for running a program, wherein the program is run to perform any one of the methods for predicting probabilistic short-term load of an electric power system.
By applying the technical scheme of the application, a plurality of probabilistic load prediction models are built based on the power system, and the comprehensive prediction model is determined according to the quantiles corresponding to the probabilistic load prediction models and the weight of each quantile. The problems that the application range of the load prediction method is small and the prediction precision is low are solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
FIG. 1 illustrates a flow diagram of a method of predicting a probabilistic short-term load of a power system according to an embodiment of the application;
fig. 2 shows a schematic diagram of a prediction apparatus for probabilistic short term loading of a power system according to an embodiment of the application.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
It will be understood that when an element such as a layer, film, region, or substrate is referred to as being "on" another element, it can be directly on the other element or intervening elements may also be present. Also, in the specification and claims, when an element is described as being "connected" to another element, the element may be "directly connected" to the other element or "connected" to the other element through a third element.
As described in the background art, the load prediction method in the prior art has a small application range and low prediction accuracy, and in order to solve the problem that the load prediction method has a small application range and low prediction accuracy, the present application provides a prediction method, a prediction apparatus, a computer-readable storage medium, and a processor for a probabilistic short-term load of a power system.
According to an embodiment of the application, a method of predicting a probabilistic short-term load of a power system is provided.
Fig. 1 is a flowchart of a method for predicting a probabilistic short-term load of a power system according to an embodiment of the present application. As shown in fig. 1, the method comprises the steps of:
step S101, constructing a plurality of probabilistic load prediction models based on a power system, wherein each probabilistic load prediction model corresponds to a plurality of quantiles;
step S102, determining the weight of each quantile;
step S103, obtaining a comprehensive prediction model according to the weight of each quantile and each probabilistic load prediction model;
and step S104, predicting the short-term load of the power system according to the comprehensive prediction model.
Specifically, the comprehensive prediction model obtained by integrating the plurality of probabilistic load prediction models according to the scheme is an optimal model and is suitable for predicting short-term loads of various power systems.
In the scheme, a plurality of probabilistic load prediction models are built based on the power system, and a comprehensive prediction model is determined according to the quantiles corresponding to the probabilistic load prediction models and the weight of each quantile. The problems that the application range of the load prediction method is small and the prediction precision is low are solved.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
Alternatively, in a case where the weights of each single probabilistic load prediction model for all the quantiles are the same, the comprehensive prediction model for the quantile q is expressed as:
wherein f isn,qDenotes the nth probabilistic load prediction model for the quantile q, Xn,tInputs representing regression models at time t, including historical load dataWorking day variables and weather conditions, Wn,qParameter, ω, of the nth regression model representing the quantile qnThe weight of the nth probabilistic load prediction model is shown.
Alternatively, in a case where the weights of each single probabilistic load prediction model for all the quantiles are not the same, the comprehensive prediction model of the quantile q is expressed as:
wherein f isn,qDenotes the nth probabilistic load prediction model for the quantile q, Xn,tInputs representing the regression model at time t, including historical load data, day of work variables and weather conditions, Wn,qParameter, ω, of the nth regression model representing the quantile qn,qAnd a weight representing the nth probabilistic load prediction model quantile q.
Alternatively, for ωnThe estimation method is expressed by a formula I, wherein the formula I is as follows:
Alternatively, for ωn,qThe estimation method is expressed by a formula two, wherein the formula two is as follows:
Optionally, the formula one is optimized to obtain a formula three, where the formula three is expressed as:
ytrepresenting the time t, the true value of the short-term load of the power system,a predicted value of the short-term load of the power system corresponding to the quantile q at time t,are aid decision variables.
Optionally, the formula three is optimized to obtain a formula four, where the formula four is expressed as:
it should be noted that the prediction apparatus for the probabilistic short-term load of the power system according to the embodiment of the present application may be used to execute the prediction method for the probabilistic short-term load of the power system according to the embodiment of the present application. The following describes a prediction device for a probabilistic short-term load of a power system according to an embodiment of the present application.
Fig. 2 is a schematic diagram of a prediction apparatus for a probabilistic short-term load of a power system according to an embodiment of the present application. As shown in fig. 2, the apparatus includes:
a construction unit 10 configured to construct a plurality of probabilistic load prediction models based on a power system, each of the probabilistic load prediction models corresponding to a plurality of quantiles;
a determining unit 20 for determining a weight of each of the quantiles;
a processing unit 30 configured to obtain a comprehensive prediction model based on the weight of each quantile and each probabilistic load prediction model;
and the prediction unit 40 is used for predicting the short-term load of the power system according to the comprehensive prediction model.
In the above scheme, the building unit builds a plurality of probabilistic load prediction models based on the power system, and determines a comprehensive prediction model according to a plurality of quantiles corresponding to each probabilistic load prediction model and the weight of each quantile, wherein the comprehensive prediction model can realize accurate prediction of short-term load of the power system, and is not only suitable for the power system under the influence of extreme factors, but also suitable for the power system under the influence of non-extreme factors. The problems that the application range of the load prediction method is small and the prediction precision is low are solved.
The device for predicting the probabilistic short-term load of the power system comprises a processor and a memory, wherein the constructing unit, the determining unit, the processing unit, the predicting unit and the like are stored in the memory as program units, and the program units stored in the memory are executed by the processor to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. One or more than one kernel can be set, and the problems of small application range and low prediction precision of the load prediction method are solved by adjusting kernel parameters.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
The embodiment of the invention provides a computer-readable storage medium, which comprises a stored program, wherein when the program runs, a device where the computer-readable storage medium is located is controlled to execute the method for predicting the probabilistic short-term load of the power system.
The embodiment of the invention provides a processor, wherein the processor is used for running a program, and the method for predicting the probabilistic short-term load of the power system is executed when the program runs.
The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein when the processor executes the program, at least the following steps are realized:
step S101, constructing a plurality of probabilistic load prediction models based on a power system, wherein each probabilistic load prediction model corresponds to a plurality of quantiles;
step S102, determining the weight of each quantile;
step S103, obtaining a comprehensive prediction model according to the weight of each quantile and each probabilistic load prediction model;
and step S104, predicting the short-term load of the power system according to the comprehensive prediction model.
The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program of initializing at least the following method steps when executed on a data processing device:
step S101, constructing a plurality of probabilistic load prediction models based on a power system, wherein each probabilistic load prediction model corresponds to a plurality of quantiles;
step S102, determining the weight of each quantile;
step S103, obtaining a comprehensive prediction model according to the weight of each quantile and each probabilistic load prediction model;
and step S104, predicting the short-term load of the power system according to the comprehensive prediction model.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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 apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
Examples
The embodiment relates to a method for predicting a probabilistic short-term load of a power system. The method specifically comprises the following parts:
(1) model construction
If the weight of each single model for all quantiles is the same, the probabilistic predictive optimal composite model for the quantile q can be expressed as follows:
the corresponding weight ω is estimated by solving the following optimization problem:
conversely, if each individual model weights a different quantile differently, the optimal composite model is represented as:
this section will focus on the predictive synthesis method for each quantile. For each quantile, the determination of the weight ω is converted to solve Q optimization problems, where the qth problem is:
(2) data splitting
Optimizing the weights directly using equations 2 and 4 may risk over-learning, and therefore a part of the validation set is partitioned from the original training set to reduce the risk of over-learning. The entire data set is then divided into four parts: the first part T1 is used to train a single model; the second part T2 is used to verify and adjust the hyper-parametric adjustments of each model; the third section T3 is used to test each individual model and the predicted results are used for model synthesis in equation 2 or equation 4 to reduce the risk of over-learning. The final section T4 was used to test the final predictive combinatorial model. Since the solving methods of equation 2 and equation 4 are the same, equation 2 is taken as an example to describe the model combination algorithm.
(3) Model synthesis
This subsection presents an algorithm for solving model synthetic optimization problems. A complete probability distribution cannot be obtained only from a limited number of quantiles, and therefore a certain quantile cannot be calculated by a weighted sum of several quantile distributions. The qquantile of the weighted sum of several distributions can be estimated simply by the weighted sum of the qquantiles of all distributions:
thus, the loss function in equation 2 can be rewritten as follows:
introducing an auxiliary decision variable for q quantile at t momentThe problem in equation 6 can be translated into:
without the last constraint in equation 7, the problem becomes a linear optimization (LP) problem. The model without the last constraint in equation 7 is denoted as the RLP model. The optimal solution for RLP can be shown in a back-proof way to be also the optimal solution for model equation 7:
if the optimal solution [ omega, v ] of RLP]The last constraint is not satisfied, then there is at least one quantile satisfiedAndand then another value v can be foundt′,q=vt,qε to satisfyOrWhere epsilon is a positive value. Then, [ omega, v']Rather than [ omega, v ]]Is the best solution for RLP.
Thus, the model (shown in equation 4) can be transformed into an LP problem with multiple T optimization variables and 2T constraints for approximate combined quantiles.
(4) Method comparison
This section presents nine methods for comparison with the method of this example, including simple ranking, median, simple averaging, weighted averaging, and three Quantile Regression Averaging (QRA) methods and two constraint-Containing Quantile Regression Averaging (CQRA) methods.
1) Simple ranking method (NS): each prediction model will produce Q quantiles, in the sense that N × Q quantiles can be obtained by N prediction models. By sorting these observations in descending order, a new sequence S can be obtainedt={St,j,j=[1,Q×N]}. The q quantile is therefore estimated as follows:
2) median Method (MED): selecting the median of all qth quantiles of the N models as the final quantile:
3) simple average method (SA): all the prediction models are simply weighted equally, and the final integrated model is then obtained according to equation 15:
wn,q1/N (formula 10)
4) Weighted average method (WA): the basic idea is that the higher the model prediction accuracy is, the greater the weight is given:
5) QRAE: as described above, the N prediction models produce N × Q quantiles. These quantiles can also be considered as N × Q point predictions, denoted SAt|1×(Q×N). The mean value S of the quantiles can then be calculatedEt|1×NWherein the mean value of quantile SEt,nThe elements of (d) are calculated as follows:
QRA-E applies linear quantile regression to the mean S of Q quantilesEt:
Further, the optimal weights are determined by minimizing the quantile loss function:
6) QRAA: in contrast to QRAE, QRAA does not perform QRA on the mean of the quantiles, but rather applies linear quantile regression directly to all quantiles to generate a new quantile SAt:
7) QRA-T: can also be selected from SAt,qQ target quantiles are selected for QRA. Target quantile STt,q|1×NThe following were chosen:
STt,q,n=SAt,Q×(n-1)+q(formula 16)
TABLE 1 various integrated models based on quantile regression averages
Table 1 summarizes various QRA methods in terms of whether there are constraints on whether the model weights are non-negative and sum to 1, and which quantiles are specifically considered.
The regression of QRA-E is the qth target quantile S, as compared to QRA-ATt,q:
8) CQRA-E: the addition of CQRA-E compared to QRA-E adds the constraint of non-negative weight and summing to 1:
9) CQRA-A: CQRA-A performs a constrained regression S on all quantiles compared to CQRA-EAt:
In conclusion, the optimal comprehensive model for probabilistic load prediction takes quantile loss as a core, and the optimal comprehensive model is converted into a linear optimization problem easy to solve, so that efficient solution is achieved, and the optimal comprehensive model shows better performance for load prediction under the condition of extreme factors.
Probabilistic predictions can provide boundary conditions for many stochastic optimization problems, and are also a measure of their uncertainty from a load modeling perspective. More regular load predictions tend to be more accurate and vice versa. Different prediction methods may yield different uncertainty measures as different "rules".
From the above description, it can be seen that the above-described embodiments of the present application achieve the following technical effects:
1) according to the method for predicting the probabilistic short-term load of the power system, a plurality of probabilistic load prediction models are built based on the power system, and the comprehensive prediction model is determined according to the corresponding quantiles of the probabilistic load prediction models and the weight of each quantile, so that the short-term load of the power system can be accurately predicted by the comprehensive prediction model, and the comprehensive prediction model is not only suitable for the power system under the influence of extreme factors, but also suitable for the power system under the influence of non-extreme factors. The problems that the application range of the load prediction method is small and the prediction precision is low are solved.
2) According to the device for predicting the probabilistic short-term load of the power system, the building unit builds a plurality of probabilistic load prediction models based on the power system, and determines the comprehensive prediction model according to the corresponding quantiles of the probabilistic load prediction models and the weight of each quantile, wherein the comprehensive prediction model can realize accurate prediction of the short-term load of the power system, and is not only suitable for the power system under the influence of extreme factors, but also suitable for the power system under the influence of non-extreme factors. The problems that the application range of the load prediction method is small and the prediction precision is low are solved.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A method for predicting a probabilistic short-term load of a power system, comprising:
constructing a plurality of probabilistic load prediction models based on a power system, each of the probabilistic load prediction models corresponding to a plurality of quantiles;
determining the weight of each quantile;
obtaining a comprehensive prediction model according to the weight of each quantile and each probabilistic load prediction model;
and predicting the short-term load of the power system according to the comprehensive prediction model.
2. The prediction method according to claim 1, characterized in that in case each single probabilistic load prediction model has the same weight for all quantiles, the comprehensive prediction model for a quantile q is represented as:
wherein the content of the first and second substances,fn,qrepresenting the nth said probabilistic load prediction model for quantile q, Xn,tInputs representing the regression model at time t, including historical load data, day of work variables and weather conditions, Wn,qParameter, ω, of the nth regression model representing the quantile qnRepresenting weights of an nth one of the probabilistic load prediction models.
3. The prediction method according to claim 1, wherein in case each single probabilistic load prediction model has a different weight for all quantiles, the comprehensive prediction model for a quantile q is represented as:
wherein f isn,qRepresenting the nth said probabilistic load prediction model for quantile q, Xn,tInputs representing the regression model at time t, including historical load data, day of work variables and weather conditions, Wn,qParameter, ω, of the nth regression model representing the quantile qn,qA weight representing the nth probabilistic load prediction model quantile q.
6. The prediction method of claim 4, wherein the optimization of the first formula results in a third formula, wherein the third formula is expressed as:
8. an apparatus for predicting a probabilistic short-term load of an electric power system, comprising:
a construction unit configured to construct a plurality of probabilistic load prediction models based on a power system, each of the probabilistic load prediction models corresponding to a plurality of quantiles;
a determining unit configured to determine a weight of each of the quantiles;
the processing unit is used for obtaining a comprehensive prediction model according to the weight of each quantile and each probabilistic load prediction model;
and the prediction unit is used for predicting the short-term load of the power system according to the comprehensive prediction model.
9. A computer-readable storage medium, comprising a stored program, wherein the program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the method for predicting probabilistic short-term load of an electric power system according to any one of claims 1 to 7.
10. A processor, characterized in that the processor is configured to run a program, wherein the program is configured to perform the method of predicting probabilistic short-term load of an electric power system according to any one of claims 1 to 7 when running.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011308426.5A CN112308337A (en) | 2020-11-19 | 2020-11-19 | Prediction method, prediction device and processor for probabilistic short-term load of power system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011308426.5A CN112308337A (en) | 2020-11-19 | 2020-11-19 | Prediction method, prediction device and processor for probabilistic short-term load of power system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112308337A true CN112308337A (en) | 2021-02-02 |
Family
ID=74336222
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011308426.5A Pending CN112308337A (en) | 2020-11-19 | 2020-11-19 | Prediction method, prediction device and processor for probabilistic short-term load of power system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112308337A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112926801A (en) * | 2021-03-31 | 2021-06-08 | 云南电网有限责任公司 | Load curve combined prediction method and device based on quantile regression |
CN113516276A (en) * | 2021-04-09 | 2021-10-19 | 国网安徽省电力有限公司铜陵供电公司 | Medium-short term load prediction method based on data mining processing framework |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108846517A (en) * | 2018-06-12 | 2018-11-20 | 清华大学 | A kind of probability short-term electric load prediction integrated approach of quantile |
CN109558975A (en) * | 2018-11-21 | 2019-04-02 | 清华大学 | A kind of integrated approach of a variety of prediction results of electric load probability density |
CN109657844A (en) * | 2018-11-28 | 2019-04-19 | 国电南瑞科技股份有限公司 | Power Short-Term Load Forecasting method and apparatus |
CN111860977A (en) * | 2020-06-30 | 2020-10-30 | 清华大学 | Probability prediction method and probability prediction device for short-term load |
-
2020
- 2020-11-19 CN CN202011308426.5A patent/CN112308337A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108846517A (en) * | 2018-06-12 | 2018-11-20 | 清华大学 | A kind of probability short-term electric load prediction integrated approach of quantile |
CN109558975A (en) * | 2018-11-21 | 2019-04-02 | 清华大学 | A kind of integrated approach of a variety of prediction results of electric load probability density |
CN109657844A (en) * | 2018-11-28 | 2019-04-19 | 国电南瑞科技股份有限公司 | Power Short-Term Load Forecasting method and apparatus |
CN111860977A (en) * | 2020-06-30 | 2020-10-30 | 清华大学 | Probability prediction method and probability prediction device for short-term load |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112926801A (en) * | 2021-03-31 | 2021-06-08 | 云南电网有限责任公司 | Load curve combined prediction method and device based on quantile regression |
CN112926801B (en) * | 2021-03-31 | 2022-11-01 | 云南电网有限责任公司 | Load curve combined prediction method and device based on quantile regression |
CN113516276A (en) * | 2021-04-09 | 2021-10-19 | 国网安徽省电力有限公司铜陵供电公司 | Medium-short term load prediction method based on data mining processing framework |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107464023B (en) | Online learning method and equipment of life cycle prediction model | |
CN102056182B (en) | Method for predicting mobile traffic based on LS-SVM | |
CN111091196B (en) | Passenger flow data determination method and device, computer equipment and storage medium | |
CN109697977B (en) | Speech recognition method and device | |
CN112990587B (en) | Method, system, equipment and medium for accurately predicting power consumption of transformer area | |
CN112308337A (en) | Prediction method, prediction device and processor for probabilistic short-term load of power system | |
KR102239464B1 (en) | Methods and apparatuses for forecasting power demand using deep structure | |
CN107609583A (en) | Parameter optimization method, device, computer equipment and the storage medium of disaggregated model | |
Li et al. | Efficient resource scaling based on load fluctuation in edge-cloud computing environment | |
CN111355246B (en) | Prediction method, system and storage medium for reactive compensation of camera | |
CN113449257A (en) | Power distribution network line loss prediction method, control device, and storage medium | |
CN111680712A (en) | Transformer oil temperature prediction method, device and system based on similar moments in the day | |
CN113807589A (en) | Rolling optimization method and device for operator energy storage based on model prediction | |
CN113837383B (en) | Model training method and device, electronic equipment and storage medium | |
CN112487612A (en) | Bus load combination prediction method and system based on distribution factor and information entropy | |
CN112270454B (en) | Method and device for predicting short-term load of power system under influence of extreme factors | |
CN117252288A (en) | Regional resource active support capacity prediction method and system | |
CN116933451A (en) | Multi-dimensional architecture mapping relation model evaluation method, device and equipment based on Petri network | |
CN112926801A (en) | Load curve combined prediction method and device based on quantile regression | |
CN112070354A (en) | Power grid equipment operation efficiency evaluation method | |
CN117495032A (en) | Park energy distribution method, device, equipment and medium | |
CN117896671B (en) | Intelligent management method and system for Bluetooth AOA base station | |
CN116629133A (en) | Prediction method, equipment and medium for building multi-region temperature | |
CN116579477A (en) | Method and device for predicting traffic flow based on extreme learning machine model and electronic equipment | |
Miroshnyk et al. | Short-Term Load Forecasting in Electrical Networks and Systems with Artificial Neural Networks and Taking into Account Additional Factors |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210202 |
|
RJ01 | Rejection of invention patent application after publication |