CN108960520A - Power load prediction method, system, computer equipment and medium - Google Patents
Power load prediction method, system, computer equipment and medium Download PDFInfo
- Publication number
- CN108960520A CN108960520A CN201810763995.5A CN201810763995A CN108960520A CN 108960520 A CN108960520 A CN 108960520A CN 201810763995 A CN201810763995 A CN 201810763995A CN 108960520 A CN108960520 A CN 108960520A
- Authority
- CN
- China
- Prior art keywords
- series data
- electric load
- model
- prediction
- historical series
- 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 52
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims abstract description 72
- 238000005311 autocorrelation function Methods 0.000 claims description 48
- 206010019133 Hangover Diseases 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 5
- 241001123248 Arma Species 0.000 description 4
- 240000002853 Nelumbo nucifera Species 0.000 description 4
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 4
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 4
- 230000006854 communication Effects 0.000 description 4
- 230000001373 regressive effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000013277 forecasting method Methods 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000005611 electricity Effects 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000005295 random walk Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 241000728173 Sarima Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
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)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a power load prediction method, which comprises the following steps: acquiring historical sequence data of the power load changing along with time; establishing a power prediction ARIMA model by using the historical sequence data; and predicting the power load of a specified time period by using the power prediction ARIMA model. The invention adopts ARIMA model to predict the power load, and the historical sequence data of the power load is real power coincidence data, which contains various factors, such as meteorological factor, economic factor, air temperature, etc., which have influence on the power load, and the factors generally have periodicity on the whole, so that the power load value in a specified time period is predicted more accurately by using the periodicity of the factors. The power load prediction system, the computer device and the medium provided by the invention also have the beneficial effects, and are not described again.
Description
Technical field
The present invention relates to electric load balanced arrangement technical field, in particular to a kind of Methods of electric load forecasting, system,
Computer equipment, medium.
Background technique
Electric load variation mainly by social production, the domination of rule of life and regularity is presented, and by it is meteorological because
The influence of numerous correlative factors such as element, economic factor, and since the total load in a region is by millions of a Systemic Burden groups
At, therefore there is the component largely changed at random in load.Electric load have biggish periodicity, hour, day, year etc., together
When electric load be sensitive, different season to season, temperature, weather etc., the variation of different weathers and temperature all can
Load is caused significantly to influence.The key of load prediction work is to collect a large amount of historical data, using historical data as base
Plinth carries out a large number of experiments Journal of Sex Research, scientific and effective prediction model, and constantly correction model and algorithm is established, to really anti-
Reflect load variations rule.
The Return Law that has itd is proposed since twentieth century, time series method, exponential smoothing are based primarily upon load shape and function
Form studies load characteristic, and the uncertainty of load prediction is mainly classified as stochastic problems by these methods, and is used
The method of Probability Theory and Math Statistics is handled, and such methods have the disadvantage in that determining rank, solution, identifying difficulty for model；
The adaptability of model is not strong；Model is not separated with data, and data volume needed for modeling is big, and arithmetic speed is slow；Precision is low etc..Hair recently
The load predictions sides such as grey method, expert system approach, Kalman filtering method, wavelet analysis method and the neural network that exhibition is got up
Method further relates to many external factors for considering to influence load, as weather conditions, season are special in addition to considering the factors such as load shape
Sign etc., thus precision further increases.
Therefore, a kind of load forecast scheme how is provided, the electricity for the following one end time that can more calculate to a nicety
Power load condition is those skilled in the art's technical problem urgently to be resolved.
Summary of the invention
In view of this, the purpose of the present invention is to provide.Its concrete scheme is as follows:
In a first aspect, the present invention provides a kind of Methods of electric load forecasting, comprising:
Obtain the historical series data that electric load changes over time；
Using the historical series data, power prediction ARIMA model is established；
Using the power prediction ARIMA model, the electric load of designated time period is predicted.
Preferably, after the historical series data that the acquisition electric load changes over time, described in the utilization
Historical series data are established before power prediction ARIMA model, further includes:
Judge whether the historical series data are steady；
If it is not, then carrying out tranquilization processing to the historical series data.
Preferably,
It is described that tranquilization processing is carried out to the historical series data, comprising:
Judge that the historical series data whether there is and rise or fall trend,
If it is, carrying out difference processing to the historical series data.
Preferably,
It is described that tranquilization processing is carried out to the historical series data, comprising:
Judge the historical series data with the presence or absence of Singular variance；
If it is, being adjusted to the historical series data, until the auto-correlation function of the historical series data
Value and deviation―related function value are without significantly different from zero.
Preferably,
The historical series data are being utilized, are being established after power prediction ARIMA model；
Before the utilization power prediction ARIMA model, the electric load for predicting designated time period, further includes:
White noise sound detection is carried out to the residual sequence of the power prediction ARIMA model.
Preferably,
It is described to utilize the historical series data, establish power prediction ARIMA model, comprising:
Judge the partial autocorrelation function of the historical series data, the type of auto-correlation function；
If the partial autocorrelation function is truncation type, and the auto-correlation function is hangover type, then using described
Historical series data establish the AR model of prediction electric load；
If the partial autocorrelation function is hangover type, and the auto-correlation function is truncation type, then using described
Historical series data establish the MA model of prediction electric load；
If the partial autocorrelation function is hangover type, and the auto-correlation function is hangover type, then using described
Historical series data establish the ARIMA model of prediction electric load.
Second aspect, the present invention provide a kind of Electric Load Prediction System, comprising:
Historical data obtains module, the historical series data changed over time for obtaining electric load；
Prediction model establishes module, for utilizing the historical series data, establishes power prediction ARIMA model；
Electric load presets module, for utilizing the power prediction ARIMA model, predicts the power load of designated time period
Lotus.
Preferably,
The prediction model establishes module, comprising:
Type function judging submodule, for judging partial autocorrelation function, the auto-correlation function of the historical series data
Type；
AR model foundation submodule, if being used for the partial autocorrelation function as truncation type, and the auto-correlation function
For type of trailing, then the AR model of prediction electric load is established using the historical series data；
MA model foundation submodule, if being used for the partial autocorrelation function as hangover type, and the auto-correlation function
For truncation type, then the MA model of prediction electric load is established using the historical series data；
ARIMA model foundation submodule, if being used for the partial autocorrelation function as hangover type, and the auto-correlation letter
Number is hangover type, then the ARIMA model of prediction electric load is established using the historical series data.
The third aspect, the present invention provide a kind of computer equipment, comprising:
Memory, for storing computer program；
Processor realizes the step of any of the above-described kind of Methods of electric load forecasting when for executing the computer program
Suddenly.
Fourth aspect, the present invention provide a kind of computer readable storage medium,
Computer program is stored on the computer readable storage medium；
The computer program realizes the step of any of the above-described kind of Methods of electric load forecasting when being executed by processor.
The present invention provides a kind of Methods of electric load forecasting, comprising: obtains the historical series that electric load changes over time
Data；Using the historical series data, power prediction ARIMA model is established；Using the power prediction ARIMA model, in advance
Survey the electric load of designated time period.The present invention carries out the prediction of electric load, and the power load used using ARIMA model
The historical series data of lotus are that true electric power meets data, wherein having contained various factors, such as meteorologic factor, economy
The influence to electric load such as factor, temperature, and these factors generally have periodically on the whole, therefore, utilize these
The periodicity of factor relatively accurately predicts some designated time period power load charge values.
A kind of Electric Load Prediction System provided by the invention, computer equipment, medium also have above-mentioned beneficial effect,
Details are not described herein.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of flow chart of Methods of electric load forecasting provided by a kind of specific embodiment of the present invention；
Fig. 2 is the composition schematic diagram of Electric Load Prediction System provided by a kind of specific embodiment of the present invention；
Fig. 3 is the composition schematic diagram that prediction model provided by a kind of specific embodiment of the present invention establishes module；
Fig. 4 is the structural schematic diagram of computer equipment provided by another specific embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to FIG. 1, Fig. 1 is a kind of stream of Methods of electric load forecasting provided by a kind of specific embodiment of the present invention
Cheng Tu.
In a kind of specific embodiment of the invention, the embodiment of the present invention provides a kind of Methods of electric load forecasting, packet
It includes:
S11: the historical series data that electric load changes over time are obtained；
Firstly, Methods of electric load forecasting of the invention needs to obtain the historical series data of electric load at any time, example
Such as the electric load situation of every month during 1999 to 2011 can be formed into a data sequence changed over time, this
Sample just obtains the historical series data that electric load changes over time.
S12: the historical series data are utilized, power prediction ARIMA model is established；
After getting historical series data, it can use these historical series data and establish power prediction ARIMA model,
Such as can use statistical software spss and recall corresponding ARIMA model, historical series data are inputted, form what the present invention needed
Power prediction ARIMA model.
S13: the power prediction ARIMA model is utilized, predicts the electric load of designated time period.
Power prediction ARIMA model is being constructed, i.e., can predict the power load charge values of designated time period using the model.
The basic thought of power prediction ARIMA model provided by the present invention is: will predict object electric load shape over time
At data sequence be considered as a random sequence, with certain mathematical model come this sequence of approximate description.This model is once
Value future value can be predicted from the past value of time series and now after identified.
Further, in order to enable the historical series data for establishing power prediction ARIMA model are all stable ARIMA moulds
The utilizable data of type, can be after the historical series data that the acquisition electric load changes over time, in the benefit
It with the historical series data, establishes before power prediction ARIMA model, further includes: whether judge the historical series data
Steadily；If it is not, then carrying out tranquilization processing to the historical series data.
Specifically, the primary condition of ARIMA model modeling is that ordered series of numbers to be predicted is required to meet stable condition, i.e., individual
Value will fluctuate up and down around serial mean, cannot have and significantly rise or fall trend, if there is trend is risen or fallen, need
Difference tranquilization processing is carried out to original series, it therefore, can be further described that the historical series data are carried out
Tranquilization is handled, and may include:
Judge that the historical series data whether there is and rise or fall trend,
If it is, carrying out difference processing to the historical series data.
Also may include:
Judge the historical series data with the presence or absence of Singular variance；
If it is, being adjusted to the historical series data, until the auto-correlation function of the historical series data
Value and deviation―related function value are without significantly different from zero.
Wherein, one can be set close to the preset range example with zero in practice by referring to " without significantly different from zero "
Such as in the range of positive and negative 0.1, as long as auto-correlation function value and deviation―related function value reach in this preset range, then can
To be considered " without significantly different from zero ".
Preferably,
The historical series data are being utilized, are being established after power prediction ARIMA model；
Before the utilization power prediction ARIMA model, the electric load for predicting designated time period, further includes:
White noise sound detection is carried out to the residual sequence of the power prediction ARIMA model.White noise sequence refers to white noise
The sample of process claims in fact, abbreviation white noise.Stochastic variable 4 (t) (t=1,2,3 ...), if it is incoherent random by one
The Sequence composition of variable, i.e., T is not equal to for all S, the covariance of stochastic variable 4t and 4s are zero, then are called pure random
Process.For a purely random process, if it is desired for 0, variance is constant, then referred to as white-noise process.Why
Referred to as white noise is because he is similar with the characteristic of white light, and the spectrum of white light has identical intensity, white noise in each frequency
Value of the spectrum density in each frequency it is identical.
Further, it is illustrated to establishing power prediction ARIMA model, it is described to utilize the historical series data,
Establish power prediction ARIMA model, comprising:
Judge the partial autocorrelation function of the historical series data, the type of auto-correlation function；
If the partial autocorrelation function is truncation type, and the auto-correlation function is hangover type, then using described
Historical series data establish the AR model of prediction electric load；
If the partial autocorrelation function is hangover type, and the auto-correlation function is truncation type, then using described
Historical series data establish the MA model of prediction electric load；
If the partial autocorrelation function is hangover type, and the auto-correlation function is hangover type, then using described
Historical series data establish the ARIMA model of prediction electric load.
The present invention provides a kind of load forecasting method for integrating rolling average autoregression model based on difference, this method with
Difference integrate rolling average autoregression model (Auto Regressive Integrated Moving Average Model,
ARIMA based on), influence of the historical datas such as load, weather and economic data to load prediction has been comprehensively considered.In addition,
The present invention has also carried out sample calculation analysis using load forecasting method of the real data to offer.Difference is used in sample calculation analysis
Time series mathematical model, the application to load forecasting method provided by the invention in Mid-long term load forecasting field has been done complete
Face and thorough test analysis, and successively the various possible factors for influencing prediction results are screened, study one by one it is different because
Influence of the element to Mid-long term load forecasting.Sample calculation analysis the result shows that, meteorologic factor (including the year highest temperature, average temperature of the whole year,
Year/every Month average rainfall), economic factor (including regional population's quantity, population years months growth rate, years months GDP growth rate)
Mid-long term load forecasting is influenced very big.
AR model, MA model, ARIMA model are illustrated below:
AR 1. (Auto Regressive) model
Give a time series Xt, t is positive integer, X heretIt is real number, AR (p) model can be described as:
Here φi, i=1,2 ..., p are constant, εtIt is noise data.This formula describes a p rank autoregression
Model.If indicating to postpone with L operator, above-mentioned formula can be rewritten are as follows:
Here LiXt=Xt-i.If p=1, φ1=1, then available AR (1) model:
Xt=Xt-1+εt
This is a Random Walk model.
2. MA (Moving Average) moves translation model
Give a time series Xt, t is positive integer, X heretIt is real number, MA (q) model can be described as:
If postponing operator with L to describe, can rewrite are as follows:
If q=0, available MA (0) model:
Xt=εt
This is a white noise (White Noise) model.
ARMA 3. (Auto Regressive Moving Average) model
It is as follows in conjunction with AR (p) and available ARMA (p, the q) model of MA (q):
If postponing operator with L to describe, can rewrite are as follows:
ARIMA 4. (Auto Regressive Integrated Moving Average) model
Equation is assumed in arma modelingThere is no unit repeated root.If there is repeated root, such as (1-
L d repeated root), then arma modeling can be rewritten are as follows:
Here it is ARIMA (p-d, d, q) models, and wherein L is lag operator (Lag operator).If p-d write as
P, then being exactly ARIMA (p, d, q) model.(1-L)dXtPhysical meaning be by XtTime series data does d difference.
ARIMA (0,1,0) corresponding A R (1) model, that is, Random Walk model.
ARIMA (0,0,0) corresponds to MA (0) model, that is, white noise (White Noise) model.
ARIMA (0,1,1) is exponential smoothing model (Basic E4ponential Smoothing Model).
(2) ARIMA model application process
ARIMA model can be counted as " cascade " of two models.The first is unfixed:
Yt=(1-L)dXt
And second is that broad sense is static:
It now can be to process YtIt is predicted, uses the popularization of Autoregressive Prediction Method.
1. the predicting interval
Predicting interval (confidence interval of prediction) uncorrelated based on residual error and normal distribution hypothesis of ARIMA model.Such as
Any one of these hypothesis of fruit are all invalid, then the predicting interval may be incorrect.For this reason, researcher draws
ACF and residual error histogram are assumed with checking before generate the predicting interval.
95% predicting interval:
Wherein, vT+h|TFor yT+h|y1..., yTVariance.
For
It is suitable for all ARIMA models.
For
In general, with the increase of predicted time, the predicting interval of ARIMA model will be will increase.
2. variation and extension
Usually using some variations of ARIMA model.If using multiple time serieses, 4t be considered to
Amount, and VARIMA model may be suitable.Seasonal effect is suspected in model sometimes；In this case, usually best
Using SARIMA (seasonal ARIMA) model, rather than increase the sequence of the part AR or MA of model.If suspecting time series
Growth process dependence is shown, then can permit d parameter has non-integer in autoregression score integral moving average model(MA model)
Value, the model are also referred to as score ARIMA (FARIMA or ARFIMA) model.
The present invention provides a kind of Methods of electric load forecasting, comprising: obtains the historical series that electric load changes over time
Data；Using the historical series data, power prediction ARIMA model is established；Using the power prediction ARIMA model, in advance
Survey the electric load of designated time period.The present invention carries out the prediction of electric load, and the power load used using ARIMA model
The historical series data of lotus are that true electric power meets data, wherein having contained various factors, such as meteorologic factor, economy
The influence to electric load such as factor, temperature, and these factors generally have periodically on the whole, therefore, utilize these
The periodicity of factor relatively accurately predicts some designated time period power load charge values.
Fig. 2, Fig. 3 are please referred to, Fig. 2 is the group of Electric Load Prediction System provided by a kind of specific embodiment of the present invention
At schematic diagram；Fig. 3 is the composition schematic diagram that prediction model provided by a kind of specific embodiment of the present invention establishes module.
In a kind of specific embodiment of the invention, the embodiment of the present invention provides a kind of Electric Load Prediction System 200,
Include:
Historical data obtains module 210, the historical series data changed over time for obtaining electric load；
Prediction model establishes module 220, for utilizing the historical series data, establishes power prediction ARIMA model；
Electric load presets module 230, for utilizing the power prediction ARIMA model, predicts the electricity of designated time period
Power load.
Preferably,
The prediction model establishes module 220, comprising:
Type function judging submodule 221, for judging partial autocorrelation function, the auto-correlation letter of the historical series data
Several types；
AR model foundation submodule 222, if being used for the partial autocorrelation function as truncation type, and the auto-correlation letter
Number is hangover type, then the AR model of prediction electric load is established using the historical series data；
MA model foundation submodule 223, if being used for the partial autocorrelation function as hangover type, and the auto-correlation letter
Number is truncation type, then the MA model of prediction electric load is established using the historical series data；
ARIMA model foundation submodule 224, if being hangover type for the partial autocorrelation function, and described from phase
Closing function is hangover type, then the ARIMA model of prediction electric load is established using the historical series data.
Referring to FIG. 4, Fig. 4 is the structural representation of computer equipment provided by another specific embodiment of the invention
Figure.
In another specific embodiment of the invention, the embodiment of the present invention provides a kind of computer equipment, comprising:
Memory, for storing computer program；
Processor realizes power load described in any of the above-described kind of specific embodiment when for executing the computer program
The step of lotus prediction technique.
Below with reference to Fig. 4, it illustrates the structural schematic diagrams for the computer equipment for being suitable for being used to realize the embodiment of the present application.
Computer equipment shown in Fig. 4 is only an example, should not function to the embodiment of the present application and use scope bring it is any
Limitation.
As shown in figure 4, computer system 400 includes processor (CPU) 401, it can be according to being stored in read-only memory
(ROM) it the program in 402 or is executed respectively from the program that storage section 408 is loaded into random access storage device (RAM) 403
Kind movement appropriate and processing.In RAM 403, also it is stored with system 400 and operates required various programs and data.
CPU 401, ROM 402 and RAM 403 are connected with each other by bus 404.Input/output (I/O) interface 403
It is connected to bus 404.
I/O interface 405 is connected to lower component: the importation 406 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 407 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 408 including hard disk etc.；
And the communications portion 409 of the network interface card including LAN card, modem etc..Communications portion 409 via such as because
The network of spy's net executes communication process.Driver 410 is also connected to I/O interface 407 as needed.Detachable media 411, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 410, in order to read from thereon
Computer program be mounted into storage section 408 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 409, and/or from detachable media
411 are mounted.When the computer program is executed by processor (CPU) 401, the above-mentioned function limited in the present processes is executed
Energy.It should be noted that computer-readable medium described herein can be computer-readable signal media or computer
Readable medium either the two any combination.Computer-readable medium for example may be-but not limited to-electricity,
Magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Computer-readable medium
More specific example can include but is not limited to: there is the electrical connection of one or more conducting wires, portable computer diskette, hard
Disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or flash memory), light
Fibre, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate
Combination.In this application, it includes or the tangible medium of storage program that the program can be with that computer-readable medium, which can be any,
It is commanded execution system, device or device use or in connection.And in this application, computer-readable signal
Medium may include in a base band or as the data-signal that carrier wave a part is propagated, wherein carrying computer-readable journey
Sequence code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal, optical signal or above-mentioned
Any appropriate combination.Computer-readable signal media can also be any computer-readable other than computer-readable medium
Medium, the computer-readable medium can be sent, propagated or transmitted for being used by instruction execution system, device or device
Or program in connection.The program code for including on computer-readable medium can pass with any suitable medium
It is defeated, including but not limited to: wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object-oriented programming language-such as Java, Smalltalk, C+
+, further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local
Net (LAN) or wide area network (WAN)-are connected to subscriber computer, or, it may be connected to outer computer (such as using because of spy
Service provider is netted to connect by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
As still another embodiment of the invention, the embodiment of the present invention provides a kind of computer readable storage medium institute
It states and is stored with computer program on computer readable storage medium, the computer program realizes above-mentioned when being executed by processor
Anticipate specific embodiment in Methods of electric load forecasting the step of.
The computer-readable medium can be included in computer equipment or terminal device described in above-described embodiment
's；It is also possible to individualism, and without in the supplying computer equipment.Above-mentioned computer-readable medium carry one or
Multiple programs, when said one or multiple programs are executed by the computer equipment, so that the computer equipment: obtaining electric power
The historical series data that load changes over time；Using the historical series data, power prediction ARIMA model is established；It utilizes
The power prediction ARIMA model, predicts the electric load of designated time period.And storage medium above-mentioned includes: USB flash disk, movement
Hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), the various media that can store program code such as magnetic or disk.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
A kind of Methods of electric load forecasting provided by the present invention, system, computer equipment, medium have been carried out in detail above
Thin to introduce, used herein a specific example illustrates the principle and implementation of the invention, and above embodiments are said
It is bright to be merely used to help understand method and its core concept of the invention；At the same time, for those skilled in the art, foundation
Thought of the invention, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (10)
1. a kind of Methods of electric load forecasting characterized by comprising
Obtain the historical series data that electric load changes over time；
Using the historical series data, power prediction ARIMA model is established；
Using the power prediction ARIMA model, the electric load of designated time period is predicted.
2. Methods of electric load forecasting according to claim 1, which is characterized in that the acquisition electric load at any time
After the historical series data of variation, the historical series data are utilized described, are established before power prediction ARIMA model,
Further include:
Judge whether the historical series data are steady；
If it is not, then carrying out tranquilization processing to the historical series data.
3. Methods of electric load forecasting according to claim 2, which is characterized in that
It is described that tranquilization processing is carried out to the historical series data, comprising:
Judge that the historical series data whether there is and rise or fall trend,
If it is, carrying out difference processing to the historical series data.
4. Methods of electric load forecasting according to claim 2, which is characterized in that
It is described that tranquilization processing is carried out to the historical series data, comprising:
Judge the historical series data with the presence or absence of Singular variance；
If it is, be adjusted to the historical series data, until the historical series data auto-correlation function value and
Deviation―related function value is without significantly different from zero.
5. Methods of electric load forecasting according to claim 1, which is characterized in that
The historical series data are being utilized, are being established after power prediction ARIMA model；
Before the utilization power prediction ARIMA model, the electric load for predicting designated time period, further includes:
White noise sound detection is carried out to the residual sequence of the power prediction ARIMA model.
6. Methods of electric load forecasting according to any one of claims 1 to 5, which is characterized in that
It is described to utilize the historical series data, establish power prediction ARIMA model, comprising:
Judge the partial autocorrelation function of the historical series data, the type of auto-correlation function；
If the partial autocorrelation function is truncation type, and the auto-correlation function is hangover type, then utilizes the history
Sequence data establishes the AR model of prediction electric load；
If the partial autocorrelation function is hangover type, and the auto-correlation function is truncation type, then utilizes the history
Sequence data establishes the MA model of prediction electric load；
If the partial autocorrelation function is hangover type, and the auto-correlation function is hangover type, then utilizes the history
Sequence data establishes the ARIMA model of prediction electric load.
7. a kind of Electric Load Prediction System characterized by comprising
Historical data obtains module, the historical series data changed over time for obtaining electric load；
Prediction model establishes module, for utilizing the historical series data, establishes power prediction ARIMA model；
Electric load presets module, for utilizing the power prediction ARIMA model, predicts the electric load of designated time period.
8. Electric Load Prediction System according to claim 7, which is characterized in that
The prediction model establishes module, comprising:
Type function judging submodule, for judging the partial autocorrelation function of the historical series data, the class of auto-correlation function
Type；
AR model foundation submodule, if being truncation type for the partial autocorrelation function, and the auto-correlation function is to drag
Tail type then establishes the AR model of prediction electric load using the historical series data；
MA model foundation submodule, if being hangover type for the partial autocorrelation function, and the auto-correlation function is to cut
Tail type then establishes the MA model of prediction electric load using the historical series data；
ARIMA model foundation submodule, if being hangover type for the partial autocorrelation function, and the auto-correlation function is
Hangover type, then establish the ARIMA model of prediction electric load using the historical series data.
9. a kind of computer equipment characterized by comprising
Memory, for storing computer program；
Processor realizes the load forecast side as described in any one of claim 1 to 6 when for executing the computer program
The step of method.
10. a kind of computer readable storage medium, which is characterized in that
Computer program is stored on the computer readable storage medium；
The Methods of electric load forecasting as described in any one of claim 1 to 6 is realized when the computer program is executed by processor
The step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810763995.5A CN108960520A (en) | 2018-07-12 | 2018-07-12 | Power load prediction method, system, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810763995.5A CN108960520A (en) | 2018-07-12 | 2018-07-12 | Power load prediction method, system, computer equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108960520A true CN108960520A (en) | 2018-12-07 |
Family
ID=64483861
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810763995.5A Pending CN108960520A (en) | 2018-07-12 | 2018-07-12 | Power load prediction method, system, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108960520A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110648026A (en) * | 2019-09-27 | 2020-01-03 | 京东方科技集团股份有限公司 | Prediction model construction method, prediction method, device, equipment and medium |
| CN111177278A (en) * | 2019-12-19 | 2020-05-19 | 绍兴大明电力设计院有限公司 | Grid user short-term load prediction real-time processing tool |
| CN112163702A (en) * | 2020-09-24 | 2021-01-01 | 国网江苏省电力有限公司徐州供电分公司 | Prediction method and device for stable section load rate, electronic device and storage medium |
| CN112348282A (en) * | 2020-11-25 | 2021-02-09 | 新智数字科技有限公司 | Load prediction method and device |
| CN112418921A (en) * | 2020-11-11 | 2021-02-26 | 深圳力维智联技术有限公司 | Power demand prediction method, device, system and computer storage medium |
| CN112434430A (en) * | 2020-11-27 | 2021-03-02 | 国网北京市电力公司 | Method and device for predicting cell capacity |
| CN113095608A (en) * | 2019-12-23 | 2021-07-09 | 中国移动通信集团上海有限公司 | Index analysis method, device, equipment and storage medium |
| CN113743667A (en) * | 2021-09-06 | 2021-12-03 | 广东电网有限责任公司 | Method, device, equipment and storage medium for predicting power consumption of transformer area |
| CN116107854A (en) * | 2023-02-20 | 2023-05-12 | 中国人民财产保险股份有限公司 | Method, system, equipment and medium for predicting operation maintenance index of computer |
| CN117349647A (en) * | 2023-09-08 | 2024-01-05 | 哈尔滨工业大学 | Correction time sequence trend decomposition feature extraction method for Barker code variable pulse width modulation heat source induced thermal wave signals |
| CN117808325A (en) * | 2024-02-29 | 2024-04-02 | 山东浪潮数据库技术有限公司 | Power load prediction method based on user supply and demand big data |
| CN118520428A (en) * | 2024-07-22 | 2024-08-20 | 湖北华中电力科技开发有限责任公司 | Power load prediction method and system based on artificial intelligence |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120278051A1 (en) * | 2011-04-29 | 2012-11-01 | International Business Machines Corporation | Anomaly detection, forecasting and root cause analysis of energy consumption for a portfolio of buildings using multi-step statistical modeling |
| CN105069535A (en) * | 2015-08-19 | 2015-11-18 | 中国电力科学研究院 | Method for predicting operational reliability of power distribution network based on ARIMA model |
| CN105701559A (en) * | 2015-12-31 | 2016-06-22 | 国网上海市电力公司 | Short-term load prediction method based on time sequence |
-
2018
- 2018-07-12 CN CN201810763995.5A patent/CN108960520A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120278051A1 (en) * | 2011-04-29 | 2012-11-01 | International Business Machines Corporation | Anomaly detection, forecasting and root cause analysis of energy consumption for a portfolio of buildings using multi-step statistical modeling |
| CN105069535A (en) * | 2015-08-19 | 2015-11-18 | 中国电力科学研究院 | Method for predicting operational reliability of power distribution network based on ARIMA model |
| CN105701559A (en) * | 2015-12-31 | 2016-06-22 | 国网上海市电力公司 | Short-term load prediction method based on time sequence |
Non-Patent Citations (1)
| Title |
|---|
| 贾竹青: "基于ARIMA模型的呼和浩特地区10kV配电网负荷预测", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110648026A (en) * | 2019-09-27 | 2020-01-03 | 京东方科技集团股份有限公司 | Prediction model construction method, prediction method, device, equipment and medium |
| CN111177278A (en) * | 2019-12-19 | 2020-05-19 | 绍兴大明电力设计院有限公司 | Grid user short-term load prediction real-time processing tool |
| CN113095608A (en) * | 2019-12-23 | 2021-07-09 | 中国移动通信集团上海有限公司 | Index analysis method, device, equipment and storage medium |
| CN112163702B (en) * | 2020-09-24 | 2023-08-08 | 国网江苏省电力有限公司徐州供电分公司 | Method and device for predicting stable section load rate, electronic equipment and storage medium |
| CN112163702A (en) * | 2020-09-24 | 2021-01-01 | 国网江苏省电力有限公司徐州供电分公司 | Prediction method and device for stable section load rate, electronic device and storage medium |
| CN112418921A (en) * | 2020-11-11 | 2021-02-26 | 深圳力维智联技术有限公司 | Power demand prediction method, device, system and computer storage medium |
| CN112348282A (en) * | 2020-11-25 | 2021-02-09 | 新智数字科技有限公司 | Load prediction method and device |
| CN112434430A (en) * | 2020-11-27 | 2021-03-02 | 国网北京市电力公司 | Method and device for predicting cell capacity |
| CN113743667A (en) * | 2021-09-06 | 2021-12-03 | 广东电网有限责任公司 | Method, device, equipment and storage medium for predicting power consumption of transformer area |
| CN116107854A (en) * | 2023-02-20 | 2023-05-12 | 中国人民财产保险股份有限公司 | Method, system, equipment and medium for predicting operation maintenance index of computer |
| CN117349647A (en) * | 2023-09-08 | 2024-01-05 | 哈尔滨工业大学 | Correction time sequence trend decomposition feature extraction method for Barker code variable pulse width modulation heat source induced thermal wave signals |
| CN117808325A (en) * | 2024-02-29 | 2024-04-02 | 山东浪潮数据库技术有限公司 | Power load prediction method based on user supply and demand big data |
| CN117808325B (en) * | 2024-02-29 | 2024-05-14 | 山东浪潮数据库技术有限公司 | Power load prediction method based on user supply and demand big data |
| CN118520428A (en) * | 2024-07-22 | 2024-08-20 | 湖北华中电力科技开发有限责任公司 | Power load prediction method and system based on artificial intelligence |
| CN118520428B (en) * | 2024-07-22 | 2024-10-18 | 湖北华中电力科技开发有限责任公司 | Power load prediction method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108960520A (en) | Power load prediction method, system, computer equipment and medium | |
| CN110443657B (en) | Client flow data processing method and device, electronic equipment and readable medium | |
| CN109587713A (en) | A kind of network index prediction technique, device and storage medium based on ARIMA model | |
| CN110060090A (en) | Method, apparatus, electronic equipment and the readable storage medium storing program for executing of Recommendations combination | |
| CN108229754A (en) | Short-term load forecasting method based on similar day segmentation and LM-BP networks | |
| CN109697522A (en) | A kind of method and apparatus of data prediction | |
| CN112285807B (en) | Meteorological information prediction method and device | |
| CN107689008A (en) | A kind of user insures the method and device of behavior prediction | |
| CN106549772A (en) | Resource prediction method, system and capacity management device | |
| CN108053242A (en) | Sight spot admission ticket ticket amount Forecasting Methodology, system, equipment and storage medium | |
| CN108805174A (en) | clustering method and device | |
| CN109615152A (en) | Wind power generation prediction method and product based on cost-oriented gradient ascending regression tree | |
| CN110674208B (en) | Method and device for determining position information of user | |
| CN110766184A (en) | Order quantity prediction method and device | |
| CN112308281A (en) | Temperature information prediction method and device | |
| CN109817222A (en) | A kind of age recognition methods, device and terminal device | |
| CN112308173B (en) | Multi-target object evaluation method based on multi-evaluation factor fusion and related equipment thereof | |
| CN113837488B (en) | Method, system and equipment for predicting energy consumption data | |
| CN109002925A (en) | Traffic prediction method and apparatus | |
| CN109087138A (en) | Data processing method and system, computer system and readable storage medium storing program for executing | |
| CN113837383B (en) | Model training method and device, electronic equipment and storage medium | |
| CN110069629A (en) | House transaction task processing method, equipment, storage medium and device | |
| CN111191825A (en) | User default prediction method and device and electronic equipment | |
| CN116684330A (en) | Traffic prediction method, device, equipment and storage medium based on artificial intelligence | |
| CN110598775A (en) | Prediction method, system and storage medium based on fuzzy clustering and BP neural network |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210520 Address after: 510663 3 building, 3, 4, 5 and J1 building, 11 building, No. 11, Ke Xiang Road, Luogang District Science City, Guangzhou, Guangdong. Applicant after: China South Power Grid International Co.,Ltd. Address before: 510663 3 building, 3, 4, 5 and J1 building, 11 building, No. 11, Ke Xiang Road, Luogang District Science City, Guangzhou, Guangdong. Applicant before: China South Power Grid International Co.,Ltd. Applicant before: POWER GRID TECHNOLOGY RESEARCH CENTER. CHINA SOUTHERN POWER GRID |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181207 |