CN107590570A - A kind of bearing power Forecasting Methodology and system - Google Patents
A kind of bearing power Forecasting Methodology and system Download PDFInfo
- Publication number
- CN107590570A CN107590570A CN201710899987.9A CN201710899987A CN107590570A CN 107590570 A CN107590570 A CN 107590570A CN 201710899987 A CN201710899987 A CN 201710899987A CN 107590570 A CN107590570 A CN 107590570A
- Authority
- CN
- China
- Prior art keywords
- moment
- weather
- data
- forecast model
- bearing power
- 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
Abstract
The present invention provides a kind of bearing power Forecasting Methodology and system, including：S1, obtain weather data corresponding to historic load power data and the historic load power data；S2, based on default multilayer perceptron neutral net, the historic load power data at each moment and the weather data are fitted, obtain the overall volatility forecast model of the bearing power on weather at each moment；S3, based on the overall volatility forecast model, default coarse path random fluctuation forecast model and default point process random fluctuation forecast model, the bearing power at associated prediction each moment.Bearing power Forecasting Methodology and system provided in an embodiment of the present invention, on the basis of using multilayer perceptron neutral net to bearing power entirety volatility forecast, random fluctuation error also is calculated using default coarse path random fluctuation forecast model and default point process random fluctuation forecast model, greatly improves bearing power accuracy.
Description
Technical field
The present invention relates to intelligent power grid technology field, more particularly, to a kind of bearing power Forecasting Methodology and system.
Background technology
In network system instantly, whether for bulk power grid or micro-capacitance sensor, the prediction to load end electric power
It is all particularly significant always.The many areas in China still can be perplexed in summer by shortage of electric power at present, especially scorching in weather
When hot, a large amount of large power air-conditioned runnings, but may be limited due to generating total amount, it is necessary to consume substantial amounts of electric energy, or comes
Electric energy is dispatched not as good as from surrounding area, or the preparation largely to generate electricity is not carried out in some power plants, then some electricity shortages
Region situation about may have a power failure.In order to avoid this kind of situation, the reasonable prediction of power consumption is just particularly important.Such as
Fruit can learn the prediction data of electric power in advance, then generating unit can is ready in advance, allocates electric unit
The rational allocation of electric energy in certain limit area can be got out in advance.
In existing network system, bearing power be largely residential electricity consumption, therefore its changing rule is also mainly by ought
The influence of the consumption habit of ground resident, in general have used line for load electric power modeling method, traditional forecast model
Property ODE, bearing power is asked by establishing one of the bearing power ordinary differential model with linear dimensions
Solution.
But the load electric power Forecasting Methodology that prior art uses, can not describe load within a very short time with
Machine fluctuates, so as to which the result for the bearing power forecast model prediction for causing to establish has larger error.
The content of the invention
It is pre- that the present invention provides a kind of a kind of bearing power for overcoming above mentioned problem or solving the above problems at least in part
Survey method and system.
According to an aspect of the present invention, there is provided a kind of bearing power Forecasting Methodology, including：
S1, obtain weather data corresponding to historic load power data and the historic load power data；
S2, based on default multilayer perceptron neutral net, to the historic load power data at each moment and institute
State weather data to be fitted, obtain the overall volatility forecast model of the bearing power on weather at each moment；
S3, based on the overall volatility forecast model, default coarse path random fluctuation forecast model and default
Point process random fluctuation forecast model, the bearing power at associated prediction each moment.
Wherein, step S2 foregoing description method also includes：
Based on moving average algorithm, data smoothing is carried out to the historic load power data.
Wherein, step S2 includes：
Based on the historic load power data and the weather data, computational load power accumulates on the Pearson came of weather
Square coefficient correlation；
Based on the Pearson product-moment correlation coefficient and default multilayer perceptron neutral net, the negative of each moment is obtained
Carry overall volatility forecast model of the power on weather.
Wherein, step S3 foregoing description method also includes：
Based on the overall volatility forecast model, the coarse path random fluctuation forecast model and described pre- is established respectively
If point process random fluctuation forecast model.
Wherein, step S3 includes：
The overall volatility model and default coarse path of S31, the bearing power based on each moment on weather
Random fluctuation forecast model, calculate first random fluctuation data of each moment bearing power on weather；
S32, the bearing power based on each moment are on the overall volatility model of weather and the default point
Journey random fluctuation forecast model, calculate second random fluctuation data of each moment bearing power on weather；
S33, by the bearing power at each moment on the overall fluctuation data in the overall volatility forecast model of weather, institute
Each moment bearing power is stated on the first random fluctuation data of weather and each moment bearing power on weather
Second random fluctuation data are corresponding to be added, and obtains the bearing power at each moment.
Wherein, S31 is specifically included：
Overall volatility model of the bearing power based on each moment on weather, computing system parameter μ1And σ1；
Based on the systematic parameter μ1And σ1And the default coarse path random fluctuation forecast model, calculate each
First random fluctuation data of the moment bearing power on weather.
Wherein, it is described to be based on the systematic parameter μ1And σ1And the default coarse path random fluctuation forecast model,
The first random fluctuation data that each moment bearing power is calculated on weather specifically include：
dPLe(t)=μ1PLe(t)dt+σ1DR (t),
Wherein, R (t) is the coarse path random process, μ1And σ1For systematic parameter, PLe(t) it is random for described first
Fluctuate data.
According to the second aspect of the invention, there is provided a kind of bearing power forecasting system, it is characterised in that including：
Acquisition module, for obtaining day destiny corresponding to historic load power data and the historic load power data
According to；
Fitting module, for based on default multilayer perceptron neutral net, to the historic load work(at each moment
Rate data and the weather data are fitted, and obtain the overall volatility forecast mould of the bearing power on weather at each moment
Type；
Prediction module, for based on the overall volatility forecast model, default coarse path random fluctuation forecast model
And default point process random fluctuation forecast model, the bearing power at associated prediction each moment.
According to the third aspect of the invention we, there is provided a kind of computer program product, including program code, described program code
For performing bearing power Forecasting Methodology described above.
According to the fourth aspect of the invention, there is provided a kind of non-transient computer readable storage medium storing program for executing, for storing such as preceding institute
The computer program stated.
Bearing power Forecasting Methodology and system provided in an embodiment of the present invention, multilayer perceptron neutral net is being used to negative
On the basis of carrying power entirety volatility forecast, also using default coarse path random fluctuation forecast model and default point
Journey random fluctuation forecast model calculates random fluctuation error, greatly improves bearing power accuracy.
Brief description of the drawings
Fig. 1 is a kind of bearing power Forecasting Methodology flow chart provided in an embodiment of the present invention；
Fig. 2 is the schematic diagram that Several Typical Load power provided in an embodiment of the present invention changes over time；
Fig. 3 is a kind of bearing power forecasting system structure chart provided in an embodiment of the present invention.
Embodiment
With reference to the accompanying drawings and examples, the embodiment of the present invention is described in further detail.Implement below
Example is used to illustrate the present invention, but is not limited to the scope of the present invention.
Fig. 1 is a kind of bearing power Forecasting Methodology flow chart provided in an embodiment of the present invention, as shown in figure 1, including：
S1, obtain weather data corresponding to historic load power data and the historic load power data；
S2, based on default multilayer perceptron neutral net, to the historic load power data at each moment and institute
State weather data to be fitted, obtain the overall volatility forecast model of the bearing power on weather at each moment；
S3, based on the overall volatility forecast model, default coarse path random fluctuation forecast model and default
Point process random fluctuation forecast model, the bearing power at associated prediction each moment.
It is understood that the Forecasting Methodology provided in an embodiment of the present invention to bearing power is substantially to establishing one
Individual bearing power forecast model, the forecast model provided according to embodiments of the present invention can accurately predict user at each moment
Bearing power.
In the prior art, document is predicted using neutral net to photovoltaic generation power in recent years, but mesh
Before rarely have see by multilayer perceptron neutral net be used for load electric power be predicted.
On the basis of existing technology, predicted the embodiments of the invention provide one kind with multilayer perceptron neural network
The method of model, this, which allows for the multilayer perceptron neutral net, has very outstanding nonlinear fitting ability, so as to
The trend of all kinds of Weather informations and bearing power change can be fitted.
It should be noted that it both is from the use such as air-conditioning and warmer due to loading the major part of power consumption in existing power network
In the equipment of regulation indoor environment, and comparatively the service condition of these equipment and local weather have than relatively straightforward pass
System, then can be formed to bearing power one than calibrated essentially by the relation found between load electric power and weather
True prediction.
In general, the changing rule of bearing power and the behavior of resident have contact closely, are connected to micro-capacitance sensor
The random opening and closing of a large amount of electrical equipments all bearing power can be fluctuated, this also causes the change of bearing power
A certain degree of randomness be present, it is difficult to describe using deterministic equation.
Therefore the embodiment of the present invention is fitted bearing power data and weather data by multilayer perceptron neutral net, so as to
So that bearing power general trend prediction result is more reliable.
Specifically, in S1, the historic load power data is provided in an embodiment of the present invention in default historical time model
In enclosing, the summation of selected areas scope whole residential electricity consumption, it is to be understood that corresponding daily each moment can get
The historic load power data, Fig. 2 are the schematic diagrames that Several Typical Load power provided in an embodiment of the present invention changes over time.
In S1, weather data corresponding to the historic load power data is in daily each moment weather weather station
Acquired weather data, corresponded with the historic load power data of acquisition, wherein, the weather data includes：Temperature,
Humidity, atmospheric pressure, wind speed, cloud amount, precipitation probability.
In S2, the multilayer perceptron neutral net (Multi-layer perceptron neural networks,
MLP neural netwoks) effect be by the way that multiple perceptrons are combined, realize the segmentation of complex space, so as to will load
Power data and weather data carry out nonlinear fitting, obtain the overall volatility forecast model P required for usLp(t)。
Default coarse path random fluctuation forecast model described in S3 and default point process random fluctuation prediction mould
Type is the simulated power dynamic change for transient state, so as to calculate random fluctuation data, it is to be understood that default coarse road
Footpath random fluctuation forecast model and default point process random fluctuation forecast model belong to stochastic differential equation, it is necessary to illustrate
, the species of stochastic differential equation has a lot, typically such as stochastic differential equation of Brownian movement driving, be used alone with
The machine differential equation can not fictitious load longer period of time all changed power models, but for simulating the random of transient state
Fluctuation can but play very good effect.
In S3, it is to be understood that can obtain the load work(based on each moment by the overall volatility forecast model
Overall fluctuation data of the rate on weather, it is random by default coarse path random fluctuation forecast model and default point process
Volatility forecast model can obtain random fluctuation data of each moment bearing power on weather, predict the load at each moment
Power, i.e., by the overall random fluctuation data linear phase that fluctuates data and bearing power on weather of the bearing power on weather
Add, so as to predict the bearing power at each moment.
Bearing power Forecasting Methodology and system provided in an embodiment of the present invention, multilayer perceptron neutral net is being used to negative
On the basis of carrying power entirety volatility forecast, random fluctuation error also is calculated using stochastic differential equation, makes bearing power smart
Exactness greatly improves.
On the basis of above-described embodiment, step S2 foregoing description methods also include：
Based on moving average algorithm, data smoothing is carried out to the historic load power data.
It is understood that as shown in Fig. 2 obtain historic load power data include substantial amounts of random noise, these
The presence of noise can cause greatly to disturb to calculating process provided in an embodiment of the present invention, in order to remove these noise jammings,
The embodiment of the present invention preferably employs moving average algorithm, and data smoothing is carried out to the historic load power data.
Wherein, moving average algorithm provided in an embodiment of the present invention uses default slipping smoothness window, in window
All exceptional values are done sums averagely, the exceptional value using required average value as window center point, until being clicked through to all data
Row is once smooth.
The embodiment of the present invention will it is smooth after historic load power data be denoted as
Moving average algorithm provided in an embodiment of the present invention, can effectively eliminate contain in historic load power data with
Machine noise, so as to lift the accuracy rate of prediction.
On the basis of above-described embodiment, step S2 includes：
Based on the historic load power data and the weather data, computational load power accumulates on the Pearson came of weather
Square coefficient correlation；
Based on the Pearson product-moment correlation coefficient and default multilayer perceptron neutral net, the negative of each moment is obtained
Carry overall fluctuation data of the power on weather.
Wherein, the Pearson product-moment correlation coefficient is to be used for correlation degree between two groups of data of expression, and its calculating formula is such as
Shown in following formula：
Wherein, X represents historic load power data, and Y represents a certain weather data, such as：Temperature, humidity, air
Pressure, wind speed, cloud amount or precipitation probability.So calculate respectively temperature, humidity, atmospheric pressure, wind speed, cloud amount and precipitation probability with
Pearson product-moment correlation coefficient between historic load power data, you can according to its coefficient correlation order of magnitude and reality
Correlation analysis selects weather characteristics of the good weather factor as input multilayer perceptron neutral net.
It is understood that the size of the corresponding Pearson product-moment correlation coefficient calculated can have differences, it is preferred that
From weather characteristics of the maximum weather conditions of Pearson product-moment correlation coefficient as input multilayer perceptron neutral net.
According to the weather characteristics of input multilayer perceptron neutral net, further according to gradient descent method to multilayer perceptron god
It is trained through network, so as to obtain the overall fluctuation data of the bearing power on weather at each moment, this is integrally fluctuated
Data are denoted as PLp(t)。
On the basis of above-described embodiment, step S3 foregoing description methods also include：
Based on the overall volatility forecast model, the coarse path random fluctuation forecast model and described pre- is established respectively
If point process random fluctuation forecast model.
It is understood that stochastic differential equation provided in an embodiment of the present invention includes the random micro- of driven in two modes
Divide equation to combine to calculate random fluctuation data, wherein the coarse path random fluctuation forecast model is by British mathematician
Terry Lyons proposed that it can simulate a series of abnormal violent stochastic variable of fluctuations, so as to fictitious load work(in 1994
The random process of rate fluctuation；The point process random fluctuation forecast model is mainly used in simulating the random process of dynamic jump.
It should be noted that in the case where country advocates overall situation of the new-energy automobile instead of gasoline car, it is substantial amounts of plug-in mixed
Electrical automobile and pure electric automobile are linked into power network, and their access can cause the random punching on certain power to network load end
Hit.Due to the independence and randomness of automobile charging access, similar fast hop can occur within a period of time for bearing power
Fluctuation.
Thus point process random fluctuation forecast model provided in an embodiment of the present invention is well suited for a large amount of plug-in for simulating
The power ramp up formula to caused by load side fluctuates when mixed electrical automobile or pure electric car access power network.
On the basis of above-described embodiment, step S3 includes：
The overall volatility model and default coarse path of S31, the bearing power based on each moment on weather
Random fluctuation forecast model, calculate first random fluctuation data of each moment bearing power on weather；
S32, the bearing power based on each moment are on the overall volatility model of weather and the default point
Journey random fluctuation forecast model, calculate second random fluctuation data of each moment bearing power on weather；
S33, by the bearing power at each moment on the overall fluctuation data in the overall volatility forecast model of weather, institute
Each moment bearing power is stated on the first random fluctuation data of weather and each moment bearing power on weather
Second random fluctuation data are corresponding to be added, and obtains the bearing power at each moment.
On the basis of above-described embodiment, S31 is specifically included：
Overall volatility model of the bearing power based on each moment on weather, computing system parameter μ1And σ1；
Based on the systematic parameter μ1And σ1And the default coarse path random fluctuation forecast model, calculate each
First random fluctuation data of the moment bearing power on weather.
It is described to be based on the systematic parameter μ1And σ1And the default coarse path random fluctuation forecast model, calculate
Each moment bearing power specifically includes on the first random fluctuation data of weather：
dPLe(t)=μ1PLe(t)dt+σ1DR (t),
Wherein, R (t) is the coarse path random process, μ1And σ1For systematic parameter, PLe(t) it is random for described first
Fluctuate data.
It is understood that above formula is the coarse path differential equation (rough differential equation),
μ1And σ1For systematic parameter, the systematic parameter obtains a series of possible systems by actual jump bearing power DATA REASONING
Parameter array, i.e. { μ1i,σ1i, wherein i=1,2 ..., N, the i.e. possible parameter values of N groups.
Then the possible parameter values of N groups are fitted and approached, until obtaining one group of optimal solution, the optimal solution is
μ1And σ1。
Further according to formula dPLe(t)=μ1PLe(t)dt+σ1DR (t), it can solve and there emerged a moment bearing power on weather
First random fluctuation data PLe(t)。
In S32, the specific calculating process of the second stochastic differential equation of the point process driving is shown below：
dPN(t)=μ2PLe(t)dt+σ2dN(t),
Wherein, N (t) is point process (Point Process), also referred to as (Jump diffusion), μ2And σ2Join for system
Number, the systematic parameter obtain a series of possible systematic parameter arrays by actual jump bearing power DATA REASONING, i.e.,
{μ2i,σ2i, wherein i=1,2 ..., N, the i.e. possible parameter values of N groups.
The actual jump bearing power data are fluctuated by the bearing power at each moment on the entirety of weather
DATA REASONING obtains.
Then the possible parameter values of N groups are fitted and approached, until obtaining one group of optimal solution, the optimal solution is
μ2And σ2。
Further according to formula dPN(t)=μ2PLe(t)dt+σ2DN (t), there emerged a moment bearing power on weather can be solved
Two random fluctuation data PN(t)。
In S33, according to the first random fluctuation data P tried to achieve in S31Le(t) the second random fluctuation and in S32 tried to achieve
Data PN(t) data linear, additive at the time of, correspondence obtains the summation of random fluctuation data, then by random fluctuation data
Data linear fit is fluctuated with overall, obtains the bearing power at each moment.
Specific prediction calculating formula is as follows：
PL(t)=PLp(t)+PLe(t)+PN(t),
Wherein, PL(t) bearing power predicted by the embodiment of the present invention, PLp(t) to be whole described in the embodiment of the present invention
Bulk wave moves data, PLe(t) calculated for the first stochastic differential equation based on coarse path driving described in the embodiment of the present invention
First random fluctuation data, PN(t) it is the second stochastic differential equation meter based on point process driving described in the embodiment of the present invention
The the second random fluctuation data calculated.
Fig. 3 is a kind of bearing power forecasting system structure chart provided in an embodiment of the present invention, as shown in figure 3, the system
Including：Acquisition module 1, fitting module 2 and prediction module 3, wherein：
Acquisition module 1 is used to obtain day destiny corresponding to historic load power data and the historic load power data
According to；
Fitting module 2 is used to be based on default multilayer perceptron neutral net, to the historic load work(at each moment
Rate data and the weather data are fitted, and obtain the overall volatility forecast mould of the bearing power on weather at each moment
Type；
Prediction module 3 is used for based on the overall volatility forecast model, default coarse path random fluctuation forecast model
And default point process random fluctuation forecast model, the bearing power at associated prediction each moment.
Specifically, acquisition module 1 obtains the electricity consumption historical data and the history of all users in FX first
Weather data corresponding to data, then fitting module 2 be based on default multilayer perceptron neutral net, to described in each moment
Historic load power data and the weather data are fitted, so that overall ripple of the bearing power at each moment on weather
Dynamic data PLp(t) the first random fluctuation data P that the first stochastic differential equation based on coarse path driving calculates, is calculatedLe
(t) the second random fluctuation data P that the second stochastic differential equation and based on point process driven calculatesN(t) mould, is finally predicted
Block 3 is by PLp(t)、PLeAnd P (t)N(t) it is added, so as to bearing power PL(t) it is predicted.
Bearing power forecasting system provided in an embodiment of the present invention, fitting module are using multilayer perceptron neutral net pair
On the basis of bearing power entirety volatility forecast, computing module also calculates random fluctuation error using stochastic differential equation, makes
Bearing power accuracy greatly improves.
The embodiment of the present invention provides a kind of bearing power forecasting system, including：At least one processor；And with the place
At least one memory of device communication connection is managed, wherein：
The memory storage has and by the programmed instruction of the computing device, the processor described program can be called to refer to
Order to perform the method that above-mentioned each method embodiment is provided, such as including：S1, obtain historic load power data and described
Weather data corresponding to historic load power data；S2, based on default multilayer perceptron neutral net, to the institute at each moment
State historic load power data and the weather data is fitted, obtain the entirety of the bearing power on weather at each moment
Volatility forecast model；S3, based on the overall volatility forecast model, default coarse path random fluctuation forecast model and pre-
If point process random fluctuation forecast model, the bearing power at associated prediction each moment.
The embodiment of the present invention discloses a kind of computer program product, and the computer program product is non-transient including being stored in
Computer program on computer-readable recording medium, the computer program include programmed instruction, when described program instructs quilt
When computer performs, computer is able to carry out the method that above-mentioned each method embodiment is provided, such as including：S1, obtain history
Weather data corresponding to bearing power data and the historic load power data；S2, based on default multilayer perceptron god
Through network, the historic load power data at each moment and the weather data are fitted, obtain each moment
Overall volatility forecast model of the bearing power on weather；S3, based on the overall volatility forecast model, default coarse path
Random fluctuation forecast model and default point process random fluctuation forecast model, the bearing power at associated prediction each moment.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium storing program for executing, the non-transient computer readable storage
Medium storing computer instructs, and the computer instruction makes the computer perform the side that above-mentioned each method embodiment is provided
Method, such as including：S1, obtain weather data corresponding to historic load power data and the historic load power data；S2、
Based on default multilayer perceptron neutral net, the historic load power data at each moment and the weather data are entered
Row fitting, obtains the overall volatility forecast model of the bearing power on weather at each moment；It is S3, pre- based on the overall fluctuation
Model, default coarse path random fluctuation forecast model and default point process random fluctuation forecast model are surveyed, joint is pre-
Survey the bearing power at each moment.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above method embodiment can pass through
Programmed instruction related hardware is completed, and foregoing program can be stored in a computer read/write memory medium, the program
Upon execution, the step of execution includes above method embodiment；And foregoing storage medium includes：ROM, RAM, magnetic disc or light
Disk etc. is various can be with the medium of store program codes.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
Realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on such understanding, on
The part that technical scheme substantially in other words contributes to prior art is stated to embody in the form of software product, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including some fingers
Make to cause a computer equipment (can be personal computer, server, or network equipment etc.) to perform each implementation
Method described in some parts of example or embodiment.
In the present invention, term " first ", " second " are only used for describing purpose, and it is not intended that instruction or hint are relative
Importance.Term " multiple " refers to two or more, is limited unless otherwise clear and definite.
Finally, the present processes are only preferable embodiment, are not intended to limit the scope of the present invention.It is all
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvements made etc., the protection of the present invention should be included in
Within the scope of.
Claims (10)
- A kind of 1. bearing power Forecasting Methodology, it is characterised in that including：S1, obtain weather data corresponding to historic load power data and the historic load power data；S2, based on default multilayer perceptron neutral net, to the historic load power data at each moment and the day Destiny obtains the overall volatility forecast model of the bearing power on weather at each moment according to being fitted；S3, based on the overall volatility forecast model, default coarse path random fluctuation forecast model and default point Journey random fluctuation forecast model, the bearing power at associated prediction each moment.
- 2. according to the method for claim 1, it is characterised in that step S2 foregoing description methods also include：Based on moving average algorithm, data smoothing is carried out to the historic load power data.
- 3. according to the method for claim 1, it is characterised in that step S2 includes：Based on the historic load power data and the weather data, Pearson product-moment phase of the computational load power on weather Relation number；Based on the Pearson product-moment correlation coefficient and default multilayer perceptron neutral net, the load work(at each moment is obtained Overall volatility forecast model of the rate on weather.
- 4. according to the method for claim 1, it is characterised in that step S3 foregoing description methods also include：Based on the overall volatility forecast model, the coarse path random fluctuation forecast model and described default is established respectively Point process random fluctuation forecast model.
- 5. according to the method for claim 4, it is characterised in that step S3 includes：S31, the bearing power based on each moment are random on the overall volatility model of weather and default coarse path Volatility forecast model, calculate first random fluctuation data of each moment bearing power on weather；S32, the bearing power based on each moment on weather overall volatility model and the default point process with Machine volatility forecast model, calculate second random fluctuation data of each moment bearing power on weather；S33, by the bearing power at each moment on overall fluctuation data in the overall volatility forecast model of weather, described every Individual moment bearing power on weather the first random fluctuation data and each moment bearing power on weather second Random fluctuation data are corresponding to be added, and obtains the bearing power at each moment.
- 6. according to the method for claim 5, it is characterised in that S31 is specifically included：Overall volatility model of the bearing power based on each moment on weather, computing system parameter μ1And σ1；Based on the systematic parameter μ1And σ1And the default coarse path random fluctuation forecast model, calculate each moment First random fluctuation data of the bearing power on weather.
- 7. according to the method for claim 6, it is characterised in that described to be based on the systematic parameter μ1And σ1It is and described pre- If coarse path random fluctuation forecast model, calculate each moment bearing power on weather the first random fluctuation data have Body includes：dPLe(t)=μ1PLe(t)dt+σ1DR (t),Wherein, R (t) is the coarse path random process, μ1And σ1For systematic parameter, PLe(t) it is the first random fluctuation number According to.
- A kind of 8. bearing power forecasting system, it is characterised in that including：Acquisition module, for obtaining weather data corresponding to historic load power data and the historic load power data；Fitting module, for based on default multilayer perceptron neutral net, to the historic load power number at each moment It is fitted according to the weather data, obtains the overall volatility forecast model of the bearing power on weather at each moment；Prediction module, for based on the overall volatility forecast model, default coarse path random fluctuation forecast model and Default point process random fluctuation forecast model, the bearing power at associated prediction each moment.
- 9. a kind of computer program product, it is characterised in that the computer program product includes being stored in non-transient computer Computer program on readable storage medium storing program for executing, the computer program include programmed instruction, when described program is instructed by computer During execution, the computer is set to perform the method as described in claim 1 to 7 is any.
- 10. a kind of non-transient computer readable storage medium storing program for executing, it is characterised in that the non-transient computer readable storage medium storing program for executing is deposited Computer program is stored up, the computer program makes the computer perform the method as described in claim 1 to 7 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710899987.9A CN107590570A (en) | 2017-09-28 | 2017-09-28 | A kind of bearing power Forecasting Methodology and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710899987.9A CN107590570A (en) | 2017-09-28 | 2017-09-28 | A kind of bearing power Forecasting Methodology and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107590570A true CN107590570A (en) | 2018-01-16 |
Family
ID=61048788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710899987.9A Pending CN107590570A (en) | 2017-09-28 | 2017-09-28 | A kind of bearing power Forecasting Methodology and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107590570A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876007A (en) * | 2018-05-11 | 2018-11-23 | 国网四川省电力公司 | A kind of electricity demand forecasting method |
| CN109274092A (en) * | 2018-10-16 | 2019-01-25 | 清华大学 | Energy management method and device based on energy internet |
| CN111950763A (en) * | 2020-07-02 | 2020-11-17 | 江苏能来能源互联网研究院有限公司 | Method for predicting output power of distributed wind power station |
| CN112699998A (en) * | 2021-03-25 | 2021-04-23 | 北京瑞莱智慧科技有限公司 | Time series prediction method and device, electronic equipment and readable storage medium |
| CN113108959A (en) * | 2021-04-13 | 2021-07-13 | 辽宁瑞华实业集团高新科技有限公司 | Power prediction method and device for transport tool and transport tool |
-
2017
- 2017-09-28 CN CN201710899987.9A patent/CN107590570A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876007A (en) * | 2018-05-11 | 2018-11-23 | 国网四川省电力公司 | A kind of electricity demand forecasting method |
| CN109274092A (en) * | 2018-10-16 | 2019-01-25 | 清华大学 | Energy management method and device based on energy internet |
| CN111950763A (en) * | 2020-07-02 | 2020-11-17 | 江苏能来能源互联网研究院有限公司 | Method for predicting output power of distributed wind power station |
| CN111950763B (en) * | 2020-07-02 | 2023-12-05 | 江苏能来能源互联网研究院有限公司 | Method for predicting output power of distributed wind power station |
| CN112699998A (en) * | 2021-03-25 | 2021-04-23 | 北京瑞莱智慧科技有限公司 | Time series prediction method and device, electronic equipment and readable storage medium |
| CN112699998B (en) * | 2021-03-25 | 2021-09-07 | 北京瑞莱智慧科技有限公司 | Time series prediction method and device, electronic equipment and readable storage medium |
| CN113108959A (en) * | 2021-04-13 | 2021-07-13 | 辽宁瑞华实业集团高新科技有限公司 | Power prediction method and device for transport tool and transport tool |
| CN113108959B (en) * | 2021-04-13 | 2022-10-11 | 辽宁瑞华实业集团高新科技有限公司 | Power prediction method and device for transport tool and transport tool |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107590570A (en) | A kind of bearing power Forecasting Methodology and system | |
| Ye et al. | Predicting electricity consumption in a building using an optimized back-propagation and Levenberg–Marquardt back-propagation neural network: Case study of a shopping mall in China | |
| Catalao et al. | An artificial neural network approach for short-term wind power forecasting in Portugal | |
| Ghadimi et al. | PSO based fuzzy stochastic long-term model for deployment of distributed energy resources in distribution systems with several objectives | |
| Wang et al. | Chance constrained unit commitment considering comprehensive modelling of demand response resources | |
| CN102509173B (en) | A kind of based on markovian power system load Accurate Prediction method | |
| CN103793887B (en) | Short-term electric load on-line prediction method based on self-adaptive enhancement algorithm | |
| CN107423839A (en) | A kind of method of the intelligent building microgrid load prediction based on deep learning | |
| Wang et al. | Multi-objective unit commitment with wind penetration and emission concerns under stochastic and fuzzy uncertainties | |
| CA2996731C (en) | Methods and systems for energy use normalization and forecasting | |
| CN107133695A (en) | A kind of wind power forecasting method and system | |
| CN113572157A (en) | User real-time autonomous energy management optimization method based on near-end policy optimization | |
| Guegan et al. | Developing a module for estimating climate warming effects on hydropower pricing in California | |
| Padhi et al. | Solving dynamic economic emission dispatch problem with uncertainty of wind and load using whale optimization algorithm | |
| CN106933649A (en) | Virtual machine load predicting method and system based on rolling average and neutral net | |
| CN102510059A (en) | Super short-term wind power forecasting method based on back propagation (BP) neural network | |
| Mandal et al. | A new recursive neural network algorithm to forecast electricity price for PJM day‐ahead market | |
| CN104036328A (en) | Self-adaptive wind power prediction system and prediction method | |
| CN112329997A (en) | Power demand load prediction method and system, electronic device, and storage medium | |
| Jeyaraj et al. | Computer‐assisted demand‐side energy management in residential smart grid employing novel pooling deep learning algorithm | |
| Khalili-Damghani et al. | Solving land-use suitability analysis and planning problem by a hybrid meta-heuristic algorithm | |
| CN103618315B (en) | A kind of line voltage idle work optimization method based on BART algorithm and super-absorbent wall | |
| Anderson Jr | Resilience assessment of islanded renewable energy microgrids | |
| Tang et al. | Optimisation of wind farm layout in complex terrain via mixed‐installation of different types of turbines | |
| CN112613637A (en) | Method and device for processing charging load |
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: 20180116 |
|
| RJ01 | Rejection of invention patent application after publication |