CN109711612A - Wind power generation power prediction method and device for optimizing echo state network - Google Patents
Wind power generation power prediction method and device for optimizing echo state network Download PDFInfo
- Publication number
- CN109711612A CN109711612A CN201811552246.4A CN201811552246A CN109711612A CN 109711612 A CN109711612 A CN 109711612A CN 201811552246 A CN201811552246 A CN 201811552246A CN 109711612 A CN109711612 A CN 109711612A
- Authority
- CN
- China
- Prior art keywords
- state network
- echo state
- wind
- power
- echo
- 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 15
- 238000010248 power generation Methods 0.000 title abstract description 8
- 238000005457 optimization Methods 0.000 claims abstract description 60
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 19
- 241000254158 Lampyridae Species 0.000 claims abstract description 16
- 230000005611 electricity Effects 0.000 claims description 52
- 230000006870 function Effects 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 18
- 241000131894 Lampyris noctiluca Species 0.000 claims description 14
- 238000013277 forecasting method Methods 0.000 claims description 10
- 210000005036 nerve Anatomy 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 6
- 230000008555 neuronal activation Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 abstract 1
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000006872 improvement Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000000739 chaotic effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a wind power generation power prediction method and a wind power generation power prediction device for optimizing an echo state network, wherein the method comprises the following steps: training to obtain an echo state network model for predicting wind power generation power by using the historical wind power generation power data as a training sample; optimizing parameters of the echo state network model by taking the minimum prediction error of the echo state network model as a target; and predicting the wind power generation power by using the optimized echo state network model. The technical scheme provided by the invention utilizes the strong nonlinear mapping capability of the echo state network and combines the rapid and accurate optimization capability of the firefly optimization algorithm, and the key parameters of the echo state network are continuously optimized and updated according to the historical input samples so as to improve the accuracy of the echo state network prediction.
Description
Technical field
The present invention relates to the technical fields of wind-power electricity generation, and in particular to a kind of wind-power electricity generation function for optimizing echo state network
Rate prediction technique and device.
Background technique
Echo state network belongs to novel recurrent neural network, nonlinear chaotic system predict modeling in terms of with it is traditional
For recurrent neural network compared to there is larger improvement, learning algorithm itself belongs to convex optimization, therefore avoids and fall into local minimum
The problem of, especially in the forecasting problem of time series using splendid.
Glowworm swarm algorithm is that a kind of principle is concise, required parameter is less, more novel intelligent optimization algorithm, passes through introducing
Firefly individual adaptation degree makes a variation link, the problems such as overcoming convergence rate, the solving precision of standard glowworm swarm algorithm.
With the gradually in-depth of the increasingly deficient and low-carbon, environmentally friendly concept of worldwide petrochemical resource reserve, wind energy is as one
The typical renewable resource of kind, since its is resourceful, and has the condition of large-scale development, develop and uses in full generation
It is had received widespread attention within the scope of boundary.
Wind energy is also faced with distinct issues while fast development.In recent years, with the continuous expansion of wind power plant scale
Greatly, randomness possessed by itself and intermittence all cause the safety of power grid, stability and power quality etc. huge
Impact and influence, this will obviously to large-scale wind-electricity integration, peak load regulation network, frequency modulation band come huge difficulty.Therefore, by wind
Power generated output becomes from unknown it is known that the operation to electric system has great meaning.Accurate wind power prediction, can
With under the premise of guaranteeing power supply system balance with safety, when reducing the cost of wind-power electricity generation, and reducing wind power-generating grid-connected pair
The impact of grid stability, to achieve the purpose that improve wind-power electricity generation value.
Currently, main output power of wind power generation prediction technique includes time series method, based on numerical weather forecast
Prediction technique, statistical method etc., these methods attempt to find out the relationship of weather conditions Yu wind-power electricity generation power by historical data
Wind power is predicted, but its there are model prediction accuracies low, problem of model complexity.
Summary of the invention
In order to solve the problems, such as that output power of wind power generation forecasting inaccuracy is true, the present invention provides a kind of optimization echo state network
The Wind power forecasting method and device of network introduces echo state from wind power time series data by this method
Network sufficiently excavates ordered series of numbers information, constantly excellent to the key parameter progress of echo state network in conjunction with firefly optimization algorithm is improved
Change and update, to predict wind-power electricity generation power with simplifying rapidly, and prediction result has very high accuracy.
A kind of Wind power forecasting method optimizing echo state network provided by the invention, improvements exist
In, comprising:
Using wind-power electricity generation power historical data as training sample, training is obtained for predicting returning for wind-power electricity generation power
Sound state network model；
With the parameter of echo state network model described in the minimum objective optimization of echo state network model predictive error；
Wind-power electricity generation power is predicted using the echo state network model after optimization.
Preferably, described with echo state network mould described in the minimum objective optimization of echo state network model predictive error
The parameter of type, comprising:
Optimize the parameter of the echo state network model using glowworm swarm algorithm, wherein sharp in the glowworm swarm algorithm
With the parameter building firefly individual of the echo state network model and firefly population, the fitness of the glowworm swarm algorithm
Function are as follows:
In above formula, M is predicted time segment length, and y (k) is prediction wind-power electricity generation of the echo state network at the k moment
Power,For the echo state network the k moment practical wind-power electricity generation power.
Further, the parameter of the echo state network model includes connection weight spectral radius, reserve pool scale, input list
First scale and sparse degree.
Preferably, the echo state network model using after optimization predicts wind-power electricity generation power, comprising:
Determine the wind-power electricity generation power y (M+1) of subsequent time as the following formula using the echo state network model after optimization:
Y (M+1)=fout×(Wbest×(u(M),x(M)))
In above formula, foutTo export layer functions, u (M) is the wind-power electricity generation power historical data at the M moment of acquisition, and x (M) is
State vector of the echo state network at the M moment, WbestFor the output weight matrix for optimizing echo state network；
Wherein, determine the echo state network in the state vector x (M) at M moment as the following formula:
X (M)=f (Win×u(M)+Wbackx(M-1))
In above formula, WinFor input layer in the echo state network after the optimization to reserve pool N × K rank connection weight square
Battle array, WbackFor N × L rank connection weight matrix of output layer feedback in the echo state network after the optimization to reserve pool, N is
Echo state network intrinsic nerve member number after the optimization, L are output dimension, and K is input dimension, and f is neuronal activation
Function Sigmoid, x (M-1) are state vector of the echo state network at the M-1 moment.
A kind of Wind power forecasting device optimizing echo state network provided by the invention, improvements exist
In, comprising:
Training module, for using wind-power electricity generation power historical data as training sample, training to be obtained for predicting wind
The echo state network model of power generated output；
Optimization module, for echo state network described in the minimum objective optimization of echo state network model predictive error
The parameter of model；
Prediction module, for being predicted using the echo state network model after optimization wind-power electricity generation power.
Preferably, the optimization module, is used for:
Optimize the parameter of the echo state network model using glowworm swarm algorithm, wherein sharp in the glowworm swarm algorithm
With the parameter building firefly individual of the echo state network model and firefly population, the fitness of the glowworm swarm algorithm
Function are as follows:
In above formula, M is predicted time segment length, and y (k) is prediction wind-power electricity generation of the echo state network at the k moment
Power,For the echo state network the k moment practical wind-power electricity generation power.
Further, the parameter of the echo state network model includes connection weight spectral radius, reserve pool scale, input list
First scale and sparse degree.
Preferably, the prediction module, is used for:
Determine the wind-power electricity generation power y (M+1) of subsequent time as the following formula using the echo state network model after optimization:
Y (M+1)=fout×(Wbest×(u(M),x(M)))
In above formula, foutTo export layer functions, u (M) is the wind-power electricity generation power historical data at the M moment of acquisition, and x (M) is
State vector of the echo state network at the M moment, WbestFor the output weight matrix for optimizing echo state network；
Wherein, determine the echo state network in the state vector x (M) at M moment as the following formula:
X (M)=f (Win×u(M)+Wbackx(M-1))
In above formula, WinFor input layer in the echo state network after the optimization to reserve pool N × K rank connection weight square
Battle array, WbackFor N × L rank connection weight matrix of output layer feedback in the echo state network after the optimization to reserve pool, N is
Echo state network intrinsic nerve member number after the optimization, L are output dimension, and K is input dimension, and f is neuronal activation
Function Sigmoid, x (M-1) are state vector of the echo state network at the M-1 moment.
Compared with the latest prior art, technical solution provided by the invention has following excellent effect:
The present invention provides a kind of Wind power forecasting method and devices for optimizing echo state network, utilize echo
State network carries out data mining, trend fitting to chaotic time series ordered series of numbers, quickly and accurately in conjunction with firefly optimization algorithm
Optimizing ability constantly optimizes update to the key parameter of echo state network according to the input sample of variation, improves echo
The accuracy of state network prediction, under the premise of guaranteeing power supply system balance with safety, to electricity when reducing wind power-generating grid-connected
The impact of net stability, to achieve the purpose that improve wind-power electricity generation value.
Detailed description of the invention
Fig. 1 is the flow chart of the Wind power forecasting method of optimization echo state network provided by the invention；
Fig. 2 is the structure of the Wind power forecasting device of the optimization echo state network provided in the embodiment of the present invention
Figure.
Specific embodiment
It elaborates with reference to the accompanying drawing to a specific embodiment of the invention.
Embodiment one
The embodiment of the present invention proposes a kind of Wind power forecasting method for optimizing echo state network, and flow chart is as schemed
Shown in 1, comprising the following steps:
Using wind-power electricity generation power historical data as training sample, training is obtained for predicting returning for wind-power electricity generation power
Sound state network model；
With the parameter of echo state network model described in the minimum objective optimization of echo state network model predictive error；
Wind-power electricity generation power is predicted using the echo state network model after optimization.
Specifically, described using wind-power electricity generation power historical data as training sample, training is obtained for predicting wind-force
The echo state network model of generated output, comprising:
Echo state network is indicated with following formula:
U (k)=[u1(k),u2(k),...,uK(k)]T
X (k)=[x1(k),x2(k),...,xN(k)]T
Y (k)=[y1(k),y2(k),...,yL(k)]T
Wherein, K is input dimension, and N is intrinsic nerve member number, and L is output dimension, and u (k), x (k), y (k) are respectively back
Input vector, state vector and the output vector of sound state network, u (k) are wind-power electricity generation power historical data:
According to the input vector of the echo state network, state vector and output vector, as the following formula to the echo shape
State network is trained:
X (k+1)=f (Win×u(k+1)+Wbackx(k))
Y (k+1)=fout×(Wout×(u(k+1),x(k+1)))
In above formula, f () is neuron activation functions Sigmoid, foutTo export layer functions, WinFor the input generated at random
Layer arrives reserve pool N × K rank connection weight matrix, WbackOutput layer to generate at random feeds back N × L rank connection weight to reserve pool
Weight matrix, WoutWeight matrix is exported for L × (K+N+L) rank of reserve pool to output layer.
Specifically, described with echo state network mould described in the minimum objective optimization of echo state network model predictive error
The parameter of type, comprising:
The fitness function Z (M) of firefly optimization algorithm according to the following formula:
In above formula, M is predicted time segment length, and y (k) is prediction wind-power electricity generation of the echo state network at the k moment
Power,For the echo state network the k moment practical wind-power electricity generation power；
When fitness function Z (M) is minimum, the echo state network mould is updated using firefly optimization algorithm
The key parameter optimal solution of type, including connection weight spectral radius SR, reserve pool scale N, input unit scale IS and sparse degree SD,
And parameter is set using the optimal solution as the reserve pool of the echo state network model.
Specifically, the echo state network model using after optimization predicts wind-power electricity generation power, comprising:
The weight matrix W of echo state network model after optimization is calculated as followsbest:
WBest=(C-1×D)T
In above formula, C be input vector u (k) constitute matrix, D be the optimization after echo state network output to
Measure the column matrix that y (k) is constituted.
Determine the wind-power electricity generation power y (M+1) of subsequent time as the following formula using the echo state network model after optimization:
Y (M+1)=fout×(Wbest×(u(M),x(M)))
In above formula, foutTo export layer functions, u (M) is the wind-power electricity generation power historical data at the M moment of acquisition, and x (M) is
State vector of the echo state network at the M moment；
Wherein, determine the echo state network in the state vector x (M) at M moment as the following formula:
X (M)=f (Win×u(M)+Wbackx(M-1))
In above formula, x (M-1) is state vector of the echo state network at the M-1 moment.
Embodiment two
The embodiment of the present invention proposes a kind of Wind power forecasting device for optimizing echo state network, structure such as Fig. 2
It is shown, comprising:
Training module, for using wind-power electricity generation power historical data as training sample, training to be obtained for predicting wind
The echo state network model of power generated output；
Optimization module, for echo state network described in the minimum objective optimization of echo state network model predictive error
The parameter of model；
Prediction module, for being predicted using the echo state network model after optimization wind-power electricity generation power.
The optimization module, is used for:
The fitness function Z (M) of firefly optimization algorithm according to the following formula:
In above formula, M is predicted time segment length, and y (k) is prediction wind-power electricity generation of the echo state network at the k moment
Power,For the echo state network the k moment practical wind-power electricity generation power；
When fitness function Z (M) is minimum, the echo state network mould is updated using firefly optimization algorithm
The key parameter optimal solution of type, including connection weight spectral radius SR, reserve pool scale N, input unit scale IS and sparse degree SD,
And parameter is set using the optimal solution as the reserve pool of the echo state network model.
The prediction module, is used for:
Determine the wind-power electricity generation power y (M+1) of subsequent time as the following formula using the echo state network model after optimization:
Y (M+1)=fout×(Wbest×(u(M),x(M)))
In above formula, foutTo export layer functions, u (M) is the wind-power electricity generation power historical data at the M moment of acquisition, and x (M) is
State vector of the echo state network at the M moment, WbestFor the output weight matrix for optimizing echo state network；
Wherein, determine the echo state network in the state vector x (M) at M moment as the following formula:
X (M)=f (Win×u(M)+Wbackx(M-1))
In above formula, WinFor input layer in the echo state network after the optimization to reserve pool N × K rank connection weight square
Battle array, WbackFor N × L rank connection weight matrix of output layer feedback in the echo state network after the optimization to reserve pool, N is
Echo state network intrinsic nerve member number after the optimization, L are output dimension, and K is input dimension, and f is neuronal activation
Function Sigmoid, x (M-1) are state vector of the echo state network at the M-1 moment.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
The above is only the embodiment of the present invention, are not intended to restrict the invention, all in the spirit and principles in the present invention
Within, any modification, equivalent substitution, improvement and etc. done, be all contained in apply pending scope of the presently claimed invention it
It is interior.
Claims (8)
1. a kind of Wind power forecasting method for optimizing echo state network, which is characterized in that the described method includes:
Using wind-power electricity generation power historical data as training sample, training obtains the echo shape for predicting wind-power electricity generation power
State network model；
With the parameter of echo state network model described in the minimum objective optimization of echo state network model predictive error；
Wind-power electricity generation power is predicted using the echo state network model after optimization.
2. Wind power forecasting method as described in claim 1, which is characterized in that described with echo state network model
Predict the parameter of echo state network model described in the minimum objective optimization of error, comprising:
Optimize the parameter of the echo state network model using glowworm swarm algorithm, wherein institute is utilized in the glowworm swarm algorithm
State parameter building firefly individual and the firefly population of echo state network model, the fitness function of the glowworm swarm algorithm
Are as follows:
In above formula, M is predicted time segment length, and y (k) is prediction wind-power electricity generation power of the echo state network at the k moment,For the echo state network the k moment practical wind-power electricity generation power.
3. Wind power forecasting method as claimed in claim 2, which is characterized in that the echo state network model
Parameter includes connection weight spectral radius, reserve pool scale, input unit scale and sparse degree.
4. Wind power forecasting method as described in claim 1, which is characterized in that the echo shape using after optimization
State network model predicts wind-power electricity generation power, comprising:
Determine the wind-power electricity generation power y (M+1) of subsequent time as the following formula using the echo state network model after optimization:
Y (M+1)=fout×(Wbest×(u(M),x(M)))
In above formula, foutTo export layer functions, u (M) is the wind-power electricity generation power historical data at the M moment of acquisition, and x (M) is described
State vector of the echo state network at the M moment, WbestFor the output weight matrix for optimizing echo state network；
Wherein, determine the echo state network in the state vector x (M) at M moment as the following formula:
X (M)=f (Win×u(M)+Wbackx(M-1))
In above formula, WinFor input layer in the echo state network after the optimization to reserve pool N × K rank connection weight matrix,
WbackFor output layer feedback in the echo state network after the optimization, to N × L rank connection weight matrix of reserve pool, N is institute
Echo state network intrinsic nerve member number after stating optimization, L are output dimension, and K is input dimension, and f is neuronal activation letter
Number Sigmoid, x (M-1) are state vector of the echo state network at the M-1 moment.
5. a kind of Wind power forecasting device for optimizing echo state network, which is characterized in that described device includes:
Training module, for using wind-power electricity generation power historical data as training sample, training to be obtained for predicting that wind-force is sent out
The echo state network model of electrical power；
Optimization module, for echo state network model described in the minimum objective optimization of echo state network model predictive error
Parameter；
Prediction module, for being predicted using the echo state network model after optimization wind-power electricity generation power.
6. Wind power forecasting device as described in claim 1, which is characterized in that the optimization module is used for:
Optimize the parameter of the echo state network model using glowworm swarm algorithm, wherein institute is utilized in the glowworm swarm algorithm
State parameter building firefly individual and the firefly population of echo state network model, the fitness function of the glowworm swarm algorithm
Are as follows:
In above formula, M is predicted time segment length, and y (k) is prediction wind-power electricity generation power of the echo state network at the k moment,For the echo state network the k moment practical wind-power electricity generation power.
7. Wind power forecasting device as claimed in claim 6, which is characterized in that the echo state network model
Parameter includes connection weight spectral radius, reserve pool scale, input unit scale and sparse degree.
8. Wind power forecasting device as claimed in claim 5, which is characterized in that the prediction module is used for:
Determine the wind-power electricity generation power y (M+1) of subsequent time as the following formula using the echo state network model after optimization:
Y (M+1)=fout×(Wbest×(u(M),x(M)))
In above formula, foutTo export layer functions, u (M) is the wind-power electricity generation power historical data at the M moment of acquisition, and x (M) is described
State vector of the echo state network at the M moment, WbestFor the output weight matrix for optimizing echo state network；
Wherein, determine the echo state network in the state vector x (M) at M moment as the following formula:
X (M)=f (Win×u(M)+Wbackx(M-1))
In above formula, WinFor input layer in the echo state network after the optimization to reserve pool N × K rank connection weight matrix,
WbackFor output layer feedback in the echo state network after the optimization, to N × L rank connection weight matrix of reserve pool, N is institute
Echo state network intrinsic nerve member number after stating optimization, L are output dimension, and K is input dimension, and f is neuronal activation letter
Number Sigmoid, x (M-1) are state vector of the echo state network at the M-1 moment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811552246.4A CN109711612A (en) | 2018-12-18 | 2018-12-18 | Wind power generation power prediction method and device for optimizing echo state network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811552246.4A CN109711612A (en) | 2018-12-18 | 2018-12-18 | Wind power generation power prediction method and device for optimizing echo state network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109711612A true CN109711612A (en) | 2019-05-03 |
Family
ID=66255881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811552246.4A Pending CN109711612A (en) | 2018-12-18 | 2018-12-18 | Wind power generation power prediction method and device for optimizing echo state network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109711612A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309979A (en) * | 2019-07-09 | 2019-10-08 | 南方电网科学研究院有限责任公司 | Power load prediction method, device and equipment based on echo state network |
| CN111062170A (en) * | 2019-12-03 | 2020-04-24 | 广东电网有限责任公司 | Transformer top layer oil temperature prediction method |
| CN113610665A (en) * | 2021-08-12 | 2021-11-05 | 东北电力大学 | Wind power generation power prediction method based on multi-delay output echo state network |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6400996B1 (en) * | 1999-02-01 | 2002-06-04 | Steven M. Hoffberg | Adaptive pattern recognition based control system and method |
| US20070185823A1 (en) * | 2005-07-28 | 2007-08-09 | Dingguo Chen | Load prediction based on-line and off-line training of neural networks |
| CN106846173A (en) * | 2016-12-30 | 2017-06-13 | 国网新疆电力公司电力科学研究院 | Short-term wind power forecast method based on EWT ESN |
| CN107133695A (en) * | 2017-04-28 | 2017-09-05 | 北京天诚同创电气有限公司 | A kind of wind power forecasting method and system |
| CN107766986A (en) * | 2017-10-31 | 2018-03-06 | 天津大学 | Leak integral form echo state network on-line study photovoltaic power Forecasting Methodology |
| CN107886193A (en) * | 2017-10-27 | 2018-04-06 | 太原理工大学 | A kind of time sequence forecasting method based on grey wolf optimization echo state network |
-
2018
- 2018-12-18 CN CN201811552246.4A patent/CN109711612A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6400996B1 (en) * | 1999-02-01 | 2002-06-04 | Steven M. Hoffberg | Adaptive pattern recognition based control system and method |
| US20070185823A1 (en) * | 2005-07-28 | 2007-08-09 | Dingguo Chen | Load prediction based on-line and off-line training of neural networks |
| CN106846173A (en) * | 2016-12-30 | 2017-06-13 | 国网新疆电力公司电力科学研究院 | Short-term wind power forecast method based on EWT ESN |
| CN107133695A (en) * | 2017-04-28 | 2017-09-05 | 北京天诚同创电气有限公司 | A kind of wind power forecasting method and system |
| CN107886193A (en) * | 2017-10-27 | 2018-04-06 | 太原理工大学 | A kind of time sequence forecasting method based on grey wolf optimization echo state network |
| CN107766986A (en) * | 2017-10-31 | 2018-03-06 | 天津大学 | Leak integral form echo state network on-line study photovoltaic power Forecasting Methodology |
Non-Patent Citations (3)
| Title |
|---|
| 刘长年: "基于萤火虫优化算法的回声状态网络预测控制研究" * |
| 宋福龙 等: "大规模风电下基于模糊场景聚类的网-储协调规划方法" * |
| 胡海峰 等: "基于Leaky-ESN的光伏发电输出功率预测" * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309979A (en) * | 2019-07-09 | 2019-10-08 | 南方电网科学研究院有限责任公司 | Power load prediction method, device and equipment based on echo state network |
| CN111062170A (en) * | 2019-12-03 | 2020-04-24 | 广东电网有限责任公司 | Transformer top layer oil temperature prediction method |
| CN113610665A (en) * | 2021-08-12 | 2021-11-05 | 东北电力大学 | Wind power generation power prediction method based on multi-delay output echo state network |
| CN113610665B (en) * | 2021-08-12 | 2024-01-30 | 东北电力大学 | Wind power generation power prediction method based on multi-delay output echo state network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lin et al. | An improved moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation | |
| Xi et al. | A novel multi-agent DDQN-AD method-based distributed strategy for automatic generation control of integrated energy systems | |
| CN112186743B (en) | Dynamic power system economic dispatching method based on deep reinforcement learning | |
| CN103390116B (en) | Use the photovoltaic power station power generation power forecasting method of stepping mode | |
| CN106532778B (en) | Method for calculating maximum access capacity of distributed photovoltaic grid connection | |
| Guo et al. | Study on short-term photovoltaic power prediction model based on the Stacking ensemble learning | |
| CN105654207A (en) | Wind power prediction method based on wind speed information and wind direction information | |
| Ye et al. | Combined approach for short-term wind power forecasting based on wave division and Seq2Seq model using deep learning | |
| CN102184453A (en) | Wind power combination predicting method based on fuzzy neural network and support vector machine | |
| CN105449713A (en) | Active power distribution network soft normally open point (SNOP) planning method considering distributed generator characteristics | |
| CN107204615B (en) | Method and system for realizing power prediction | |
| CN103218674A (en) | Method for predicating output power of photovoltaic power generation system based on BP (Back Propagation) neural network model | |
| CN109711612A (en) | Wind power generation power prediction method and device for optimizing echo state network | |
| CN102509027B (en) | Wind powder combined predication method based on cross entropy theory | |
| CN104077632A (en) | Wind power field power prediction method based on deep neural network | |
| CN106451418A (en) | Online clustering equivalent modeling method of photovoltaic power plant | |
| Phan et al. | An approach using transformer-based model for short-term PV generation forecasting | |
| Luo et al. | Short-term photovoltaic generation forecasting based on similar day selection and extreme learning machine | |
| CN108694475B (en) | Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model | |
| CN114638396A (en) | Photovoltaic power prediction method and system based on neural network instantiation | |
| Wang et al. | An LSTM-attention wind power prediction method considering multiple factors | |
| Chenhong et al. | Wind speed prediction research based on time series model with residual correction | |
| Zivkovic et al. | Optimized recurrent neural networks with attention for wind farm energy generation forecasting | |
| CN116070509A (en) | Photovoltaic power ultra-short-term prediction method and system | |
| Yu et al. | Day-ahead wind power prediction based on BP neural network optimized by improved sparrow search algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190503 |