Advanced
Prediction of Wind Power by Chaos and BP Artificial Neural Networks Approach Based on Genetic Algorithm
Prediction of Wind Power by Chaos and BP Artificial Neural Networks Approach Based on Genetic Algorithm
Journal of Electrical Engineering and Technology. 2015. Jan, 10(1): 41-46
Copyright © 2015, The Korean Institute of Electrical Engineers
This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/)which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • Received : August 25, 2013
  • Accepted : September 04, 2014
  • Published : January 01, 2015
Download
PDF
e-PUB
PubReader
PPT
Export by style
Article
Author
Metrics
Cited by
TagCloud
About the Authors
Dai-Zheng Huang
School of Electrical Engineering, Guangxi University, Nanning 530004, China. (huangdaizheng@gmail.com;871009450@qq.com)
Ren-Xi Gong
Corresponding Author: School of Electrical Engineering, Guangxi University, Nanning 530004, China. (rxgong@gxu.edu.cn)
Shu Gong
School of Electrical Engineering, Guangxi University, Nanning 530004, China. (huangdaizheng@gmail.com;871009450@qq.com)

Abstract
It is very important to make accurate forecast of wind power because of its indispensable requirement for power system stable operation. The research is to predict wind power by chaos and BP artificial neural networks (CBPANNs) method based on genetic algorithm, and to evaluate feasibility of the method of predicting wind power. A description of the method is performed. Firstly, a calculation of the largest Lyapunov exponent of the time series of wind power and a judgment of whether wind power has chaotic behavior are made. Secondly, phase space of the time series is reconstructed. Finally, the prediction model is constructed based on the best embedding dimension and best delay time to approximate the uncertain function by which the wind power is forecasted. And then an optimization of the weights and thresholds of the model is conducted by genetic algorithm (GA). And a simulation of the method and an evaluation of its effectiveness are performed. The results show that the proposed method has more accuracy than that of BP artificial neural networks (BP-ANNs).
Keywords
1. Introduction
Wind energy is an inexhaustible energy source and it has been paid more attention to worldwide in recent years [1 - 4] . Wind power prediction is an indispensable requirement for grid-connection operation because of the randomness of wind power.
The prediction of wind power has become an important issue on power system planning and many researchers have established mathematical models with which to predict in recent years [5 - 8] . But the most models to study wind power are based on linear theory. Because of its complicated and nonlinear characteristics, the results will be inaccurate with wind power predicted by linear theory.
Chaos theory has become a powerful theory for nonlinear science research [9 , 10] , by which the order and regularity hidden behind the disordered and complex phenomena can be revealed. In predicting wind power, a reconstruction of the phase space of one dimensional time series is made and the laws hidden behind it are revealed with this theory.
BP-ANNs, often referred to as ‘black boxes’ in which the parameters are difficult to obtain, provide a powerful method of identifying highly complex traits in data sets. It can be widely used in time series forecasting due to its characteristics of extreme computational power, massive parallelism, and fault tolerance [1 , 11 - 13] . And it is more efficient through learning without enormous programming. BP-ANNs is not only can learn the smooth prediction function but also can be trained to enumerate unexpected short term regularities in time series.
CBPANNs approach is employed for wind power forecasting in the paper. A calculation of the largest Lyapunov exponent of the time series of wind power and a judgment of whether wind power has chaotic behavior are made at first. Secondly, the best delay time and best embedding dimension are calculated to reconstruct the phase space and determine the structure of CBPANNs. In CBPANNs, the weights and thresholds are optimized by GA. Finally, the output of a wind farm, as an example, is simulated by CBPANNs and BP-ANNs approaches. The result shows that the CBPANNs algorithm has great advantages over that of BP-ANNs in accuracy.
2. Proposed Methodology
The CBPANNs modeling is based on chaos theory, BPANNs theory and genetic optimization.
- 2.1 Chaos determination
The Lyapunov exponent is the average rate of exponential separation in adjacent orbit of phase space and it is the most important characteristic of chaotic dynamical system. The system with the time series having at least one positive largest Lyapunov exponent is a chaotic system. Wolf method [14] is used to calculate the largest Lyapunov exponent.
- 2.2 Phase space reconstitution
The output of wind power, sampled at the given intervals, is a discrete time series. The phase space of this time series can be reconstructed according to Pakard and Takens theory [15] . On the basis of the theory, all the dynamic information determining the system state, are contained in time series of the system variables. The system state orbit will still retain the main features of the original system state when the time series of single system variable is embedded to a new coordinate system. During the process of the phase space reconstruction, the evolution information of system variables can be extracted from one-dimensional time series of the system variables. That is to say, the time series x 0 , x 1 , x 2 , ..., xn can be transformed into xn ( m, τ ) = ( xn , x n+τ ,..., x n+(m-1)τ ) . Where m is the embedded dimension, τ is the time delay, which is an integral multiple of the sampling time interval.
- 2.3 Calculation of best embedding dimension and best delay time
The best embedding dimension and best delay time can be calculated by C-C method [16] , which can be described as follows:
The time series { x ( i ), i = 1,2,..., n } is decomposed into n non-overlapping subsequences at first.
PPT Slide
Lager Image
where n is the length of the time series and it is an integral multiple of τ .
Block averaging strategy is used to calculate test statistics as follows.
PPT Slide
Lager Image
where r is the search radius. If the time series { x ( t )} distributes independently and identically, S 2 ( m, r, τ ) will equal zero for all the r when both τ and m are fixed and n tends to infinity. The actual time series is finite and interrelated, however, S 2 ( m, r, τ ) is not always equal to zero. τ ~ S 2 ( m, r, τ ) expresses the autocorrelation of time series. The first zero point in τ ~ S 2 ( m, r, τ ) or the time of the minimum difference for all the radiuses can be selected as the optimal time delay τd .
The parameters for calculating τd and m are taken as:
  • n= 120 ,m= 2,3,4,5 ,ri=i× 0.5σ,i= 1,2,3
where σ = std ( x ) is the standard deviation of time series.
PPT Slide
Lager Image
PPT Slide
Lager Image
The first zero point or the first local minimum in
PPT Slide
Lager Image
is taken as τd .
Define
PPT Slide
Lager Image
And the global minimum in S 2cor ( t ) is taken as embedded window τw . Then m can be obtained by τw = ( m −1) τ .
- 2.4 BP-ANNs
The BP-ANNs model contains three layers: one input, one hidden and one output layer. If the model has i input nodes, j hidden nodes, and k output nodes, there will be weights of N = i×j between input layer and hidden layer, thresholds of j in hidden layer, weights of M = j×k between hidden layer and output layer and thresholds of k in output layer.
- 2.5 BP-ANNs
The initial weights and thresholds of BP-ANNs are optimized by GA, which can improve network performance to make forecasting more accurate.
- 2.5.1 Population Initialization
The four variables of BP-ANNs, including the weights between the input layer and hidden layer, the thresholds of the hidden layer, the weights between the hidden layer and output layer, and the thresholds of the output layer, are encoded as binary string. And all of them are sequentially combined as an individual code.
- 2.5.2 Fitness Selection
The error matrix norm between the prediction and actual data in samples is taken as the objective function, the sort of which is made by calling the ranking function FitnV=ranking (obj) (obj is objective function), and the results act as the fitness function.
- 2.5.3 Genetic manipulation
In genetic operation, the selection, crossing and mutation of individuals are respectively made by stochastic universal sampling, single point crossover and probability choosing.
- 2.6 CBPANNs algorithm
On the basis of the analysis above, the method can be descried as follows.
The data of wind power are sampled at intervals of 15 minutes and the sampled data are taken as the original time series at first. Then the largest Lyapunov exponent of the time series is calculated by Wolf method to determine whether the time series have chaotic behavior. If so, the best embedding dimension and best delay time are calculated based on C-C method, and then the phase space is reconstructed. Finally, a three-layer CBPANNs is constructed according to the phase space, at the same time, the weights and thresholds of CBPANNs are optimized by GA. The algorithm flow chart is shown in Fig. 1 .
PPT Slide
Lager Image
Flow chart
3. Simulation
In order to verify the validity of CBPANNs method, a sampled data of wind power is simulated and analyzed.
The wind power data are sampled at intervals of 15 minutes from 0:00 on 5/10/2012 to 23:00 on 6/6/2012 in a wind farm, which are taken as the original time series, and shown in Fig. 2 .
PPT Slide
Lager Image
Time series of wind power
The largest Lyapunov exponent λ max = 0.1943 can be obtained. Therefore, the time series of wind power have chaotic behavior. The variation of
PPT Slide
Lager Image
,
PPT Slide
Lager Image
and S 2cor ( t ) with time can be drawn in Fig. 3 . Then τd = 12 and τW = 72 can be obtained, thus having m = 7 .
PPT Slide
Lager Image
Variation of , and S2cor(t) with time
τd and m are used to reconstruct the phase space of X = { x (1), x (2),..., x (2688)} . A reconstructed phase space which is a matrix of ( n - τw m , is established by taking the data in X. The elements of the row are composed of the data taken at the interval of τd and those of the column of the data taken from x ( i ) to x ( i + τw ) ( i =1,2,…,(n- τw )) successively. Therefore, the reconstructed phase space can be expressed by:
PPT Slide
Lager Image
The hidden node n 2 and the input node n 1 in three-layer BP-ANNs are related by n 2 =2 n 1 +1. Therefore, a three-layer CBPANNs model with 7 ( n 1 = m ) input nodes, 15 hidden nodes and 1 output node (7-15-1) is obtained, which is shown in Fig. 4 . The following fitting function can be achieved by the model.
PPT Slide
Lager Image
PPT Slide
Lager Image
CBPANNs model
The original time series that come from the 73th to 2208th data are taken as training samples and the 2209th to 2688th data are taken as testing samples. Let the error between training output and expected output (actual output) be 0.001, learning rate be 0.9, momentum factor be 0.95, the training time be 1000, and the parameters of GA be as shown in Table 1 .
Parameters of GA
PPT Slide
Lager Image
Parameters of GA
In order to compare the results forecasted by BP-ANNs and CBPANNs methods, a simulation is performed under the same conditions, and the results are shown in Fig. 5 .
PPT Slide
Lager Image
Comparison output of BP-ANNs and CBPANNs
The absolute error (AE), relative error (RE), correlation coefficient(R), mean square error (MSE), root mean square error (RMSE), mean average error (MAE), mean average percentage error (MAPE) and sum of squared error (SSE) are used to evaluate the forecasting effect of CBPANNs. They are defined as shown in Eqs. (8)-(15).
PPT Slide
Lager Image
where ŷi are the forecasting values and yi are the actual values.
PPT Slide
Lager Image
AE and RE are respectively plotted in Figs. 6 and 7 . From the figures, it can be seen that the forecasted results by CBPANNs method have higher accuracy and smaller AE and RE than those by BP-ANNs approach. When the wind power fluctuates drastically, both the AE and RE calculated by the two methods will increase. But they are much smaller by CBPANNs than by BP-ANNs.
PPT Slide
Lager Image
PPT Slide
Lager Image
PPT Slide
Lager Image
PPT Slide
Lager Image
PPT Slide
Lager Image
PPT Slide
Lager Image
PPT Slide
Lager Image
Comparison of absolute errors
PPT Slide
Lager Image
Comparison of relative errors
In Table 2 are listed the main evaluation indexes calculated by these two methods. It can be seen that CBPANNs method has advantages over BP-ANNs in all the evaluation indexes, thus proving the effectiveness of the prediction by CBPANNs.
Comparison of evaluation indexes
PPT Slide
Lager Image
Comparison of evaluation indexes
The evaluation indexes will become poor with the increasing length of testing samples. In order to analyze the variation of the evaluation indexes with training samples and testing samples, four groups of data are taken which are shown in Table 3 , and a simulation of them is performed. The RE of prediction of the final original time series that come from the 2209th to 2688th data(from 0:00 on 6/1/2012 to 23:00 on 6/6/2012)are compared, which are plotted in Fig. 8 . It can be seen that the shorter the length of the training samples and the longer the length of the testing samples, the greater the RE will be.
Four groups of data taken for simulation
PPT Slide
Lager Image
Four groups of data taken for simulation
Comparison of evaluation indexes under the condition of the different lengths of the training samples and testing samples
PPT Slide
Lager Image
Comparison of evaluation indexes under the condition of the different lengths of the training samples and testing samples
PPT Slide
Lager Image
Variation of relative errors with testing data
4. Conclusion
The research proposes CBPANNs, a new method for forecasting wind power, of which the initial weights and thresholds are optimized by GA. The results obtained show that this method is characterized by high precision.
Acknowledgements
This work was supported by natural science foundation of Guangxi Province(Grant number: 2010GXNSFA 013023); science and technology plans of Nanning City (Grant number:20121025) and graduate innovation fund of Guangxi Province(Grant number: GXU11T31085).
BIO
Dai-Zheng Huang He received a M.S. degree in optical engineering from Huazhong University of science and technology in 2006, and is presently working toward a Ph.D. degree in electric power system and automation in Guangxi University. He now research interests are artificial intelligence and microgrids.
Ren-Xi Gong He received a Ph.D. degree in microelectronics and solidstate electronics from Xidian University in 2002, and is presently a professor at Electrical Engineering School of Guangxi University. His present research interests concentrate on new energy.
Shu Gong was born in 1989 and received the B.S degree in electrical engineering from Guangxi University in Guangxi, China. She is currently an postgraduate in electrical engineering college in Guangxi University. Her research interests in power system operation and planning.
References
Ramesh Babu N , Arulmozhivarman P 2013 “Improving forecast accuracy of wind speed using wavelet transform and neural networks,” J Electr Eng Technol 8 559 - 564    DOI : 10.5370/JEET.2013.8.3.559
Ramesh Babu N , Arulmozhivarman P 2012 “Forecasting of wind speed using artificial neural networks,” Int. Rev. Mod. Sim 5 (5)
Lyu Jae-Kun , Heo Jae-Haeng , Kim Mun-Kyeom , Park Jong-Keun 2013 “Impacts of wind power integration on generation dispatch in power systems,” J Electr Eng Technol 8 453 - 463    DOI : 10.5370/JEET.2013.8.3.453
Ch. Ulam-Orgil , Lee Hye-Won , Kang Yong-Cheol 2012 “Evaluation of the wind power penetration limit and wind energy penetration in the Mongolian central power system,” J Electr Eng Technol 7 852 - 858    DOI : 10.5370/JEET.2012.7.6.852
Marta Poncela , Pilar Poncela , Peran Jose Ramon 2013 “Automatic tuning of Kalman filters by maximum likelihood methods for wind energy forecasting,” Appl. Energy 108 349 - 362    DOI : 10.1016/j.apenergy.2013.03.041
Peng Kou , Feng Gao , Xiaohong Guan 2013 “Sparse online warped Gaussian process for wind power probabilistic forecasting,” Appl. Energy 108 410 - 428    DOI : 10.1016/j.apenergy.2013.03.038
Wenyu Zhang , Jujie Wang , Jianzhou Wang 2013 “Shortterm wind speed forecasting based on a hybrid model,” Appl. Soft Comput 13 3225 - 3233    DOI : 10.1016/j.asoc.2013.02.016
Zhou Z , Botterud A , Wang J 2013 “Application of probabilistic wind power forecasting in electricity markets,” Wind Energy 16 321 - 338    DOI : 10.1002/we.1496
Rasoolzadeh Arsalan , Tavazoei Mohammad Saleh 2012 “Prediction of chaos in non-salient permanent-magnet synchronous machines,” Phys Lett A 33 73 - 79
Farzin S , Ifaei P , Farzin N 2012 “An investigation on changes and prediction of Urmia Lake water surface evaporation by chaos theory,” Int J Environ Res 6 815 - 824
PaoH siao-Tien 2007 “Forecasting electricity market pricing using artificial neural networks,” Energ Convers Manage 48 907 - 912    DOI : 10.1016/j.enconman.2006.08.016
Ozgur Tayfun , Tuccar Gokhan , Ozcanli Mustafa 2011 “Prediction of emissions of a diesel engine fueled with soybean biodiesel using artificial neural networks,” Energy Education Science And T 27 301 - 312
Grossi Enzo , Buscema Massimo 2007 “Introduction to artificial neural networks,” Eur J Gastroen Hepat 19 1046 - 1054    DOI : 10.1097/MEG.0b013e3282f198a0
Wolf A 1985 “Determining Lyapunov exponents from a time series,” Physica D 16 285 - 317    DOI : 10.1016/0167-2789(85)90011-9
Grassberger P 1983 “Generalized dimensions of strange attractors,” Phys Lett A 97 227 - 230    DOI : 10.1016/0375-9601(83)90753-3
Kim H S , Eykholt R , Salas J D 1999 “Nonlinear dynamics, delay times and embedding windows,” Physica D 127 48 - 60    DOI : 10.1016/S0167-2789(98)00240-1