A Combined Model Based on Neural Networks, LSSVM and Weight Coefficients Optimization for Short-Term Electric Load Forecasting

As an essential energy in the daily life, electricity which is difficult to store has become a hot issue in power system. Short-term electric load forecasting (STLF) which is regarded as a vital tool helps electric power companies make good decisions. It can not only guarantee adequate energy supply but also avoid unnecessary wastes. Although there exists quantity of forecasting methods, most of them are not able to make accurate predictions. Therefore, a forecasting method with high accuracy is particularly important. In this paper, a combined model based on neural networks and least squares support vector machine (LSSVM) is proposed to improve the forecasting accuracy. At first, three forecasting methods named generalized regression neural network (GRNN), Elman, LSSVM are utilized to forecast respectively. Among them, simulate anneal (SA) arithmetic is used to optimize GRNN. Then, SA is employed to determine the weight coefficients of each individual method. At last, multiplying all the three forecasting results with the corresponding weights, the final result of the combined model can be attained. Using the electric load data of Queensland of Australia as experimental simulation, case studies show that the proposed combined model works well for STLF and the results prove more accurate.

[1]  Rohitash Chandra,et al.  Competition and Collaboration in Cooperative Coevolution of Elman Recurrent Neural Networks for Time-Series Prediction , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Li Xie,et al.  Electricity price forecasting by clustering-LSSVM , 2007, 2007 International Power Engineering Conference (IPEC 2007).

[3]  Ning An,et al.  Using multi-output feedforward neural network with empirical mode decomposition based signal filtering for electricity demand forecasting , 2013 .

[4]  Sanjay M. Kelo,et al.  A wavelet Elman neural network for short-term electrical load prediction under the influence of temperature , 2012 .

[5]  Bangjun Lei,et al.  GRNN Short-term Load Forecasting Model and Virtual Instrument Design , 2011 .

[6]  E. Caamaño-Martín,et al.  Improving photovoltaics grid integration through short time forecasting and self-consumption , 2014 .

[7]  Rui Zhang,et al.  Short-term load forecasting of Australian National Electricity Market by an ensemble model of extreme learning machine , 2013 .

[8]  Ali Deihimi,et al.  Application of echo state networks in short-term electric load forecasting , 2012 .

[9]  Maarouf Saad,et al.  An efficient approach for short term load forecasting using artificial neural networks , 2006 .

[10]  Pin Lv,et al.  Cloud theory-based simulated annealing algorithm and application , 2009, Eng. Appl. Artif. Intell..

[11]  Jianzhou Wang,et al.  A hybrid model based on data preprocessing for electrical power forecasting , 2015 .

[12]  S. C. Chelgani,et al.  Microwave irradiation pretreatment and peroxyacetic acid desulfurization of coal and application of GRNN simultaneous predictor , 2011 .

[13]  Ilias Petrounias,et al.  A hybrid intelligent approach for the prediction of electricity consumption , 2012 .

[14]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[15]  Song Li,et al.  Short-term load forecasting by wavelet transform and evolutionary extreme learning machine , 2015 .

[16]  Kin Keung Lai,et al.  A neuro-fuzzy combination model based on singular spectrum analysis for air transport demand forecasting , 2014 .

[17]  Haiyan Lu,et al.  Combined modeling for electric load forecasting with adaptive particle swarm optimization , 2010 .

[18]  Qing Song,et al.  On the Weight Convergence of Elman Networks , 2010, IEEE Transactions on Neural Networks.

[19]  H. Shayeghi,et al.  Day-ahead electricity prices forecasting by a modified CGSA technique and hybrid WT in LSSVM based scheme , 2013 .

[20]  Jianhua Zhang,et al.  A hybrid forecasting model with parameter optimization for short-term load forecasting of micro-grids , 2014 .

[21]  Wei-Chiang Hong,et al.  Electric load forecasting by seasonal recurrent SVR (support vector regression) with chaotic artific , 2011 .

[22]  Xiang Zhou,et al.  Short-term power load forecasting using grey correlation contest modeling , 2012, Expert Syst. Appl..

[23]  Wei-Chiang Hong,et al.  Traffic flow forecasting by seasonal SVR with chaotic simulated annealing algorithm , 2011, Neurocomputing.

[24]  Sen Guo,et al.  A hybrid annual power load forecasting model based on generalized regression neural network with fruit fly optimization algorithm , 2013, Knowl. Based Syst..

[25]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[26]  Lihua Fu,et al.  Unbiased Least Squares Support Vector Machine with Polynomial kernel , 2006, 2006 8th international Conference on Signal Processing.

[27]  Dilip Kumar Pratihar,et al.  A combined neural network and genetic algorithm based approach for optimally designed femoral implant having improved primary stability , 2016, Appl. Soft Comput..

[28]  Ping-Feng Pai,et al.  Support Vector Machines with Simulated Annealing Algorithms in Electricity Load Forecasting , 2005 .

[29]  Xiang Li,et al.  Chaotifying linear Elman networks , 2002, IEEE Trans. Neural Networks.

[30]  Saifur Rahman,et al.  Analysis and Evaluation of Five Short-Term Load Forecasting Techniques , 1989, IEEE Power Engineering Review.