Average Hourly Wind Speed Forecasting with ANFIS

Wind energy is increasing its participation as a main source of energy in power grids and electric utility systems around the world. One of the main difficulties of integrating large amounts of wind energy in power grids is the natural intermittency of its generated power [1, 2] due to the energy produced from the wind turbine being dependent on the availability of the wind, which is highly stochastic in nature. To address this problem, more accurate and reliable wind power forecasting techniques have been proposed [1, 2]. This paper explores a new approach using Adaptive Neuro-Fuzzy Inference Systems (ANFIS) to forecast the average hourly wind speed. To determine the characteristics of ANFIS that best suited the target wind speed forecasting system, several ANFIS models were trained, tested and compared. Different types and number of inputs, training and checking sizes, type and number of membership functions and techniques to generate the initial Fuzzy Inference Systems (FIS) were analyzed. Comparisons of the different models were performed and the results showed that the 4 inputs models generated by grid partitioning and the 6 inputs models generated by subtractive clustering provided the smallest errors with the models using wind speed and air pressure as inputs having the best forecasting accuracy. Since using different variables that are correlated with wind speed provided the best overall results, recommendations are provided for continued research into this area.

[1]  S. Mathew.  Wind Energy: Fundamentals, Resource Analysis and Economics , 2006 .

[2]  Yuan-Kang Wu,et al.  A literature review of wind forecasting technology in the world , 2007, 2007 IEEE Lausanne Power Tech.

[3]  Georges Kariniotakis,et al.  Evaluation of advanced wind power and load forecasting methods for the optimal management of isolated power systems , 1999 .

[4]  Ferenc Szeifert,et al.  Fuzzy modeling with multivariate membership functions: gray-box identification and control design , 2001, IEEE Trans. Syst. Man Cybern. Part B.

[5]  Walter Vandaele,et al.  Applied Time Series and Box-Jenkins Models , 1983 .

[6]  M. Negnevitsky,et al.  Very short-term wind forecasting for Tasmanian power generation , 2006, 2006 IEEE Power Engineering Society General Meeting.

[7]  Michael Negnevitsky,et al.  SHORT-TERM WIND FORECASTING TECHNIQUES FOR POWER GENERATION , 2004 .

[8]  M. Negnevitsky,et al.  Innovative short-term wind generation prediction techniques , 2006, 2006 IEEE Power Engineering Society General Meeting.

[9]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[10]  J. J. Christy.  Pressure and Wind , 1971 .

[11]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[12]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[13]  J.-S.R. Jang,et al.  Input selection for ANFIS learning , 1996, Proceedings of IEEE 5th International Fuzzy Systems.