A new hybrid iterative method for short-term wind speed forecasting Nima Amjady 1 * ,y , Farshid Keynia 1 and Hamidreza Zareipour 2 1 Electrical Engineering Department, Semnan University, Semnan, Iran 2 Department of Electrical and Computer Engineering, Schulich School of Engineering, University of Calgary, Calgary, Alberta, Canada SUMMARY Forecasting wind power is recognized as a tool in mitigating the operational challenges imposed on power systems by large-scale integration of intermittent wind-powered generators. Wind energy is directly dependent upon wind speed, which is a complex signal to model and forecast. In this paper, a new Hybrid Iterative Forecast Method (HIFM) for wind speed forecasting is presented which takes into account the interactions of temperature and wind speed. To select the most relevant and the less redundant input variables from the available data, a two-stage feature selection technique is also introduced. The forecast accuracy of the proposed wind power prediction strategy is evaluated by means of real data of wind power farms of Iran and Spain’s power systems. Copyright # 2010 John Wiley & Sons, Ltd. key words: wind power; wind speed forecast; hybrid iterative forecast method; neural network; feature selection 1. INTRODUCTION Power generation accounts for a significant portion of green house gases generated by human activities [1]. For instance, 26% of greenhouse gas emissions in Europe were resulted from electricity and heat production in year 2007 [2]. To reduce this share, clean energy sources are being increasingly considered in the power sector for electricity generation. Among the available technologies, wind power generation is an important renewable resource used in many countries to replace conventional generation and reduce greenhouse gas emissions [3]. Various multi-megawatt turbines are commercially available for installation in utility scale wind farm configurations [1]. Wind power generation is growing rapidly in many countries. For example, the share of wind power generation in the United States has been increasing with an annual rate of 25% since 1990 [4]. In Spain, wind power generation accounts for 4% of total electric energy production [5]. In the Greek island of Crete, wind power generation may reach 20–40% of its power generation [6]. In the province of Alberta, Canada, the installed wind generation capacity is currently about 600 MW and more than 9000 MW of wind development proposal are under study [7]. In Reference [8], it has been discussed that wind power has potential to supply up to 20% of electric energy in the United Kingdom in the coming years, which requires about 26 GW of installed wind power. Despite the environmental benefits of deploying wind power for electricity generation, its variability can potentially jeopardize power system reliability, which in turn requires more backup conventional generation in the form of reserve and regulation services [9]. In addition, wind power generation impacts electricity market integration and design, real-time grid operations, interconnection standards, ancillary service requirements and costs, power quality, transmission capacity upgrades, and power EUROPEAN TRANSACTIONS ON ELECTRICAL POWER Euro. Trans. Electr. Power 2011; 21:581–595 Published online 8 June 2010 in Wiley Online Library (wileyonlinelibrary.com). DOI: 10.1002/etep.463 *Correspondence to: Nima Amjady, Electrical Engineering Department, Semnan University, Semnan, Iran. y E-mail: amjady@tavanir.org.ir Copyright # 2010 John Wiley & Sons, Ltd.