Predicting of the short term wind speed by using a real valued genetic algorithm based least squared support vector machine

The possible future energy shortage has become a very serious problem in the world. An alternative energy which can replace the limited reservation of fossil fuels will be very helpful. The wind has emerged as one of the fastest growing and most important alternative energy sources during the past decade. However, the most serious problem being faced by human beings in wind applications is the dependence on the volatility of the wind. To apply the wind power efficiently, predictions of the wind speed are very important. Thus, this paper aims to precisely predict the short term regional wind speed by using a real valued genetic algorithm (RGA) based least squared support vector machine (LS-SVM). A dataset including the time, temperature, humidity, and the average regional wind speed being measured in a randomly selected date from a wind farm being located in Penghu, Taiwan was selected for verifying the forecast efficiency of the proposed RGA based LS-SVM. In this empirical study, prediction errors of the wind turbine speed are very limited. In the future, the proposed forecast mechanism can further be applied to the wind forecast problems based on various time spans.