Wind Power Generation Forecasting Using Machine Learning

Wind power has become an important source of power for some countries because wind is renewable,wind power is clean and no pollutants are produced compared to fossil fuels which are mainly used for the generation of energy today.Because of these reasons the world's attention towards the use of wind power has grown.In the past decade,a lot of research has been performed on the forecasting of wind power production over a period of minutes,days,months and years.This thesis focuses on short term forecasting and starts with a theoretical overview of Wind energy.The main reason to focus short term forecasting is to ensure the balance between the demand and supply of electricity.Based on a literature study in the field of forecasting wind power,it has been found that factors such as geographical location,data sources and forecasting methods show influence on the accuracy of prediction of wind power.Furthermore,it is found in literature that input parameters such as wind speed,wind direction,weather stability,availability,relative humidity and seasonal data are very useful as input data for forecasting methods to forecast wind power.From a large set of forecasting methods it has been found that the most used techniques to predict wind power are physical methods,and statistical or hybrid methods such as neural networks.This research has obtained forecasting results from using RNN,LSTM,hybrid approach and ensemble approach.Novel method is introduced by combining both hybrid and ensemble approach.