TIME SERIES WIND SPED PREDICTION WITH ENERGY MAPPING USING HYBRID INTRINSIC MODE FUNCTION (IMF) AND EXTENDED INPUT NEURAL NETWORK (EINN)

Accurate and precise wind speed predictions are a prerequisite requirement that isnecessary before siting of wind turbines. The output power of wind energy system iscompletely depends on the behavior of wind speed; a small deviation of wind speed willlead to large energy losses. This paper presents a new technique for predicting the windspeed based on hybrid model Intrinsic Mode Function (IMF) and Extended Input NeuralNetwork (EINN) in the regions where there are limited wind stations. In the first instant,the important parameters for training the artificial neural network (ANN) are acquiredusing the principal component correlation analysis and wind speed signal decomposition,these parameters used as inputs to the ENN. To illustrate the trend and seasonal factor inthe wind speed time series, the data are decomposed into six empirical time series IMF, thenonlinear and non- stationary characteristic of wind speed is handled by empirical modedecomposition (EMD) and EINN respectively. The final predicted values are obtained bysumming all the individual prediction sub models. Wind speed data observed in theexisting wind stations in Sarawak for a period of 1 year from 2015 to 2016 were used forthe simulation. The model implementation confirmed that the proposed model is robust andcapable compared to auto-regression integrated moving average (ARIMA) method.