Abstract:

The forecast of the power generated by a wind power plant is a process that wind farm companies need to do every day. Electrical system manager uses these forecasts to plan the next day’s electrical generation. Thus, while generation-consumption balance in the grid is maintained, numbers of reserve power plants are decreased. Wind power has uncertainty as it depends on nature. Therefore, wind speed forecasts and wind direction forecasts of the power plant area are generally used in wind power forecasts. In this study, hourly wind power generation of next day is forecasted by using Adaptive Neuro Fuzzy Inference System (ANFIS) and Support Vector Regression (SVR) methods. The hour of day, wind speed forecast and wind direction forecast are the inputs of the forecast system. One-year data are selected as training data, six-mount data are forecasted. Five different models are formed by using the system inputs in different configurations and final forecast are found by averaging the model forecasts. The average normalized mean absolute error values are found 10.86% and %10.8 with ANFIS and SVR, respectively. 

Keywords: