Estimating the output power and wind speed with ML methods: A case study in Texas

Abstract

Because there is such a significant problem with global warming and emissions of greenhouse gases, we decided to reduce the adverse effects on the environment caused by the burning of fossil fuels during the generation of electricity in fossil fuel power plants by using renewable energy instead of fossil fuels in this article. As a result, a study was conducted on a wind farm in Texas, the United States.Random Forest, Ada Boost, and K Neighbors methods were used to predict the turbine output capacity and wind speed, which is the most critical factor in wind farm production power, and evaluation criteria such as mean absolute error, root mean square error, mean absolute percentage error, R2, and algorithms' running time were calculated.Results showed that Random Forest had the best performance in Predicting Power Generation and predicting Wind Speed also K Neighbors algorithm had the weakest performance and shortest running time in predicting wind speed and power generation.