One, Two and Three Steps Ahead Wind Speed Prediction Using Enhanced Random Forest with Bayesian Optimisation

Wind energy-based power production worldwide adapts to meet energy demand and maintain sustainability. However, wind and maximum energy yield uncertainty require a precise and top-notch prediction model. The development of stakeholders’ businesses requires technological advancements to boost their profits. To address the issue as mentioned above, this paper endeavours to develop an enhanced Random Forest with Bayesian Optimisation (ERF-BO) for short-term wind speed forecasting, focusing on one-step, two-step, and three-step ahead predictions. The superiority of the proposed ERF-BO is verified based on the comparative investigation with other classical baseline models, namely autoregressive integrated moving average (ARIMA), Random Forest (RF), Support Vector Regression (SVR), Long short-term memory (LSTM), eXtreme Gradient Boosting (XGBoost) and Random Forest with Bayesian Optimisation (RF-BO). The simulation results analysis confirms that the proposed multi-objective optimisation framework-based ERF-BO model yields superior forecasting compared to baseline models. This paper suggests that the ERF-BO prediction model may assist stakeholders and power systems in optimal management.