A New Hybrid ARAR and Neural Network Model for Multi-Step Ahead Wind Speed Forecasting in Three Regions of Pakistan

摘要: Wind is one of the most essential sources clean, environmental friendly, socially constructive, economically beneficial, and renewable energy. To intuit potential this energy in a region accurate wind speed modeling forecasting are crucially important, even for planning, conversion to electricity, trading, reducing instability. However, prediction difficult due intermittency intrinsic complexity data. This study aims suggest more appropriate model Jhimpir, Gharo, Talhar, regions Sindh, Pakistan. Therefore, present combined Autoregressive-Autoregressive (ARAR) Artificial Neural Network (ANN) models propose new hybrid ARAR-ANN better by precisely capturing different patterns time-series data sets. The proposed efficient modeling, statistical errors, effectively. performance compared using three error-statistics Nash-Sutcliffe efficiency-coefficient. empirical results four indices fully demonstrated superiority than persistence model, ARAR, ANN SVM. Indeed, an effective feasible approach forecasting.