Long-Term Wind Speed Forecasting using Spiking Neural Network Optimized by Improved Modified Grey Wolf Optimization Algorithm.

Wind speed forecasting is most needed due to its essentiality in wind farm and power system control and planning operation. Due to the increase of energy demands in order to meet the energy requirement wind energy receive a center of attraction because of its huge amount of availability and eco-friendly characteristics. Though numerous researches implemented different wind speed forecasting models, exact forecasting with the greatest accuracy is still thrusting topic in research. This article proposes two fold novel techniques for long-term wind speed forecasting namely improved spike prop algorithm incorporate spiking neural network (SNN) and improved modified grey wolf optimization algorithm (IMGWOA) based hybrid technique (SNN-IMGWOA). Proposed long-term forecasting technique using spiking neural network optimized through improved modified grew wolf optimization algorithm suitability and performance evaluation analyzed and compared with various earlier optimization algorithm namely GA, ES, PSO, ABC, GSA, CS, CSS and GWO and improved spike prop algorithm associated spiking neural network superiority confirmed with comparison between various traditional techniques such as Persistence, ARIMA, BPN, MLPN, RBFN, ELMAN Network and SVM. Simulations performed based on the observed real-time wind data’s; numerical results and analyzes prove the virtue of proposed techniques.