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

Abstract

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 ecofriendly 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.

Application of AMOGWO in Multi-Objective Optimal Allocation of Water Resources in Handan, China

“…Luo et al proposed an improved GWO algorithm based on complex numerical coding [69]. Madhiarasan et al reduced the grouping the of gray wolf population and classified the subordinate wolf group and the lowest level wolf group into one population, thereby reducing the computational complexity and increasing the convergence speed of the algorithm [70]. Long et al used the good point set theory to initialize the population [71].…”

Non‐destructive detection for mold colonies in rice based on hyperspectra and GWO‐SVR

“…in optimization problems . It has therefore become more widely applied in areas such as wind speed prediction, water allocation and function optimization . In this study, the GWO algorithm was adopted to search for the optimal parameters c (penalty factor) and g (kernel function parameter) in SVR, and the specific process was as follows: The rice mold data were was partitioned into calibration and prediction sets; the calibration set was then used as training samples for the SVR model.…”

Accurate prediction of different forecast horizons wind speed using a recursive radial basis function neural network

“…Hence, the suggested novel criterion improves forecasting accuracy. Other related work on developing wind speed forecasting models has also been reported in [14][15][16][17][18][19][20][21][22].…”