Wind Speed Prediction Using a Hybrid Model of the Multi-Layer Perceptron and Whale Optimization Algorithm

Abstract

Wind power as a renewable source of energy, has numerous economic, environmental and social benefits. In order to enhance and control the renewable wind power, it is vital to utilize models that predict wind speed with high accuracy. Due to neglecting of requirement and significance of data preprocessing and disregarding the inadequacy of using a single predicting model, many traditional models have poor performance in wind speed prediction. In the current study, for predicting wind speed at target stations in the north of Iran, the combination of a multi-layer perceptron model (MLP) with the Whale Optimization Algorithm (WOA) used to build new method (MLP-WOA) with a limited set of data (2004)(2005)(2006)(2007)(2008)(2009)(2010)(2011)(2012)(2013)(2014). Then, the MLP-WOA model was utilized at each of the ten target stations, with the nine stations for training and tenth station for testing (namely: Astara, Bandar-E-Anzali, Rasht, Manjil, Jirandeh, Talesh, Kiyashahr, Lahijan, Masuleh and Deylaman) to increase the accuracy of the subsequent hybrid model. Capability of the hybrid model in wind speed forecasting at each target station was compared with the MLP model without the WOA optimizer. To determine definite results, numerous statistical performances were utilized. For all ten target stations, the MLP-WOA model had precise outcomes than the standalone MLP model. The hybrid model had acceptable performances with lower amounts of the RMSE, SI and RE parameters and higher values of NSE, WI and KGE parameters. It was concluded that WOA optimization algorithm can improve prediction accuracy of MLP model and may be recommended for accurate wind speed prediction.

Parameter Reduction in Fuzzy Soft Set Based on Whale Optimization Algorithm

“…Beyond the certain rang, whales will search randomly. At present, WOA algorithm has been successfully applied in many fields, such as wind speed prediction [22] , irrigation scheduling [23] and energy saving [24] .…”

Generation Expansion Planning in the Presence of Wind Power Plants Using a Genetic Algorithm Model

“…To calculate the amount of energy supplied by each unit at each stage ( , ), at each planning stage, the units are arranged in descending order of variable operating cost. Using the LDC linear curve, the energy supplied by each unit, which is equivalent to the area below the curve, is calculated from Equation (17).…”

“…For example, objective functions can be profit maximization of a generation company in the restructured power market [9], maximizing reliability [10,11], minimizing operating costs [12,13], and minimizing environmental pollution [14,15]. In addition, constraints such as network security constraints [16][17][18][19][20][21], investment costs [22][23][24], reliability [25][26][27][28][29], and environmental pollution [30] could be part of the constraints that are required to be considered in the GEP problem. Although less attention has been paid to the GEP problem in the presence of wind power plants in the literature, extensive studies have been carried out on GEP of traditional power plants with various objective functions and constraints [31,32].…”

A Hybrid Deep Interval Prediction Model for Wind Speed Forecasting

“…In [39], the researchers presented a deep learning-based GRU and tree-based model for estimating daily reference evapotranspiration. A hybrid model of the multi-layer perceptron and whale optimization algorithm has been proposed to forecasting win speed and achieved high-quality prediction results [40]. Nowadays, the prediction models are mostly hybrid models, so we study and propose one hybrid model in the paper.…”