Design of Neural Network Based Wind Speed Prediction Model Using GWO

Abstract

The prediction of wind speed is imperative nowadays due to the increased and effective generation of wind power. Wind power is the clean, free and conservative renewable energy. It is necessary to predict the wind speed, to implement wind power generation. This paper proposes a new model, named WT-GWO-BPNN, by integrating Wavelet Transform (WT), Back Propagation Neural Network (BPNN) and Grey Wolf Optimization (GWO). The wavelet transform is adopted to decompose the original time series data (wind speed) into approximation and detailed band. GWO -BPNN is applied to predict the wind speed. GWO is used to optimize the parameters of back propagation neural network and to improve the convergence state. This work uses wind power data of six months with 25, 086 data points to test and verify the performance of the proposed model. The proposed work, WT-GWO-BPNN, predicts the wind speed using a three-step procedure and provides better results. Mean Absolute Error (MAE), Mean Squared Error (MSE), Mean absolute percentage error (MAPE) and Root mean squared error (RMSE) are calculated to validate the performance of the proposed model. Experimental results demonstrate that the proposed model has better performance when compared to other methods in the literature.

The Development and Application Research of Grey Wolf Optimization Algorithm

“…The optimized CNN-LSTM network exhibited enhanced learning capabilities. Grace et al [29] introduced a novel model for wind speed prediction by combining wavelet transformation, backpropagation neural networks, and the GWO algorithm. They utilized the GWO to optimize the parameters of the backpropagation neural network, improving convergence and enhancing the model's performance.…”

Prediction of Water Resistance of Magnesium Oxychloride Cement Concrete Based upon Hybrid-BP Neural Network

“…The grey wolf has a strict social hierarchy, as shown in Figure 8a [23], in which the α is the leader and is responsible for all decisions; the β helps the α make decisions and assumes responsibility when necessary; δ is subject to α; β is responsible for sentry, reconnaissance, and other affairs; while ω is at the bottom of the hierarchy, and is responsible for balancing the population's internal relationships. The hunting process includes three steps primarily: (1) Tracking and approaching prey; (2) Harassing, pursuing, and encircling prey; (3) Attacking prey.…”

“…The core idea of the GWOA is to assume that α, β, and δ understand the potential location of prey better, i.e., the location of the best solution in the decision-making space of optimization problems, and other wolves update their own position basis on gray wolves α, β, and δ, and approach the prey gradually (optimal solution). The schematic diagram of the gray wolf position update is shown in Figure 8b [23]. The behavior of gray wolves during collective hunting is defined as follows [23].…”

“…The schematic diagram of the gray wolf position update is shown in Figure 8b [23]. The behavior of gray wolves during collective hunting is defined as follows [23].…”

“…Inspired by various animal group behaviors in nature, experts and scholars have proposed swarm intelligence optimization algorithms to optimize the BPNN algorithm and reach the goal of achieving global optimal solutions that can be applied to solve largescale, high-dimensional problems based upon different activity mechanisms within animal populations. Algorithms that are used commonly include the gray wolf optimization algorithm (GWO) [23], whale optimization algorithm (WOA) [24], particle swarm optimization algorithm (PSO) [25], etc. These algorithms take the population particles as the starting position of the target function to be processed and simulate the movement update like an animal group to identify the best position and find a suitable global optimal solution ultimately.…”