Wind Speed Ensemble Forecasting Based on Deep Learning Using Adaptive Dynamic Optimization Algorithm

The development and deployment of an effective wind speed forecasting technology can improve the stability safety power systems with significant penetration. However, due to wind’s unpredictable unstable qualities, accurate is extremely challenging. Several algorithms were proposed for this purpose level reliability. A common method making predictions based on time series data long short-term memory (LSTM) network. This paper a machine learning algorithm, called adaptive dynamic particle swarm algorithm (AD-PSO) combined guided whale optimization (Guided WOA), ensemble forecasting. AD-PSO-Guided WOA selects optimal hyper-parameters value LSTM deep model purposes speed. In experiments, dataset employed predict hourly generation up forty-eight hours ahead at seven farms. case study taken from Kaggle Global Energy Forecasting Competition 2012 in results demonstrated that AD-PSO-GuidedWOA provides high accuracy outperforms number comparative algorithms. Different tests’ statistical analysis, including Wilcoxon’s rank-sum one-way analysis variance (ANOVA), confirms algorithm.