The present research focuses on the development and optimization of the particle swarm techniques inspired in nature to predict wind speed in renewable energies with real-time wind farm data structures, of unique machine learning architectures for neural networks alongside certain mathematical and stochastic populations. The research work in this article includes six modules, i.e., designing proposed architectures of the neural network with variants based on population stochastic particle swarm (SPS) optimization and developed mathematical parameters in place of hidden neuron numbers to effectively predict the speed of renewable energy systems that reach the set number of neurons. The wind farm data sets are used for training, testing and validation of the proposed model of wind speed predictors. The final prediction model proposed involves the applicability of a neural wavelet network for a predictive wind velocity and the mother wavelet function is used to allow the hidden neurons and to measure the wind speed output with the reduction of the set parameters.

: Renewable energy, stochastic particle swarm (SPS) optimization, Machine learning, wind speed