A CNN-LSTM Model Trained with Grey Wolf Optimizer for Prediction of Household Power Consumption

Abstract

Recent trends in research reveal evolution of hybrid machine learning models based on deep neural networks and nature inspired computing. In this paper, a combined model of convolutional neural network (CNN) and long-short term memory (LSTM) termed as CNN-LSTM network has been used for modelling. A popular swarm intelligence technique Grey Wolf optimizer (GWO) is used to compute the meaningful and best hyper-parameters of the CNN-LSTM network. The GWO algorithm has become popular due to its ability of fast convergence and determining accurate solutions among other meta-heuristic techniques. The proposed hybrid model has been suitably applied to predict the household power consumption. Simulation results reveal the superior accuracy achieved by the proposed model compared to the same CNN-LSTM model trained with particle swarm optimization, artificial bee colony and social spider optimization.