PSO Based Optimized Ensemble Learning and Feature Selection Approach for Efficient Energy Forecast

Swarm intelligence techniques with incredible success rates are broadly used for various irregular and interdisciplinary topics. However, their impact on ensemble models is considerably unexplored. This study proposes an optimized-ensemble model integrated smart home energy consumption management based learning particle swarm optimization (PSO). The proposed exploits PSO in two distinct ways; first, PSO-based feature selection performed to select the essential features from raw dataset. Secondly, larger datasets comprehensive range problems, it can become a cumbersome task tune hyper-parameters trial-and-error manner manually. Therefore, was as technique fine-tune of selected model. A hybrid built by using combinations five different baseline models. Hyper-parameters each combination were optimized followed training random samples. We compared our previously ANN-PSO few other state-of-the-art results show that outperform individual minimizing RMSE 6.05 9.63 increasing prediction accuracy 95.6%. Moreover, sampling help improve 92.3% around 96%.