A hybrid PSO-LSTM-based electricity prediction and optimization technique for home appliances

With population growth and technological advancements, electricity demand in residential buildings has increased sharply. Accurate energy consumption forecasting enables building owners and operators to understand and predict the energy usage patterns of their buildings. However, the prevailing forecasting techniques have certain limitations that must be addressed for improved energy optimization. To address these concerns, this paper proposes a novel three-stage energy optimization framework for individual home appliances. In the first stage, season-wise cluster analysis is performed using a hierarchical clustering algorithm. In the second stage, an adaptive Long Short-Term Memory (LSTM) model is developed to estimate the electricity consumption of home appliances. Next stage integrates Particle Swarm Optimization (PSO) for hyperparameter tuning of the LSTM model to improve prediction accuracy. Then, the hybrid PSO-LSTM technique has been rigorously evaluated using a benchmark dataset on energy consumption of individual home appliances. Comparative analysis with previous state-of-the-art prediction models reveals the superiority of the proposed work. Integration of clustering, deep learning, and optimization offers a practical solution for smart energy management. The extracted insights show that the proposed approach leads to sustainable, efficient, and user-aware energy practices in households.