Grey Wolf Optimization Based CNN-LSTM Network for the Prediction of Energy Consumption in Smart Home Environment

In smart homes, the management of energy is gaining huge significance among researchers in recent times. This paper presents a system for predicting power utilization and scheduling household appliances homes. The utilizes combination Grey Wolf optimization (GWO), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) to improve management. GWO algorithm used enhance performance CNN-LSTM model. an inspired by hunting behaviour grey wolves. It helps finding optimal solutions complex problems mimicking social hierarchy mechanisms fusion CNN LSTM serves as pattern strategy effective extracting spatial features from data, while can capture temporal dependencies. By combining these two approaches, model analyze consumption patterns make accurate predictions. To evaluate proposed model, uses three error metrics: Root Mean Square Error (RMSE), (MSE), Absolute (MAE). reported values RMSE, MSE, MAE are 0.6213, 0.3860, 0.2808, respectively. These metrics indicate accuracy model’s predictions, with lower indicating better performance. Furthermore, this compares approach existing baseline models access its superiority. According results, outperforms approaches terms prediction accuracy, it achieves errors, compared models. summary, GWO-based network demonstrates improved indicated evolution metrics.