Forecasting of Appliances House in a Low-Energy Depend on Grey Wolf Optimizer

This paper gives and analyses data-driven prediction models for the energy usage of appliances. Data utilized include readings temperature humidity sensors from a wireless network. The building envelope is meant to minimize demand or required power house independent appliance mechanical system efficiency. Approximating mapping function between input variables continuous output variable work regression. discusses forecasting framework FOPF (Feature Optimization Prediction Framework), which includes feature selection optimization: by removing non-predictive parameters choose best-selected hybrid optimization technique has been approached. k-nearest neighbors (KNN) Ensemble Models data use appliances have tested against some bases machine learning algorithms. comparison study showed powerful, best accuracy lowest error KNN with RMSE = 0.0078. Finally, suggested ensemble model's performance assessed using one-way analysis variance (ANOVA) test Wilcoxon Signed Rank Test. (Two-tailed P-value: 0.0001).