Energy-efficiency model for residential buildings using supervised machine learning algorithm

Abstract

The real-time management and control of heating-system networks in residential buildings has tremendous energy-saving potential, and accurate load prediction is the basis for system monitoring. In this regard, selecting the appro-priate input parameters is the key to accurate heating-load forecasting. In existing models for forecasting heating loads and selecting input parameters, with an increase in the length of the prediction cycle, the heating-load rate gradually decreases, and the influence of the outside temperature gradually increases. In view of different types of solutions for improving buildings’ energy efficiency, this study proposed a Energy-efficiency model for residential buildings based on gradient descent optimization (E2B-GDO). This model can predict a building’s heating-load conservation based on a building energy performance dataset. The input layer includes area (distribution of the glazing area, wall area, and surface area), relative density, and overall elevation. The proposed E2B-GDO model achieved an accuracy of 99.98% for training and 98.00% for validation.