Motivation, preference, socioeconomic, and building features: New paradigm of analyzing electricity consumption in residential buildings: Fid-Bau Portal

Motivation, preference, socioeconomic, and building features: New paradigm of analyzing electricity consumption in residential buildings

Zaidan, Esmat / Abulibdeh, Ammar / Alban, Ahmad / Jabbar, Rateb

Abstract

Abstract In strategic energy planning, human-oriented factors are uncertain and lead to unpredictable challenges. Thus, decision-makers must contextualize the target society to address these uncertainties. More precisely, uncertainties lead to performance gaps between assumed and actual sustainability target outcomes. This study proposed a new framework that considers vital elements, including occupant motivation, preference, socioeconomic characteristics, and building features (MPSEB). To utilize this model, a thorough face-to-face survey questionnaire was administered to measure these elements. This study explored how these elements affect the patterns of residential energy consumption in a region with numerous expat communities of various ethnic and cultural backgrounds. In particular, the study investigated the patterns of energy behaviors and human-building interactions among the residents of Qatar by collecting empirical evidence and conducting a subsequent survey analysis. Machine learning approaches were employed to explore the survey data and determine the interdependencies between features, as well as the significance of the fundamental factors influencing human-building interactions. The XGBoost method was used to conduct a feature importance analysis to determine factors contributing to residential energy consumption. The results revealed the primary behavioral and socioeconomic factors that affect residential energy consumption, and confirmed the influence of human factors in Qatar while considering its diverse population.

Highlights • Investigate the patterns of energy behaviors and human-building interactions. • This study proposed a new model to measure electricity consumption. • Motivation, preference, socioeconomic, and building features are used. • Different spatial and machine learning techniques were used. • The results highlight the feature importance and cluster electricity consumers.