A review of the-state-of-the-art in data-driven approaches for building energy prediction

By Ying Sun, F. Haghighat, Benjamin C. M. Fung. 2020

459 citations recorded by the source corpus.

Abstract Building energy prediction plays a vital role in developing a model predictive controller for consumers and optimizing energy distribution plan for utilities. Common approaches for energy prediction include physical models, data-driven models and hybrid models. Among them, data-driven approaches have become a popular topic in recent years due to their ability to discover statistical patterns without expertise knowledge. To acquire the latest research trends, this study first summarizes the limitations of earlier reviews: seldom present comprehensive review for the entire data-driven process for building energy prediction and rarely summarize the input updating strategies when applying the trained data-driven model to multi-step energy prediction. To overcome these gaps, this paper provides a comprehensive review on building energy prediction, covering the entire data-driven process that includes feature engineering, potential data-driven models and expected outputs. The distribution of 105 papers, which focus on building energy prediction by data-driven approaches, are reviewed over data source, feature types, model utilization and prediction outputs. Then, in order to implement the trained data-driven models into multi-step prediction, input updating strategies are reviewed to deal with the time series property of energy related data. Finally, the review concludes with some potential future research directions based on discussion of existing research gaps.

Subfields: Building and Construction, Electrical and Electronic Engineering, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/d5131cb8a090c2685f93cf7730d04314a3d9f3a4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

AI-big data analytics for building automation and management systems: a survey, actual challenges and future perspectives (2022, background): “; Wang and Chen 2021; Yucong and Bo 2020), heating and ventilation load prediction (Sun et al. 2020), HVAC optimization (Li 2020), Space cooling load forecasting (Feng et al.”