Home / Current Issue / Paper 1719689
A Data Analytics Perspective on Energy Benchmarking in Campus Buildings: A Review of Recent Research
Subject area: Science,Engineering and Technology · Area of research: Data Analysis
DOI: https://doi.org/10.64388/IREV9I11-1719689
Abstract
Energy benchmarking of campus buildings has become an important research area as universities seek to reduce operational costs, improve sustainability, and support carbon-reduction goals. This review examines data-analytics approaches used for benchmarking campus building energy performance, with attention to methods, metrics, datasets, and research challenges. The literature shows that benchmarking studies often rely on energy use intensity, weather-normalized indicators, regression analysis, clustering, forecasting, and machine learning to compare buildings and identify inefficiencies. Common data sources include smart meters, utility bills, occupancy information, weather data, and building management systems. The review also highlights major challenges such as data quality, lack of standardized benchmarks, limited occupancy-aware modeling, and few campus-specific studies in developing contexts. Based on the review, future research should focus on real-time analytics, explainable AI, integrated sustainability indicators, and benchmarking frameworks suitable for university campuses.
Keywords
Energy Benchmarking, Campus Buildings, Data Analytics, Machine Learning, Energy Use Intensity (EUI)
How to cite this paper
@article{1719689,
author = {Dr. Sangeeta Joshi, Lalit Kumar Joshi },
title = {A Data Analytics Perspective on Energy Benchmarking in Campus Buildings: A Review of Recent Research},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {5755-5761},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1719689.pdf},
abstract = {Energy benchmarking of campus buildings has become an important research area as universities seek to reduce operational costs, improve sustainability, and support carbon-reduction goals. This review examines data-analytics approaches used for benchmarking campus building energy performance, with attention to methods, metrics, datasets, and research challenges. The literature shows that benchmarking studies often rely on energy use intensity, weather-normalized indicators, regression analysis, clustering, forecasting, and machine learning to compare buildings and identify inefficiencies. Common data sources include smart meters, utility bills, occupancy information, weather data, and building management systems. The review also highlights major challenges such as data quality, lack of standardized benchmarks, limited occupancy-aware modeling, and few campus-specific studies in developing contexts. Based on the review, future research should focus on real-time analytics, explainable AI, integrated sustainability indicators, and benchmarking frameworks suitable for university campuses.},
keywords = {Energy Benchmarking, Campus Buildings, Data Analytics, Machine Learning, Energy Use Intensity (EUI)},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1719689}
}