A 2.5-year campus-level smart meter database with equipment data for energy analytics

In response to the increasing necessity for accurate campus electricity
management, understanding load patterns is essential for enhancing energy
efficiency and optimizing usage. Yet, comprehensive electricity load data
for campus buildings and their internal systems is often insufficient,
posing challenges for research. This paper presents an energy consumption
monitoring dataset from the Hong Kong University of Science and Technology
(HKUST) campus, featuring data from over 1,400 meters across more than 20
buildings, collected over two and a half years. Utilizing the Brick Schema
curation strategy, raw data was refined into a research-ready format. This
dataset facilitates a variety of research applications, including load
pattern recognition, fault detection, demand response strategies, and load
forecasting.