… systems are also briefly studied. The primary goal of this work was to identify common issues
useful in future studies on ML … This study was concluded with many energy perspectives on …

… We bring to light both applied and theoretical recent developments. Inspired by [50], we …
of Robust Optimization. In section 5 we discuss current challenges and opportunities in robust …

… as accelerating training and enhancing control robustness, as … users avoid the tedious work
of developing and calibrating a … the recent and rapid developments in the machine learning …

… , and (4) the performance might not be reliable and robust for … include all published work on
machine learning for buildings. … sites to support progress measurement and project control. …

… —to make AI more reliable. We highlight technical advances that … research progress in
modelling, and now the incremental gains from improving models are diminishing in many tasks …

… developments to come. Given the rapid changes in this field, it is challenging to understand
both the breadth of opportunities … cannot be used to make robust broad conclusions, but the …

… Second, we review case studies to extract problems and … to these issues and further work.
Ours is not the first survey of … handling of edge cases and overall robustness, as well as satisfy …

… reported machine learning applications often focus on tasks … as a roadmap supporting a
progression from basic capabilities … have appeared to influence the work reported in this paper. …

… in buildings provide great opportunities for applying machine … scheduling of power system,
secure and reliable operation of … of building operations as well as of equipment status and …

… In Section 2, we provide a brief overview of ML and its main categories and sub-categories
or tasks. In Section 3, we review the current status of ML use in reliability and safety, and we …