Reproduce “From PID to Reinforcement Learning in Building HVAC Control: A Control-Architecture Review of Tuning Strategies, Formulations, and Deployment Trade-offs” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Erfan Haghighat Damavandi, Davide Papurello, Mahdi Alibeigi, Armin Keshavarz

The authors review four ways reinforcement learning can connect to existing building HVAC controls: tuning PID gains, replacing the regulatory controller, working with model predictive control, or setting supervisory targets and schedules. In one two-month real-building cooling study, indoor-temperature control improved 68% over the best rule-based controller without increased energy use; this single result does not rank the architectures.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.