Tag
This paper presents CQD-ERL, a contextual quality-diversity evolutionary reinforcement-learning controller for tropical commercial building HVAC systems, evaluated against an ASHRAE Guideline 36 baseline. It addresses the unique challenges of tropical climates with a safety-shielded, multi-policy archive approach.
This paper presents FDD-ON, a modular ontology for representing VAV HVAC system components, faults, symptoms, and impacts to enable interoperable fault detection and diagnostics applications.
Introduces Building2Building (B2B), a large-scale benchmark for studying generalization and transfer in reinforcement learning using realistic HVAC control environments built on EnergyPlus, compatible with Gymnasium.
A unified Python framework using PPO-based deep reinforcement learning for optimizing HVAC control with economizer logic and CO2-constrained ventilation is presented, showing improved energy efficiency and temperature stability over traditional PID controllers.
WIRED reviews the best window air conditioners of 2026, including models from Midea, Zafro, GE, Della, and LG, highlighting smart features like app control and voice assistant support, as well as heat pump efficiency.