热带商业建筑 HVAC 控制的上下文质量-多样性进化强化学习
Contextual Quality-Diversity Evolutionary Reinforcement Learning for HVAC Control in Tropical Commercial Buildings
浏览论文内容
中文总结 AI 辅助
本文提出 CQD-ERL 控制器，用于热带商业建筑 HVAC 监督控制，在新加坡建筑降阶环境训练后，经年度回测与 ASHRAE Guideline 36 基线对比，实现更优控制性能。
中文摘要 AI 辅助
本文提出一种上下文质量-多样性进化强化学习控制器 CQD-ERL，用于热带水冷冷水机组及其空气侧的监督控制。该控制器不收敛至单一标量策略，而是维护一个由专用策略构成的乘积归档，这些策略由数据驱动的运行上下文（日常天气与负荷模式的聚类）和上下文不变行为描述符共同索引，由无梯度进化算子与共享同一经验回放池的软 Actor-Critic 策略梯度算子填充。所有动作在执行前均经确定性安全屏蔽过滤。该控制器在代表新加坡某商业建筑潜在负荷、冷却塔逼近温差及湿度约束的两层降阶环境中训练，并通过完整年度回测与 ASHRAE Guideline 36 基线对比评估。
英文摘要
This paper proposes a contextual quality-diversity evolutionary reinforcement-learning controller, CQD-ERL, for the supervisory control of a tropical, water-cooled chiller plant and its associated air side. Rather than converging to a single scalarised policy, the controller maintains a product archive of specialised policies indexed jointly by a data- driven operating context, a cluster of daily weather and load regime, and a context-invariant behaviour descriptor, filled by a gradient-free evolutionary operator and a soft-actor-critic policy-gradient operator that share one replay buffer. Every action is filtered through a deterministic safety shield before execution. The controller is trained on a two-tier reduced-order environment representing the latent load, cooling-tower approach and humidity constraints of a Singapore commercial building, and is evaluated over a full annual backtest against an ASHRAE Guideline 36 baseline.
