Co-LLM: A retrieval-augmented language model framework for chiller optimization control

Guangyu Liu

doi:10.1016/j.jobe.2026.115683

Co-LLM: A retrieval-augmented language model framework for chiller optimization control

2026-02-23

0

PRE

AI

DOI：10.1016/j.jobe.2026.115683

Original

Original request for help

Save

Abstract

En 中文

• Propose a Framework Co-LLM to enable real-time HVAC load optimization. • Introduce a selective re-calibration mechanism to fine-tune sensitive sub-policies. • Integrate RAG-tuned exploration policy retrieval with domain knowledge support. • Simulations on a hospital chiller plant show Co-LLM outperforms baseline methods.

Keywords:

Co-LLM

HVAC load optimization

selective re-calibration

RAG-tuned exploration

chiller optimization control

Co-LLM: A retrieval-augmented language model framework for chiller optimization control

Abstract

Journal

Organization