华南理工大学学报(自然科学版) ›› 2025, Vol. 53 ›› Issue (1): 21-31.doi: 10.12141/j.issn.1000-565X.240105

• 能源、动力与电气工程 • 上一篇    下一篇

基于改进H-AC算法的冷源系统节能优化控制策略

周璇1,2,3, 莫浩华1, 闫军威1,2,3   

  1. 1.华南理工大学 机械与汽车工程学院,广东 广州 510640
    2.广州现代产业技术研究院,广东 广州 511458
    3.人工智能与数字经济广东省实验室(广州),广东 广州 511442
  • 收稿日期:2024-03-08 出版日期:2025-01-25 发布日期:2025-01-02
  • 作者简介:周璇(1976—),女,博士,教授级高级工程师,主要从事建筑节能、数据挖掘研究。E-mail: zhouxuan@scut.edu.cn
  • 基金资助:
    广东省自然科学基金项目(2022A1515011128)

Investigating an Enhanced H-AC Algorithm-Based Strategy for Energy-Saving Optimization Control in Cold Source System

ZHOU Xuan1,2,3, MO Haohua1, YAN Junwei1,2,3   

  1. 1.School of Mechanical and Automotive Engineering,South China University of Technology,Guangzhou 510640,Guangdong,China
    2.Guangzhou Institute of Modern Industrial Technology,Guangzhou 511458,Guangdong,China
    3.Guangdong Artificial Intelligence and Digital Economy Laboratory (Guangzhou),Guangzhou 511442,Guangdong,China
  • Received:2024-03-08 Online:2025-01-25 Published:2025-01-02
  • About author:周璇(1976—),女,博士,教授级高级工程师,主要从事建筑节能、数据挖掘研究。E-mail: zhouxuan@scut.edu.cn
  • Supported by:
    the Natural Science Foundation of Guangdong Province(2022A1515011128)

摘要:

中央空调冷源设备台数与运行参数的优化是一类离散与连续变量的协同优化问题,而经典强化学习算法难以优化此类问题。为此,该文提出了一种结合选项-评论者与演员-评论者框架的中央空调冷源系统节能优化控制策略。首先,采用分层演员-评论者(H-AC)算法分层优化设备台数与运行参数,且高层和底层模型共用Q网络评估状态价值,以解决多时间尺度下的优化难题;然后,在智能体架构、策略与网络更新方式等方面对H-AC算法进行改进,以加速智能体的收敛;最后,以夏热冬暖地区某科研办公建筑中央空调冷源系统为研究对象,基于冷源系统TRNSYS仿真平台进行实验。结果表明:在平均室内舒适时间占比分别增加14.08、11.23、29.70、9.07个百分比的前提下,基于改进H-AC算法的系统能耗分别比其他4种常规深度强化学习算法减少了32.28%、28.55%、28.63%、11.53%;虽然基于改进H-AC算法的系统能耗比基于选项-评论者框架的算法增加了0.27%,但获得了更平稳的学习过程且平均室内舒适时间占比增加了4.8个百分点。该文算法可为各类建筑中央空调冷源系统节能优化提供有效的技术手段,助力建筑“双碳”目标的实现。

关键词: 冷源系统, TRNSYS仿真平台, 深度分层强化学习, 选项-评论者框架, 协同优化

Abstract:

The optimization of the number of central air-conditioning cooling source units and their operating parameters is a collaborative optimization problem involving both discrete and continuous variables, which poses challenges for classical reinforcement learning algorithms. To address this problem, this paper proposed an energy-saving optimization control strategy for central air-conditioning cooling source systems based on a combination of the options-critic and actor-critic frameworks. Firstly, a hierarchical actor-critic (H-AC) algorithm was utilized to hierarchically optimize the number of units and operating parameters, with both the high-level and low-level models sharing a Q-network to evaluate state values, thereby addressing optimization challenges across multiple time scales. Secondly, the H-AC algorithm was improved in terms of agent architecture, policy, and network update mechanisms to accelerate the convergence of the agent. Finally, the proposed method was validated on the cooling source system of a research building located in a hot summer and warm winter region, using a TRNSYS simulation platform for experiments. The results demonstrate that, under conditions where the average indoor comfort time proportion is increased by 14.08, 11.23, 29.70 and 9.07 percentage points, respectively, the system energy consumption based on the improved H-AC algorithm is reduced by 32.28%, 28.55%, 28.64%, and 11.53% compared to four classical DRL algorithms. Although the system energy consumption of the improved H-AC algorithm is 0.27% higher than that of the options-critic framework, it achieves a more stable learning process and increases the average indoor comfort time proportion by 4.8%. This approach offers effective technical solutions for energy-saving optimization of central air-conditioning cold source systems in various building types, contributing to the achievement of buildings’ dual-carbon goals.

Key words: cold source system, TRNSYS simulation platform, deep hierarchical reinforcement learning, option-critic framework, co-optimization

中图分类号: