A PID-Lagrange-SAC based deep reinforcement learning strategy for building energy management

凌 飞; 陈 涛; 高赐威

doi:10.3969/j.issn.1009-1831.2025.05.014

您当前的位置：

首页 >

文章列表页 >

A PID-Lagrange-SAC based deep reinforcement learning strategy for building energy management

更新时间：2026-03-05

- A PID-Lagrange-SAC based deep reinforcement learning strategy for building energy management
- Vol. 27, Issue 5, (2025)
- 作者机构：
  
  1. 东南大学软件学院,江苏,苏州,215000
  2. 东南大学电气工程学院,南京,210096
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1009-1831.2025.05.014
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
凌飞, 陈涛, 高赐威. A PID-Lagrange-SAC based deep reinforcement learning strategy for building energy management[J]. 2025, 27(5).
DOI：

凌飞, 陈涛, 高赐威. A PID-Lagrange-SAC based deep reinforcement learning strategy for building energy management[J]. 2025, 27(5). DOI： 10.3969/j.issn.1009-1831.2025.05.014.

摘要

楼宇建筑的用能行为有着巨大的调节潜力，为解决此问题提出了一种基于PID-Lagrange-SAC算法的调控方法。首先，将楼宇建筑用能行为调控问题建模为马尔科夫决策过程（markov decision process，MDP）模型，将可调控设备的状态及外部变量建立为状态空间，可调控设备的运行功率作为决策变量，设计恰当的奖励函数以指导智能体学习较好的动作策略。为了抑制智能体违反约束条件的行为，进一步将问题建立为带约束项的马尔科夫决策过程（constrained MDP，CMDP），并将 PID 控制与 La?grange方法结合应用于Soft actor-critic算法进行训练。算例分析表明，最终得到的调控策略在满足用户舒适度的同时降低了楼宇建筑的运行成本及碳排放，验证了所提方法的有效性及优越性。

Abstract

There is a huge potential in building energy management. To solve the problem

a PID-Lagrange-SAC algorithm-based regulation method is proposed. Firstly

the problem statement of regulating building energy consumption behavior is modeled as a markov decision process（MDP）model. The state of controllable devices and external variables which introduce uncertainties are established as the state space

and the operating power of controllable devices is used as the decision variable to form the action space. Then

proper reward functions are designed to instruct the agent to learn better regulating strategies. The problem is further extended to a constrained markov decision process（CMDP）

and the Soft actor-critic algorithm is employed to train the agent while PID control and Lagrange method are applied to suppress the behavior of agents violating constraint conditions. The case study shows that the regulating strategy reduces the operating costs and carbon emissions of the building while meeting users’comfort demand

demonstrating the effectiveness and superiority of the proposed method.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Optimization scheduling of photovoltaic-hydrogen-storage for new energy vehicle charging station based on deep reinforcement learning

Low-carbon economic scheduling of virtual power plant based on proximal policy optimization

Collaborative control strategy for household air conditioners with adaptive access

Research on energy optimization allocation strategy for microgrids based on double delay deep deterministic strategy gradient algorithm

Research on online topology optimization strategy of distribution network based on deep reinforcement learning

Related Author

聂兴鹏

张帅

李学军

苏勋文

赵为光

刘启航

杨莹

赵晨

Related Institution

黑龙江科技大学电气与控制工程学院

中国能源建设集团有限公司湖南省电力设计院

国网安徽省电力有限公司经济技术研究院

需求侧多能互补优化与供需互动技术北京市重点实验室（中国电力科学研究院有限公司）

华北电力大学电气与电子工程学院

AI问答

⁰