基于DQN和DDPG算法的多智能体泵系统节能控制优化研究

打开文本图片集

中图分类号：TU991 文献标志码：A doi：10.3969/j.issn.1006-0316.2025.08.003

文章编号：1006-0316（2025）08-0014-09

Research on Optimization of Energy-Saving Control for Pump System Based on Multiple-Agent of DQN and DDPG Algorithms

ZHONG Lintao， SONG Dongmei， ZHANG Hengjing，QIAN Yucong，MIN Ziqiang （Sichuan Institute of Machinery Research & Design （Group） Co.， Ltd.， Chengdu 610063， China）

Abstract ：To addressthe issue of multi-equipment cooperativecontrolin the energy-saving optimization process of pump systems，this paper proposes a multiple-agent reinforcement learning energy-saving control optimization strategy for pump systems based on the Deep Q-Network （DQN）and Deep Deterministic Policy Gradient （DDPG） algorithms.The pump system is modeled as a Markov Decision Process（MDP）， where the DQN algorithm is employed to construct the discrete action space for pump start/stop operations，and the DDPG algorithm is used to build the continuous action space for motor speed control.Additionally，Long Short-Term Memory （LSTM） networks are embedded into both the DQNand DDPG algorithms to memorize historical operational data， thereby enhancing agent training and control performance.Experimental results demonstrate that the pump system controlled by the multi-gent reinforcement learning approach achieves a 15.81% energy saving compared to manual regulation， exhibiting superior energy-saving control effectiveness.

Key words：pump-system； energy-saving;deep reinforcement learning;multiple-agent

泵是工业生产中的通用设备，据统计，泵用电量约占我国工业用电的 20%[1] 。（剩余8296字）