Layered Temporal Spatial Graph Attention Reinforcement Learning for Multiplex Networked Industrial Chains Energy Management  

作　　者：Yuanshuang Jiang Kai Di Xingyu Wu Zhongjian Hu Fulin Chen Pan Li Yichuan Jiang 

机构地区：[1]School of Computer Science and Engineering,Southeast University,Nanjing 211189,China [2]School of Software,Southeast University,Nanjing 211189,China [3]School of Cyber Science and Engineering,Southeast University,Nanjing 211189

出　　处：《Tsinghua Science and Technology》2025年第2期528-542,共15页清华大学学报自然科学版(英文版)

基　　金：supported by the National Key Research and Development Program of China(No.2022YFB3304400);the National Natural Science Foundation of China(Nos.62303111,62076060,and 61932007);the Key Research and Development Program of Jiangsu Province of China(No.BE2022157);the Defense Industrial Technology Development Program(No.JCKY2021214B002);the Fellowship of China Postdoctoral Science Foundation(No.2022M720715).

摘　　要：Demand response has recently become an essential means for businesses to reduce production costs in industrial chains.Meanwhile,the current industrial chain structure has also become increasingly complex,forming new characteristics of multiplex networked industrial chains.Fluctuations in real-time electricity prices in demand response propagate through the coupling and cascading relationships within and among these network layers,resulting in negative impacts on the overall energy management cost.However,existing demand response methods based on reinforcement learning typically focus only on individual agents without considering the influence of dynamic factors on intra and inter-network relationships.This paper proposes a Layered Temporal Spatial Graph Attention(LTSGA)reinforcement learning algorithm suitable for demand response in multiplex networked industrial chains to address this issue.The algorithm first uses Long Short-Term Memory(LSTM)to learn the dynamic temporal characteristics of electricity prices for decision-making.Then,LTSGA incorporates a layered spatial graph attention model to evaluate the impact of dynamic factors on the complex multiplex networked industrial chain structure.Experiments demonstrate that the proposed LTSGA approach effectively characterizes the influence of dynamic factors on intra-and inter-network relationships within the multiplex industrial chain,enhancing convergence speed and algorithm performance compared with existing state-of-the-art algorithms.

关 键 词：demand response multiplex networked industrial chains MULTIAGENT reinforcement learning 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]