Deep reinforcement learning for scheduling in large-scale networked control systems

被引：10
|
作者：
Redder, Adrian [1 ]
Ramaswamy, Arunselvan [1 ]
Quevedo, Daniel E. [1 ]
机构：
[1] Paderborn Univ, Fac Comp Sci Elect Engn & Math, Paderborn, Germany
来源：
IFAC PAPERSONLINE | 2019年 / 52卷 / 20期
关键词：
Networked control systems; deep reinforcement learning; large-scale systems; resource scheduling; stochastic control;
D O I：
10.1016/j.ifacol.2019.12.177
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This work considers the problem of control and resource allocation in networked systems. To this end, we present DIRA a Deep reinforcement learning based Iterative Resource Allocation algorithm, which is scalable and control-aware. Our algorithm is tailored towards large-scale problems where control and scheduling need to act jointly to optimize performance. DIRA can be used to schedule general time-domain optimization based controllers. In the present work, we focus on control designs based on suitably adapted linear quadratic regulators. We apply our algorithm to networked systems with correlated fading communication channels. Our simulations show that DIRA scales well to large scheduling problems. Copyright (C) 2019. The Authors. Published by Elsevier Ltd. All rights reserved.
引用
收藏
页码：333 / 338
页数：6
相关论文
共 50 条
  • [1] Deep Reinforcement Learning for Large-Scale Epidemic Control
    Libin, Pieter J. K.
    Moonens, Arno
    Verstraeten, Timothy
    Perez-Sanjines, Fabian
    Hens, Niel
    Lemey, Philippe
    Nowe, Ann
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: APPLIED DATA SCIENCE AND DEMO TRACK, ECML PKDD 2020, PT V, 2021, 12461 : 155 - 170
  • [2] Energy-aware task scheduling optimization with deep reinforcement learning for large-scale heterogeneous systems
    Li, Jingbo
    Zhang, Xingjun
    Wei, Zheng
    Wei, Jia
    Ji, Zeyu
    CCF TRANSACTIONS ON HIGH PERFORMANCE COMPUTING, 2021, 3 (04) : 383 - 392
  • [3] Energy-aware task scheduling optimization with deep reinforcement learning for large-scale heterogeneous systems
    Jingbo Li
    Xingjun Zhang
    Zheng Wei
    Jia Wei
    Zeyu Ji
    CCF Transactions on High Performance Computing, 2021, 3 : 383 - 392
  • [4] Tractable large-scale deep reinforcement learning
    Sarang, Nima
    Poullis, Charalambos
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2023, 232
  • [5] Prediction-Based Control of Large-Scale Networked Control Systems
    Guo, Xiaoxiao
    Xia, Jianwei
    Park, Ju H.
    Chen, Guoliang
    Xie, Xiangpeng
    IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2024, 54 (08): : 4736 - 4748
  • [6] Distributed Resource Scheduling for Large-Scale MEC Systems: A Multiagent Ensemble Deep Reinforcement Learning With Imitation Acceleration
    Jiang, Feibo
    Dong, Li
    Wang, Kezhi
    Yang, Kun
    Pan, Cunhua
    IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (09) : 6597 - 6610
  • [7] Distributed Hierarchical Deep Reinforcement Learning for Large-Scale Grid Emergency Control
    Chen, Yixi
    Zhu, Jizhong
    Liu, Yun
    Zhang, Le
    Zhou, Jialin
    IEEE TRANSACTIONS ON POWER SYSTEMS, 2024, 39 (02) : 4446 - 4458
  • [8] GARLSched: Generative adversarial deep reinforcement learning task scheduling optimization for large-scale high performance computing systems
    Li, Jingbo
    Zhang, Xingjun
    Wei, Jia
    Ji, Zeyu
    Wei, Zheng
    FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2022, 135 : 259 - 269
  • [9] Distributed Control of Large-Scale Networked Control Systems With Communication Constraints and Topology Switching
    Zhang, Dan
    Nguang, Sing Kiong
    Yu, Li
    IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2017, 47 (07): : 1746 - 1757
  • [10] Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control
    Chu, Tianshu
    Wang, Jie
    Codeca, Lara
    Li, Zhaojian
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2020, 21 (03) : 1086 - 1095
12345