Engineering a QoS Provider Mechanism for Edge Computing with Deep Reinforcement Learning

被引:2
|
作者
Carpio, Francisco [1 ]
Jukan, Admela [1 ]
Sosa, Roman [2 ]
Juan Ferrer, Ana [2 ]
机构
[1] Tech Univ Carolo Wilhelmina Braunschweig, Braunschweig, Germany
[2] ATOS Res & Innovat, Madrid, Spain
来源
2019 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM) | 2019年
关键词
Reinforcement learning; QoS provisioning; edge computing; fog-to-cloud; deep Q-learning;
D O I
10.1109/globecom38437.2019.9013946
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
With the development of new system solutions that integrate traditional cloud computing with the edge/fog computing paradigm, dynamic optimization of service execution has become a challenge due to the edge computing resources being more distributed and dynamic. How to optimize the execution to provide Quality of Service (QoS) in edge computing depends on both the system architecture and the resource allocation algorithms in place. We design and develop a QoS provider mechanism, as an integral component of a fog-to-cloud system, to work in dynamic scenarios by using deep reinforcement learning. We choose reinforcement learning since it is particularly well suited for solving problems in dynamic and adaptive environments where the decision process needs to be frequently updated. We specifically use a Deep Q-learning algorithm that optimizes QoS by identifying and blocking devices that potentially cause service disruption due to dynamicity. We compare the reinforcement learning based solution with state-of-the-art heuristics that use telemetry data, and analyze pros and cons.
引用
收藏
页数:6
相关论文
共 50 条
  • [1] Deep Reinforcement Learning for QoS-Aware Package Caching in Serverless Edge Computing
    Jeon, Hongseok
    Shin, Seungjae
    Cho, Chunglae
    Yoon, Seunghyun
    2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2021,
  • [2] Deep Reinforcement Learning for Task Offloading in Edge Computing
    Xie, Bo
    Cui, Haixia
    2024 4TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND INTELLIGENT SYSTEMS ENGINEERING, MLISE 2024, 2024, : 250 - 254
  • [3] Novel Resource Allocation Algorithm of Edge Computing Based on Deep Reinforcement Learning Mechanism
    Zhang, Degan
    Fan, Hongrui
    Zhang, Jie
    19TH IEEE INTERNATIONAL SYMPOSIUM ON PARALLEL AND DISTRIBUTED PROCESSING WITH APPLICATIONS (ISPA/BDCLOUD/SOCIALCOM/SUSTAINCOM 2021), 2021, : 437 - 444
  • [4] Computation Offloading with Reinforcement Learning for Improving QoS in Edge Computing Environments
    Park, Jinho
    Chung, Kwangsue
    2022 IEEE 8TH WORLD FORUM ON INTERNET OF THINGS, WF-IOT, 2022,
  • [5] Deep Reinforcement Learning Edge Workload Orchestrator for Vehicular Edge Computing
    Silva, Eliana Neuza
    da Silva, Fernando Mira
    2023 IEEE 9TH INTERNATIONAL CONFERENCE ON NETWORK SOFTWARIZATION, NETSOFT, 2023, : 44 - 52
  • [6] Learning IoV in Edge: Deep Reinforcement Learning for Edge Computing Enabled Vehicular Networks
    Xu, Shilin
    Guo, Caili
    Hu, Rose Qingyang
    Qian, Yi
    IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021), 2021,
  • [7] A Deep Reinforcement Learning Based Offloading Game in Edge Computing
    Zhan, Yufeng
    Guo, Song
    Li, Peng
    Zhang, Jiang
    IEEE TRANSACTIONS ON COMPUTERS, 2020, 69 (06) : 883 - 893
  • [8] Computation Offloading in Edge Computing Based on Deep Reinforcement Learning
    Li, MingChu
    Mao, Ning
    Zheng, Xiao
    Gadekallu, Thippa Reddy
    PROCEEDINGS OF INTERNATIONAL CONFERENCE ON COMPUTING AND COMMUNICATION NETWORKS (ICCCN 2021), 2022, 394 : 339 - 353
  • [9] Hardware-oriented deep reinforcement learning for edge computing
    Yamagishi, Yoshiharu
    Kaneko, Tatsuya
    Akai-Kasaya, Megumi
    Asai, Tetsuya
    IEICE NONLINEAR THEORY AND ITS APPLICATIONS, 2021, 12 (03): : 526 - 544
  • [10] Deep Reinforcement Learning based Energy Scheduling for Edge Computing
    Yang, Qinglin
    Li, Peng
    2020 IEEE INTERNATIONAL CONFERENCE ON SMART CLOUD (SMARTCLOUD 2020), 2020, : 175 - 180