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 13 条
[1]  
Abundo M, 2015, PROCEEDINGS OF THE 2015 IFIP/IEEE INTERNATIONAL SYMPOSIUM ON INTEGRATED NETWORK MANAGEMENT (IM), P53, DOI 10.1109/INM.2015.7140276
[2]  
Andrieux A., TECH REP
[3]  
[Anonymous], MF2C OP SEC DEC COOR
[4]   A Systematic Review of Service Level Management in the Cloud [J].
Faniyi, Funmilade ;
Bahsoon, Rami .
ACM COMPUTING SURVEYS, 2015, 48 (03)
[5]  
Huang L, 2017, P 3 ACM SIGSPATIAL W, P1
[6]  
Kan TY, 2018, WIRELESS OPTIC COMM, P129
[7]  
Khelifi H., 2019, IEEE COMMUNICATIONS, P1
[8]   A Reinforcement Learning based Self-optimizing QoS Controller Framework for Distributed Services [J].
Li, DaHai ;
Levy, David .
2010 CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1-5, 2010, :2917-2922
[9]   QoS-aware Adaptive Routing in Multi-layer Hierarchical Software Defined Networks: A Reinforcement Learning Approach [J].
Lin, Shih-Chun ;
Akyildiz, Ian F. ;
Wang, Pu ;
Luo, Min .
PROCEEDINGS 2016 IEEE INTERNATIONAL CONFERENCE ON SERVICES COMPUTING (SCC 2016), 2016, :25-33
[10]  
O. Consortium, 2017, OPENFOG CONS