PreGAN: Preemptive Migration Prediction Network for Proactive Fault-Tolerant Edge Computing

被引:29
作者
Tuli, Shreshth [1 ]
Casale, Giuliano [1 ]
Jennings, Nicholas R. [1 ,2 ]
机构
[1] Imperial Coll London, London, England
[2] Loughborough Univ, Loughborough, Leics, England
来源
IEEE CONFERENCE ON COMPUTER COMMUNICATIONS (IEEE INFOCOM 2022) | 2022年
关键词
Fault Tolerance; Preemptive Migrations; Edge Computing; Generative Adversarial Networks; STRATEGY;
D O I
10.1109/INFOCOM48880.2022.9796778
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Building a fault-tolerant edge system that can quickly react to node overloads or failures is challenging due to the unreliability of edge devices and the strict service deadlines of modern applications. Moreover, unnecessary task migrations can stress the system network, giving rise to the need for a smart and parsimonious failure recovery scheme. Prior approaches often fail to adapt to highly volatile workloads or accurately detect and diagnose faults for optimal remediation. There is thus a need for a robust and proactive fault-tolerance mechanism to meet service level objectives. In this work, we propose PreGAN, a composite AI model using a Generative Adversarial Network (GAN) to predict preemptive migration decisions for proactive fault-tolerance in containerized edge deployments. PreGAN uses co-simulations in tandem with a GAN to learn a few-shot anomaly classifier and proactively predict migration decisions for reliable computing. Extensive experiments on a Raspberry-Pi based edge environment show that PreGAN can outperform state-of-the-art baseline methods in fault-detection, diagnosis and classification, thus achieving high quality of service. PreGAN accomplishes this by 5.1% more accurate fault detection, higher diagnosis scores and 23.8% lower overheads compared to the best method among the considered baselines.
引用
收藏
页码:670 / 679
页数:10
相关论文
共 46 条
[1]  
Ataallah SMA, 2015, 2015 11TH INTERNATIONAL COMPUTER ENGINEERING CONFERENCE (ICENCO), P241, DOI 10.1109/ICENCO.2015.7416355
[2]   USAD : UnSupervised Anomaly Detection on Multivariate Time Series [J].
Audibert, Julien ;
Michiardi, Pietro ;
Guyard, Frederic ;
Marti, Sebastien ;
Zuluaga, Maria A. .
KDD '20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2020, :3395-3404
[3]   Learn-as-you-go with Megh: Efficient Live Migration of Virtual Machines [J].
Basu, Debabrota ;
Wang, Xiayang ;
Hong, Yang ;
Chen, Haibo ;
Bressan, Stephane .
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2019, 30 (08) :1786-1801
[4]   Optimal online deterministic algorithms and adaptive heuristics for energy and performance efficient dynamic consolidation of virtual machines in Cloud data centers [J].
Beloglazov, Anton ;
Buyya, Rajkumar .
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2012, 24 (13) :1397-1420
[5]   RADON: rational decomposition and orchestration for serverless computing [J].
Casale, G. ;
Artac, M. ;
van den Heuvel, W-J. ;
van Hoorn, A. ;
Jakovits, P. ;
Leymann, F. ;
Long, M. ;
Papanikolaou, V. ;
Presenza, D. ;
Russo, A. ;
Srirama, S. N. ;
Tamburri, D. A. ;
Wurster, M. ;
Zhu, L. .
SICS SOFTWARE-INTENSIVE CYBER-PHYSICAL SYSTEMS, 2020, 35 (1-2) :77-87
[6]  
Chung Junyoung, 2014, EMPIRICAL EVALUATION
[7]   Fog Computing: Helping the Internet of Things Realize Its Potential [J].
Dastjerdi, Amir Vahid ;
Buyya, Rajkumar .
COMPUTER, 2016, 49 (08) :112-116
[8]  
Engelmann C, 2009, EUROMICRO WORKSHOP P, P252, DOI [10.1109/.30, 10.1109/PDP.2009.31]
[9]   Transformative effects of IoT, Blockchain and Artificial Intelligence on cloud computing: Evolution, vision, trends and open challenges [J].
Gill, Sukhpal Singh ;
Tuli, Shreshth ;
Xu, Minxian ;
Singh, Inderpreet ;
Singh, Karan Vijay ;
Lindsay, Dominic ;
Tuli, Shikhar ;
Smirnova, Daria ;
Singh, Manmeet ;
Jain, Udit ;
Pervaiz, Haris ;
Sehgal, Bhanu ;
Kaila, Sukhwinder Singh ;
Misra, Sanjay ;
Aslanpour, Mohammad Sadegh ;
Mehta, Harshit ;
Stankovski, Vlado ;
Garraghan, Peter .
INTERNET OF THINGS, 2019, 8
[10]   A Spatiotemporal Deep Learning Approach for Unsupervised Anomaly Detection in Cloud Systems [J].
He, Zilong ;
Chen, Pengfei ;
Li, Xiaoyun ;
Wang, Yongfeng ;
Yu, Guangba ;
Chen, Cailin ;
Li, Xinrui ;
Zheng, Zibin .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (04) :1705-1719