An Improved Task Allocation Scheme in Serverless Computing Using Gray Wolf Optimization (GWO) Based Reinforcement Learni
- PDF / 1,246,026 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 68 Downloads / 207 Views
An Improved Task Allocation Scheme in Serverless Computing Using Gray Wolf Optimization (GWO) Based Reinforcement Learning (RIL) Approach N. Yuvaraj1 · T. Karthikeyan2 · K. Praghash3 Accepted: 11 November 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Serverless computing offers a wide variety of event-driven integrations and cloud services, easy development and implementation frameworks, and complex balancing and control of costs. With these benefits into consideration, the growing implementation of serverless systems means that the performance of the serverless system is measured and new techniques created to maximize the potential of the software. The serverless or system runtime features have shown major performance and cost advantages for event-driven cloud applications. While serverless runtimes are limited to applications requiring lightweight data and storage, such as the prediction and inference of machine learning, these applications have been improved beyond other cloud runtimes. In this paper, we propose a machine learning model to parallelize the jobs allocated to the event queue and the dispatcher of the serverless framework. We hence use Gray Wolf Optimization (GWO) model to improve the process of task allocation. Further, to optimize GWO, we use the Reinforcement Learning (RIL) approach that simultaneously optimizes the parameters of GWO and improves the task allocation. The simulation studies show that the proposed GWO-RIL offers reduced runtimes and it adapts with varying load conditions. Keywords Serverless computing · Reinforcement Learning (RL) · Gray Wolf Optimization (GWO) · Resource allocation · Run time
* N. Yuvaraj [email protected] 1
Research and Development, ICT Academy, Chennai, India
2
Department of Electronics and Communication Engineering, Annamacharya Institute of Technology and Sciences, Rajampet, AP, India
3
Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, AP, India
13
Vol.:(0123456789)
N. Yuvaraj et al.
1 Introduction The word serverless does not mean that it has gone ‘no Servers’. Nevertheless, the cloud provider avoids the difficulty of maintaining specific servers and offers an ephemeral computing system that will execute a software piece on request caused by programs and incidents, paying the network client only during the execution time. Serverless Computing [1, 2] is a fresh and impressive paradigm for cloud applications [3–7], largely due to the recent shift to containers and micro-services of enterprise applications [8]. Cloud infrastructure is becoming crucial with the increasing application of cloud infrastructure to deliver a variety of IT services. However, only qualitative network performance information is revealed by cloud providers [9]. Serverless computing is a newly emerging paradigm that usually refers to a software architecture in which the application is breakdown into events or triggers and functions or actions, and where a platform provides
Data Loading...
