A Deep Reinforcement Learning Framework for Task Scheduling for Leveraging Energy Efficiency in Cloud Computing

DOI

10.2991/978-94-6463-252-1_51How to use a DOI?

Keywords

Cloud Computing; Cloud Efficiency Enhancement; Reinforcement Learning; Task Scheduling

Abstract

Cloud computing and its popularity has resulted in increased usage of cloud in real world applications. Thus there is unprecedented growth in user base and their tasks. In this context, it is indispensable to improve cloud computing towards achieving equilibrium by satisfying consumer needs and infrastructure efficiency. In this paper, we proposed a framework for efficient task scheduling based on Reinforcement Learning (RL). Instead of heuristics based approach employed traditionally, our framework is based on learning runtime situation for making scheduling decisions. As there are number of historical instance available, our approach is based on RL. We proposed an algorithm known as Reinforcement Learning based Task Scheduling (RL-TS). This algorithm exploits RL for making scheduling decisions based on the action-reward cycle for decision convergence. In presence of large number of tasks arriving for scheduling our agent based phenomenon strives to improve efficiency of cloud infrastructure with appropriate scheduling decisions. Our empirical study with workloads consisting of 1000, 2000 and 5000 jobs respectively revealed that the success rate of the proposed algorithm is higher besides improving optimal energy utilization when compared with the state of the art.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Imtiyaz Khan
AU  - Syed Shabbeer Ahmad
AU  - Shaik Neeha
AU  - Asad Hussain Syed
AU  - Sayyada Mubeen
PY  - 2023
DA  - 2023/11/09
TI  - A Deep Reinforcement Learning Framework for Task Scheduling for Leveraging Energy Efficiency in Cloud Computing
BT  - Proceedings of the Second International Conference on Emerging Trends in Engineering (ICETE 2023)
PB  - Atlantis Press
SP  - 484
EP  - 493
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-252-1_51
DO  - 10.2991/978-94-6463-252-1_51
ID  - Khan2023
ER  -