Efficient deep reinforcement learning based task scheduler in multi cloud environment.

Autor: Mangalampalli S; Department of CSE, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India. ms.sudheer@manipal.edu., Karri GR; School of Computer Science and Engineering, VIT-AP University, Amaravati, AP, 522237, India., Ratnamani MV; Aditya Institute of Technology and Management, Tekkali, Srikakulam, AP, 530021, India., Mohanty SN; School of Computer Science and Engineering, VIT-AP University, Amaravati, AP, 522237, India., Jabr BA; Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, P.O. Box 51178, 11543, Riyadh, Saudi Arabia., Ali YA; Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, P.O. Box 51178, 11543, Riyadh, Saudi Arabia., Ali S; Battery Management System, Research and Development Center, EVE Lithium Energy Company, Huizhou, People's Republic of China. alikhan@pku.edu.cn., Abdullaeva BS; Department of Mathematics and Information Technologies, Vice-Rector for Scientific Affairs, Tashkent State Pedagogical University, Tashkent, Uzbekistan.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2024 Sep 19; Vol. 14 (1), pp. 21850. Date of Electronic Publication: 2024 Sep 19.
DOI: 10.1038/s41598-024-72774-5
Abstrakt: Task scheduling problem (TSP) is huge challenge in cloud computing paradigm as number of tasks comes to cloud application platform vary from time to time and all the tasks consists of variable length, runtime capacities. All these tasks may generated from various heterogeneous resources which comes onto cloud console directly effects the performance of cloud paradigm with increase in makespan, energy consumption, resource costs. Traditional task scheduling algorithms cannot handle these type of complex workloads in cloud paradigm. Many authors developed Task Scheduling algorithms by using metaheuristic techniques, hybrid approaches but all these algorithms give near optimal solutions but still TSP is a highly challenging and dynamic scenario as it resembles NP hard problem. Therefore, to tackle the TSP in cloud computing paradigm and schedule the tasks in an effective way in cloud paradigm, we formulated Adaptive Task scheduler which segments all the tasks comes to cloud console as sub tasks and fed these to the scheduler which is modeled by Improved Asynchronous Advantage Actor Critic Algorithm(IA3C) to generate schedules. This scheduling process is carried out in two stages. In first stage, all incoming tasks are segmented as sub tasks. After segmentation, all these sub tasks according to their size, execution time, communication time are grouped together and fed to the (ATSIA3C) scheduler. In the second stage, it checks for the above said constraints and disperse them onto the corresponding suitable processing capacity VMs resided in datacenters. Proposed ATSIA3C is simulated on Cloudsim. Extensive simulations are conducted using both fabricated worklogs and as well as realtime supercomputing worklogs. Our proposed mechanism evaluated over baseline algorithms i.e. RATS-HM, AINN-BPSO, MOABCQ. From results it is evident that our proposed ATSIA3C outperforms existing task schedulers by improving makespan by 70.49%. Resource cost is improved by 77.42%. Energy Consumption is improved over compared algorithms 74.24% in multi cloud environment by proposed ATSIA3C.
(© 2024. The Author(s).)
Databáze: MEDLINE