Title: Towards improving resource management in cloud systems using a multi-agent framework

Authors: Mahmoud Al-Ayyoub; Mustafa Daraghmeh; Yaser Jararweh; Qutaibah Althebyan

Addresses: Jordan University of Science and Technology, P.O. Box: 3030, Irbid 22110, Jordan ' Jordan University of Science and Technology, P.O. Box: 3030, Irbid 22110, Jordan ' Jordan University of Science and Technology, P.O. Box: 3030, Irbid 22110, Jordan ' Jordan University of Science and Technology, P.O. Box: 3030, Irbid 22110, Jordan

Abstract: With the goal of efficient sharing of resources and services, the cloud computing paradigm has gained a lot of interest recently. This work focuses on improving the resource utilisation by optimising the resource provisioning through a multi-agent framework in which different agents are responsible for different tasks including the monitoring of customers (behaviour, resource usage patterns and QoS requirements as stated in the SLA) and available resources based on customer's requests. Moreover, we introduce the concept of TaskFlow which allows a more elastic resources provisioning to match the customer real usage of the resources. The proposed system is implemented and tested on the CloudSim simulator and the results show it increases resource utilisation and decreases power consumption while avoiding SLA violations. The results also show that the introduction of the concept of TaskFlow into our proposed system leads to more resource saving but with a higher risk of SLA violations.

Keywords: multi-agent systems; MAS: agent-based systems; resource management; virtual machine selection; virtual machine allocation; request reformulation; virtual machines; cloud computing; customer monitoring; user behaviour; resource usage patterns; QoS requirements; quality of service; SLA; service level agreements; resource monitoring; resource provisioning.

DOI: 10.1504/IJCC.2016.075112

International Journal of Cloud Computing, 2016 Vol.5 No.1/2, pp.112 - 133

Received: 18 Oct 2014
Accepted: 25 Jun 2015

Published online: 03 Mar 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article