Towards workload-aware cloud resource provisioning using a multi-controller fuzzy switching approach

Ullah, Amjad; Li, Jingpeng; Hussain, Amir

Abstract

Elasticity enables cloud customers to enrich their applications to dynamically adjust underlying cloud resources. Over the past, a plethora of techniques have been introduced to implement elasticity. Control theory is one such technique that offers a systematic method to design feedback controllers to perform elasticity. Many of the available such approaches utilise the single system model. However, for cloud applications that are subject to time varying workload conditions (e.g., e-commerce applications), it becomes difficult for such approaches to perform effectively at all times to achieve the desired performance goals. This paper exploits the novel use of a recently developed multi-controller based approach, where each controller is designed specifically for different operating conditions. Moreover, the use of fuzzy logic is exploited for the selection of a suitable controller at runtime. Initial results in comparison with the conventional feedback control approach demonstrate better achievement of the performance goals.

Citation

Ullah, A., Li, J., & Hussain, A. (2018). Towards workload-aware cloud resource provisioning using a multi-controller fuzzy switching approach. International Journal of High Performance Computing and Networking, 12(1), 13-25. https://doi.org/10.1504/IJHPCN.2018.093838

• Journal Article Type: Article
• Online Publication Date: Jul 27, 2018
• Publication Date: 2018
• Deposit Date: Jul 19, 2019
• Journal: International Journal of High Performance Computing and Networking
• Print ISSN: 1740-0562
• Electronic ISSN: 1740-0570
• Publisher: Inderscience
• Peer Reviewed: Peer Reviewed
• Volume: 12
• Issue: 1
• Pages: 13-25
• DOI: https://doi.org/10.1504/IJHPCN.2018.093838
• Keywords: cloud elasticity; control theory; multi-controller; fuzzy logic; auto-scaling; dynamic resource provisioning; feedback controllers; multi-model; elasticity rules
• Public URL: http://researchrepository.napier.ac.uk/Output/1792409
• Related Public URLs: https://www.storre.stir.ac.uk/handle/1893/28857