2012/05/26 by Michele Mazzucco, Martti Vasar, Mazzucco, Michele +3
Computer Science · #Blockchain Technology Applications and Security #Cloud Computing and Resource Management #Distributed #FOS: Computer and information sciences #IoT and Edge/Fog Computing #Parallel #Performance (cs.PF) #and Cluster Computing (cs.DC)
paper · pdf · doi:10.48550/arxiv.1205.5871
openalex publication_date 2012/05/26 · openalex created_date 2025/10/24 · openalex updated_date 2026/07/28
We study the problem of maximizing the average hourly profit earned by a\nSoftware-as-a-Service (SaaS) provider who runs a software service on behalf of\na customer using servers rented from an Infrastructure-as-a-Service (IaaS)\nprovider. The SaaS provider earns a fee per successful transaction and incurs\ncosts proportional to the number of server-hours it uses. A number of resource\nallocation policies for this or similar problems have been proposed in previous\nwork. However, to the best of our knowledge, these policies have not been\ncomparatively evaluated in a cloud environment. This paper reports on an\nempirical evaluation of three policies using a replica of Wikipedia deployed on\nthe Amazon EC2 cloud. Experimental results show that a policy based on a\nsolution to an optimization problem derived from the SaaS provider's utility\nfunction outperforms well-known heuristics that have been proposed for similar\nproblems. It is also shown that all three policies outperform a "reactive"\nallocation approach based on Amazon's auto-scaling feature.\n