Authors: Jouhra Dad; Ghalem Belalem
Addresses: Department of Computer Science, Faculty of Exact Sciences and Applied, University of Oran, P.B. 1524, El M'Naouer – 31000 Oran, Algeria ' Department of Computer Science, Faculty of Exact Sciences and Applied, University of Oran, P.B. 1524, El M'Naouer – 31000 Oran, Algeria
Abstract: With the development of the environment of cloud, which treats user requests, store data and provides services, energy consumption issue has become a very important problem in these systems. A high energy consumption of data centres does not cause only the decrease of cloud provider's profit but also emit a large amount of CO2. Virtualisation technology, migration, DVFS technique and workloads consolidation are among the effective solutions to reduce energy consumption and power. In this work, we study the optimisation of energy consumption and CO2 emission. In our model, we adopt two algorithms to solve this problem. Firstly, we use a modified minimisation of migration algorithm (MMM) which is used to select some or all the VMs. Secondly, we use the modified knapsack problem to allocate the VMs. These algorithms take into account two physical resources (CPU cores and memory capacity).
Keywords: cloud computing; energy optimisation; virtualisation; consolidation; dynamic voltage frequency scaling; DVFS; migration; energy consumption; CO2; carbon dioxide; carbon emissions.
International Journal of Information Technology, Communications and Convergence, 2014 Vol.3 No.1, pp.1 - 12
Published online: 05 Sep 2014 *Full-text access for editors Access for subscribers Purchase this article Comment on this article