Strathmore Research Brown Bag Sessions

Permanent URI for this community

Now showing 1 - 1 of 1

Energy-efficient resource utilization algorithms in cloud data-centre servers
(Strathmore University, 2019-02-13) Kenga, Derdus
The use of cloud computing has increased exponentially in recent years to satisfy computing needs in both big and small organisations. However, cloud data-centres consume enormous amounts of energy. This raises their operating costs, reduces profits, increases Total Cost of Ownership (TCO) of datacentre infrastructure and increases carbon dioxide emissions. The main cause of energy wastage in data-centres is low levels of server utilization, leading to wastage of idle energy. The fact that servers are energy un-proportional compounds this problem. Low levels of server utilization lead to resource wastage. The current techniques for addressing the problem of resource under-utilization for energy savings are VM consolidation and DVFS. However, these techniques have failed. For instance, VM consolidation does not take into account workload type energy profiles before consolidation. On the other hand, DVFS works well only on CPU-bound tasks because dynamic power ranges for other computing resources such as memory are narrower.