Reblog > Decentralizing the Cloud: How Can Small Data Centers Cooperate?

Note: while reading last Autumn newsletter from our scientific committee partner Ecocloud (EPFL), among the many interesting papers the center is publishing, I stumbled upon this one written by researchers Hao Zhuang, Rameez Rahman, and Prof. Karl Aberer. It surprised me how their technological goals linked to decentralization seem to question similar issues as our design ones (decentralization, small and networked data centers, privacy, peer to peer models, etc.)! Yet not in such a small size as ours, which rather look toward the “personal/small” and  “maker community” size. They are rather investigating “regional” data centers, which is considered small when you start talking about data centers.

This, combined with the recent developments mentioned by Lucien Langton in his post about Fog Computing let us think that our goals match well with some envisioned technological evolutions of the global “cloud infrastructure”. They seem to be rooted in similar questions.


Via via Ecocloud newsletter



Cloud computing has become pervasive due to attractive features such as on-demand resource provisioning and elasticity. Most cloud providers are centralized entities that employ massive data centers. However, in recent times, due to increasing concerns about privacy and data control, many small data centers (SDCs) established by different providers are emerging in an attempt to meet demand locally.

However, SDCs can suffer from resource in-elasticity due to their relatively scarce resources, resulting in a loss of performance and revenue. In this paper we propose a decentralized cloud model in which a group of SDCs can cooperate with each other to improve performance. Moreover, we design a general strategy function for the SDCs to evaluate the performance of cooperation based on different dimensions of resource sharing. Through extensive simulations using a realistic data center model, we show that the strategies based on reciprocity are more effective than other involved strategies, e.g., those using prediction on historical data.

Our results show that the reciprocity-based strategy can thrive in a heterogeneous environment with competing strategies.


More about the paper HERE.

Comments are closed.