The case for crowd computing

Abstract

We introduce and motivate "crowd computing", which combines mobile devices and social interactions to achieve large-scale distributed computation. An opportunistic network of mobile devices offers substantial aggregate bandwidth and processing power. In this paper, we analyse encounter traces to place an upper bound on the amount of computation that is possible in such networks. We also investigate a practical task-farming algorithm that approaches this upper bound, and show that exploiting social structure can dramatically increase its performance.