查看文章

Cloud computing is a prevailing approach for running various data-analysis algorithms to obtain insight from massive raw data. However, the current cloud computing architecture suffers from large computation and communication overhead when processing data in big size. In this work, we develop a systematic approach to efficiently process large-scale image processing tasks under an edge-assisted cloud computing architecture. We use a two-stage processing mechanism, which is to pre-process raw data on edge servers and feed only the most relevant information to the cloud, for the purpose of reducing system overhead. We model and formulate a problem that jointly optimizes the responding strategy and task placement strategy. We then propose a solution with a queuing mechanism to capture the impact of background workload on heterogeneous edge devices. We implement our system and use extensive …