Computational Cost and Energy Efficient Task Offloading in Hierarchical Edge-Clouds

Given the inability of Mobile Cloud Computing (MCC) to guarantee the requirements of the delay-sensitive applications, Mobile Edge Computing (MEC) has been proposed to drastically reduce that latency. But since edge servers suffer from limited capabilities that offset the latency benefits in periods of high load, a hierarchical edge cloud architecture has been studied as a way to mitigate that problem. However, such model incurs different computational costs that depend on the cloudlet layer. In this paper, we jointly minimize the mobile devices' energy consumption and computational cost in a multilayered MEC, by optimizing their transmission power and the assigned server computation while respecting their latency threshold. We mathematically formulate the mixed integer non-convex program and propose an efficient algorithm based on Successive Convex Approximation (SCA) method to solve and obtain a high-quality solution. Through numerical results, we analyze different scenarios, and show the efficiency of our algorithm in providing an approximate solution that efficiently decreases the total energy consumption and computational cost.