Energy-Efficient Resource Allocation for Latency-Sensitive Mobile Edge Computing

Resource allocation algorithms are conceived for minimizing the energy consumption of multiuser mobile edge computing (MEC) systems operating in the face of interference channels, and where mobile users can offload their latency-sensitive tasks to the mobile edge server via a base station (BS). Latency-sensitive applications that benefit from MEC services can be divided into two major classes: 1) applications requiring uninterrupted execution and that cannot be fragmented and therefore require full offloading (FO); 2) applications which can benefit from fractional or partial offloading (PO). For each class of applications, we first formulate a joint optimization problem where the aim is to minimize the overall energy consumption across the sub-network subject to latency, transmission quality, computational budget and transmit power constraints. The proposed optimization problems are nonconvex, tightly coupled, and consequently challenging to solve. By exploiting binary relaxation, smooth approximation and auxiliary variables, we convert these problems into more tractable forms and subsequently develop novel algorithms based on the concave-convex procedure (CCCP) to solve them. Furthermore, by incorporating a measure of user priority, a reduced-complexity solution is proposed for the FO scheme. The benefits of our energy-efficient resource allocation algorithms for latency-sensitive MEC are demonstrated through simulations.