Optimizing AI Service Placement and Computation Offloading in Mobile Edge Intelligence Systems

In this paper, we consider the service placement problem in a multi-user MEC system, where the access point (AP) places the most up-to-date artificial intelligent (AI) program at user devices via a broadcast channel. In particular, a user that successfully receives the program can execute its tasks both locally and remotely at the AP via partial task offloading. Otherwise, all its computations must be offloaded to and executed at the AP. We formulate a mixed-integer non-linear programming (MINLP) problem to minimize the total computation time and energy consumption of all users. The problem is particularly challenging because the service placement solution (i.e., which users to receive the program) is combinatorial in nature and strongly coupled with the computation offloading decision of each user (how much task to be executed at the AP) and resource allocation (on local CPU frequencies and uplink bandwidth). We tackle the problem with an ADMM (alternating direction method of multipliers) based method that effectively decomposes the problem into parallel smaller and tractable MINLP subproblems. Simulation results show that the proposed method achieves a performance extremely close to the optimum and has a low computational complexity that grows linearly with the number of users.