Computation Offloading and Server Deployment in Heterogeneous Mobile Edge Computing Networks

This paper considers the cost minimization problem in a heterogeneous mobile edge computing network, where the macro base stations are scattered over the ground to ensure the service coverage, and the small base stations are clustered around the user hotspots to improve the users’ quality of service. Specifically, the network-wide communication and computation performance are analyzed using stochastic geometry and queueing theory. Taking the obtained performance metrics as constraints, a cost minimization problem is formulated. To solve the formulated problem, we propose a globally optimal algorithm, whose optimality and complexity are theoretically analyzed. Then, to further reduce the computational complexity, the problem is reformulated as the difference of convex programming problems, which can be addressed by the concave-convex procedure. Numerical simulations verify the accuracy of the theoretical results and illustrate the superiority of the proposed algorithms.