Small Cells Clustering and Resource Allocation in Dense Network with Mobile Edge Computing

Ultra Dense Network (UDN) and Mobile Edge Computing (MEC) are two key technologies for the next generation network. Small cells are deployed densely in UDN. MEC brings computation resource and storage resource to users as close as possible. In this paper, we consider a multi-users scenario in UDNs with MEC. Each user offload its task to MEC servers in order to meet the task's delay constraint. A set of small cells are clustered together to provide computing power for a given user. We formulate a overall delay minimization problem by jointly consider small cells clustering, transmission power allocation and computation task allocation in UDN with MEC. Due to the formulated problem is a mixed integer non-linear programming (MINLP)problem which is NP-hard, We decompose the problem and solve it in two steps. We firstly propose a low-complexity heuristic algorithm for small cells clustering. Secondly, for a given set of clusters, we derive resource allocation algorithm based on genetic algorithm that minimize the delay of the task of a user in a cluster and in turn minimize the overall delay of all users. Simulation results demonstrate that our proposed scheme can significantly improve the performance.