Virtual Network Function Service Provisioning for Offloading Tasks in MEC by Trading off Computing and Communication Resource Usages

Abstract

Mobile edge computing (MEC) has emerged as a promising technology that offers resource-intensive yet delaysensitive applications from the edge of mobile networks. With the emergence of complicated and resource-hungry mobile applications, offloading user tasks to cloudlets of nearby mobile edgecloud networks is becoming an important approach to leverage the processing capability of mobile devices, reduce mobile device energy consumptions, and improve experiences of mobile users. In this paper we study the joint VNF instance deployment and offloading task request assignment in MEC, by explicitly exploring a non-trivial tradeoff between usages of different types of resources. We aim to maximize the number of request admissions while minimizing their admission cost. To this end, we first formulate the cost minimization problem that admits all requests, by assuming that there are sufficient computing resources to accommodate the requested VNF instances of all requests, for which we formulate an Integer Linear Program solution and an efficient heuristic. We then deal with the throughput maximization problem by admitting as many requests as possible, subject to computing resource capacity at each cloudlet, for which we devise an efficient algorithm. We finally evaluate the performance of the proposed algorithms through experimental simulations. Experimental results demonstrate that the proposed algorithms are promising.