QoE-Aware User Allocation in Edge Computing Systems for Popular Services

Abstract

As edge computing has found its way into people's everyday life, many app vendors put the quality of experience (QoE) in an important position. QoE experienced by users of different application services vary even with same resources. Because of the restricted resource of edge computing nodes, it's very necessary to assign different amounts of resources to different kinds of services to reach better QoE. In this paper, we need to decide how many edge node resources each user can get respectively in the service area. When allocating resources, app vendors should fully consider the fairness of resource allocation and maximize the total users' experience. We first establish the Multi-service Q oE model for four popular services. We determine the multi-objective function to evaluate fairness and utility by setting the resource impact factors of different service types. Being an NP-hard problem, the classical NSGA-II algorithm combined with CPLEX solver is proposed to accelerate the process of solution. Then experiments are carried out on simulated data, and the applicability of the algorithm is evaluated in user-sparse scenarios, user-intensive scenarios and other scenarios.