Mobility-aware edge server placement for mobile edge computing

Abstract

Edge server placement plays a vital role in mobile edge computing to enable low-latency and high-throughput services by deploying edge servers at suitable geographical locations. Exiting work mainly focused on satisfying the QoS metrics of deployment while the impact of the dynamic movement of users is ignored. Dynamic movements result from different lifestyles and routines of mobile users whose points of interest thus changes over time which leads to significant unbalanced workload for edge servers. To address this challenge, we present a mobility-aware edge server placement method with two key features: (1) in the offline phase, we designed a fast heuristic algorithm to generate an edge server deployment strategy for massive data; (2) in the online phase, we designed a fine-tuning mechanism of deployment strategy based on cooperative game theory to adapt to users’ dynamic movements. To demonstrate the utility of the proposed method, we have performed a comprehensive experimental evaluation on a large-scale dataset of over 1500 edge devices collected over a year. Experimental results show our method outperforms all baselines significantly in terms of query throughput and response time.