Energy-Aware Application Placement in Mobile Edge Computing: A Stochastic Optimization Approach

• Published in: IEEE transactions on parallel and distributed systems 2020-04, Vol.31 (4), p.909-922
• Main Authors: Badri, Hossein, Bahreini, Tayebeh, Grosu, Daniel, Yang, Kai
• Format: Article
• Language: English
• Subjects: Algorithms; Cloud computing; Computational modeling; Edge computing; Energy budget; Energy consumption; Energy management; energy-aware application placement; Mobile computing; Mobile edge computing; multi-stage stochastic programming; Optimization; parallel algorithms; Placement; Quality of service; sample average approximation; Servers; Stochastic processes
• ISSN: 1045-9219; 1558-2183
• DOI: 10.1109/TPDS.2019.2950937

The Quality of Service (QoS) in Mobile Edge Computing (MEC) systems is significantly dependent on the application offloading and placement decisions. Due to the movement of users in MEC networks, an optimal application placement might turn into the least efficient placement in few minutes. Thus, it is crucial to take the dynamics of the system into account when designing application placement mechanisms. On the other hand, energy consumption of servers is a significant component of the cost of services in MEC systems and must also be considered in the design of the mechanisms. In this article, we model the problem of energy-aware application placement in edge computing systems as a multi-stage stochastic program. The objective is to maximize the QoS of the system while taking into account the limited energy budget of the edge servers. To solve the problem, we design a novel parallel Sample Average Approximation (SAA) algorithm. We conduct an extensive experimental analysis to evaluate the performance of the proposed algorithm using real-world trace data.