Interference-aware Game-theoretic Device Allocation for Mobile Edge Computing
Guangming Cui, Qiang He, Feifei Chen, Yiwen Zhang, Hai Jin, Yun Yang
Abstract
Mobile Edge Computing (MEC), as an emerging and prospective mobile computing paradigm, allows a content provider to serve its users by allocating their mobile devices to nearby edge servers to lower the latency in the delivery of its content to those mobile services. From the content provider's perspective, a cost-effective mobile device allocation (MDA) aims to allocate maximum mobile devices to minimum edge servers. However, the allocation of excessive mobile devices to an edge server may result in severe communication interference and consequently, impact mobile devices data rates. Sometimes, not all users mobile devices can be allocated to edge servers. Unallocated mobile devices can still retrieve content from the remote cloud through base stations, however with high latency. The connection between these mobile devices and the base stations also incur communication interference. We formally model this Interference-aware Mobile Edge Device Allocation (I-MEDA) problem and propose a game-theoretic based approach named I-MEDAGame to formulate the I-MEDA problem as an I-MEDA game. Our theoretical analysis of I-MEDAGame shows that it admits a Nash equilibrium. I-MEDAGame employs a novel decentralized algorithm to find the Nash equilibrium of the IMEDA game. The performance of I-MEDAGame is theoretically analyzed and experimentally evaluated.