Interference-aware SaaS user allocation game for edge computing

Guangming Cui, Qiang He, Xiaoyu Xia, Phu Lai, Feifei Chen, Tao Gu, Yun Yang

Research output: Contribution to journalArticlepeer-review

21 Citations (Scopus)

Abstract

Edge Computing, extending cloud computing, has emerged as a prospective computing paradigm. It allows a SaaS (Software-as-a-Service) vendor to allocate its users to nearby edge servers to minimize network latency and energy consumption on their devices. From the SaaS vendor's perspective, a cost-effective SaaS user allocation (SUA) aims to allocate maximum SaaS users on minimum edge servers. However, the allocation of excessive SaaS users to an edge server may result in severe interference and consequently impact SaaS users' data rates. In this article, we formally model this problem and prove that finding the optimal solution to this problem is NP-hard. Thus, we propose ISUAGame, a game-theoretic approach that formulates the interference-aware SUA (ISUA) problem as a potential game. We analyze the game and show that it admits a Nash equilibrium. Then, we design a novel decentralized algorithm for finding a Nash equilibrium in the game as a solution to the ISUA problem. The performance of this algorithm is theoretically analyzed and experimentally evaluated. The results show that the ISUA problem can be solved effectively and efficiently.

Original languageEnglish
Pages (from-to)1888-1899
Number of pages12
JournalIEEE Transactions on Cloud Computing
Volume10
Issue number3
Early online date10 Jul 2020
DOIs
Publication statusPublished - 2022
Externally publishedYes

Keywords

  • Edge computing
  • SaaS user allocation
  • data rate
  • game theory
  • interference
  • nash equilibrium
  • potential game

Fingerprint

Dive into the research topics of 'Interference-aware SaaS user allocation game for edge computing'. Together they form a unique fingerprint.

Cite this