Game Theory for Big Data Processing: Multileader Multifollower Game-Based ADMM

Zijie Zheng, Lingyang Song, Zhu Han, Geoffrey Ye Li, H. Vincent Poor

Research output: Contribution to journalArticlepeer-review

17 Scopus citations

Abstract

In this paper, tradeoff and convergence issues for incentive mechanisms are addressed by combining optimization and game theory. Specifically, a multiple-leader multiple-follower (MLMF) game-based alternating direction method of multipliers (ADMM) is developed that incentivizes the agents to perform a group of controllers' tasks in order to satisfy their corresponding objectives. Both analytical and simulation results verify that the proposed method reaches a hierarchical social optimum and converges linearly. More importantly, the convergence rate is independent of the network size, which indicates that the MLMF game-based ADMM can be used in very large networks, such as highly virtualized communication networks with two-layer hierarchies, for big data processing.

Original languageEnglish (US)
Pages (from-to)3933-3945
Number of pages13
JournalIEEE Transactions on Signal Processing
Volume66
Issue number15
DOIs
StatePublished - Aug 1 2018

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Keywords

  • ADMM
  • Big data
  • game theory
  • large-scale network

Fingerprint

Dive into the research topics of 'Game Theory for Big Data Processing: Multileader Multifollower Game-Based ADMM'. Together they form a unique fingerprint.

Cite this