An Online Learning Algorithm for Distributed Task Offloading in Multi-Access Edge Computing

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)
174 Downloads (Pure)


This paper addresses the problem of distributed task offloading centred at individual user terminals in a cellular multi-access edge computing (MEC) system. We introduce an online learning-assisted algorithm based on distributed bandit optimization (DBO) to cope with time-varying cost and time- varying constraint functions with unknown statistics on-the- go. The proposed algorithm jointly exploits the projected dual gradient iterations and a greedy method as well as a single broadcast communicating the MEC states to the users at the end of each decision cycle to minimize task computing-communication delay in the long run at user terminals. To track the performance of the proposed online learning algorithm over time, we define a dynamic regret to assess the closeness of the underlying delay cost of the DBO to a clairvoyant dynamic optimum, and an aggregate violation metric to evaluate the asymptotic satisfaction of the constraints. We derive lower and upper bounds for dynamic regret as well as an upper-bound for the aggregate violation and show that the upper-bounds are sub-linear under sub-linear accumulated hindsight variations. The simulation results and comparisons confirm the effectiveness of the proposed algorithm in the long run.
Original languageEnglish
Article number9082169
Pages (from-to)3090-3102
Number of pages13
JournalIEEE Transactions on Signal Processing
Early online date29 Apr 2020
Publication statusPublished - Apr 2020


  • Aggregate violation
  • dynamic regret
  • multi-access edge computing,online learning
  • projected dual gradient


Dive into the research topics of 'An Online Learning Algorithm for Distributed Task Offloading in Multi-Access Edge Computing'. Together they form a unique fingerprint.

Cite this