Adaptive data collection protocol using reinforcement learning for VANETs

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Data Collection is considered as an inherent challenging problem to Vehicular Ad-Hoc networks. Here, an Adaptive Data cOllection Protocol using rEinforcement Learning (ADOPEL) is proposed for VANETs. It is based on a distributed Qlearning technique making the collecting operation more reactive to nodes mobility and topology changes. A reward function is provided and defined to take into account the delay and the number of aggregatable packets. Simulations results confirm the efficiency of our technique compared to a non-learning version and demonstrate the trade-off achieved between delay and collection ratio.

Original languageEnglish
Title of host publication2013 9th International Wireless Communications and Mobile Computing Conference, IWCMC 2013
Pages1040-1045
Number of pages6
DOIs
Publication statusPublished - 16 Sept 2013
Externally publishedYes
Event2013 9th International Wireless Communications and Mobile Computing Conference, IWCMC 2013 - Cagliari, Sardinia, Italy
Duration: 1 Jul 20135 Jul 2013

Publication series

Name2013 9th International Wireless Communications and Mobile Computing Conference, IWCMC 2013

Conference

Conference2013 9th International Wireless Communications and Mobile Computing Conference, IWCMC 2013
Country/TerritoryItaly
CityCagliari, Sardinia
Period1/07/135/07/13

Keywords

  • Collection ratio
  • Data collection
  • Number of hops
  • Qlearning
  • Reinforcement learning
  • Vehicular Ad Hoc Networks (VANETs)

Fingerprint

Dive into the research topics of 'Adaptive data collection protocol using reinforcement learning for VANETs'. Together they form a unique fingerprint.

Cite this