Learning for adaptive anycast in vehicular delay tolerant networks
- 61 Downloads
We propose a protocol for vehicular delay tolerant networks (DTN) with special focus on anycast communications from a vehicle to the cloud where multiple gateways (such as road side units) exist. The protocol employs a Q-learning algorithm to estimate the multi-hop destination encounter probability by discounting the reward with the number of forwards (number of hops). Anycast encounter probability is maintained in a specific entry which considers multiple gateways as the same virtual destination. The proposed protocol also uses an adaptive data replication scheme to take into account the destination encounter probability and the relative velocity between vehicles jointly, which can achieve a high data delivery ratio and low overhead. We use computer simulations to evaluate the proposed protocol.
This research was supported in part by the open collaborative research program at National Institute of Informatics (NII) Japan (FY2018), Inner Mongolia Autonomous Region Research project No. MW-2018-MGYWXXH-211, JSPS KAKENHI Grant Number 16H02817, and 16K00121.
- Bista BB, Rawat DB (2016) Enhancement of PRoPHET routing in delay tolerant networks from an energy prospective. In: Proc. IEEE TENCON, pp 1579–1582Google Scholar
- Freitas EP, Heimfarth T, Costa LAG, Ferreira AM, Pereira CE, Wagner FR, Larsson T (2011) Analyzing different levels of geographic context awareness in agent ferrying over VANETs. In: Proc. the 2011 ACM Symposium on Applied Computing, pp 413–418Google Scholar
- Grondman I, Busoniu L, Lopes GAD, Babuska R (2012) A survey of actor-critic reinforcement learning: standard and natural policy gradients. IEEE Trans Syst Man Cybern. Part C 42(6):1291–1307Google Scholar
- Keranen A, Ott J, Karkkainen T (2009) The ONE simulator for DTN protocol evaluation, In: Proc. SIMUTools, pp 1–10Google Scholar
- Khan A, Sadhu S, Yeleswarapu M (2009) A comparative analysis of DSRC and 802.11 over Vehicular Ad hoc Networks, Project Report, University of California, Santa Barbara, pp 1–8Google Scholar
- Prophet v2 (2012) Prophet v2 router [online]. https://www.netlab.tkk.fi/tutkimus/dtn/theone/contrib/ProphetV2Router.java [Accessed 19 Feb. 2018]Google Scholar
- Sharma DK, Dhurandher SK, Woungang I, Srivastava RK, Mohananey A, Rodrigues JJPC (2018) A machine learning-based protocol for efficient routing in opportunistic networks. IEEE Syst J. DOI: https://doi.org/10.1109/JSYST.2016.2630923
- Spyropoulos T, Psounis K, Raghavendra CS (2005) Spray and wait: an efficient routing scheme for intermittently connected mobile networks. In: Proc. the 2005 ACM SIGCOMM workshop on Delay-tolerant networking, pp 252–259Google Scholar
- The ONE (2009) The ONE simulator [online]. https://www.netlab.tkk.fi/tutkimus/dtn/theone/ [Accessed 19 Feb. 2018]Google Scholar
- Wu C, Kumekawa K, Kato T (2010) Distributed reinforcement learning approach for vehicular ad hoc networks. IEICE Trans. Commun. E93-B(6):1431–1442Google Scholar