, YannAel Le Borgne, Ann Nowe, Patrick De Causmaecker, Joris Maervoet, Tommy Messelis, Katja Verbeeck, Tim Vermeulen
In this paper we study the potential of using energy aware metrics in reinforcement learning based routing algorithms for wireless sensor networks. This paper contributes with an enhanced version of an existing energy aware algorithm and with a study that tests the in?uence of combining energy aware metrics with load balancing metrics from delay based Q-routing. We show that our enhanced algorithm can signi?cantly improve the lifetime of a network without requiring any extra information or communication, by propagating energy information beyond direct neighbors throughout the network. Our study also shows that topologies composed from heterogenous nodes can have a significant impact on an algorithm's performance. Furthermore we show that load balancing in routing algorithms can help to improve the network lifetime while only requiring energy information about a node's direct neighbors.
Deville, M, Le Borgne, Y-A, Nowe, A, Causmaecker, PD (ed.), Maervoet, J (ed.), Messelis, T (ed.), Verbeeck, K (ed.) & Vermeulen, T (ed.) 2011, 'Reinforcement Learning for Energy Efficient Routing in Wireless Sensor Networks', Proceedings of the Benelux Conference on Artificial Intelligence, vol. 23, pp. 89-96. <http://allserv.kahosl.be/bnaic2011/sites/default/files/bnaic2011_submission_82.pdf>
Deville, M., Le Borgne, Y.-A., Nowe, A., Causmaecker, P. D. (Ed.), Maervoet, J. (Ed.), Messelis, T. (Ed.), Verbeeck, K. (Ed.), & Vermeulen, T. (Ed.) (2011). Reinforcement Learning for Energy Efficient Routing in Wireless Sensor Networks. Proceedings of the Benelux Conference on Artificial Intelligence, 23, 89-96. http://allserv.kahosl.be/bnaic2011/sites/default/files/bnaic2011_submission_82.pdf
@article{f3e98ffdf2404897993291c5f7ffa1a9,
title = "Reinforcement Learning for Energy Efficient Routing in Wireless Sensor Networks",
abstract = "In this paper we study the potential of using energy aware metrics in reinforcement learning based routing algorithms for wireless sensor networks. This paper contributes with an enhanced version of an existing energy aware algorithm and with a study that tests the in?uence of combining energy aware metrics with load balancing metrics from delay based Q-routing. We show that our enhanced algorithm can signi?cantly improve the lifetime of a network without requiring any extra information or communication, by propagating energy information beyond direct neighbors throughout the network. Our study also shows that topologies composed from heterogenous nodes can have a significant impact on an algorithm's performance. Furthermore we show that load balancing in routing algorithms can help to improve the network lifetime while only requiring energy information about a node's direct neighbors.",
keywords = "Wireless Sensor Networks, Multi-Agent Learning, Network Routing, Q-learning",
author = "Maarten Deville and {Le Borgne}, Yann-A{\"e}l and Ann Nowe and Causmaecker, {Patrick De} and Joris Maervoet and Tommy Messelis and Katja Verbeeck and Tim Vermeulen",
note = "Patrick De Causmaecker, Joris Maervoet, Tommy Messelis, Katja Verbeeck, Tim Vermeulen; 23rd Benelux Conference on Artificial Intelligence ; Conference date: 03-11-2011 Through 04-11-2011",
year = "2011",
month = nov,
day = "3",
language = "English",
volume = "23",
pages = "89--96",
journal = "Proceedings of the Benelux Conference on Artificial Intelligence",
issn = "1568-7805",
}