Research Article
DCLA: A Duty-Cycle Learning Algorithm for IEEE 802.15.4 Beacon-Enabled WSNs
@INPROCEEDINGS{10.1007/978-3-642-17994-5_15, author={Rodolfo Paz and Dirk Pesch}, title={DCLA: A Duty-Cycle Learning Algorithm for IEEE 802.15.4 Beacon-Enabled WSNs}, proceedings={Ad Hoc Networks. Second International Conference, ADHOCNETS 2010, Victoria, BC, Canada, August 18-20, 2010, Revised Selected Papers}, proceedings_a={ADHOCNETS}, year={2012}, month={5}, keywords={Wireless Sensor Networks (WSNs) IEEE 802.15.4 duty-cycle energy efficiency machine learning reinforcement learning}, doi={10.1007/978-3-642-17994-5_15} }- Rodolfo Paz
Dirk Pesch
Year: 2012
DCLA: A Duty-Cycle Learning Algorithm for IEEE 802.15.4 Beacon-Enabled WSNs
ADHOCNETS
Springer
DOI: 10.1007/978-3-642-17994-5_15
Abstract
The current specification for IEEE 802.15.4 beacon-enabled networks does not define how active and sleep schedules should be configured in order to achieve the optimal network performance in all traffic conditions. Several algorithms exist in the literature that dynamically vary these schedules based on traffic load estimations. But it is still uncertain how these adaptive schemes perform with regard to each other as their performance has only been compared with the standard beacon mode. In this paper, we compare the current state-of-the-art schemes, and with the objective of overcoming the performance deficiencies shown by previous approaches, we introduce DCLA, an adaptive duty-cycle scheme for IEEE 802.15.4 beacon-enabled Wireless Sensor Networks (WSN) that employs a reinforcement learning technique. Simulation results show that the proposed scheme achieves the best overall network performance for a wide range of traffic conditions and performance parameters when compared with existing IEEE 802.15.4 duty-cycle adaptation schemes.
