Research Article
DQR: A Double Q Learning Multi Agent Routing Protocol for Wireless Medical Sensor Network
@INPROCEEDINGS{10.1007/978-3-031-25538-0_32, author={Muhammad Shadi Hajar and Harsha Kalutarage and M. Omar Al-Kadri}, title={DQR: A Double Q Learning Multi Agent Routing Protocol for Wireless Medical Sensor Network}, proceedings={Security and Privacy in Communication Networks. 18th EAI International Conference, SecureComm 2022, Virtual Event, October 2022, Proceedings}, proceedings_a={SECURECOMM}, year={2023}, month={2}, keywords={Double Q-learning Routing Reinforcement Learning Trust management Blackhole attack Selective forwarding attack Sinkhole attack}, doi={10.1007/978-3-031-25538-0_32} }- Muhammad Shadi Hajar
Harsha Kalutarage
M. Omar Al-Kadri
Year: 2023
DQR: A Double Q Learning Multi Agent Routing Protocol for Wireless Medical Sensor Network
SECURECOMM
Springer
DOI: 10.1007/978-3-031-25538-0_32
Abstract
Wireless Medical Sensor Network (WMSN) offers innovative solutions in the healthcare domain. It alleviates the patients’ everyday life difficulties and supports the already overloaded medical staff with continuous monitoring tools. However, widespread adoption of these advancements is still restrained by security concerns and limitations of existing routing protocols. Routing is challenging in WMSN owing to the fact that some critical requirements, such as reliable delivery, have been neglected. To address these challenges, this paper proposes DQR, a double Q-learning routing protocol to meet WMSN requirements and overcome the positive bias estimation problem of the Q-learning based routing protocols. DQR uses a novel Reinforcement Learning (RL) model to reduce computational and communication overheads. It is combined with an effective trust management system to ensure a reliable data transfer and defeat packet dropping attacks. The experimental results demonstrate robust performance under various attacks with minimal resource footprint and efficient energy consumption.
