Centralized Routing for Lifetime Optimization Using Genetic Algorithm and Reinforcement Learning for WSNs

Elvis Obi (1, 2, 3) , Zoubir Mammeri (1, 2, 3) , Okechukwu Emmanuel Ochia (4)

1 IRIT - Institut de recherche en informatique de Toulouse
2 IRIT-T2RS - Temps Réel dans les Réseaux et Systèmes
3 UT3 - Université Toulouse III - Paul Sabatier
4 University of Calgary

The sensor nodes' energy-efficient utilization is a major challenge in the design of Wireless Sensor Networks (WSNs). This is because the network lifetime is determined by the sensor nodes' limited energy sources whose replacement or recharging is almost impossible due to the mostly deployment of the sensor nodes in harsh environments. An effective way to prolong the network lifetime is by designing an energy-efficient routing protocol for WSNs. This paper discusses an optimization method for routing in WSNs to extend the network lifetime. Although the conventional method can extend the network lifetime, the computation time increases exponentially with the number of sensor nodes. Therefore, this method cannot apply to large-scale WSNs. This paper proposes a method to reduce the computation time using a genetic algorithm and shows that the proposed method can provide a suboptimal routing path through evaluation experiments.

Mots clés: reinforcement learning; genetic algorithm; routing; wireless sensor network; network lifetime; path optimization

Domaines: Informatique [cs]

Elvis Obi, Zoubir Mammeri, Okechukwu Emmanuel Ochia. Centralized Routing for Lifetime Optimization Using Genetic Algorithm and Reinforcement Learning for WSNs. Sixteenth International Conference on Sensor Technologies and Applications (SENSORCOMM 2022), IARIA, Oct 2022, Lisbon, Portugal. ⟨hal-04278531⟩