Reinforcement Learning based Transmission Range Control in Software-Defined Wireless Sensor Networks with Moving Sensor

TL;DR

This paper proposes a reinforcement learning approach using epsilon-greedy to optimize transmission power levels in dynamic, moving sensor networks, significantly reducing energy consumption while maintaining throughput.

Contribution

It introduces a novel RL-based transmission range control method tailored for mobile sensors in SD-WSNs, improving energy efficiency and network stability.

Findings

Reduced energy consumption in sensor networks

Maintained network throughput with RL control

Achieved network equilibrium through adaptive power levels

Abstract

Routing in Software-Defined Wireless sensor networks (SD-WSNs) can be either single or multi-hop, whereas the network is either static or dynamic. In static SD-WSN, the selection of the optimum route from source to destination is accomplished by the SDN controller(s). On the other hand, if moving sensors are there, then SDN controllers of zones cannot handle route discovery sessions by themselves; they can only store information about the most recent zone state. Moving sensors find lots of robotics applications where robots continue to move from one room to another to sensing the environment. A huge amount of energy can be saved in these networks if transmission range control is applied. Multiple power levels exist in each node, and each of these levels takes possible actions after a potential sender node decides to transmit/forward a message. Based on each such activity, the next states of the concerned sender node and the communication session are re-determined while the router receives a reward. The Epsilon-greedy algorithm is applied in this study to decide the optimum power level in the next iteration. It is determined anew depending upon the present network scenario. Simulation results show that our proposed work leads the network to equilibrium by reducing energy consumption and maintaining network throughput.