Routing in dynamically changing node location scenarios: A reinforcement learning approach

Routing in dynamically changing node location scenarios is quite challenging and time consuming. The emerging wireless communication networks such as LTE advanced and 5G, device-to-device communications present such dynamically changing node locations. In mobile ad hoc networks, very often we come across such dynamically changing node location scenarios. In the Internet of things (IoTs), we will come across many such cases where the main communicating node locations will change very much dynamically. These dynamically changing node locations bring a lot of complexities in the traffic management in the networks. In this work, we present a routing scheme based on reinforcement learning algorithm that is able to provide near optimal results under the high traffic conditions, and compare it with the shortest path algorithm in terms of the average delivery time.