Deep reinforcement learning enhanced skeleton based pipe routing for high-throughput transmission in flying ad-hoc networks

Abstract

Artificial Intelligence (AI) is a huge step towards the emergence of powerful and smart decision-makers which can optimally tune the network parameters. In this work, a novel idea of an intelligent pipe (iPipe) routing scheme for a network of unmanned aerial vehicles (UAVs) is presented by considering the availability of a centralized entity with enough computational resources. The proposed scheme deploys artificial intelligence to optimally decide on the direction of the routing pipe (i.e. the medial axis), based on the current network information and the prediction of the immediate future. To address the potential influx of input data, the application of Deep Reinforcement Learning (DRL) is proposed to enhance the throughput performance and adapt more effectively to network dynamics. The scheme benefits from the concept of flying ad hoc network (FANET) to provide nodes with geometric coordinates in order to facilitate the data forwarding mechanism. Compared to the conventional AI-based routing strategies, the proposed scheme does not require making decisions for the routing table of all the nodes. Instead, it only finds the trend as a set of geometric indices which will be included in the packet headers. However, the pipe nodes still act in a distributed manner. They build their routing tables according to the trend suggested by the controller and adjust the transmission probability of each link based on the local feedback. This reduces the complexity of the centralized solution. The simulation results show that the proposed iPipe method can outperform the other state-of-the-art SSR routing scheme, which is a distributed but low-cost pipe routing.