A Machine Learning-Based Protocol for Efficient Routing in Opportunistic Networks

Abstract

This paper proposes a novel routing protocol for OppNets called MLProph, which uses machine learning (ML) algorithms, namely decision tree and neural networks, to determine the probability of successful deliveries. The ML model is trained by using various factors such as the predictability value inherited from the PROPHET routing scheme, node popularity, node's power consumption, speed, and location. Simulation results show that MLProph outperforms PROPHET+, a probabilistic-based routing protocol for OppNets, in terms of number of successful deliveries, dropped messages, overhead, and hop count, at the cost of small increases in buffer time and buffer occupancy values.