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

作者：Sharma Deepak K; Dhurandher Sanjay K; Woungang Isaac; Srivastava Rohit K; Mohananey Anhad; Rodrigues Joel J P C

来源：IEEE Systems Journal, 2018, 12(3): 2207-2213.

DOI：10.1109/JSYST.2016.2630923

• Decision tree
• delay-tolerant networks
• machine learning (ML)
• neural networks
• opportunistic networks (OppNets)
• PROPHET

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 butler occupancy values.

• 出版日期2018-9