摘要

Underwater wireless sensor networks are expected to explore natural undersea resources and gathering of scientific data in aqueous environments. The characteristics of mobile underwater sensor networks, such as low communication bandwidth, large propagation delay, floating node mobility, and high error probability, are significantly different from terrestrial wireless sensor networks. Energy-efficient communication protocols are thus urgently demanded in mobile underwater sensor networks. In this paper, two routing protocols are developed to tackle these problems in underwater wireless sensor networks, in which fuzzy logic inference systems and support vector machines are employed to determine the appropriate sensors to forward the packets to the destination. The proposed protocols are compared with a representative routing protocol for mobile underwater sensor networks in the literature. The experimental results verify the effectiveness and feasibility of the proposed work.