Energy-Efficient Routing and Rate Allocation for Delay Tolerant Networks

Routing for Delay Tolerant Networks (DTNs) are challengeable for the continuously varied network environment. Most of existing DTN routing algorithms mainly focus on metrics such as delay, hop count and bandwidth, etc. Green communication is a new focus with the goal of saving energy by optimizing network performance and ultimately protecting the natural climate. In this paper, we present an Energy-efficient Routing and Rate Allocation (ERRA) scheme based on Q-learning that can optimize the energy efficiency with the constraints of congestion, buffer and delay. ERRA solves the routing and rate allocation together with reinforce leaning, and then make decisions on relay selection and rate schedule. ERRA explores the possible strategies, and then exploits the knowledge obtained to adapt its relay and schedule strategies. ERRA achieves the desired overall objective by considering the stochastic non-cooperative game under on-line multi-commodity routing situations. The simulation results show that ERRA achieves good energy efficiency and delivery ratio within the delay bound.