Adaptive buffering using Markov Decision Process in tree-based Wireless Sensor and Actor Networks

In a tree-based Wireless Sensor and Actor Network (WSAN), data acquisition can be done through a mobile actor to reduce the traffic congestion. However, packet dropping at the resource-limited (such as, buffer space and energy) intermediate nodes leads to poor data delivery and energy efficiency. In this paper, a Markov Decision Process (MDP) based buffer management mechanism has been proposed in tree-based WSAN to reduce the data delivery delay and to improve the energy efficiency. A mathematical model for a mobile actor has been presented to analyze buffer occupancy and energy consumption with real-time traffic. The state of a node is represented based on buffer levels which may change with dynamic traffic. The buffer states are analyzed at which packets will be dropped to minimize the average delivery delay and energy consumption. Extensive simulations have been performed to show the efficacy of proposed mechanism in terms of average end-to-end delay and energy consumption. (C) 2017 Elsevier Ltd. All rights reserved.