ENERGY AWARENESS AND AD HOC ROUTING

摘要

In this paper, we focus on a way to extend the working lifetime of mobile nodes in a wireless, ad hoc network. For this, we employ ad hoc cognitive packet networks (AHCPN), which are inspired by previous research in cognitive packet networks (CPN). These networks employ smart packets to build networked learning systems that support adaptive, quality of service-driven routing of packets. To make smart packets seek a desired routing goal, appropriate adjustments are required in weights of a random neural network prior to use the decision making procedure. Reinforcement learning is employed to achieve this task with a new routing metric that we have introduced (path availability) to manage efficiently the low energy resources typically present in ad hoc networks. The new metric quantifies a path via the probability to find nodes and links available for routing. In this paper, we define this metric as a function of battery lifetime at nodes. This addition enables smart packets to make power-aware routing decisions, and consequently, nodes, which have low power, are able to extend their working lifetime and routes are selected based on power considerations, leading to the establishment of more robust communication paths over time. This paper examines the AHCPN algorithm and defines path availability in relation to energy factors.