An Autonomous Access Point for Cognitive Wireless Networks

Tamma, Bheemarjuna Reddy and Manoj, B.S. and Rao, Ramesh (2011) An Autonomous Access Point for Cognitive Wireless Networks. Cognitive Radio Mobile Ad Hoc Networks. pp. 373-400. ISSN 2522-0160

Full text not available from this repository. (Request a copy)

Abstract

In this chapter, we present an application of the Cognitive Networking paradigm to the design and development of autonomous Cognitive Access Point (CogAP) for Wi-Fi hotspots and home wireless networks. In these environments, we typically use only one AP per service provider/residence for providing wireless connectivity to the users. Here we can reduce the cost of autonomic network control by equipping the same AP with a cognitive functionality. We first present the architecture of autonomous CogAP which consists of two main modules: Traffic sensing module and cognitive controller module. The traffic sensing module uses an efficient packet sampling scheme to characterize traffic from all Wi-Fi channels with single wireless interface. The cognitive controller module consists of two submodules: traffic predictor and cognitive decision engine. The Neural Network-based traffic predictor module makes use of the historical traffic traces for traffic prediction on all channels. The cognitive decision engine makes use of traffic forecasts to dynamically decide which channel is best for CogAP to operate on. We have built a prototype CogAP device using off-the-shelf hardware components and obtained better performance with respect to state-of-the-art channel selection strategies.

[error in script]

IITH Creators: