Frequency Allocation for WLANs Using Graph Colouring Techniques
WONS '05 Proceedings of the Second Annual Conference on Wireless On-demand Network Systems and Services
Trends in the development of communication networks: Cognitive networks
Computer Networks: The International Journal of Computer and Telecommunications Networking
A neural network based cognitive controller for dynamic channel selection
ICC'09 Proceedings of the 2009 IEEE international conference on Communications
Multi-channel wireless traffic sensing and characterization for cognitive networking
ICC'09 Proceedings of the 2009 IEEE international conference on Communications
Cognitive networks: adaptation and learning to achieve end-to-end performance objectives
IEEE Communications Magazine
Green Access Point Selection for Wireless Local Area Networks Enhanced by Cognitive Radio
Mobile Networks and Applications
Hi-index | 0.00 |
In this paper, we present an application of the Cognitive Networking paradigm to the problem of development of autonomous Cognitive Access Point (CogAP) for small scale wireless network environments such as Wi-Fi hotspots and home networks. In these environments we typically use only one AP per service provider/residence for providing wireless services to the users. However, note that larger number of APs from multiple service providers/residences vie for bandwidth in any geographic region. Here we can reduce the cost of autonomic network control by equipping the same AP with a cognitive functionality. We first present architecture of our autonomous CogAP. Then we introduce our algorithmic solution, in which a Neural Network-based traffic predictor makes use of historical traffic traces to learn network traffic conditions and predicts traffic loads on each of 802.11 b/g channels. The cognitive decision engine makes use of traffic forecasts to dynamically decide which channel is best for CogAP to operate on for serving its clients. One of the challenges in autonomous cognitive decision making is the computation resource constraints in today's embedded APs. We have built a prototype CogAP device using cognitive software modules and off-the-self hardware components. We carried out performance evaluation of the proposed CogAP system by conducting experimental measurements on our testbed platform; the obtained results show that the proposed CogAP is effective in achieving performance enhancements with respect to state-of-the-art channel selection strategies.