UCSD DSP Lab Log in Home Faculty Classes Group Info Prospective Students Publications Projects Projects Novel (Channel Modeling, Feedback and Cognitive) Next Generation of Cognitive Networks: From Agile Radios to Smart Phones PI: Tara Javidi Co-PI: Massimo Franceschetti, Alon Orlitsky, Bhaskar Rao and Ramesh Rao Sponsors: Huawei, Qualcomm, Viasat, L-3, Center for Wireless Communications Duration: 10/1/2011-9/30/2013 As the demand for mobile/wireless services as well as the complexity and the diversity of networks and devices continue to grow, there is a need for developing affordable and scalable means for effectively utilizing the available resources to deliver the complex applications and services of future. It this context, cognitive networking has come to the forefront of wireless networking research. While, cognitive radio technology was first envisioned around the notion of spectrum agility, with the ever increasing popularity of the “smart” devices -not only equipped with multiple wireless interface cards but also with significant storage and computational capabilities- the once dream-like notions of sensing and network computations, adaptability, and learning are now generalized across the network and protocol stack.There is an ever-increasing need for network cognition, i.e. estimation and control protocols that can rapidly evaluate, track and manage dynamics both in the type of information content exchanged on networks and in the environmental factors such as location, time, and spectrum availability. This project leverages our existing cognitive networking testbed (UCSD-CogNet testbed) to propose a comprehensive plan enabling learning-based and decision theoretic approach to network design. The proposal consists of the following three components: First we consider the problem of cognitive protocol design. This set of research activities are focused on how context, model, and situation awareness can be integrated into the protocol stack design. Secondly, we consider the issues regarding estimation and learning in networks. This set of research activities are focused on how the context, model, and situations are learned and/or estimated in a realistic network where network resources are constrained in the number of observations, time to learn, and/or statistical correlation structure. The last element of our proposed research integrates and validates our theoretical research on an experimental testbed as validation and proof of concept. To develop new knowledge on cognitive networking, we built a 36 node cognitive networking testbed (UCSD-CogNet testbed). We are planning to use the experimental testbed to verify and compare our theoretical tools and approaches.