School of Physics, Engineering and Technology

Learning and Reasoning Strategies for Cognitive Radio Networks

This project will explore how different learning and reasoning strategies should be applied to cognitive radio systems. Strategies could include artificial neural networks and reinforcement learning, possibly applied using game theoretic techniques. By modelling a realistic wireless communications environment, the purpose of the project will be to show how, by applying this form of intelligence, it is possible to improve the flexibility and usage of pooled radio spectrum, both on a local and system wide basis. The project will establish where the learning /reasoning should best reside (nodes and/or network), and also the degree of control information exchange required between nodes. A mixture of simulation and analysis will be used to assess performance.

A mixture of simulation and analysis will be used to assess performance. Set theory and Markov analysis will be particularly important analytical tools. This work will integrate closely with other activities within the Group.

Key objectives

To understand the use and impact of different learning and reasoning strategies on the performance of the wireless network.
To understand the possibility of using learning techniques in developing the energy efficiency of the wireless network.
To understand the efficiency of the learning strategies on different levels of distributive learning.

Outputs

A simulation showing the impact and effect of learning strategies on both network performance and energy efficiency.
Extra knowledge on applying learning techniques on different distributive learning levels.
Contributions to conference and journal papers.

Members

Sinan S. Nuuman

David Grace

Tim Clarke

Dates

Start: May 2012

Research