The purpose of the project is to investigate different artificial intelligence (DAI) algorithms, such as reinforcement learning, including transfer learning to improve energy efficiency of next generation wireless communications and beyond.
Currently, worldwide mobile data connections have reached 1.1 billion mobile increasing at 60% each year to reach 5 billion in 2017. In addition to this increase in mobile web traffic, mobile terminals are also evolving to accommodate a broader range of application such as machine-to-machine (M2M) communication, smart objects, and ubiquitous computing creating the Internet of Things. This shift to new data-intensive application is a key factor behind the development of new standards for the so called gigabit mobile networks such as Long Term Evolution Advanced, and Beyond Next Generation Mobile Broadband systems (BuNGee). Even though these systems are being designed to cope with such growth from the capacity density point of view, by means of densification, the impact on energy consumption has not been taken into account.
This project will explore a range of solutions using Artificial Intelligence (AI) along with Cognitive Radio (CR) techniques to develop energy efficient topology and resource management schemes in order to tackle the energy consumption issue.
Members
- Salahedin Rehan
- David Grace
Dates
Start: February 2012
Research