Distributed resource and service management for large-scale dynamic spectrum access systems through coordinated learning

We develop resource and service management techniques to support spectrum users (SUs) with quality of service requirements in large-scale distributed dynamic spectrum access (DSA) systems. The proposed techniques empower SUs to seek and exploit spectrum opportunities dynamically and effectively, thereby maximizing the long-term service satisfaction levels that SUs receive from accessing and using the DSA system. Our techniques are efficient in terms of optimality, scalability, distributivity, and fairness. First, they enable SUs to achieve high service satisfaction levels by quickly locating and accessing available spectrum opportunities. Second, they are scalable by performing well in systems with small as well as large numbers of SUs. Third, they can be implemented in a decentralized manner by relying on local information only. Finally, they ensure fairness among SUs by allowing them to receive equal amounts of service.

[1]  Fangwen Fu,et al.  Detection of Spectral Resources in Cognitive Radios Using Reinforcement Learning , 2008, 2008 3rd IEEE Symposium on New Frontiers in Dynamic Spectrum Access Networks.

[2]  Kagan Tumer,et al.  Multi-agent reward analysis for learning in noisy domains , 2005, AAMAS '05.

[3]  Kagan Tumer,et al.  Efficient Evaluation Functions for Evolving Coordination , 2008, Evolutionary Computation.

[4]  Kagan Tumer,et al.  Distributed agent-based air traffic flow management , 2007, AAMAS '07.

[5]  Venugopal V. Veeravalli,et al.  Algorithms for Dynamic Spectrum Access With Learning for Cognitive Radio , 2008, IEEE Transactions on Signal Processing.

[6]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[7]  Hua Liu,et al.  Cooperation and Learning in Multiuser Opportunistic Spectrum Access , 2008, ICC Workshops - 2008 IEEE International Conference on Communications Workshops.

[8]  Qing Zhao,et al.  Distributed Learning in Multi-Armed Bandit With Multiple Players , 2009, IEEE Transactions on Signal Processing.