Sequential Learning in Wireless Communications and Computer Networks

Advisor: Prof. Jianping Pan

In this research project, we model the problems in wireless communications and computer networks (e.g., wireless caching systems, opportunistic spectrum access, opportunitic routing, and task dispatching in crowdsourcing, etc) as the multi-armed bandit problems. Theoretically, driven by problems, we develop new variants of bandits and derive regret bounds. Practically, we build systems implementing the proposed algorithms to solve the identified problems.


[1] Hu, B., Chen, Y., Huang, Z., Mehta, N. A., & Pan, J., Intelligent Caching Algorithms in Heterogeneous Wireless Networks with Uncertainty. In Proc. IEEE ICDCS 2019.

[2] Huang, Z., Hu, B., & Pan, J., Caching by User Preference with Delayed Feedback for Heterogeneous Cellular Networks, Minor Revisions to IEEE Transactions on Wireless Communication.

[3] Huang, Z., Xu, Y., Hu, B., Wang, Q., & Pan, J., Thompson Sampling for Combinatorial Semi-bandits with Sleeping Arms and Long-Term Fairness Constraints, arXiv preprint arXiv:2005.06725.

[4] Huang, Z., Xu, Y. & Pan, J. TSOR: Thompson Sampling-based Opportunistic Routing, Submitted to IEEE Transactions on Mobile Computing (TMC).

Machine Learning Meets Radio Channel Modeling

Advisors: Prof. Ruonan Zhang, Prof. Jianping Pan

Many problems in radio channel modeling can be solved by machine learning techniques. In this project, we focus on the clustering of Multi-Path Components (MPCs) in radio channel modeling. Extensive field channel measurements have shown that MPCs are not independent to each other but distributed in groups. However, many automatic clustering tools does not consider the effect of noise. We are motivated to develop effective algrotihms to cluster those MPCs automatically while reducing the effect of noise.


[1] Huang, Z., Zhang, R., Pan, J., Jiang, Y., & Zhai, D., A Framework of Multipath Clustering based on Space-Transformed Fuzzy c-Means and Data Fusion for Radio Channel Modeling. IEEE Transactions on Vehicular Technology (TVT), 2019.