We focus on C-RAN random access protocols for IoT devices that yield low-latency high-rate active-device detection in dense networks of large-array remote radio heads. In this context, we study the problem of learning the strengths of links between detected devices and network sites. In particular, we develop recommendation-system inspired algorithms, which exploit random-access observations collected across the network to classify links between active devices and network sites across the network. Our simulations and analysis reveal the potential merit of data-driven schemes for such on-the-fly link classification and subsequent resource allocation across a wide-area network.
@article{arxiv.1801.04001,
title = {Efficient C-RAN Random Access for IoT Devices: Learning Links via Recommendation Systems},
author = {Ozgun Y. Bursalioglu and Zheda Li and Chenwei Wang and Haralabos Papadopoulos},
journal= {arXiv preprint arXiv:1801.04001},
year = {2018}
}
Comments
This manuscript has been submitted to 2018 IEEE International Conference on Communications Workshops (ICC Workshops): Promises and Challenges of Machine Learning in Communication Networks