AI-Enhanced Connection Management for Cellular Networks-Reference-Cited by-同舟云学术

AI-Enhanced Connection Management for Cellular Networks

Published:2024 Issue: Volume: Page:169-183
ISSN:1860-949X
Container-title:Studies in Computational Intelligence
language:en
Short-container-title:

Author:

Wenning Bernd-Ludwig

Abstract

AbstractCellular networks such as 4G, 5G and beyond are essential components of current and future communication infrastructure. Current research topics such as smart mobility, intelligent transportation systems and autonomous driving heavily depend on the availability of ubiquitous connectivity. In addition, consumer demand for cellular network resources is ever growing. In the context of the InSecTT project, cellular connectivity contributes, e.g., to use cases in the rail domain, where remote monitoring, maintenance and diagnostics rely on the presence of cellular uplinks from the rolling stock to cloud services. As the rolling stock moves, these uplinks are subject to continuously changing conditions that affect the availability and quality of the connection. To counteract this and to increase resilience, onboard systems may be equipped with a number of uplink options that can be used. This chapter discusses the use of AI to assess and manage the available connections and to move data traffic between the available links according to their expected data rates.

Publisher

Springer Nature Switzerland

Link

https://link.springer.com/content/pdf/10.1007/978-3-031-54049-3_10

Reference17 articles.

1. Oshiba, T., Nogami, K., Nihei, K., Satoda, K.: Robust available bandwidth estimation against dynamic behavior of packet scheduler in operational LTE networks. In: IEEE Symposium on Computers and Communication (ISCC) (2016)

2. Tachibana, A., Paul, A.K., Hasegawa, T.: Next-t: Available bandwidth measurement over 4G/LTE networks - a curve-fitting approach. In: IEEE 30th International Conference on Advanced Information Networking and Applications (AINA) (2016)

3. Shiobara, S., Okamawari, T.: A novel available bandwidth estimation method for mobile networks using a train of packet groups. In: 11th International Conference on Ubiquitous Information Management and Communication (IMCOM) (2017)

4. Oshiba, T., Sato, N., Nogami, K., Sawabe, A., Satoda, K.: Experimental comparison of machine learning-based available bandwidth estimation methods over operational LTE networks. In: IEEE Symposium on Computers and Communications (ISCC) (2017)

5. Qian, F., Huang, J., Guo, Y., Zhou, Y., Mao, Z.M., Xu, Q., Sen, S., Spatscheck, O.: An in-depth study of LTE: effect of network protocol and application behavior on performance. ACM SIGCOMM 2013, 363–374 (2013)