BROWSE
Detail
Conference Paper
The Empirical Evaluation of Machine Learning Models Predicting Round-Trip Time in Cellular Network
Cited 3 time in 
Share 
Share
- Authors
- Seunghan Choi, Changki Kim
- Issue Date
- 2021-10
- Citation
- International Conference on Information and Communication Technology Convergence (ICTC) 2021, pp.1374-1376
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- QoS guarantee of end-to-end path between mobile terminals and TSN terminals in TSN network is important to realize TSN service, which require ultra-low latency services. In order to calculate the optimal new end-to-end path, it is effective to predict the measurements at the point in time reflecting the end-to-end path and reflect them in the end-to-end path calculation. Model forecasting network latency, such as RTT, is required in order to calculate the optimal new end-to-end path. In this paper, we present the evaluation of the machine learning models with RTT dataset collected from cellular network. Random Forest, GBM, XGBoost, and LGBM regressor are used for evaluation.
- KSP Keywords
- Cellular networks, End to End(E2E), Network QoS, Network latency, Path calculation, QoS guarantee, Round-trip time(RTT), Ultra-low latency, empirical evaluation, end-to-end path, machine learning models