Effect of Spatial, Temporal and Network Features on Uplink and Downlink Throughput Prediction

被引:6
作者
Palaios, Alexandros [1 ]
Vielhaus, Christian [2 ]
Kuelzer, Daniel F. [3 ]
Geuer, Philipp [1 ]
Sattiraju, Raja [4 ]
Fink, Jochen [5 ]
Kasparick, Martin [5 ]
Watermann, Cara [1 ]
Fettweis, Gerhard [2 ]
Fitzek, Frank H. P. [2 ]
Schotten, Hans D. [4 ]
Stanczak, Slawomir [5 ,6 ]
机构
[1] Ericsson Res, Dusseldorf, Germany
[2] Tech Univ Dresden, Dresden, Germany
[3] BMW Grp, Munich, Germany
[4] Tech Univ Kaiserslautern, Kaiserslautern, Germany
[5] Fraunhofer Heinrich Herz Inst, Berlin, Germany
[6] Tech Univ Berlin, Network Informat Theory Grp, Berlin, Germany
来源
2021 IEEE 4TH 5G WORLD FORUM (5GWF 2021) | 2021年
关键词
Artificial Intelligence; Machine Learning; Quality of Service; Throughput Prediction; High Mobility;
D O I
10.1109/5GWF52925.2021.00080
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Recently, there have been many attempts to apply Machine Learning (ML)-based prediction mechanisms in wireless networks. One open question is how reliable such predictions can be, and how well ML models can learn from the radio environment. In this paper, we present initial results on Quality of Service (QoS) prediction using the example of throughput prediction. We focus on suggesting new sets of features that can improve the prediction performance for different prediction horizons. Thereby, we identify important features that have a large impact when using radio environment data as input for ML models. To this end, we consider information from space, time, and network domains. In particular, we show that features, such as cell throughput and previous users' data can significantly improve the ML model performance. Besides the importance of input features, we also investigate how the prediction performance deteriorates for different prediction horizons.
引用
收藏
页码:418 / 423
页数:6
相关论文
共 15 条
[1]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[2]  
Falkenberg R., 2017, P GLOBECOM 2017 2017, P1, DOI [DOI 10.1109/GLOCOM.2017.8254567.1069, 10.1109/GLOCOM.2017.8254567.1069]
[3]  
Ghasemi A, 2018, IEEE INT SYMP DYNAM
[4]  
Jinsung Lee, 2020, MobiSys '20: Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services, P377, DOI 10.1145/3386901.3388911
[5]  
Kulzer D. F., 2021, P IEEE VEH TECHN C V, P1
[6]   INTELLIGENT 5G: WHEN CELLULAR NETWORKS MEET ARTIFICIAL INTELLIGENCE [J].
Li, Rongpeng ;
Zhao, Zhifeng ;
Zhou, Xuan ;
Ding, Guoru ;
Chen, Yan ;
Wang, Zhongyao ;
Zhang, Honggang .
IEEE WIRELESS COMMUNICATIONS, 2017, 24 (05) :175-183
[7]  
Louppe G., 2013, Advances in Neural Information Processing Systems
[8]  
Ma CYT, 2010, MOBICOM 10 & MOBIHOC 10: PROCEEDINGS OF THE 16TH ANNUAL INTERNATIONAL CONFERENCE ON MOBILE COMPUTING AND NETWORKING AND THE 11TH ACM INTERNATIONAL SYMPOSIUM ON MOBILE AD HOC NETWORKING AND COMPUTING, P185
[9]  
Palaios A., 2021, PROC IEEE INT S PERS, P1
[10]   Tensor Completion for Radio Map Reconstruction using Low Rank and Smoothness [J].
Schaeufele, Daniel ;
Cavalcante, Renato L. G. ;
Stanczak, Slawomir .
2019 IEEE 20TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (SPAWC 2019), 2019,