Short-Term Multivariate KPI Forecasting in Rural Fixed Wireless LTE Networks

被引：0

作者：

Colpitts, Alexander G. B. ^{[1
]}

Petersen, Brent R. ^{[1
]}

机构：

[1] University of New Brunswick, Department of Electrical and Computer Engineering, Fredericton, E3B 5A3, NB

来源：

IEEE Networking Letters | 2023年 / 5卷 / 01期

关键词：

communication system performance; Forecasting; neural network application; rural areas;

D O I：

10.1109/LNET.2023.3242680

中图分类号：

学科分类号：

摘要：

Time series forecasting has gained significant traction in LTE networks as a way to enable dynamic resource allocation, upgrade planning, and anomaly detection. This letter investigates short-term key performance indicator (KPI) forecasting for rural fixed wireless LTE networks. We show that rural fixed wireless LTE KPIs have shorter temporal dependencies compared to urban mobile networks. Second, we identify that the inclusion of environmental exogenous features yields minimal accuracy improvements. Finally, we find that sequence-to-sequence-based (Seq2Seq) models outperform simpler recurrent neural network (RNN) models, such as long short-term memory (LSTM) and gated recurrent unit (GRU), and random forest (RF). © 2019 IEEE.

引用

页码：11 / 15

页数：4

共 21 条

[1]

Zhang C., Patras P., Haddadi H., Deep learning in mobile and wireless networking: A survey, IEEE Commun. Surveys Tuts., 21, 3, pp. 2224-2287, (2019)

[2]

Kuber T., Seskar I., Mandayam N., Traffic prediction by augmenting cellular data with non-cellular attributes, Proc. IEEE Wireless Commun. Netw. Conf., pp. 1-6, (2021)

[3]

Abhayawardhana V.S., Wassellt I.J., Crosby D., Sellars M.P., Brown M.G., Comparison of empirical propagation path loss models for fixed wireless access systems, Proc. IEEE Veh. Technol. Conf., 61, pp. 73-77, (2005)

[4]

Wagner A.L., Keusch F., Yan T., Clarke P.J., The impact of weather on summer and winter exercise behaviors, J. Sport Health Sci., 8, 1, pp. 39-45, (2019)

[5]

Lara-Benitez P., Carranza-Garcia M., Riquelme J.C., An experimental review on deep learning architectures for time series forecasting, Int. J. Neural Syst., 31, 3, pp. 1-25, (2021)

[6]

Lindemann B., Muller T., Vietz H., Jazdi N., Weyrich M., A survey on long short-term memory networks for time series prediction, Procedia CIRP, 99, pp. 650-655, (2021)

[7]

Jung S., Kim K.-M., Kwak H., Park Y.-J., A worrying analysis of probabilistic time-series models for sales forecasting, (2020)

[8]

Bhorkar A., Zhang K., Wang J., DeepAuto: A hierarchical deep learning framework for real-time prediction in cellular networks, (2019)

[9]

Xu F., Et al., Big data driven mobile traffic understanding and forecasting: A time series approach, IEEE Trans. Services Comput., 9, 5, pp. 796-805, (2016)

[10]

Lovisotto E., Et al., Cell traffic prediction using joint spatio-temporal information, Proc. 6th Int. Conf. Modern Circuits Syst. Technol., pp. 1-4, (2017)

← 1 2 3 →