Delivery-Aware Hybrid Throughput Forecasting for Targeted Capacity Planning and Proactive Congestion Avoidance in Microwave Transmission Networks
DOI:
https://doi.org/10.62146/ijecbe.v4i1.239Keywords:
Microwave transmission, throughput forecasting, hybrid forecasting, LightGBM residual correction, Hybrid Framework, multi-horizon predictionAbstract
Microwave transmission networks operate under strict physical-layer capacity constraints, where excessive utilization may reduce service reliability and increase congestion risk. In practical operations, capacity expansion decisions are both time-sensitive and location-sensitive, requiring operators to determine not only when an upgrade should be executed, but also which links require intervention. However, many existing forecasting approaches remain focused on numerical prediction accuracy and do not explicitly support delivery-aware and targeted planning decisions. This study proposes a delivery-aware hybrid smoothing–residual forecasting framework for link-level microwave throughput prediction using hourly Network Management System (NMS) data from 110 links observed over a six-month period. The framework separates the throughput series into a smoothed structural component and a residual component, where primary forecasting is performed on the structural signal, and residual error is modeled using LightGBM. The final forecast is reconstructed by combining both components and evaluated across multiple horizons using WMAPE, MAE, and RMSE. Experimental results show that CatBoost with LightGBM residual correction provides the most consistent performance across all forecasting horizons. Beyond improving prediction accuracy, the proposed framework enables delivery-aware and targeted capacity planning by estimating threshold-crossing timing and identifying high-risk links. This supports proactive congestion avoidance, more efficient upgrade prioritization, and improved resource allocation in microwave transmission networks.
References
ITU-R, Recommendation ITU-R P.530-19: Propagation Data and Prediction Methods Required for the Design of Terrestrial Line-of-Sight Systems, Sep. 2025.
Huawei, Microwave Industry White Paper 2025, Nov. 2025.
Ericsson, Microwave Outlook 2025: Near Fiber Split, AI and 2x Capacity, Oct. 2025.
Huawei, Microwave Industry White Paper 2024, 2024.
Telecom Regulatory Authority of India (TRAI), Recommendations on Assignment of the Microwave Spectrum for Backhaul, Dec. 2025.
G. A. Christian, I. P. Wijaya, and R. F. Sari, “Network Traffic Prediction of Mobile Backhaul Capacity Using Time Series Forecasting,” in Proc. ISITIA, 2021. DOI:10.1109/ISITIA52817.2021.9502256
R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed. OTexts, 2021. https://otexts.com/fpp3/
G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control, 5th ed. Wiley, 2015.
G. O. Ferreira et al., “Forecasting Network Traffic: A Survey and Tutorial With Open-Source Comparative Evaluation,” IEEE Access, vol. 11, 2023. DOI : 10.1109/ACCESS.2023.3236261
Zhang et al., “A hybrid ARIMA and neural network model for time series forecasting,” 2001 Neurocomputing page 159-275
G. Ke et al., “LightGBM: A Highly Efficient Gradient Boosting Decision Tree,” in Advances in Neural Information Processing Systems (NeurIPS), 2017.
L. Prokhorenkova et al., “CatBoost: Unbiased Boosting With Categorical Features,” in Advances in Neural Information Processing Systems (NeurIPS), 2018.
S. Haykin, Neural Networks and Learning Machines, 3rd ed. Pearson, 2009.
M. Di Mauro et al., “Hybrid Learning Strategies for Multivariate Time Series Cellular Traffic Forecasting,” Computer Networks, 2024. DOI:10.1016/j.comnet.2024.110286
Chen & Guestrin, “XGBoost: A Scalable Tree Boosting System,” KDD 2016 DOI:10.1145/2939672.2939785
S. Li et al., “Deep Learning Based Prediction of Traffic Peaks in Mobile Networks,” Computer Networks, 2024. DOI:10.1016/j.comnet.2023.110167
X. Liu et al., “A Meta-Learning-Based Framework for Cellular Traffic Forecasting,” Applied Sciences, 2025. DOI:10.3390/app152111616
Wu et al., “Deep learning for mobile traffic forecasting: A survey,” IEEE TNSM, 2019 DOI:10.1109/TNSM.2019.2929152
Y. Peng et al., “Network Traffic Prediction With Attention-Based Spatial-Temporal Modeling,” Computer Networks, 2024. DOI:10.1016/j.comnet.2024.110296
Z. Jin et al., “A Mobility-Aware Network Traffic Prediction Model,” Computer Networks, 2023. DOI:10.1016/j.comnet.2023.109981
Pan & Yang, “A Survey on Transfer Learning,” IEEE TKDE, 2010 DOI: 10.1109/TKDE.2009.191
Y. Ge et al., “Adaptive Clockwork LSTM for Network Traffic Prediction,” 2025. DOI:10.48550/arXiv.1503.04069
M. Abbasi et al., “Deep Learning for Network Traffic Monitoring and Analysis: A Review,” Computer Communications, 2021. DOI:10.1016/j.comcom.2021.01.021
E. Lykakis et al., “Data Traffic Prediction for 5G and Beyond,” Electronics, 2025. DOI:10.3390/electronics14234611
S. Saha et al., “Overcoming Data Limitations in Internet Traffic Forecasting,” Computer Communications, 2025. DOI: 10.1016/j.comcom.2025.108280
J. Kim et al., “A Deep Dive into AI-Based Network Traffic Prediction,” Applied Sciences, 2025. DOI:10.3390/app16010367
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Electrical, Computer, and Biomedical Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
