Probabilistic Forecasting for Network Resource Analysis in Integrated Terrestrial and Non-Terrestrial Networks

TL;DR

This work integrates probabilistic forecasting into an O-RAN–based TN-NTN architecture to optimize resource provisioning across terrestrial and non-terrestrial networks. It evaluates the SFF approach against deterministic LSTM in a case study using real satellite traffic data, demonstrating that probabilistic forecasts provide useful uncertainty quantification and can improve provisioning decisions, SLA adherence, and resilience to throughput variability. The paper outlines a unified TN-NTN workflow, practical deployment considerations (on-board inference, quantization, federated learning), and a standardization roadmap spanning 3GPP, ETSI, ITU, ISO, and cross-sector guidelines. The results support adopting uncertainty-aware forecasting for NTN backhaul, beam management, and cross-segment resource balancing, with significant implications for future B5G/6G networks and satellite-enabled services.

Abstract

Efficient resource management is critical for Non-Terrestrial Networks (NTNs) to provide consistent, high-quality service in remote and under-served regions. While traditional single-point prediction methods, such as Long-Short Term Memory (LSTM), have been used in terrestrial networks, they often fall short in NTNs due to the complexity of satellite dynamics, signal latency and coverage variability. Probabilistic forecasting, which quantifies the uncertainties of the predictions, is a robust alternative. In this paper, we evaluate the application of probabilistic forecasting techniques, in particular SFF, to NTN resource allocation scenarios. Our results show their effectiveness in predicting bandwidth and capacity requirements in different NTN segments of probabilistic forecasting compared to single-point prediction techniques such as LSTM. The results show the potential of black probabilistic forecasting models to provide accurate and reliable predictions and to quantify their uncertainty, making them indispensable for optimizing NTN resource allocation. At the end of the paper, we also present application scenarios and a standardization roadmap for the use of probabilistic forecasting in integrated Terrestrial Network (TN)-NTN environments.

Figures (6)

• Figure 1: Integrated NTN and TN (with Open RAN) architecture with probabilistic forecasting as rApp.
• Figure 2: Enhanced workflow of integrated TN-NTN infrastructure for Resource Provisioning.
• Figure 3: SFF probabilistic satellite traffic forecasting.
• Figure 4: LSTM deterministic satellite traffic forecasting.
• Figure 5: Prediction errors for SFF and LSTM.