PRB-RUPFormer: A Recursive Unified Probabilistic Transformer for Residual PRB Forecasting

TL;DR

The paper introduces PRB-RUPFormer, a probabilistic Transformer model that jointly forecasts residual PRBs across carriers and sectors, providing accurate, uncertainty-aware predictions to enhance spectrum management in cellular networks.

Contribution

It proposes a novel recursive probabilistic Transformer that captures cross-carrier dependencies and provides confidence intervals for residual PRB forecasting, trained on multi-sector LTE data.

Findings

Median MAE below 0.05 on six months of LTE data

Hit probabilities above 0.80 for 1-day and 7-day forecasts

Efficient joint modeling across carriers and sectors

Abstract

Accurate forecasting of residual Physical Resource Blocks (PRBs) is critical for proactive network slice provisioning, energy-efficient operation, and spectrum-aware decision making in cellular systems, where residual PRBs serve as a practical proxy for short- and medium-term spectrum availability. Existing PRB prediction methods typically rely only on historical PRB values and are trained independently per carrier or sector, limiting their ability to capture cross-carrier dependencies and providing no measure of forecast uncertainty. Moreover, point forecasts alone are insufficient for robust spectrum-aware control under highly variable traffic conditions. This paper proposes PRB-RUPFormer, a recursive unified probabilistic Transformer for residual PRB forecasting. The proposed model jointly processes multivariate KPI time series using temporal, seasonal, and carrier-aware embeddings, preserving inter-metric temporal coupling during recursive rollout and stabilizing long-horizon forecasting. A single shared model is trained across all carriers and sectors of an eNB, enabling efficient learning of joint traffic dynamics with low computational overhead. Forecast uncertainty is captured through quantile-based prediction intervals, providing confidence-aware estimates of future PRB availability. Evaluations on six months of commercial LTE network data from multiple U.S. locations demonstrate median MAE below 0.05 and hit probabilities above 0.80 for both one-day and seven-day recursive forecasts. These probabilistic predictions directly support spectrum-aware RAN functions such as dynamic carrier activation, congestion avoidance, and proactive spectrum sharing, making the proposed framework well-suited for dynamic spectrum access scenarios.