arXiv Machine Learning September 16, 2026 By Oier Larumbe-Lizarraga, Roberto Pereira, Cristian J. Vaca-Rubio

Goal-oriented probabilistic forecasting for dynamic PRB allocation in 5G networks

Read the original on arXiv Machine Learning →

The paper introduces a goal‑oriented probabilistic forecasting framework for dynamic physical resource block (PRB) allocation in 5G networks. By training DeepAR and Temporal Fusion Transformer models with the Pinball Loss function and selecting an optimal allocation quantile based on an operator’s cost matrix, the approach aligns forecasting with operational objectives. Experiments on real beam‑level 5G traffic data show reduced operational cost compared to MSE‑trained baselines while preserving calibrated uncertainty estimates.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

llms

Hugging Face Trending Papers

Sep 15

Goal-oriented probabilistic forecasting for dynamic PRB allocation in 5G networks

Efficient physical resource block (PRB) allocation in 5G networks requires accurate demand forecasting. Conventional methods minimize symmetric error metrics (MAE, RMSE), ignoring the operational cost...

llms

arXiv AI

Jul 23

Time Series Network Utilization KPI Forecasting Using Advanced AI/ML Models

arXiv:2607. 19974v1 Announce Type: cross Abstract: The rapid proliferation of data-intensive applications, cloud infrastructure, and IoT ecosystems has made proactive resource provisioning critical for maintaining optimal network performance.

By Niraj Gadhe, Kirti Bhardwaj, Moulik Jain, Shubhi Sharma, Vinay Saini

arXiv AI

Sep 10

TD-STGT: A Spatio-Temporal Graph Transformer for Mobile Traffic Demand Forecasting

arXiv:2609.06636v1 Announce Type: cross Abstract: Fine-grained mobile traffic demand forecasting is essential for long-term planning of 5G and future 6G networks, including radio upgrades, site densi...

By Mohamad Alkadamani, Halim Yanikomeroglu

llms

arXiv AI

Jun 29

Parameter Efficient Hybrid Transformer (PEHT) for Network Traffic Prediction via Dynamic Urban Congestion Integration

arXiv:2606. 28274v1 Announce Type: cross Abstract: Accurate network traffic prediction is a critical element for efficient resource allocation in dynamic urban cellular networks.

By Abdolazim Rezaei, Mehdi Sookhak, Mahboobeh Haghparast

llms fine-tuning multimodal benchmarks

arXiv AI

Jul 15

Learning-based Probabilistic Load Forecasting with Post-hoc and In-model Uncertainty

arXiv:2607. 12730v1 Announce Type: cross Abstract: Smart-building load forecasters are often trained offline on dense, multivariate, high-frequency data, but deployment may provide only hourly, feature-limited inputs.

By Sarah Al-Shareeda, Gulcihan Ozdemir, Heung Seok Jeon

llms

arXiv Machine Learning

Aug 11

ML-Based Hierarchical Prediction for Practical Energy Scheduling in Dynamic NTN-WPT Systems

arXiv:2608. 08804v1 Announce Type: cross Abstract: With advancements in long-distance wireless power transfer (WPT) and space-based energy technologies, integrating WPT into non-terrestrial networks (NTNs), referred to as NTN-WPT, is emerging as a promising approach for next-generation wireless networks.

By Zhanyu Ju, Wenchi Cheng

agents reinforcement-learning

One email a morning, machine-written

Related stories

Goal-oriented probabilistic forecasting for dynamic PRB allocation in 5G networks

Time Series Network Utilization KPI Forecasting Using Advanced AI/ML Models

TD-STGT: A Spatio-Temporal Graph Transformer for Mobile Traffic Demand Forecasting

Parameter Efficient Hybrid Transformer (PEHT) for Network Traffic Prediction via Dynamic Urban Congestion Integration

Learning-based Probabilistic Load Forecasting with Post-hoc and In-model Uncertainty

ML-Based Hierarchical Prediction for Practical Energy Scheduling in Dynamic NTN-WPT Systems