A Family of Open Time-Series Foundation Models for the Radio Access Network

TL;DR

This paper introduces TimeRAN, a unified foundation model for RAN time-series analytics, enabling transfer learning, large-scale pretraining, and efficient deployment across diverse tasks.

Contribution

The paper presents a novel multi-task learning framework and a large RAN time-series dataset, advancing unified modeling and transfer learning in RAN analytics.

Findings

TimeRAN achieves state-of-the-art results across multiple RAN tasks.

Pretraining on TimeRAN DataPile improves performance with limited supervision.

Efficient deployment demonstrated in a 5G testbed.

Abstract

The Radio Access Network (RAN) is evolving into a programmable and disaggregated infrastructure that increasingly relies on AI-native algorithms for optimization and closed-loop control. However, current RAN intelligence is still largely built from task-specific models tailored to individual functions, resulting in model fragmentation, limited knowledge sharing across tasks, poor generalization, and increased system complexity. To address these limitations, we introduce TimeRAN, a unified multi-task learning framework for time-series modeling in the RAN. TimeRAN leverages a lightweight time-series foundation model with few task-specific heads to learn transferable representations that can be efficiently adapted across diverse tasks with limited supervision. To enable large-scale pretraining, we further curate and open-source TimeRAN DataPile, the largest time-series corpus for RAN analytics to date, comprising over 355K time series and 0.56B measurements across diverse telemetry sources, protocol layers, and deployment scenarios. We evaluate TimeRAN across a comprehensive set of RAN analytics tasks, including anomaly detection, classification, forecasting, and imputation, and show that it achieves state-of-the-art performance with minimal or no task-specific fine-tuning. Finally, we integrate TimeRAN into a proof-of-concept 5G testbed and demonstrate that it operates efficiently with limited resource requirements in real-world scenarios.