Benchmark dataset enables machine learning for smarter wireless networks
A 3GPP-Compliant Benchmark Dataset for RIS-Aided Beyond 5G Networks
DatabasesArtificial Intelligence
Summary
Wireless networks use special surfaces called Reconfigurable Intelligent Surfaces (RIS) to improve signal quality in challenging environments. However, researchers lacked large, realistic datasets to train machines to optimize these surfaces effectively. The authors created a comprehensive dataset that follows industry standards and includes perfect setup information for the RIS, allowing computers to learn how to improve wireless signals better. They also introduced a new way to predict connection quality from signal data more easily. This dataset helps speed up research and development in next-generation wireless communication.
What this means in practice
- •For wireless network engineers: Use the dataset to train machine learning models that optimize RIS configurations for improved signal quality in advanced wireless networks.
- •For telecommunications hardware designers: Validate and benchmark new RIS hardware and algorithms against a realistic, comprehensive set of scenarios and optimal configurations.
Authors
Pujitha Mamillapalli, Pankaj Singh Rathour, Abhinav Kumar
Abstract
Reconfigurable Intelligent Surfaces (RIS) are emerging as a key technology for programmable wireless environments in the beyond the fifth generation (B5G) networks. However, data-driven RIS research remains bottleneck by the lack of standardized, high-fidelity and open-source datasets. In this paper, we introduce a large-scale 3GPP TR 38.901-compliant dataset for RIS-aided millimeter wave (mmWave) networks, that considers severe path loss, blockage sensitivity, and spatial channel sparsity make the RIS assistance more impactful. The dataset spans various canonical 3GPP deployment scenarios across 20 controlled variants, capturing diverse user densities, fading conditions, and blockage regimes. Uniquely, every sample includes oracle RIS phase configurations obtained via a globally optimal brute-force codebook search, providing gold-standard supervision labels that are absent from any existing public dataset. Rich multi-task annotations comprising full channel state information (CSI), per-link channel decomposition, optimal phase matrices, and channel quality index (CQI) labels support a broad range of machine learning paradigms and downstream tasks, including phase optimization, channel estimation, and interference management. As the primary benchmark task, we introduce a novel CSI-to-CQI mapping that frames RIS-aided link-quality prediction as a scalable scalar classification problem, thereby avoiding the exponential output complexity of the direct phase vector prediction. We have evaluated this mapping against state-of-the-art architectures under in-distribution, out-of-distribution, and real-world hardware measurement conditions. Our dataset provides a reproducible, extensible, and community-ready foundation to accelerate data-driven research in RIS-aided B5G networks.