Fraunhofer HHI and Japan’s NICT launch optical testbed ‘data space’

08 Apr 2025

OTDS platform is intended to develop AI and machine learning models for optical networks.

Representatives of the HHI and NICT team with their set up and paper.

With the joint aim of revolutionizing network technologies, the Fraunhofer Heinrich Hertz Institute(HHI) and Japan’s National Institute of Information and Communications Technology (NICT) have together launched the Optical Testbed Dataspace (OTDS).

OTDS is designed to accelerate the development and testing of artificial intelligence and machine learning (AI and ML) models for optical networks. The partners last week stated that the platform is designed to “foster global collaboration by enabling international partners to securely share and aggregate testbed data from diverse environments, pushing the boundaries of network optimization and automation.”

Dataset availability is a significant challenge in advancing networks with AI/ML research. Network data is typically classified by operators and regulatory bodies, while vendors restrict access to specific equipment telemetry. Alternatives, such as experimental or synthetic data, often result in overfitting and poor generalization performance.

To address this, optical network testbeds are evolving to play a crucial role in delivering big data — specifically, telemetry data for rare and abnormal events, such as network failures. This data is essential for training and validating AI-assisted network functions. However, assembling a comprehensive dataset, particularly for the emerging disaggregated, multi-vendor environments, remains a challenge for a single testbed while maintaining cost-effectiveness.

Innovation meets security

“Our mission is to design state-of-the-art innovations without compromising on data privacy or safety. OTDS enables the secure exchange of network data, fostering the development of innovative AI models that comply with strict data privacy and export control regulations,” said Dr. Johannes Fischer, Head of the Digital Signal Processing Group at HHI.

“The data sovereignty framework, such as OTDS, is essential to enable open innovation in an AI-driven network. OTDS would also further enhance the importance of the network testbeds operated by the respective institutions,” said Dr. Yoshinari Awaji, Director General of Photonic ICT Research Center at NICT.

OTDS, based on the Eclipse Dataspace Components Connector (EDCC) and aligned with the principles of the International Data Spaces Association (IDSA), provides a framework for testbeds to securely share their data while ensuring compliance with data sovereignty and export control requirements.

“Real-time data exchange from testbeds generates diverse datasets that are crucial for training and validating AI models, facilitating the automation and optimization of network functions,” said Dr. Behnam Shariati, Head of the AI for Photonics division at HHI. “OTDS lowers the barriers to data access and fosters an open research environment, paving the way for the rapid validation of cutting-edge network automation solutions.”

“With OTDS, we can strengthen global research collaboration and accelerate the development of the next generation of AI-powered optical networks, improving mobile connectivity for remote areas and network resiliency, or support real-time data processing in industry and critical infrastructures,” says Dr. Yuki Yoshida, Research Manager of Photonic ICT Research Center at NICT.

OTDS validation

HHI and NICT have successfully demonstrated the technology, creating a prototype for international data exchange between optical testbeds in Berlin, Germany and Sendai, Japan. The partners showcased a live demonstration of this data transfer at Tohoku University in Japan during the 5th Germany-Japan Beyond 5G/6G Research Workshop, supported by the Federal Ministry of Education and Research (BMBF) and Japan’s Ministry of Internal Affairs and Communications (MIC).

The demonstration was extended for validating AI/ML models for network failure analysis using data points of the different testbeds and was showcased at last week’s Optical Fiber Communications Conference and Exhibition, in San Francisco, California, USA. All details are published in a new paper International Testbed Data Sharing Framework with Data Sovereign Features for Network AI/ML Empowerment.