Zhihua Lai
Research Subjects
Research Interests
Zhihua Lai has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Bozidar Radunovic
Microsoft Research, Cambridge, United Kingdom
4 shared publications - Matthew Balkwill
Microsoft, Cambridge, United Kingdom
4 shared publications - Xenofon Foukas
Microsoft Research, Cambridge, United Kingdom
4 shared publications - Connor Settle
Microsoft, Cambridge, United Kingdom
3 shared publications - Yongguang Zhang
Microsoft, Redmond, USA
2 shared publications - Alec Wolman
Microsoft, Redmond, Washington, United States
1 shared publication
Latest Publications
- Open Access
- 4 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 15-21
Distributed AI Platform for the 6G RAN
- 4 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 15-21
Open AccessDistributed AI Platform for the 6G RAN
- Open Access
- 2 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Accelerating Open RAN Research Through an Enterprise-scale 5G Testbed
Open RAN is an emerging paradigm in mobile networks where the Radio Access Network (RAN) functions are disaggregated and virtualized on commodity servers. Despite the importance of Open RAN research, existing platforms often lack the fidelity and stability required to address a wide range of research problems. In response to this limitation, we have developed an enterprise-scale Open RAN testbed aimed at conducting state-of-the-art research in key areas that have received limited attention due to the lack of suitable platforms. In this poster, we provide an overview of the testbed we have created and examples of the research it has enabled, with the hope of catalyzing future open RAN research and innovation.
- 2 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessAccelerating Open RAN Research Through an Enterprise-scale 5G Testbed
Open RAN is an emerging paradigm in mobile networks where the Radio Access Network (RAN) functions are disaggregated and virtualized on commodity servers. Despite the importance of Open RAN research, existing platforms often lack the fidelity and stability required to address a wide range of research problems. In response to this limitation, we have developed an enterprise-scale Open RAN testbed aimed at conducting state-of-the-art research in key areas that have received limited attention due to the lack of suitable platforms. In this poster, we provide an overview of the testbed we have created and examples of the research it has enabled, with the hope of catalyzing future open RAN research and innovation.
- Open Access
- 2 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Programmable RAN Platform for Flexible Real-Time Control and Telemetry
A key transformation of the Radio Access Network (RAN) in 5G is the migration to an Open RAN architecture, that sees the RAN functions virtualized and disaggregated. Open RAN, aims at accelerating innovation through the introduction of a programmable RAN Intelligent Controller (RIC). However, due to latency and safety challenges, the telemetry and control provided by the RIC is mainly limited to higher layers and time scales (>10ms), while also relying on predefined service models which are hard to change. In this work, we demonstrate Minerva, a programmable monitoring and control platform, specifically designed with the RAN idiosyncrasies in mind. Minerva introduces two novel components called Janus and Decima, for the deployment of safe RAN control and telemetry applications by trusted third-parties. Janus enables the deployment of codelets in the RAN functions using userspace eBPF for fast inline control and filtering of data. Decima, enables the deployment of sandboxed real-time control applications, by leveraging data collected from Janus and the OS. We demonstrate the benefits of Minerva through two applications related to interference detection and inter-cell interference mitigation, by leveraging a commercial-grade 5G testbed deployment.
- 2 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessProgrammable RAN Platform for Flexible Real-Time Control and Telemetry
A key transformation of the Radio Access Network (RAN) in 5G is the migration to an Open RAN architecture, that sees the RAN functions virtualized and disaggregated. Open RAN, aims at accelerating innovation through the introduction of a programmable RAN Intelligent Controller (RIC). However, due to latency and safety challenges, the telemetry and control provided by the RIC is mainly limited to higher layers and time scales (>10ms), while also relying on predefined service models which are hard to change. In this work, we demonstrate Minerva, a programmable monitoring and control platform, specifically designed with the RAN idiosyncrasies in mind. Minerva introduces two novel components called Janus and Decima, for the deployment of safe RAN control and telemetry applications by trusted third-parties. Janus enables the deployment of codelets in the RAN functions using userspace eBPF for fast inline control and filtering of data. Decima, enables the deployment of sandboxed real-time control applications, by leveraging data collected from Janus and the OS. We demonstrate the benefits of Minerva through two applications related to interference detection and inter-cell interference mitigation, by leveraging a commercial-grade 5G testbed deployment.
- Open Access
- 10 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Taking 5G RAN Analytics and Control to a New Level
- 10 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Open AccessTaking 5G RAN Analytics and Control to a New Level