RINGS: Intelligent and Resilient Virtualization of Massive MIMO Physical Layer

People

• Lin Zhong (PI)
• Anurag Khandelwal (PI)
• Seung-seob Lee (Postodoctoral Associate)
• Parthiban Annamalai (Postdoctoral Associate)
• Zhiyao Ma (Graduate Student)
• Ramla Ijaz (Graduate Student)
• Yanpeng Yu (Graduate Student)
• Chaeyoung Lee(Undergraduate Student)

Project Summary

NextG network systems rely on virtualization to move away from specialized, dedicated equipment to cloud and edge datacenters, to reduce cost and accelerate innovation. So far such virtualization efforts have met with very limited success, making inroads largely with 4G/LTE small cells. This is because 5G and beyond employ compute-intensive technologies such as massive MIMO and low-density parity-check (LDPC) code to deliver the unprecedented network performance. Massive MIMO not only demands massive computational power itself, but also proportionally increases that of LDPC. Not surprisingly, existing commercial massive MIMO solutions all rely on specialized, dedicated hardware such as FPGA and application-specific integrated circuits. Massive MIMO remains the largest barrier toward virtualized mobile networks.

The goal of the proposed project is to overcome this technical barrier and virtualize massive MIMO physical layer for NextG network systems. In doing so, we not only aim at achieving performance and energy efficiency similar to that of specialized, dedicated equipment, but also will take advantage of virtualization toward previously impossible levels of resilience and intelligence in the physical layer, at low cost. While the project does not target at algorithmic or information theoretical contributions in wireless physical layer, it will empower them by allowing them to be validated at low cost and deployed in a timely manner, i.e., as software running in a datacenter.

The project targets at the following scientific contributions:

1. Design and implementation of massive MIMO physical layer that scale up on a many-core server efficiently and intelligently. We will combine the efficiency of static and elasticity of dynamic task scheduling and devise latency-driven, automated schemes for optimal resource provisioning.
2. Disaggregated design and implementation that can utilize compute resources integrated over a local-area network, beyond a single server. We will leverage programmable switches to minimize the impact of network and to utilize commodity servers as well as accelerators to achieve scale, cost effectiveness and energy efficiency beyond the reach of a single many-core server.
3. Elastic design and implementation that match up to dynamics in mobile network workload, simultaneously achieving high resilience, low cost for the network operator, and high utilization for the cloud provider, in a multi-tenant environment. We will explore serverless computing and develop it further to better meet the stringent latency requirement of massive MIMO physical layer.

The proposed project will fuel the ongoing revolution of mobile network virtualization and accelerate the development and deployment of NextG network systems. Specifically, it will expedite the adoption of massive MIMO, resulting in more capable, more efficient, and more cost-effective mobile networks. We will leverage our ongoing collaborations with industry leaders to ensure a timely transfer of technologies into industry and a broad impact on the commercial development of mobile network, edge and cloud computing. By virtualizing wireless network functions at the lowest layer, this project provides a meeting ground for software systems and wireless communication researches and creates timely content for teaching Computer Science majors about wireless physical layer. The project will provide a platform to engage undergraduate students and high-school students in computing research, especially women and underrepresented minorities.

Publications

• Yanpeng Yu, Seung-seob Lee, Anurag Khandelwal, and Lin Zhong, "GCS: Generalized cache coherence for efficient synchronization," arXiv, January 2023.
• Seung-seob Lee, Yanpeng Yu, Yupeng Tang, Anurag Khandelwal, Lin Zhong and Abhishek Bhattacharjee, "MIND: in-network memory management for disaggregated data centers," in Proc. ACM Symp. Operating Systems Principles (SOSP), October 2021. (PDF)
• Jian Ding, Rahman Doost-Mohammady, Anuj Kalia, and Lin Zhong, "Agora: real-time massive MIMO baseband in software," in Proc. ACM Int. Conf. emerging Networking EXperiments and Technologies (CoNEXT), December 2020. (Source code, PDF)

Code Repository

• Agora Github

Acknowledgments

This project is supported in part by the NSF RINGS Program and in collaboration with Intel and Microsoft.

[Home] [People] [Publications] [Projects] [Downloads] [News] [Acknowledgments] [Contact us]