Greater New England/US Research Interest Group Meeting [April 2022]
Date: April 5, 2022
Meeting Agenda: Boston University Collaboratory Project Presentations and Discussion
1. Enabling Intelligent In-Network Computing for Cloud Systems
PI: Alan Liu, Assistant Professor, Department of Electrical and Computer Engineering, Boston University
Abstract: With the network infrastructure becoming highly programmable, it is time to rethink the role of networks in the cloud computing landscape beyond just packet delivery. The network itself emerges as a computing platform with a unique advantage of full network visibility. This project enables advanced approximate telemetry (e.g., sketches) with relevant applications on programmable networks (e.g., programmable switches, SmartNICs, and FPGAs) for cloud system management. Specifically, we will develop a cloud-native, approximate telemetry framework to offer low-overhead, fine-grained, real-time visibility into the underlying network traffic. Moving forward, this line of research with “intelligent” networking aims to provide insights and system abstractions to improve the performance, reliability, and security of cloud systems. Visit the RHR Project page for the Enabling Intelligent In-Network Computing for Cloud Systems Project.
2. Open-Source Brains for Large-Scale Autonomous Systems
PI: Eshed Ohn-Bar, Assistant Professor, Department of Electrical and Computer Engineering, Boston University
Abstract: Today, autonomous systems are fragile. In particular, the restrictive and cumbersome process of instrumenting platforms and manually annotating data limits their scope and utility in our everyday lives. Indeed, AI models for autonomy (i.e., machine brains), are easily confounded by the immense complexity of the real-world, e.g., a novel scenario, weather, geographical location, camera perspective, or autonomy use-case. The data bottleneck also impacts efficiency, i.e., collection and annotation are redundantly performed across hundreds of developers and companies. In this talk, towards accelerating the development of large-scale autonomous systems, I will propose two approaches for more collaborative and open-source development paradigms for autonomous systems. The approaches provide an overall improvement in scalability, safety, and efficiency by orders of magnitude. Visit the RHR Project page for the OSMOSIS Project.