Program

Note that the following program schedule uses London Time (GMT+1).

Day 1: July 10, Monday

Day 2: July 11, Tuesday

Day 1: July 10, Monday

Opening

Chair: Gianni Antichi (Queen Mary University of London, UK) and Dimitrios Koutsonikolas (Northeastern University, USA)

9:30-10:00

Keynote 1: Open 6G: Toward a Reference Architecture for Programmable and AI-Driven NextG Open RAN Systems

Chair: Dimitrios Koutsonikolas (Northeastern University, USA)

10:00-11:00

Abstract:  This talk will present an overview of our work laying the basic architectural and algorithmic principles for new approaches to design open, programmable, AI-driven, and virtualized next-generation cellular networks. We will cover in detail challenges and opportunities associated with the evolution of cellular system into cloud-native softwarized architectures enabling fine grained control of end-to-end functionalities. We will discuss architectural aspects, automation principles, and algorithmic frameworks enabling fine-grained end-to-end control of wireless system from low-level RAN functionalities to orchestration and management. We will also explore a number of enabling technologies including network slicing, spectrum sharing, security, and energy efficiency, and discuss the way forward.

Session 1: Security and Privacy

Chair: Hulya Seferoglu (University of Illinois at Chicago, USA)

11:30-12:30

Session 2: Network Architecture

Chair: Dimitrios Koutsonikolas (Northeastern University, USA)

14:00-15:30

Invited talk 1: Accelerating Edge Computing using In-Network Computing

Chair: Gianni Antichi (Queen Mary University of London, UK)

16:00-16:45

Abstract:  Edge computing is a key enabler for real time IoT analytics as it significantly reduces the analytics latency by moving the computation close to the IoT devices. However, with emerging IoT applications that can generate large volumes of data per unit time, analyzing all that data at the edge and generating appropriate response in real time remains a challenging problem. We have two representative real-world IoT applications running on our testbed — real-time analytics from AR cameras and sensors for controlling operations on a manufacturing pipeline. Both applications have three key characteristics — they generate large amounts of streaming data, they are closed loop systems, i.e., analysis of the generated data leads to actions, and the desired latency of the loop is small, of the order of a few milliseconds. Analyzing large volumes of data in real time requires substantial compute resources at the edge, ranging from high-speed CPUs and GPUs to custom processing units such as TPUs. This not only increases the cost of deployment, but also comes with high power (and cooling) overheads. Further, load balancing the computation across the heterogeneous set of compute resources at the edge is also challenging, especially given that the resource availability is expected to change dynamically. In this talk I will talk about how we can use in-network processing using programmable routers to accelerate the IoT analytics pipeline by carefully offloading certain key computations from the edge servers to the routers, thus delivering a cost and power efficient edge computing infrastructure that can do real time analytics over large volumes of data at ultra low latencies.

Day 2: July 11, Tuesday

Keynote 2: Herding Cats: Orchestration and the Edge

Chair: Gianni Antichi (Queen Mary University of London, UK)

9:30-10:30

Abstract:  Edge computing comes in many flavors, resources may be highly diverse, and (edge) applications may behave in many different – expecially also unpredictable – ways, and be it just for their potential diversity. Trying to tame them and enforce tight coordination/control may be futile from the outset, which calls for a laid back approach to resource management at the edge. We will touch upon a number of edge computing examples and distill some differentiating factors to assess where which kind of management functionality may be applied. We choose two of them to make the case for a hierarchical and in part decentralized open source orchestration framework, Oakestra, and discuss its essential features to support a highly dynamic edge.

Poster Session

11:00-11:30

Details will be provided later.

Session 3: Routing

Chair: Patrick P. C. Lee (The Chinese University of Hong Kong, Hong Kong)

11:30-12:30

Session 4: Network Functions

Chair: Gianni Antichi (Queen Mary University of London, UK)

14:00-15:30

Invited talk 2: Cost-Aware Machine Learning on Network Traffic

Chair: Dimitrios Koutsonikolas (Northeastern University, USA)

16:00-16:45

Abstract:  Applications of machine learning to networking, from performance diagnosis to security, have conventionally relied on models that are trained on offline packet traces, without regard to the limitations of existing measurement systems nor the cost of gathering, computing, and storing the corresponding input features. As a result, there remains a significant gap between the development of statistical models for network operations and their application and systemization in practice. In this talk, we explore and identify a number of challenges that impact our ability to operationalize machine learning models in modern networks. Building on the lessons learned from a 16-month deployment, we design and develop Traffic Refinery, a new system that enables the joint evaluation of both the conventional notions of machine learning performance (e.g., model accuracy) and the systems-level costs. Traffic Refinery both highlights this design space and makes it possible to explore different representations for learning, balancing systems costs related to feature extraction and model training against model accuracy.