Seminar - Hot Topics in Edge Computing (WS 2021/22)
Course Description
Cloud computing has created a radical shift in application services and has expanded the reach of computing, networking and data storage to its users. However, growing popularity of emerging latency-sensitive, “big-data” generating applications such as Internet-of-Things, autonomous vehicles, and smart cities have motivated research in new computing paradigm, edge computing.
Edge computing is a (semi-) distributed computing paradigm which aims to bring existing cloud services and utilities near end-users. Unlike traditional cloud datacenters, edge resources are deployed in close proximity to end-users and sensors, e.g. routers, base stations, and smart speakers which allows them to provide support for mobility, context awareness and data aggregation in computations. Edge computing is becoming more important for the academia and industry alike, and significant efforts are being made to standardize its deployment, management and operation.
The Hot Topics in Edge Computing seminar will explore latest advances, challenges, and hot topics relevant in edge computing research. The aim of this seminar will be to motivate participants to investigate following topics relevant to edge computing research from practical usability standpoint.
- Distributed computing at the Edge
- Network communication between client, edge and cloud (e.g., 5G, Wi-Fi6)
- Data analytics using Edge computing (e.g., Computer Vision, Distributed Learning)
- Reliability and availability in Edge computing
- Hardware and protocols enabling Edge computing (e.g. FPGAs, edge accelerators)
- Frameworks and programming models for Edge
- Real-time applications for Edge computing (e.g. video analytics, autonomous vehicles, AR/VR)
- Security and privacy at the Edge (e.g. Trusted Execution Environments, Secure containers)
(Expected) Learning Outcomes
Upon completion of the seminar, the students will have broadened their knowledge on the current state of the edge computing research and gaps that exist in realizing a fully-functional edge computing platform. The students will also become familiar with reading, writing and presenting academic papers in a setting similar to a scientific conference.
(Recommended) Course Pre-Requisites
-
The participants are expected to have taken an undergraduate-level course on computer networks.
-
The topics require background in communications and networking technologies and distributed computing algorithms. Although the wide range of topics allows for varied technical backgrounds.
- Bachelor's degree in computer science or a related field is required.
- Very good ability to write and present in English.
Teaching and Learning Methods
- Written paper, 6-8 pages using ACM sigconf template (50%)
- Two check-points throughout the semester to ensure good progress of the manuscript (10%, with 5% each)
- Final manuscript (35%)
- Read and present a short summary about a paper we will discuss at every session (30%, divided equally over the number of discussions)
- Presentation of the manuscript you are writting for the course (~30 minutes) (25%), to be done at the end of the term
- Active participation in the course: participating in general discussion (percentage divided equally across number of discussions)
Schedule
Course Moodle Page: link
- Pre-Course Meeting: 16th July, 2021 @ 13h00 (BBB)
- First lecture: 19th October, 2021 @ 14h00 (Zoom)
- Feedback round: TBD (likely midway through the course)
- Final presentation: TBD (likely in February 2022)
The course will be held virtually over Zoom. Details of the Zoom meeting is available in Moodle page of the course.
Further Readings
- S. Keshav. "How to read a paper"
- William G. Griswold, "How to Read an Engineering Research Paper"
- Graham Cormode. 2009. "How NOT to review a paper: the tools and techniques of the adversarial reviewer."
- J Smith. "The Task of the Referee"
Contact
Dr. Nitinder Mohan - mohan at in tum de
Leonardo Tonetto - tonetto at in tum de