Energy-Efficient Edge Computing

Course manual 2024/2025

Course content

The course begins by introducing the role of low-energy design in edge computing with an emphasis on energy-efficiency at the system level. It then explains different hardware/software knobs (and techniques) commonly used in edge devices to save energy. This explanation is followed by two detailed real-world research case studies – mobile gaming and Edge AI – wherein these knobs are employed successfully to save power (energy) at the edge.

The course then introduces the use of hardware-software co-design for designing energy-efficient edge devices. Using specimens, the course explains how architecture-specific low-level system software works in tandem with underlying micro-architecture to reduce the energy consumption of edge devices. The course also emphasizes the importance of the scalability of the proposed design with examples.

The last leg of the course focuses on the importance of low-energy design in designing thermally safe and physically reliable edge devices. The course explains the use of different state-of-the-art tools used to study thermals of edge devices, and how these tools are used to perform their thermal management and to increase their reliability (lifetime).

The project (and the assignments) for the course will be based on interval simulation tool-chain called HotSniper. Assignments will be in form of milestone deliverables for the larger project.

Study materials

Literature

• https://ieeexplore.ieee.org/abstract/document/8444047

Software

• https://github.com/anujpathania/HotSniper

Objectives

• The students understand the importance of low-energy design in a resource-constrained environment at the edge and how it ties to extra-functional properties of edge devices. They understand different hardware and software knobs available on edge devices for improving their energy-efficiency with real-world case studies. They understand importance of hardware-software co-design within edge devices for improving their energy-efficiency.
• The students can setup a energy simulation environment in terms of both hardware and software. The students can then perform detailed interval energy simulations.
• The students can do a detailed energy-performance analysis of applications on different micro-architectures, and then use that analysis to create energy-efficient hardware-software system design.
• The students can evaluate the efficacy of their design in terms of energy-efficiency, overhead, and scalability.

Teaching methods

• Lecture
• Laptop seminar
• Self-study
• Working independently on e.g. a project or thesis
• Presentation/symposium

Lecture: Gives students an idea about the edge systems, the problem they are addressing, and the hardware/software involved. Lectures will also impart all the knowledge needed to get started with their practical assignment.

Practicals: Students will work with state-of-the-art edge simulator. They will get first-hand experience of working as an system software developer.

Presentation: Students will give a presentation about their observations and results. The presentation will give them a chance to improve their public speaking skill alongside giving vital experience in doing a technical presentation.

Self-Study: Students will have to understand the existing cutting-research work themselves, and learn how to apply (extend) it.
 

Learning activities

Attendance

Programme's requirements concerning attendance (TER-B):

• In the case of a practical training, the student must attend at least 100% of the practical sessions. Should the student attend less than 100%, the student must repeat the practical training, or the Examinations Board may have one or more supplementary assignments issued.
• In the case of a tutorial, the student must attend at least 100% of the tutorial sessions. Should the student attend less 100%, the student must repeat the tutorial, or the Examinations Board may have one or more supplementary assignments issued.

Additional requirements for this course:

Lectures will not be recorded or streamed. Therefore, physical participation in all the lectures is highly recommended.

Assessment

Inspection of assessed work

All grading communication is performed over Canvas.

Assignments

All the assignments are group assignments.

Feedback will be given over Canvas.

All assignments are graded.

Fraud and plagiarism

The 'Regulations governing fraud and plagiarism for UvA students' applies to this course. This will be monitored carefully. Upon suspicion of fraud or plagiarism the Examinations Board of the programme will be informed. For the 'Regulations governing fraud and plagiarism for UvA students' see: www.student.uva.nl

Course structure

Contact information

Coordinator

• dr. ing. Anuj Pathania

Staff

• S. Polstra
• dr. S. Rehman