Key information

Instructor
Omid Ardakanian
ardakanian@ualberta.[NULL]ca
http://webdocs.cs.ualberta.ca/~oardakan

Lectures
MW 9:30-10:50AM, CSC B-43

Office Hours
MW 1:00-2:00PM or by appointment, ATH 3-21

eClass
https://eclass.srv.ualberta.ca/course/view.php?id=39288

Prequisites
There are no formal prerequisites for this course

Grading
30% Paper Presentations, 15% Paper Reviews, 5% Class Participation, 10% Project Proposal, 40% Final Project

News

  • 15/08/2017 — First lecture: 9:30-10:50AM, Wednesday, September 6
  • 06/09/2017 — Use this Google Form to indicate your preference for paper presentation. It is due on Friday, September 15, at 11:59pm.
  • 16/09/2017 — Check out the spreadsheet for 'Assigned Readings' to find out which papers you are going to present.

Overview

Climate change has been described as "the defining challenge of our age". To mitigate climate change, computer scientists can help reduce the energy footprint of our society. This course will cover ways to leverage networking, sensing, and computation to make key physical infrastructure of our society (i.e., buildings, transportation systems, and power grids) smarter and more energy efficient. It will also cover emerging problems associated with the rapid growth in energy consumption of computing infrastructure. Different topics will be discussed, including integration of networked sensors in built environments, developing an operating system for smart buildings and cities, data acquisition and fusion, occupancy sensing and indoor localization, optimal control of smart buildings and transport systems, energy disaggregation, load scheduling in the smart grid, analyzing energy consumption of software systems, energy optimization for data centre networks, and security and privacy issues in cyber-physical systems and the Internet of Things.

Course Objectives

This course will introduce students to the new area of Sustainable Computing which covers both energy-efficient computing and computing for sustainability topics. This will enable students to develop the diverse range of skills required to perform research in this area. In particular, they will learn how to use Computer Science techniques to understand and improve complex cyber-physical systems, collect and analyze massive amounts of data, and build end-to-end systems that people want to use. Students will complete a group project applying computational techniques, such as machine learning, optimization, control, and simulation to real-world problems.

Organization

This course is a graduate-level seminar that will consist primarily of reading, reviewing, and presenting research papers in the field of Sustainable Computing. Two papers will be assigned to each class. All students must read both of the papers before the class and submit a review (critical analysis) for one of the papers (of their choice) by 8:00AM on the day of the lecture (refer to this article for advice on how to evaluate a paper and write a report). The reviews should be submitted through eClass. Each paper will be presented to the class by one student in a 25-minute conference style presentation, followed by a 15-minute discussion of the paper which will be led by the presenter. All students should also submit presentation feedback for each paper discussed in the class by noon of the day following the lecture. The feedback forms will be anonymized and made available to the presenter in the next class.

Students will work in pairs on an original research project on some topic related to Sustainable Computing. The instructor will provide some project ideas, but students are free to come up with their own projects related to the topics discussed in the course. Each pair will submit a proposal to the instructor no later than October 18. They will also write a workshop-quality paper, 8-10 pages in length, describing their project, and will present their work to the class in a 25-minute conference-style presentation at the end of the term.

Project Proposal

The proposal (in pdf format) should be submitted through eClass no later than October 18. The document should be roughly 2 pages in length (double-column in ACM SIG format with 10pt font), answering the following questions:

  1. What is the problem you are trying to solve and why is it important?
  2. What are the existing solutions and why are they insufficient?
  3. What is your approach?
  4. What resources or data sets do you need?
  5. How tasks are delineated and responsibilities are assigned to the partners?

Final Report

The final report should be a 8-10 page, workshop-quality paper (double-column in ACM SIG format with 10pt font). It should be submitted through eClass no later than December 8.

Grading System

During the term, your marks will be accumulated out of 100%, as indicated in the preceding table. At the end of the term, you will be assigned a letter grade. The mapping from term mark (out of 100%) to a final letter grade will be based on your instructor's interpretation of the university grading system (as defined in Section 23.4 of the Academic Regulations) and will be consistent with the university guidelines. There is no a priori distribution or formula. See Grading policy.

Schedule

This schedule is tentative and subject to change. Paper titles and presenters will be added later. You can find the papers assigned to each class here.

Date Topic Lecture Assignment
6/9 Course Logistics slides
11/9 Introduction — Opportunities and Challenges slides Watch David MacKay's lecture
Module 1: Smart Buildings & Smart Homes
13/9 Platforms for Smart Homes and Buildings — Part 1 slides Paper review
18/9 Platforms for Smart Homes and Buildings — Part 2 slides Paper review
20/9 Occupancy Sensing (New Sensor Networks) Paper review
25/9 Occupancy Sensing (Existing Infrastructure) slides Paper review
27/9 Monitoring Energy and Water Use Paper review
2/10 Intelligent Building Control Paper review
4/10 Energy Disaggregation Project group signup & paper review
9/10 No Class — Thanksgiving Day
Module 2: Smart Grid
11/10 Smart Grid Communications, Data Management, and Analytics slides Paper review
16/10 Load Scheduling, Demand Response, and Incentive Design Paper review
18/10 Optimal Control of Distributed Energy Resources slides Project proposal & paper review
Module 3: Smart Cities
23/10 Mobility Modeling — Part 1 Paper review
25/10 Mobility Modeling — Part 2 Paper review
30/10 Urban Computing & Planning Paper review
Module 4: Energy-Efficient Computing
1/11 Green Software Engineering Paper review
6/11 Energy Management in Mobile and Embedded Systems Paper review
8/11 Class Cancelled — Meeting with students about their projects
13/11 No Class — Fall term reading week
15/11 No Class — Fall term reading week
20/11 Energy-Efficient Networking Paper review
22/11 Reducing Carbon Footprint of Data Centre Networks Paper review
Module 5: Safety, Privacy & Cyber Security
27/11 Security and Privacy — Part 1 Paper review
29/11 Security and Privacy — Part 2 Paper review
4/12 Project Presentation
6/12 Project Presentation
8/12 Last day of Fall Term classes Final project report

Resources

Students can use the following data sets, models, and tools in their projects:

  • Minutely and hourly solar irradiation data from several measurement sites in the United States [Link]
  • One-second measurements of real and reactive power consumption of 30 homes in Austria [Link]
  • One-minute electricity, gas, and water use data from hundreds of customers [Link]
  • A tool that generates household electricity, gas, hot water, and cold water data [Link]
  • micro-PMU data from LBL locations [Link]
  • A collection of Python libraries for simulating the irradiation of any point on earth [Link]
  • A public data set for energy disaggregation (REDD) [Link]
  • Smart* home and microgrid data sets [Link]
  • A data set that contains electricity, water, and natural gas measurements at one minute intervals (AMPds) [Link]
  • An online tool for obtaining a solar estimate for the area, based on the amount of usable sunlight and roof space [Link]
  • A toolkit for evaluating the accuracy of Non-Intrusive Load Monitoring (NILM) algorithms [Link]
  • System Advisor Model (SAM) for renewable energy projects [Link]
  • Lab of Things platform for IoT research [Link]
  • 'Dark Sky' weather forecast API [Link]
  • GridPV toolbox to model and simulate the integration of distributed generation into the electric power system [Link]
  • UK domestic appliance-level electricity dataset [Link]
  • Markov models for residential electricity consumption [Link]
  • A dataset of high resolution electric power and voltage profiles of Austrian households [Link]
  • Measurements of Volatile Organic Compounds from a movie theater over a month in intervals of thirty seconds [Link]
  • Smart Grid Store for smart meter data storage and analytics [Link]
  • EnergyPlus™ whole building energy simulator and DOE reference building models [Link and Link]
  • A dataset consisting of metadata of 180,000 points across 55 campus buildings [Link]
  • New York City Taxi and Uber data [Link]
  • Roadsindb provides a representation of road networks, and a dataset of parking spots, resturants, and taxi mobility traces in San Francisco [Link]
  • PJM data sets (generation, load, load forecast, energy market, etc.) [Link]

Apart from these resources, students are encouraged to use other publicly available data sets or collect data using the sensors that they deploy.

Evaluation

Students will be graded as follows:

  • 5% Class Participation,
  • 30% Paper Presentations,
  • 15% Paper Reviews (due 8:00AM on the day of the lecture),
  • 10% Project Proposal (due 11:59PM, October 18),
  • 40% Final Project (due 11:59PM, December 8).

The project is completed in groups of two. The groups are formed in the fourth week of the term. You are given the opportunity to select your groupmate. If you do not, a groupmate will be assigned to you at random. Students are expected to attend the lectures, take an active part in the discussions, and ask questions. Participation marks will be given by the instructor based on in-class discussion of papers.

Marks are translated into letter grades based on your rank in the class. The instructor reserves the right to adjust final grades up or down in light of the total distribution of marks in the course and the person's overall performance.

Policies

Academic integrity

The University of Alberta is committed to the highest standards of academic integrity and honesty. Students are expected to be familiar with these standards regarding academic honesty and to uphold the policies of the University in this respect. Students are particularly urged to familiarize themselves with the provisions of the Code of Student Behaviour (online at www.governance.ualberta.ca) and avoid any behaviour which could potentially result in suspicions of cheating, plagiarism, misrepresentation of facts and/or participation in an offence. Academic dishonesty is a serious offence and can result in suspension or expulsion from the University.

For more information about academic integrity consult the Truth in Education website (http://www.tie.ualberta.ca)

Note about recording and/or distribution of course materials

Audio or video recording of lectures, labs, seminars or any other teaching environment by students is allowed only with the prior written consent of the instructor or as a part of an approved accommodation plan. Student or instructor content, digital or otherwise, created and/or used within the context of the course is to be used solely for personal study, and is not to be used or distributed for any other purpose without prior written consent from the content author(s).

Student accessibility services

Eligible students have both rights and responsibilities with regard to accessibility-related accommodations. Consequently, scheduling ​exam accommodations in accordance with SAS deadlines and procedures is essential. Please note adherence ​to procedures and deadlines​ is required for U of A to provide accommodations. Contact SAS (http://www.ssds.ualberta.ca/) for further information.

Student success centre

Students who require additional help in developing strategies for better time management, study skills or examination skills should contact the Student Success Centre (2-300 Students’ Union Building). For assistance with writing, contact the Centre for Writers (1-42 and 1-23 Assiniboia Hall).

Course outline

Policy about course outlines can be found in Section 23.4(2) of the University Calendar. The University Calendar is available online at http://www.registrar.ualberta.ca/calendar

Disclaimer

Any typographical errors in this Course Outline are subject to change and will be announced in class.