Spring'24 Seminar Course on Green Computing and Sustainability

This semester, I'm offering the second instantiation of my seminar course on Green Computing and Sustainability. The papers we plan to discuss this semester are listed below. This time, our focus will be Sustainable AI and Sustainable Data Centers. If you have recommendations on relevant papers to add to the list for our future seminars, please let me know. 

Green and Sustainable Computing: Challenges and Opportunities 

  1. Assessing ICT Global Emissions Footprint: Trends to 2040 & Recommendations
  2. The Sky is Not the Limit: Untapped Opportunities for Green Computing
  3. Sustainable Computing – Without the Hot Air
  4. The Odd One Out: Energy is not like Other Metrics 

Sustainable AI

  1. Green AI
  2. Towards a Methodology and Framework for AI Sustainability Metrics
  3. Do Deep Learning Frameworks Have Different Costs?
  4. Adaptive and Energy-Efficient Architectures for Machine Learning: Challenges and Opportunities
  5. Energy-Efficient Deep Learning Inference on Edge Devices
  6. Towards Energy Efficient non-von Neumann Architectures for Deep Learning 
  7. Carbon-Efficient Neural Architecture Search
  8. Energy and Policy Considerations for Deep Learning in NLP
  9. Reducing the Carbon Impact of Generative AI Inference (today and in 2035)
  10. Great Power, Great Responsibility: Recommendations for Reducing Energy for Training Language Models
  11. Learning to Grow Pretrained Models for Efficient Transformer Training

Sustainable Data Centers

  1. Treehouse: A Case For Carbon-Aware Datacenter Software
  2. Green Algorithms: Quantifying the Carbon Footprint of Computation
  3. Carbon Containers: A System-level Facility for Managing Application-level Carbon Emissions
  4. CarbonScaler: Leveraging Cloud Workload Elasticity for Optimizing Carbon-Efficiency
  5. WattScope: Non-intrusive Application-level Power Disaggregation in Datacenters
  6. Real-time Carbon Footprint Minimization in Sustainable Data Centers with Reinforcement Learning
You can access the reading list for the previous offering of my seminar course on "Green Computing and Sustainability" at this link. 



Comments

  1. John FreyFebruary 26, 2024 at 3:16 PM

    Uptime Institute has many papers to recommend here, including "Beyond PUE: Tackling IT’s
    wasted terawatts" and their annual data center surveys. In addition, for software efficiency: There’s plenty of room at the Top: What will drive computer performance after Moore’s law? (https://dx.doi.org/10.1126/science.aam9744). We publish our sustainable IT whitepapers in the Tools and Resources section at the bottom of this page (https://www.hpe.com/us/en/living-progress/sustainable-it.html) and welcome comments and updates as we refresh them every two years.

    ReplyDelete
  2. John FreyFebruary 26, 2024 at 3:19 PM

    Also, starting Feb 27th, a new documentary on the environmental cost of cloud computing will be live here: https://clouded.tv (Clouded II). There are many sustainable IT voices included in this work.

    ReplyDelete
  3. Tevfik KosarFebruary 26, 2024 at 3:22 PM

    Thank you, John. I will definitely check them out.

    ReplyDelete

Post a Comment

Popular posts from this blog

Toward Sustainable Software for HPC, Cloud, and AI Workloads

Image
Software applications are considerable consumers of computing resources, leading to a significant carbon footprint. Recent estimates suggest that Information Technology accounts for approximately 11% of global energy consumption . Projections indicate that by 2030, data centers alone could account for 3–13% of global electricity use, a stark increase from the 1% recorded in 2010, propelled by escalating demands and emerging trends like large-scale AI workloads . The software industry is responsible for about 3% of global carbon emissions , which is very close to that associated with the aviation industry , and it could deteriorate if left unaddressed. Researchers have estimated that training a single machine learning algorithm for natural language processing may emit as much CO2e (carbon dioxide equivalent) as a small town with 120 homes would emit in a year . Another study reported that AI workloads in data centers made up 15% of Google’s total electricity consumption, which was 18...
Read more

OneDataShare -- Fast, Scalable, and Flexible Data Sharing Made Easy

With the emergence of complex scientific applications, social media, video over IP, and more recently the trend for Internet of Things (IoT), the global data movement requirements have already exceeded the Exabyte scale. Large scientific experiments, such as environmental and coastal hazard prediction, climate modeling, genome mapping, and high-energy physics simulations generate data volumes reaching several Petabytes per year. Data collected from remote sensors and satellites, dynamic data-driven applications, social networks, digital libraries and preservations are also producing extremely large datasets for real-time or online processing.   This so called “data deluge” in the scientific applications necessitates collaboration and sharing among the national and international education and research institutions, which results in frequent large-scale data movement over wide-area networks. We see a similar trend in the commercial applications as well. According to a stud...
Read more