My Links

Research

My research focuses on GreenCode Computing. We analyze the power consumption of AI models, study the energy consumption and impact made by cloud computing and data centers, and also delve into carbon aware algorithm designs.

Research Projects

These are projects that I have done due to in class assignments or of my own volition.

  • Windows API Eye Tracking Project (Spring 2024)
    • Leveraged the Windows API to create handles that would register keyboard inputs as mouse inputs. We would then locate the position of the iris relative to the screen in order to simulate pointing with a mouse. The error rate was less than roughly 5 pixels. This was intended for for a human ergonomics project.
  • CloudSim Temporal Shifting Simulation (Fall 2023)
    • Leveraged CloudSim, a Cloud simulator built using Java, to append sustainability features. These features included creating temporal shifting simulations that would delay processes during times of lower carbon intensity. It would then show users statistics such as the number of hours delayed and the pounds of carbon emissions that were saved.
  • IntellEco Translate (Fall 2022)
    • By analyzing four years of data, we made a carbon-aware translation service that was deployed in the cloud. Based on real-time carbon emissions data gathered from an API, we would send user requests to different translation models deployed in different parts of the world based on which region had the lowest carbon intensity at the time. We created the frontend and backend using the tools listed.

Publications

Papers that I have worked on that were submitted to conferences and journals:

  1. D. Chen, N. Soto, J. F. Tuttle and Z. Zong, "Understanding Multi-Dimensional Efficiency of Fine-Tuning Large Language Models Using SpeedUp, MemoryUp, and EnergyUp," 2024 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), San Francisco, CA, USA, 2024, pp. 929-937, doi: 10.1109/IPDPSW63119.2024.00162.
  2. B. Everman, T. Villwock, D. Chen, N. Soto, O. Zhang and Z. Zong, "Evaluating the Carbon Impact of Large Language Models at the Inference Stage," 2023 IEEE International Performance, Computing, and Communications Conference (IPCCC), Anaheim, CA, USA, 2023, pp. 150-157, doi: 10.1109/IPCCC59175.2023.10253886.