Project Description

he rapid development of connected and autonomous vehicles (CAVs) is transforming transportation. CAVs leverage advanced artificial intelligence and machine learning techniques to achieve automated sensing and decision making. Understanding the energy demands of CAVs’ computing activities and developing solutions to reduce computing energy consumption and associated carbon footprints is critical not only for improving environmental sustainability but also for reducing operation costs.

Prior studies examined the environmental impacts of CAVs at the vehicle level, neglecting those from the computing activities. This project aims to fill the data and knowledge gap to establish benchmark energy demand and carbon footprint values of data management and computing activities for CAVs. Additionally, we will develop learning-based models and tools for computing resource allocation to optimize the carbon footprints while meeting CAVs’ performance goals.

The tools and insights generated from this project can help the industry and policy makers develop sustainable transportation systems and enable the cities to understand the energy and electricity infrastructures required to support CAV system development. The two co-advisors have complementary expertise to tackle this interdisciplinary research: Dr. Ding is an expert in machine learning systems, and Dr. Cai is an expert in transportation and environmental sustainability.  

Start Date

Spring or Summer 2025

Postdoc Qualifications

- Hold a Ph.D. degree in Electrical and Computer Engineering, Computer Science, Industrial Engineering, Transportation Engineering, Industrial Ecology, or other relevant field.
- Strong data analysis and programming skills
- Prior knowledge and experience working on sustainable computing related projects
- Self motivated 

Co-advisors

Yi Ding (yiding@purdue.edu), Electrical and Computer Engineering, https://y-ding.github.io/

Hua Cai (huacai@purdue.edu), Industrial Engineering (with joint appointment in Environmental and Ecological Engineering), https://engineering.purdue.edu/uSMART

Bibliography

Amy Li, Sihang Liu, and Yi Ding. 2024. Uncertainty-Aware Decarbonization for Datacenters. In Proceedings of 3rd Workshop on Sustainable Computer Systems (HotCarbon’24). ACM, New York, NY, USA, 7 pages.

Sophia Nguyen, Beihao Zhou, Yi Ding, and Sihang Liu. 2024. Towards Sustainable Large Language Model Serving. In Proceedings of 3rd Workshop on Sustainable Computer Systems (HotCarbon’24). ACM, New York, NY, USA, 7 pages.

Yi Ding, Nikita Mishra, and Henry Hofmann. 2019. Generative and Multiphase Learning for Computer Systems Optimization. In The 46th Annual International Symposium on Computer Architecture (ISCA ’19), June 22-26, 2019, Phoenix, AZ, USA. ACM, New York, NY, USA, 14 pages

Hardaway, K., Teran, O. and Cai, H., 2022, June. Assessing the environmental implications of autonomous vehicle data management. In 2022 IEEE 31st International Symposium on Industrial Electronics (ISIE) (pp. 639-642). IEEE.