Chenyu Lin's Resume

Find me here!

Lin, C., Luo, S., & Xu, H. (2023, December). Exploring Imbalances among Microservice Containers in Large Cloud Platforms. In 2023 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom) (pp. 237-245). IEEE.
Luo, S., Lin, C., Ye, K., Xu, G., Zhang, L., Yang, G., … & Xu, C. (2024). Optimizing resource management for shared microservices: a scalable system design. ACM Transactions on Computer Systems, 42(1-2), 1-28.
Chen, L., Luo, S., Lin, C., Mo, Z., Xu, H., Ye, K., & Xu, C. (2024, June). Derm: SLA-aware Resource Management for Highly Dynamic Microservices. In 2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA) (pp. 424-436). IEEE.
Chen, L., Lin, C., Luo, S., Xu, H., Xu, C. (2024, June). Grad: Intelligent Microservice Scaling by Harnessing Resource Fungibility In 2025 IEEE International Symposium on High-Performance Computer Architecture (HPCA) (pp. 474-486). IEEE.
Luo, S., Liao, J., Lin, C., Xu, H., Zhou, Z., & Xu, C. (2025, March). Embracing Imbalance: Dynamic Load Shifting among Microservice Containers in Shared Clusters. In Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2 (pp. 309-324).

Automatic Experiment Framework for Microservice (AEFM)
AEFM is a toolkit I developed to accelerate the process of experimentation in the field of microservices research. It provides basic functionality for collecting trace data (from Jaeger), hardware data (from Prometheus), and managing Pods deployments. As an out-of-the-box toolkit, it allows researchers to quickly conduct experiments or profile microservices. As a comprehensive framework, it provides researchers with a flexible interface to implement their own scheduling/deployment/scaling strategies with a small amount of code. [Source Code]
Alibaba cluster trace data open source
Help Alibaba open source thirteen days of cluster data, the main steps include collection, cleaning, desensitization, normalization. The total amount of data is about 2T. [Data]
Interference-aware Multiplexing for Deep Learning in GPU Clusters: A Middleware Approach
Implement K8S scheduler extension for IADeep using Go, prepare launching script and setup experiment environment for Artifact Evaluation. [Source Code]
Erms: Efficient Resource Management for Shared Microservices with SLA Guarantees
Implement all modules (offline profiling module, latency target computation module and priority scheduling module) of the paper Erms (ASPLOS’23), passed Artifact Evaluation. [Source Code]

Full-Stack Developer | 2025 May. ~ Present
Capsio Technology Co., Ltd.
Research Assistant | 2022 Mar. ~ 2024 Dec.
University of Macau, Faculty of Science and Technology.
Front-end Developer | 2021 May. ~ 2021 Aug.
Teng-Chuang Medical Technology Co., Ltd.