Bio

I am now an Associate Professor at Research Center for Distribute Systems, Institute of Computing Technology, Chinese Academy of Sciences (ICT, CAS). I got my Ph.D. degree in 2016 from The University of Tokyo. I received my master degree in Computer Science from Peking University in 2009, and bachelor degree from Northwestern Polytechnical University .
彭晓晖，中国科学院计算技术研究所副研究员，博士生导师。近年来聚焦高通量算力网关键技术研究，提出了物群-机群分布式架构和T-REST架构方法，设计了任务闭包编程模型和RSEP分布式调度模型，并在上述模型和方法基础上设计实现了端云协同的分布式计算框架TIDE。部分技术已在国家重大科技基础设施——CENI上开展了试验验证，形成的系统和平台支持了多个国家重要项目的执行和验收。主持国家基金委企业联合基金重点项目子课题、面上项目、重大基础研究项目课题等10余项纵向科研任务。在包括HPDC、ICDE、PIEEE、TC、TMC、TSC、TKDE、计算机学报、计算机研究与发展、IEEE IoT-J、ACM/IEEE SEC、SoCC、 SenSys、IPDPS等在内的领域顶级刊物和会议上发表论文40余篇。兼任IEEE TMC和IEEE IC的AE，中国计算机学会分布式计算与系统专委常务委员。

Selected Publications，*为通信作者

[英文]

  1. [ICDE'27] Jiancong Zhu, Xiaohui Peng*, Zishu Yu, Yicheng Liu, Yixing Zhai, Lian Jiang, Jinghui Jia. KPred: Adaptive Auto-Scaling with Complex Workload Prediction in Cloud Services[C]. (ICDE, CCF-A), accepted, Copenhagen, Denmark, 2027.
  2. [TMC'26] Hangda Liu, Boyu Diao*, Jiashuo Luo, Yitian He, Yu Yang, Wenxin Chen, Guobang Li, Xiaohui Peng, Yongjun Xu. E2Gensor: An Enhanced Elastic Graph-basedConstruction Tensor Compilation Method forOn-device Deep Learning[J]. (IEEE TMC, CCF-A), accepted, 2026.
  3. [HPDC'26] Runfu Li, Zishu Yu, Yifan Wang, Xiaohui Peng*, Ninghui Sun, Zhiwei Xu. Enabling High-Utilization and Low-Contention FaaS: A Request-Level Resource Provisioning Approach[C]. (HPDC, CCF-A), Cleveland, OH, USA, 2026.
  4. [TMC'26] Chen Zeng, Xiaohui Peng*, Fan Liang, Yifan Wang, Deke Guo. Breaking Cloud Dependencies: A Distributed Ledger Approach to IoT Device Usufruct Management[J]. (IEEE TMC, CCF-A), 2026, DOI: 10.1109/TMC.2026.3655119.
  5. [TC'26] Zishu Yu, Runfu Li, Yifan Wang, Xiaohui Peng*, Zhiwei Xu. LASS: Reducing Cold Startup Latency in Serverless Through Loaded Library Sharing[J]. (IEEE TC, CCF-A), 2026, 75(3): 901-915.
  6. [TSC'26] Libo Feng, Junwei Guo, Fake Fang, Zhenli He, Yimin Yu, Shaowen Yao, Xiaohui Peng*. SEPP-FLBC: A Secure and Efficient Privacy Protection Scheme Using Federate Learning and Blockchain for Edge-End-Cloud Devices[J]. (IEEE TSC, CCF-A), 2026, 19(1): 657-670.
  7. [PIEEE'19] Lu Chao, Xiaohui Peng*, Zhiwei Xu, Lei Zhang. Ecosystem for Things: Hardware, Software and Architecture[J]. (PIEEE, CCF-A), 2019, 107(8): 1563-1583.
  8. [TKDE'19] Chunyu Hu, Yiqiang Chen, Xiaohui Peng, Han Yu, Chenlong Gao, Lisha Hu. A Novel Feature Incremental Learning Method for Sensor-based Activity Recognition[J]. (IEEE TKDE, CCF-A), 2019, 31(6): 1038-1050.
  9. [IWQoS'25] Jianwei Gao, Xiaohui Peng, Shaowei Liu, Jiamu Liu, Yifan Wang*, Tingting Zhang*, Deke Guo. A Case Study on Benchmarking Distributed AI Systems[C]. (IEEE IWQoS, CCF-B), Gold Coast, Australia, 2025: 1-6.
  10. [JCST'26] Fengzhi Li, Qingru Xu, Tuo Zhou, Chenxi Wang, Yifan Wang, Xiaohui Peng*. Containerlet: Software-Granular Containers for High-Performance Deployment of Machine Learning Applications[J]. (JCST, CCF-B), 2026, DOI: 10.1007/s11390-026-6073-4.
  11. [IPDPS'25] Xiaohui Peng, Wenkai Yan, Yifan Wang*, Zhiwei Xu. Tide: A Runtime Management Framework for the Things-Edge-Cloud Computing Continuum[C]. (IPDPS, CCF-B), Milan, Italy, 2025: 42-53.
  12. [IPDPS'25] Hangda Liu, Boyu Diao, Yu Yang, Wenxin Chen, Xiaohui Peng, Yongjun Xu. Gensor: A Graph-based Construction Tensor Compilation Method for Deep Learning[C]. (IPDPS, CCF-B), Milan, Italy, 2025: 558-569.
  13. [SoCC'24] Yuqiao Lan, Xiaohui Peng*, Yifan Wang. Snapipeline: Accelerating Snapshot Startup for FaaS Containers[C]. (SoCC, CCF-B), Seattle, USA, 2024: 144-159.
  14. [SenSys'24] Zijian Wang, Xingzhou Zhang, Yifan Wang, Xiaohui Peng, Zhiwei Xu. Hawk: An Efficient NALM System for Accurate Low-Power Appliance Recognition[C]. (SenSys, CCF-B), Hangzhou, China, 2024: 578-591.
  15. [JCST'25] Xiaohui Peng, Yixuan Sun, Zhenhui Zhang, Yifan Wang*. DSparse: A Distributed Training Method for Edge Clusters Based on Sparse Update[J]. (JCST, CCF-B), 2025, 40(3): 637-653.
  16. [IoT-J'19] Zhiwei Xu, Lu Chao, Xiaohui Peng*. T-REST: An Open-Enabled Architectural Style for the Internet of Things[J]. (IEEE IoT-J), 2019, 6(3): 4019-4034.
  17. [PerCom'18] Jindong Wang, Yiqiang Chen, Lisha Hu, Xiaohui Peng and Philip S. Yu. Stratified Transfer Learning for Cross-domain Activity Recognition. (PerCom, CCF-B), Athens, Greece, 2018: 1-10.
  18. [PR'18] Chunyu Hu, Yiqiang Chen, Lisha Hu, Xiaohui Peng. A novel random forests based class incremental learning method for activity recognition[J]. (PR), 2018, 78(6): 277~290.

    19. [中文]
  19. 俞子舒, 王一帆, 曾琛, 张星洲, 彭晓晖*, 徐志伟. 支持端边云多运行时协同应用的网程系统[J]. 计算机研究与发展, 2025, 62(12): 3042-3059.
  20. 俞子舒, 李奉治, 郑守建, 王一帆, 张星洲, 彭晓晖*, 徐志伟. 信息高铁的低熵高通量性质验证[J]. 计算机学报, 2023, 46(11): 2302-2321.
  21. 郑守建, 彭晓晖*, 王一帆, 任祖杰，高丰. 一种基于综合匹配度的边缘计算系统任务调度方法[J]. 计算机学报, 2022, 45(3): 485-499.
  22. 徐志伟，曾琛，朝鲁，彭晓晖*. 面向控域的体系结构：一种智能万物互联的体系结构风格[J]. 计算机研究与发展, 2019, 56(1): 90-102.
  23. 于佃存, 陈益强, 彭晓晖, 焦帅, 李啸海, 钟习. 多元数据融合的非干扰身份识别方法[J]. 计算机研究与发展, 2019, 56(3): 635-642.
  24. 彭晓晖，张星洲，王一帆，朝鲁. Web使能的物端计算系统[J]. 计算机研究与发展, 2018, 55(3): 572-584.
  25. 朝鲁，彭晓晖*，徐志伟. 变熵画像:一种数量级压缩物端数据的多粒度信息模型[J]. 计算机研究与发展, 2018, 55(8): 1653-1666.