📝 Publications

☁️ Cloud Computing

IWQoS 2016 (CCF-B)

Tetris: Optimizing cloud resource usage unbalance with elastic VM
X Ling, Y Yuan, D Wang, J Yang

• Tetris is an elastic VM strategy based on cloud system that can better optimize resource utilization to support big data applications.
• We evaluate Tetris on a real private cloud platform using Facebook trace and Wikipedia dataset. With Tetris, the cloud system can accommodate 31.3% more jobs.

JPDC 2016 (CCF-B)

Joint scheduling of MapReduce jobs with servers: Performance bounds and experiments
X Ling, Y Yuan, D Wang, J Liu, J Yang

• We formulate the MapReduce server-job organizer problem (MSJO) and show that it is NP-complete.
• We propose a 3-approximation algorithm and a fast heuristic design to address the MSJO problem.

• HPCC 2016 (CCF-C) Fast community detection in large weighted networks using graphx in the cloud, X Ling, J Yang, D Wang, J Chen, L Li

• ISCC 2016 (CCF-C) Load-aware hybrid scheduling in large compute clusters, D Fu, J Yang, X Ling, H Zhang

• HPCC 2015 (CCF-C) Cluster Scheduler on Heterogeneous Cloud, X Ling, J Yang, D Wang, Y Wang

⚙️ AIOps

ICSE 2022 (CCF-A)

Adaptive performance anomaly detection for online service systems via pattern sketching
Z Chen, J Liu, Y Su, H Zhang, X Ling, Y Yang, MR Lyu

Project

• ADSketch is an interpretable and adaptive performance anomaly detection algorithm for online service systems.
• Academic Impact: ADSketch achieves interpretability by identifying groups of anomalous metric patterns, which represent particular types of performance issues.
• Industry Impact: ADSketch is evaluated with public data as well as industrial data collected from a representative online service system in Huawei Cloud.

ASE 2021 (CCF-A)

Graph-based incident aggregation for large-scale online service systems
Z Chen, J Liu, Y Su, H Zhang, X Wen, X Ling, Y Yang, MR Lyu

Project

• GRLIA is an incident aggregation framework based on graph representation learning over the cascading graph of cloud failures.

ASE 2021 (CCF-A)

AID: efficient prediction of aggregated intensity of dependency in large-scale cloud systems
T Yang, J Shen, Y Su, X Ling, Y Yang, MR Lyu

Project

• AID is the first approach to predict the intensity of dependencies between cloud services.

🔒 Patents (8 Granted)

• Title: Scheduling Method and Apparatus (一种调度方法及装置)
  • No.: CN201811161060.6
  • Inventors: Xiao Ling
  • Grant Date: 2019-03-01
  • Description: A scheduling method and apparatus to solve the problem of large job waiting latency and low efficiency in existing technologies.
• Title: Cloud Product Recommendation Method and Apparatus (云产品的推荐方法和推荐装置)
  • No.: CN202011526847.5
  • Inventors: Xiao Ling, Yanxiang Zeng
  • Grant Date: 2022-07-08
  • Description: A cloud product recommendation method and apparatus that improves the reliability of cloud product recommendations.
• Title: Fundus Image Recognition Method, Apparatus, Device and Storage Medium (一种眼底照片的图像识别方法、装置、设备及存储介质)
  • No.: CN202211595444.5
  • Inventors: Xiao Ling, Zhaoxiang Zeng, Kai Zhang
  • Grant Date: 2023-03-21
  • Description: A multi-level segmentation network for fundus image recognition, improving segmentation precision and classification accuracy for different targets.
• Title: Cloud Platform Resource Scheduling Method (云平台资源调度方法)
  • No.: CN201310066039.9
  • Inventors: Jiahai Yang, Cong Xu, Xiao Ling, Yuding Wang
  • Grant Date: 2014-09-03
  • Description: A cloud platform resource scheduling method that calculates the average load of servers when assigning tasks to server sets.
• Title: Resource Migration Method, System and Device (一种资源迁移的方法、系统及设备)
  • No.: CN202110312058.X
  • Inventors: Leiming Du, Shuming Jing, Xiao Ling
  • Grant Date: 2021-09-10
  • Description: A resource migration method for resource provisioning systems with multiple physical hosts containing various hardware resources.
• Title: Online Data Anomaly Detection Method, Apparatus, Storage Medium and Device (一种在线数据异常检测方法、装置、存储介质及设备)
  • No.: CN202010236425.8
  • Inventors: Yuxin Su, Rongcong Lyu, Xiao Ling
  • Grant Date: 2021-10-01
  • Description: An online data anomaly detection method to solve the problem of unknown value ranges in data to be detected.
• Title: Service Quality Prediction Method and Computing Device (一种预测服务质量的方法和计算装置)
  • No.: CN202210609398.3
  • Inventors: Xiaofeng Gao, Yunlong Cheng, Xiao Ling, Guihai Chen
  • Grant Date: 2023-12-12
  • Description: A method for predicting service quality and a computing device capable of implementing the method.
• Title: Storage Pool Hotspot Processing Method and Apparatus (一种存储池的热点处理方法及装置)
  • No.: CN202011562831.X
  • Inventors: Chunguang Li, Yongqiang Zeng, Song Ye, Xiao Ling, Shuming Jing, Leiming Du
  • Grant Date: 2022-06-28
  • Description: A storage pool hotspot processing method and apparatus in the storage technology field to improve hotspot processing effectiveness.

🧑‍💻 Software Copyrights (5 Registered)

• Title: AILeader One-Stop AI Education Platform (智核苑一站式AI教学平台)
  • No.: 2024SR2114374
  • Owner: Shenzhen HeTao Technology Co., Ltd.
  • Grant Date: 2024-12-18
  • Description: An AI education platform for K-12 students, integrating AI Programming, AI Tutoring, and AI Science & Innovation modules with block-based programming, learning assistants, AI art creation, and digital life features.
• Title: AILeader Digital Avatar Creation Platform (智核苑数字人创作平台DigitalAvatar)
  • No.: 2024SR1155409
  • Owner: Shenzhen HeTao Technology Co., Ltd.
  • Grant Date: 2024-08-09
  • Description: An application for rapid generation of audio and digital human videos based on user intent, with cloud-based AI generation.
• Title: AI Drawing City (爱画之城软件)
  • No.: 2023SR0651719
  • Owner: Shenzhen HeTao Technology Co., Ltd.
  • Grant Date: 2023-06-14
  • Description: A mini-program for rapid AI-powered drawing based on user intent.
• Title: CoreMI: Cloud-Based AI Medical Imaging Diagnosis System (基于云计算的AI医学影像辅助诊断系统CoreMI)
  • No.: 2022SR1507070
  • Owner: Shenzhen HeTao Technology Co., Ltd.
  • Grant Date: 2022-11-16
  • Description: A cloud-based medical imaging analysis software for patients, hospitals, and health centers, utilizing big data processing, feature engineering, and deep learning for automated AI film reading and diagnostic report generation, improving efficiency by 10,000x while reducing misdiagnosis rates.
• Title: Tsinghua Cloud IaaS Management Platform (清华云IaaS管理平台)
  • No.: 2014SR0651374
  • Owner: Jiahai Yang, Cong Xu, Xiao Ling, Hui Yu, Jianping Weng
  • Grant Date: 2014-01-27
  • Description: An Infrastructure-as-a-Service management platform for cloud computing resource orchestration and scheduling.