Project | 科研项目
  • 西安电子科技大学杭州研究院概念验证基金
 主持  2023.05 - 2024.04
  名称:面向云原生应用的访问控制关键技术研究  GNYZ2023GY0401 
  • 横向项目
 主持  2023.03.15 - 2024.08
  名称:无服务器计算场景下安全机制研究  XH-KY-202303-0058 
  • 中央高校基本科研业务费专项 - 西安电子科技大学新教师创新基金
 主持  2023.01 - 2024.12
  名称:面向云原生应用的服务编排与配置管理关键技术研究  XJSJ23004 
  • 国家重点研发计划 - 网络空间安全专项
 参与  2017.07 - 2020.12
  名称:SDN/NFV 与 NDN 安全研究  2017YFB0801703 
  • 浙江省重点研发计划 - 云计算安全及服务系统研发及应用   
 参与  2017.07 - 2020.06
  名称:内生安全的云计算系统主动防御技术研究与应用  2018C01088 
Research | 研究工作
  • Performance Improvement of Service Mesh
       2021 - 2022
  - We analyzed the architecture of Istio and found the performance bottleneck causing the high resource consumption.
  - We proposed an adaptive configuration loading mechanism, reducing memory consumption of data plane by 98%.
   Service Mesh  Istio  Microservice  Performance Improvement   Production-ready 
  • Operation Enhancement of Service Mesh
       2020 - 2021
  - We designed the escape solution for Envoy based on Iptables, which enables the system recover from the failure
    quickly and improves the efficiency of troubleshooting.
  - We analyzed the architecture of Envoy and designed an expert system to determine the root cause by extending
    and collecting the accesslogs in a low-intrusive manner, which improves the efficiency operation and maintenance.
   Service Mesh  Envoy  Microservice  Ops   Production-ready 
  • Security Review of Serverless Computing: Challenges, Solutions, and Opportunities
2020 - 2022
  - We introduced the security challenges of serverless computing and compared the solutions adopted in the academia,
    industry, and open-sourced platforms.
  - We also analyzed the gap between solutions and proposed the potential research opportunities.
   Survey  Serverless  Security 
  • PROPHET: Efficient and Intelligent Orchestrator for Microservices Scheduling and Scaling
2019 - 2020
  - We proposed a ranking-based p-batch scheduling mechanism, which employs a pairwise ranker to achieve rapid
    and resource-efficient deployment for large-scale microservices to improve the resource utilization by reducing
    the number of running nodes in the cluster.
  - We proposed a proactive prediction-based scaling mechanism, which automatically scales microservices in advance
    based on the resource usage prediction. This scaling mechanism can effectively alleviate the sluggishness in scaling
    and mitigate resource contention and service interruption.
   Microservice  Kubernetes  Scheduling & Scaling  AI 
  • SDNKeeper: Lightweight Resource Protection and Management System for SDN-based Cloud
2017 - 2019
  - We proposed a policy-based fine-grained access control mechanism, which can effectively prevent unauthorized
    access requests initialed by users and malicious tampering of controllers and network resources by filtering and
    checking requests with predefined policies.
   SDN  OpenDaylight  Access Control 
  • Fault Management in Software-Defined Networking: A Survey
2017 - 2018
  - We first categorized the solutions according to architecture of SDN.
  - Then, we analyzed and summarized thefault management solutions of SDN from the aspects of fault analysis,
    fault detection, fault diagnosis,fault failover, and fault tolerance.
  - At last, we proposed the potential research opportunities.
   Survey  SDN  Fault Management 
  • Development of SDN controller for Cloud Data Center
  - We developed the SDN controller based on the Open SDN Controller of Cisco.
  - We chose the Tencent Cloud Data Center as the test bed to perform the network configuration test.
   Intern  SDN  OpenDaylight 
  • RuleScope: Inspecting Forwarding Faults for Software-Defined Networking
2015 - 2016
  - We presented RuleScope, a more comprehensive solution for inspecting SDN forwarding.
  - RuleScope offers a series of accurate and efficient algorithms for detecting and troubleshooting rule faults.
    They inspect forwarding behavior using customized probe packets to exercise data-plane rules.
  - The detection algorithm exposes not only missing faults but also priority faults.
  - Beyond simply detecting rule faults, the troubleshooting algorithms uncover actual dataplane flow tables.
    They help track real-time forwarding status and benefit reliable network monitoring.
   SDN  Configuration Consistency