YDYing Du

Ying Du

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ying Du has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Goal-Driven Resource Management for Microservices with Dual-Layer Deep RL

    by Zhijie Han, Anbang Wang, Ying Du

    Microservices must meet end-to-end latency SLOs while optimizing per-service resources, but heterogeneous request paths make mapping resources to latency difficult. We propose DRvalve, a dual-layer framework that decouples applicationlevel SLO feedback from service-level control via performance targets, driven by a novel objective integrating CPU utilization and throttling rates. A global deep RL controller periodically sets CPU throttling targets, and local allocators scale resources using robust rollback and self-healing mechanisms to mitigate DRL lag and suppress cascading oscillations. Moreover, median denoising and binary-tree buffers ensure stable training and O(log n) efficiency. Evaluations on three production-trace workloads show that DRvalve saves up to 29.55% CPU over the best baseline and up to 52.67% over all baselines while strictly maintaining SLO compliance.

  • Open Access

    Trustworthiness Management Based on Blockchain in the Internet of Things

    by Xiaoyu Du, Song Tao, Ying Du, Lvzhou Lin

    In the smart Internet of Things (IoT), if the identity of the message source is not evaluated, malicious nodes will attack other nodes by publishing malicious information or requests. This paper proposes a trust management mechanism for IoT devices based on blockchain. The information of each node is stored through the blockchain, and the Internet of Things equipment receiving communication messages grants different permissions by querying the reputation level of relevant nodes through the blockchain. The reputation level of nodes is calculated by historical behavior. Due to the limited storage capacity of some IoT devices, this paper proposes a special node, namely the cluster head, for storage and trust management. At the same time, the security of the proposed trust mechanism is evaluated, and the results show that the management mechanism can protect the secure communication of IoT devices more effective. CCS CONCEPTS • Security and privacy • Security services • Access control

  • Open Access

    Research on Conceptual Model of the Remote Sensing Big Data Workflow

    by Ying Du, Shuo Zhang, Mohammed K. A. Kaabar, Xiao-Guang Yue

    Remote sensing big data workflows are formed by combining workflow and the remote sensing data processing system, and have the capabilities of remote sensing data processing, analysis, and visualization. There are many issues such as numerous sensors, sophisticated processing algorithms, and lacking of a unified process management about the operation control of the remote sensing data processing system. Therefore, the concept and characteristics of remote sensing big data workflows is reanalysed and the metamodel of remote sensing big data workflows from different aspects is constructed in order to establish a conceptual framework of them, and thus establish concept framework of Remote Sensing Big Data Workflow.


  • Intelligent Service Cluster Construction Method Based on Remote Sensing Application

    by Liming Zhou, Wencheng Yang, Ying Du, Cheng Liu, Heng Li

    The production of remote sensing products needs to go through various links of evaluation and deploy a variety of software and hardware resources. It is necessary to study how to improve the efficiency of service cluster deployment, simplify the evaluation process, and optimize its structure. This paper designs an intelligent service cluster construction method based on remote sensing applications, which realizes the accurate and efficient deployment of various complex network structures and equipment on the visual interface. The method is convenient and simple to operate. It can set various types of resource information according to the needs of users, can choose a more reasonable server cluster deployment plan, improve the efficiency of data storage and processing of remote sensing products, better serve users, and greatly promote The development of related industries.