Differentially Private Cloud-Based Multi-Agent Optimization with Constraints

被引:0
|
作者
Hale, M. T. [1 ]
Egerstedt, M. [1 ]
机构
[1] Georgia Inst Technol, Sch Elect & Comp Engn, Atlanta, GA 30332 USA
关键词
ALGORITHMS;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We present an optimization framework that solves constrained multi-agent optimization problems while keeping each agent's state differentially private. The agents in the network seek to optimize a local objective function in the presence of global constraints. Agents communicate only through a trusted cloud computer and the cloud also performs computations based on global information. The cloud computer modifies the results of such computations before they are sent to the agents in order to guarantee that the agents' states are kept private. We show that under mild conditions each agent's optimization problem converges in mean-square to its unique solution while each agent's state is kept differentially private. A numerical simulation is provided to demonstrate the viability of this approach.
引用
收藏
页码:1235 / 1240
页数:6
相关论文
共 50 条
  • [31] DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning
    Zhao, Canzhe
    Ze, Yanjie
    Dong, Jing
    Wang, Baoxiang
    Li, Shuai
    [J]. PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 4638 - 4646
  • [32] Differentially Private Multi-Agent Planning for Logistic-Like Problems
    Ye, Dayong
    Zhu, Tianqing
    Shen, Sheng
    Zhou, Wanlei
    Yu, Philip S.
    [J]. IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING, 2022, 19 (02) : 1212 - 1226
  • [33] Differentially Private Consensus for Multi-Agent Systems Under Switching Topology
    Wan, Xiaoxiao
    Guo, Yun
    Wu, Xiaoqun
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2023, 70 (09) : 3499 - 3503
  • [34] Multi-agent Deep Reinforcement Learning for cloud-based digital twins in power grid management
    Pei, Luyao
    Xu, Cheng
    Yin, Xueli
    Zhang, Jinsong
    [J]. Journal of Cloud Computing, 2024, 13 (01)
  • [35] Distributed Demand Response Optimization With Global Constraints Based on Multi-agent System
    Hao R.
    Ai Q.
    Zhang Y.
    Sun S.
    Jiang Z.
    Yousif M.
    [J]. Dianwang Jishu/Power System Technology, 2019, 43 (09): : 3139 - 3148
  • [36] Event-Triggered Differentially Private Average Consensus for Multi-agent Network
    Aijuan Wang
    Xiaofeng Liao
    Haibo He
    [J]. IEEE/CAA Journal of Automatica Sinica, 2019, 6 (01) : 75 - 83
  • [37] Multi-agent reinforcement learning via knowledge transfer with differentially private noise
    Cheng, Zishuo
    Ye, Dayong
    Zhu, Tianqing
    Zhou, Wanlei
    Yu, Philip S.
    [J]. INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2022, 37 (01) : 799 - 828
  • [38] Event-Triggered Differentially Private Average Consensus for Multi-agent Network
    Wang, Aijuan
    Liao, Xiaofeng
    He, Haibo
    [J]. IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2019, 6 (01) : 75 - 83
  • [39] A User-friendly Cloud-based Multi-agent Information System for Smart Energy-saving
    Su, Yi-Jen
    Yang, Sheng-Yuan
    [J]. JOURNAL OF INTERNET TECHNOLOGY, 2024, 25 (02): : 293 - 300
  • [40] Distributed optimization with hybrid linear constraints for multi-agent networks
    Zheng, Yanling
    Liu, Qingshan
    Wang, Miao
    [J]. INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2022, 32 (04) : 2069 - 2083