Extreme Learning Machine-Based Channel Estimation in IRS-Assisted Multi-User ISAC System

被引:9
|
作者
Liu, Yu [1 ]
Al-Nahhal, Ibrahim [2 ]
Dobre, Octavia A. [2 ]
Wang, Fanggang [1 ]
Shin, Hyundong [3 ]
机构
[1] Beijing Jiaotong Univ, Frontiers Sci Ctr Smart Highspeed Railway Syst, State Key Lab Adv Rail Autonomous Operat, Sch Elect & Informat Engn, Beijing 100044, Peoples R China
[2] Mem Univ Newfoundland, Fac Engn & Appl Sci, St John, NF A1C 5S7, Canada
[3] Kyung Hee Univ, Dept Elect & Informat Convergence Engn, Yongin 17104, South Korea
关键词
Integrated sensing and communication (ISAC); intelligent reflecting surface (IRS); channel estimation; neural network (NN); extreme learning machine (ELM); INTELLIGENT REFLECTING SURFACE; SELF-INTERFERENCE CANCELLATION; JOINT RADAR; DESIGN; PERFORMANCE;
D O I
10.1109/TCOMM.2023.3308150
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Multi-user integrated sensing and communication (ISAC) assisted by intelligent reflecting surface (IRS) has been recently investigated to provide a high spectral and energy efficiency transmission. This paper proposes a practical channel estimation approach for the first time to an IRS-assisted multi-user ISAC system. The estimation problem in such a system is challenging since the sensing and communication (SAC) signals interfere with each other, and the passive IRS lacks signal processing ability. A two-stage approach is proposed to transfer the overall estimation problem into sub-ones, successively including the direct and reflected channels estimation. Based on this scheme, the ISAC base station (BS) estimates all the SAC channels associated with the target and uplink users, while each downlink user estimates the downlink communication channels individually. Considering a low-cost demand of the ISAC BS and downlink users, the proposed two-stage approach is realized by an efficient neural network (NN) framework that contains two different extreme learning machine (ELM) structures to estimate the above SAC channels. Moreover, two types of input-output pairs to train the ELMs are carefully devised, which impact the estimation accuracy and computational complexity under different system parameters. Simulation results reveal a substantial performance improvement achieved by the proposed ELM-based approach over the least-squares and NN-based benchmarks, with reduced training complexity and faster training speed.
引用
收藏
页码:6993 / 7007
页数:15
相关论文
共 50 条
  • [41] Secret Key Generation for IRS-Assisted Multi-Antenna Systems: A Machine Learning-Based Approach
    Chen, Chen
    Zhang, Junqing
    Lu, Tianyu
    Sandell, Magnus
    Chen, Liquan
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2024, 19 : 1086 - 1098
  • [42] Second Order Rectified Parallel Factor Model Based Cascaded Channel Estimation in IRS-Assisted SWIPT System
    Xu, Xiaorong
    Zhu, Weiwei
    Yang, Shuo
    Bao, Jianrong
    Zhu, Wei-Ping
    Liu, Zhaoting
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2023, 72 (10) : 13314 - 13325
  • [43] Recursive DLS solution for extreme learning machine-based channel equalizer
    Lim, JunSeok
    NEUROCOMPUTING, 2008, 71 (4-6) : 592 - 599
  • [44] Channel Estimation for a Multi-User System with Iterative Interference Cancelation
    Grinewitschus, Lukas
    Schlegel, Christian
    Jung, Peter
    2019 IEEE AEROSPACE CONFERENCE, 2019,
  • [45] A DSP-assisted IF-over-fiber system with extreme learning machine-based linearization
    Vieira, Luis Carlos
    IEEE Photonics Technology Letters, 2024,
  • [46] Fast Beamforming for IRS Assisted Multi-User Communication Systems by Lightweight Unsupervised Learning
    Yue, Chengfang
    Tang, Hui
    Chai, Li
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2024, 73 (11) : 17180 - 17191
  • [47] Extreme learning machine-based alleviation for overloaded power system
    Labed, Imen
    Labed, Djamel
    IET GENERATION TRANSMISSION & DISTRIBUTION, 2019, 13 (22) : 5058 - 5070
  • [48] A DSP-Assisted IF-Over-Fiber System With Extreme Learning Machine-Based Linearization
    Vieira, Luis Carlos
    IEEE PHOTONICS TECHNOLOGY LETTERS, 2025, 37 (02) : 65 - 68
  • [49] Deep Residual Learning for Channel Estimation in Intelligent Reflecting Surface-Assisted Multi-User Communications
    Liu, Chang
    Liu, Xuemeng
    Ng, Derrick Wing Kwan
    Yuan, Jinhong
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2022, 21 (02) : 898 - 912
  • [50] Beamforming Design of IRS-Assisted SWIPT System Based on Deep Reinforcement Learning
    Zhang, Hui
    Jia, Qiming
    Han, Xu
    Yu, Hongde
    Zhao, Jiaxiang
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2025, 21 (01) : 733 - 742