Transferable Multi-Fidelity Bayesian Optimization for Radio Resource Management

被引:1
|
作者
Zhang, Yunchuan [1 ]
Park, Sangwoo [1 ]
Simeone, Osvaldo [1 ]
机构
[1] Kings Coll London, Ctr Intelligent Informat Proc Syst CIIPS, Dept Engn, London, England
基金
英国工程与自然科学研究理事会;
关键词
Multi-fidelity Bayesian optimization; entropy search; wireless resource allocation; knowledge transfer; FRAMEWORK;
D O I
10.1109/SPAWC60668.2024.10694025
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Radio resource allocation often calls for the optimization of black-box objective functions whose evaluation is expensive in real-world deployments. Conventional optimization methods apply separately to each new system configuration, causing the number of evaluations to be impractical under constraints on computational resources or timeliness. Toward a remedy for this issue, this paper introduces a multi-fidelity continual optimization framework that hinges on a novel information-theoretic acquisition function. The new strategy probes candidate solutions so as to balance the need to retrieve information about the current optimization task with the goal of acquiring information transferable to future resource allocation tasks, while satisfying a query budget constraint. Experiments on uplink power control in a multi-cell multi-antenna system demonstrate that the proposed method substantially improves the optimization efficiency after processing a sufficiently large number of tasks.
引用
收藏
页码:176 / 180
页数:5
相关论文
共 50 条
  • [41] Multi-fidelity optimization via surrogate modelling
    Forrester, Alexander I. J.
    Sobester, Andras
    Keane, Andy J.
    PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 2007, 463 (2088): : 3251 - 3269
  • [42] Adaptive Objective Selection for Multi-Fidelity Optimization
    Akimoto, Youhei
    Shimizu, Takuma
    Yamaguchi, Takahiro
    PROCEEDINGS OF THE 2019 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'19), 2019, : 880 - 888
  • [43] Research on multi-fidelity aerodynamic optimization methods
    Huang Likeng
    Gao Zhenghong
    Zhang Dehu
    Chinese Journal of Aeronautics , 2013, (02) : 279 - 286
  • [44] Research on multi-fidelity aerodynamic optimization methods
    Huang Likeng
    Gao Zhenghong
    Zhang Dehu
    Chinese Journal of Aeronautics, 2013, 26 (02) : 279 - 286
  • [45] Multi-fidelity modeling and optimization of biogas plants
    Zaefferer, Martin
    Gaida, Daniel
    Bartz-Beielstein, Thomas
    APPLIED SOFT COMPUTING, 2016, 48 : 13 - 28
  • [46] Research on multi-fidelity aerodynamic optimization methods
    Huang Likeng
    Gao Zhenghong
    Zhang Dehu
    CHINESE JOURNAL OF AERONAUTICS, 2013, 26 (02) : 279 - 286
  • [47] TOPFARM: Multi-fidelity optimization of wind farms
    Rethore, Pierre-Elouan
    Fuglsang, Peter
    Larsen, Gunner C.
    Buhl, Thomas
    Larsen, Torben J.
    Madsen, Helge A.
    WIND ENERGY, 2014, 17 (12) : 1797 - 1816
  • [48] MULTI-FIDELITY DISCRETE OPTIMIZATION VIA SIMULATION
    Li, Dongyang
    Liu, Haitao
    Jin, Xiao
    Li, Haobin
    Chew, Ek Peng
    Tan, Kok Choon
    Lin, Yun Hui
    2022 WINTER SIMULATION CONFERENCE (WSC), 2022, : 3170 - 3181
  • [49] ROBUST DESIGN OPTIMIZATION OF A COMPRESSOR ROTOR USING RECURSIVE COKRIGING BASED MULTI-FIDELITY UNCERTAINTY QUANTIFICATION AND MULTI-FIDELITY OPTIMIZATION
    Wiegand, Marcus
    Prots, Andriy
    Meyer, Marcus
    Schmidt, Robin
    Voigt, Matthias
    Mailach, Ronald
    PROCEEDINGS OF ASME TURBO EXPO 2024: TURBOMACHINERY TECHNICAL CONFERENCE AND EXPOSITION, GT2024, VOL 12D, 2024,
  • [50] Fast and Reliable Antenna Optimization by Design Specification Management and Multi-Fidelity Models
    Pietrenko-Dabrowska, Anna
    Koziel, Slawomir
    2023 17TH EUROPEAN CONFERENCE ON ANTENNAS AND PROPAGATION, EUCAP, 2023,