Learning to Schedule in Non-Stationary Wireless Networks With Unknown Statistics

被引:0
作者
Quang Minh Nguyen [1 ]
Modiano, Eytan [1 ]
机构
[1] MIT, Cambridge, MA 02139 USA
来源
PROCEEDINGS OF THE 2023 INTERNATIONAL SYMPOSIUM ON THEORY, ALGORITHMIC FOUNDATIONS, AND PROTOCOL DESIGN FOR MOBILE NETWORKS AND MOBILE COMPUTING, MOBIHOC 2023 | 2023年
关键词
Optimal Control; Scheduling; Wireless Network; Machine Learning; Partial Observability; Non-stationarity;
D O I
10.1145/3565287.3610258
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The emergence of large-scale wireless networks with partially-observable and time-varying dynamics has imposed new challenges on the design of optimal control policies. This paper studies efficient scheduling algorithms for wireless networks subject to generalized interference constraint, where mean arrival and mean service rates are unknown and non-stationary. This model exemplifies realistic edge devices' characteristics of wireless communication in modern networks. We propose a novel algorithm termed MW-UCB for generalized wireless network scheduling, which is based on the Max-Weight policy and leverages the Sliding-Window Upper-Confidence Bound to learn the channels' statistics under non-stationarity. MW-UCB is provably throughput-optimal under mild assumptions on the variability of mean service rates. Specifically, as long as the total variation in mean service rates over any time period grows sub-linearly in time, we show that MW-UCB can achieve the stability region arbitrarily close to the stability region of the class of policies with full knowledge of the channel statistics. Extensive simulations validate our theoretical results and demonstrate the favorable performance of MW-UCB.
引用
收藏
页码:181 / 190
页数:10
相关论文
共 33 条
  • [1] Anand A, 2018, IEEE INFOCOM SER, P1979
  • [2] Andrews M, 2004, IEEE INFOCOM SER, P1694
  • [3] Finite-time analysis of the multiarmed bandit problem
    Auer, P
    Cesa-Bianchi, N
    Fischer, P
    [J]. MACHINE LEARNING, 2002, 47 (2-3) : 235 - 256
  • [4] Adaptive Management of Volatile Edge Systems at Runtime With Satisfiability
    Avasalcai, Cosmin
    Tsigkanos, Christos
    Dustdar, Schahram
    [J]. ACM TRANSACTIONS ON INTERNET TECHNOLOGY, 2022, 22 (01)
  • [5] Besbes O, 2014, ADV NEUR IN, V27
  • [6] Trust Trackers for Computation Offloading in Edge-Based IoT Networks
    Bradbury, Matthew
    Jhumka, Arshad
    Watson, Tim
    [J]. IEEE CONFERENCE ON COMPUTER COMMUNICATIONS (IEEE INFOCOM 2021), 2021,
  • [7] Distributed Link Scheduling With Constant Overhead
    Bui, Loc X.
    Sanghavi, Sujay
    Srikant, R.
    [J]. IEEE-ACM TRANSACTIONS ON NETWORKING, 2009, 17 (05) : 1467 - 1480
  • [8] Che X., 2010, P 7 ANN IEEE COMM SO, P1, DOI [DOI 10.1109/ICC.2010.5502421, 10.1109/SECON.2010.5508292, DOI 10.1109/SECON.2010.5508292]
  • [9] Chen Wei, 2020, C UNCERTAINTY ARTICI
  • [10] Cheng GZ, 2015, 2015 IFIP NETWORKING CONFERENCE (IFIP NETWORKING)