Spatial Deep Learning for Wireless Scheduling

被引:192
作者
Cui, Wei [1 ]
Shen, Kaiming [1 ]
Yu, Wei [1 ]
机构
[1] Univ Toronto, Edward S Rogers Sr Dept Elect & Comp Engn, Toronto, ON M5S 3G4, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Deep learning; discrete optimization; geographic location; proportional fairness; scheduling; spatial convolution; NETWORKS; OPTIMIZATION;
D O I
10.1109/JSAC.2019.2904352
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
The optimal scheduling of interfering links in a dense wireless network with full frequency reuse is a challenging task. The traditional method involves first estimating all the interfering channel strengths and then optimizing the scheduling based on the model. This model-based method is, however, resource intensive and computationally hard because channel estimation is expensive in dense networks; furthermore, finding even a locally optimal solution of the resulting optimization problem may be computationally complex. This paper shows that by using a deep learning approach, it is possible to bypass the channel estimation and to schedule links efficiently based solely on the geographic locations of the transmitters and the receivers due to the fact that in many propagation environments, the wireless channel strength is largely a function of the distance-dependent path-loss. This is accomplished by unsupervised training over randomly deployed networks and by using a novel neural network architecture that computes the geographic spatial convolutions of the interfering or interfered neighboring nodes along with subsequent multiple feedback stages to learn the optimum solution. The resulting neural network gives a near-optimal performance for sum-rate maximization and is capable of generalizing to larger deployment areas and to deployments of different link densities. Moreover, to provide fairness, this paper proposes a novel scheduling approach that utilizes the sum-rate optimal scheduling algorithm over judiciously chosen subsets of links for maximizing a proportional fairness objective over the network. The proposed approach shows highly competitive and generalizable network utility maximization results.
引用
收藏
页码:1248 / 1261
页数:14
相关论文
共 26 条
[1]  
Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
[2]  
[Anonymous], P14118 ITUR
[3]  
Chaponniere E. F., 1999, U.S. Patent, Patent No. 09345700
[4]  
Cui W., 2018, IEEE GLOB COMM CONF, P1
[5]  
Eisen M., 2018, LEARNING OPTIMAL RES
[6]   Modulation and coding for linear Gaussian channels [J].
Forney, GD ;
Ungerboeck, G .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1998, 44 (06) :2384-2415
[7]   MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS [J].
HORNIK, K ;
STINCHCOMBE, M ;
WHITE, H .
NEURAL NETWORKS, 1989, 2 (05) :359-366
[8]   Distributed interference compensation for wireless networks [J].
Huang, JW ;
Berry, RA ;
Honig, ML .
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2006, 24 (05) :1074-1084
[9]  
Johansson M, 2006, IEEE T WIREL COMMUN, V5, P435, DOI 10.1109/TWC.2006.02023
[10]   Convergence of proportional-fair sharing algorithms under general conditions [J].
Kushner, HJ ;
Whiting, PA .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2004, 3 (04) :1250-1259