Spatial Deep Learning for Wireless Scheduling

Abstract

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 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 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.

This paper is the full version of the paper presented at IEEE Global Communications Conference 2018. It includes 15 pages and 12 figures

References in corpus (5)

• Fractional Programming for Communication Systems--Part I: Power Control and Beamforming
• Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management
• Fractional Programming for Communication Systems--Part II: Uplink Scheduling via Matching
• Learning Optimal Resource Allocations in Wireless Systems
• Towards Optimal Power Control via Ensembling Deep Neural Networks

Cited by in corpus (48)

• Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks
• A Deep Learning Framework for Optimization of MISO Downlink Beamforming
• Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks
• Learning Decentralized Wireless Resource Allocations with Graph Neural Networks
• Learning to Branch: Accelerating Resource Allocation in Wireless Networks
• Link Scheduling using Graph Neural Networks
• Deep Learning for Channel Sensing and Hybrid Precoding in TDD Massive MIMO OFDM Systems
• Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective
• Learning Based User Scheduling in Reconfigurable Intelligent Surface Assisted Multiuser Downlink
• Heterogeneous graph neural network for power allocation in multicarrier-division duplex cell-free massive MIMO systems
• Machine Learning Methods for Management UAV Flocks -- a Survey
• Learning to Solve Network Flow Problems via Neural Decoding
• Learning-Based Multi-Channel Access in 5G and Beyond Networks with Fast Time-Varying Channels
• Uncertainty Injection: A Deep Learning Method for Robust Optimization
• Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment
• Model-Free Learning of Optimal Ergodic Policies in Wireless Systems
• Hybrid Beamforming for 5G and Beyond Millimeter-Wave Systems: A Holistic View
• Two-Stage Stochastic Optimization via Primal-Dual Decomposition and Deep Unrolling
• Rate-Splitting Multiple Access in Cache-Aided Cloud-Radio Access Networks
• A Graph Neural Network Approach for Scalable Wireless Power Control
• A Survey on Millimeter-Wave Beamforming Enabled UAV Communications and Networking
• Decentralized Inference with Graph Neural Networks in Wireless Communication Systems
• Capacity-Net-Based RIS Precoding Design without Channel Estimation for mmWave MIMO System
• Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systems
• Learning to Reflect and to Beamform for Intelligent Reflecting Surface with Implicit Channel Estimation
• Deep Neural Network Based Active User Detection for Grant-free NOMA Systems
• LORM: Learning to Optimize for Resource Management in Wireless Networks with Few Training Samples
• Distributed Scheduling using Graph Neural Networks
• Topology Aware Deep Learning for Wireless Network Optimization
• Learning to Beamform in Heterogeneous Massive MIMO Networks
• Scalable Power Control/Beamforming in Heterogeneous Wireless Networks with Graph Neural Networks
• Transfer Learning with Reconstruction Loss
• Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis
• Deep Reinforcement Learning for Multi-Agent Power Control in Heterogeneous Networks
• Expert-Calibrated Learning for Online Optimization with Switching Costs
• Accelerating Generalized Benders Decomposition for Wireless Resource Allocation
• Correlation-aware Cooperative Multigroup Broadcast 360° Video Delivery Network: A Hierarchical Deep Reinforcement Learning Approach
• Reconfigurable Intelligent Surface Empowered Device-to-Device Communication Underlaying Cellular Networks
• User Association and Load Balancing for Massive MIMO through Deep Learning
• Deep Learning for Distributed Channel Feedback and Multiuser Precoding in FDD Massive MIMO
• Scalable Multi-agent Reinforcement Learning Algorithm for Wireless Networks
• A Deep Learning Based Resource Allocator for Communication Networks with Dynamic User Utility Demands
• A Fast Graph Kernel Based Classification Method for Wireless Link Scheduling on Riemannian Manifold
• Scalable Deep Reinforcement Learning for Routing and Spectrum Access in Physical Layer
• Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
• Learning to Optimize Under Constraints with Unsupervised Deep Neural Networks
• Power-Domain Interference Graph Estimation for Multi-hop BLE Networks
• Deep Learning for Wireless Coded Caching with Unknown and Time-Variant Content Popularity