Learning Optimal Resource Allocations in Wireless Systems

Abstract

This paper considers the design of optimal resource allocation policies in wireless communication systems which are generically modeled as a functional optimization problem with stochastic constraints. These optimization problems have the structure of a learning problem in which the statistical loss appears as a constraint, motivating the development of learning methodologies to attempt their solution. To handle stochastic constraints, training is undertaken in the dual domain. It is shown that this can be done with small loss of optimality when using near-universal learning parameterizations. In particular, since deep neural networks (DNN) are near-universal their use is advocated and explored. DNNs are trained here with a model-free primal-dual method that simultaneously learns a DNN parametrization of the resource allocation policy and optimizes the primal and dual variables. Numerical simulations demonstrate the strong performance of the proposed approach on a number of common wireless resource allocation problems.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Fully Convolutional Networks for Semantic Segmentation
• Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management
• Reinforcement Learning with Deep Energy-Based Policies
• Neural Network Detection of Data Sequences in Communication Systems
• Detection Algorithms for Communication Systems Using Deep Learning
• Random Access Design for Wireless Control Systems
• Learning in Wireless Control Systems over Non-Stationary Channels
• Decentralized Deep Scheduling for Interference Channels

Cited by in corpus (47)

• 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
• White Paper on Broadband Connectivity in 6G
• Spatial Deep Learning for Wireless Scheduling
• Proximal Policy Optimization-based Transmit Beamforming and Phase-shift Design in an IRS-aided ISAC System for the THz Band
• Scoring the Terabit/s Goal:Broadband Connectivity in 6G
• Learning Decentralized Wireless Resource Allocations with Graph Neural Networks
• Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective
• Learning Resilient Radio Resource Management Policies with Graph Neural Networks
• A Tutorial on Ultra-Reliable and Low-Latency Communications in 6G: Integrating Domain Knowledge into Deep Learning
• State-Augmented Learnable Algorithms for Resource Management in Wireless Networks
• Model-Free Design of Control Systems over Wireless Fading Channels
• Graph-based Algorithm Unfolding for Energy-aware Power Allocation in Wireless Networks
• Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment
• Constrained Learning with Non-Convex Losses
• Model-Free Learning of Optimal Ergodic Policies in Wireless Systems
• Deep Learning based Wireless Resource Allocation with Application to Vehicular Networks
• ViWi Vision-Aided mmWave Beam Tracking: Dataset, Task, and Baseline Solutions
• Deep Learning for Radio Resource Allocation with Diverse Quality-of-Service Requirements in 5G
• Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systems
• LORM: Learning to Optimize for Resource Management in Wireless Networks with Few Training Samples
• Learning to Transmit with Provable Guarantees in Wireless Federated Learning
• Zeroth-order Deterministic Policy Gradient
• Unsupervised Learning for Asynchronous Resource Allocation in Ad-hoc Wireless Networks
• Scalable Power Control/Beamforming in Heterogeneous Wireless Networks with Graph Neural Networks
• Tune smarter not harder: A principled approach to tuning learning rates for shallow nets
• When Multiple Agents Learn to Schedule: A Distributed Radio Resource Management Framework
• Proactive Optimization with Machine Learning: Femto-caching with Future Content Popularity
• Percentile Optimization in Wireless Networks- Part I: Power Control for Max-Min-Rate to Sum-Rate Maximization (and Everything in Between)
• Wireless Link Scheduling via Graph Representation Learning: A Comparative Study of Different Supervision Levels
• Algorithm Unrolling for Massive Access via Deep Neural Network with Theoretical Guarantee
• Deep Learning for Reactive Power Control of Smart Inverters under Communication Constraints
• Uncertainty Aware Deep Neural Network for Multistatic Localization with Application to Ultrasonic Structural Health Monitoring
• Optimizing Wireless Systems Using Unsupervised and Reinforced-Unsupervised Deep Learning
• Resource Allocation via Model-Free Deep Learning in Free Space Optical Communications
• Optimal Resource Allocation in Wireless Control Systems via Deep Policy Gradient
• Multicell Power Control under Rate Constraints with Deep Learning
• A Deep Learning Based Resource Allocator for Communication Networks with Dynamic User Utility Demands
• Sufficiently Accurate Model Learning
• Optimal Unbiased Linear Sensor Fusion over Multiple Lossy Channels with Collective Observability
• Design of AoI-Aware 5G Uplink Scheduler UsingReinforcement Learning
• Sufficiently Accurate Model Learning for Planning
• A Statistical Learning Approach to Reactive Power Control in Distribution Systems
• Deep Learning for Wireless Coded Caching with Unknown and Time-Variant Content Popularity
• Structure of Deep Neural Networks with a Priori Information in Wireless Tasks
• Optimal WDM Power Allocation via Deep Learning for Radio on Free Space Optics Systems