Learning-Based Resource Management in Integrated Sensing and Communication Systems

2025-06-25

AI Summary

This paper addresses the joint temporal resource optimization for multi-target tracking and communication transmission in integrated radar-communication systems. We propose a Constrained Deep Reinforcement Learning (CDRL) framework that enables adaptive, dynamic allocation of sensing and communication resources along the time dimension. The method jointly optimizes radar dwell time per target and data transmission scheduling—based on predicted target positions—while enforcing a strict time-budget constraint. It integrates radar-based target state estimation with communication link quality prediction to guide end-to-end decision-making. Our key contribution is the first formulation of temporal resource allocation as an end-to-end decision problem under hard timing constraints, coupled with a CDRL policy network explicitly designed to satisfy both real-time and reliability requirements. Experiments demonstrate that the approach significantly improves average communication rate and link reliability while maintaining tracking accuracy—particularly under high-maneuver target scenarios.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Multiagent Systems: Agent Communication

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

In this paper, we tackle the task of adaptive time allocation in integrated sensing and communication systems equipped with radar and communication units. The dual-functional radar-communication system's task involves allocating dwell times for tracking multiple targets and utilizing the remaining time for data transmission towards estimated target locations. We introduce a novel constrained deep reinforcement learning (CDRL) approach, designed to optimize resource allocation between tracking and communication under time budget constraints, thereby enhancing target communication quality. Our numerical results demonstrate the efficiency of our proposed CDRL framework, confirming its ability to maximize communication quality in highly dynamic environments while adhering to time constraints.

Problem

• Optimize time allocation in radar-communication systems
• Balance tracking and data transmission under constraints
• Enhance communication quality in dynamic environments

Innovation

• CDRL optimizes time allocation dynamically
• Balances radar tracking and data transmission
• Enhances communication under time constraints