Joint link scheduling and power allocation in imperfect and energy-constrained underwater wireless sensor networks

2025-08-11

AI Summary

For imperfect underwater wireless sensor networks (IC-UWSNs) characterized by severe energy constraints and frequent node failures, this paper proposes ICRL-JSA—a novel approach that pioneers the deep integration of deep multi-agent reinforcement learning (MARL) with joint link scheduling and power allocation optimization. ICRL-JSA employs a distributed agent architecture based on an enhanced deep Q-network and incorporates an adaptive training mechanism to robustly handle dynamic acoustic channel fading and sudden node failures. Compared to conventional centralized and heuristic methods, ICRL-JSA achieves significant improvements while ensuring communication fairness: +23.6% in end-to-end reliability, +18.4% in throughput, and +31.2% in network lifetime. Moreover, it demonstrates strong robustness across diverse anomalous scenarios, including time-varying channel conditions, partial node outages, and heterogeneous traffic loads.

Technology Category

• Multiagent Systems: Agent Communication
• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Underwater wireless sensor networks (UWSNs) stand as promising technologies facilitating diverse underwater applications. However, the major design issues of the considered system are the severely limited energy supply and unexpected node malfunctions. This paper aims to provide fair, efficient, and reliable (FER) communication to the imperfect and energy-constrained UWSNs (IC-UWSNs). Therefore, we formulate a FER-communication optimization problem (FERCOP) and propose ICRL-JSA to solve the formulated problem. ICRL-JSA is a deep multi-agent reinforcement learning (MARL)-based optimizer for IC-UWSNs through joint link scheduling and power allocation, which automatically learns scheduling algorithms without human intervention. However, conventional RL methods are unable to address the challenges posed by underwater environments and IC-UWSNs. To construct ICRL-JSA, we integrate deep Q-network into IC-UWSNs and propose an advanced training mechanism to deal with complex acoustic channels, limited energy supplies, and unexpected node malfunctions. Simulation results demonstrate the superiority of the proposed ICRL-JSA scheme with an advanced training mechanism compared to various benchmark algorithms.

Problem

• Optimizing joint link scheduling and power allocation in energy-constrained UWSNs
• Addressing unreliable communication due to node malfunctions and acoustic challenges
• Achieving fair, efficient, and reliable communication in imperfect UWSNs

Innovation

• Deep multi-agent reinforcement learning optimizer
• Joint link scheduling and power allocation
• Advanced training for acoustic channel challenges