Intelligent Shoreside Data Collection in UWSNs: A Dual-Genetic-Algorithm Framework for Routing and UGV Path Optimization

Abstract

Energy-efficient data gathering remains a fundamental challenge in underwater wireless sensor networks (UWSNs) due to the inherent limitations of multihop communication, which often result in excessive energy depletion near the sink, premature network partition, and degraded data collection performance. This article proposes a genetic algorithm approach for UGV path and node routing (GA-UPNR), a novel shoreside data collection framework that decomposes the problem into two optimization subproblems. The first genetic algorithm constructs energy-balanced multihop routing trees from surface nodes to distributed shoreside nodes to maximize network lifetime. The second genetic algorithm determines the optimal set of stopping points for a UGV, minimizing the travel distance required to collect data from all shoreside nodes. The two algorithms operate independently and are executed sequentially, providing a scalable solution for efficient data retrieval. Simulation results with 500 nodes indicate that GA-UPNR-Routing achieves longer network lifetime and higher connectivity compared to the benchmark method based on breadth-first search (BMBS), SS-Dijkstra, and MS-Dijkstra. Specifically, GA-UPNR-Routing achieves a network lifetime of 40.14 rounds, in contrast to 21.16, 17.01, and 5.25 rounds for BMBS, MS-Dijkstra, and SS-Dijkstra, respectively. For the UGV stopping point selection, GA-UPNR-Path requires an average of 9.37 stops, whereas maximum contribution first (MCF) and nearest-projection stopping (NPS) require 11.07 and 105.61 stops, respectively. These results suggest that the GA-UPNR framework is suitable for scalable data collection in long-term marine monitoring applications.