Research on Cooperative Task Planning for Multi-UUV Data Collection in UWSNs

This paper investigates the task planning problem for cooperative data collection by multiple unmanned underwater vehicles (UUVs) in underwater wireless sensor networks (UWSNs). Firstly, a dual-layer encoding method is proposed for the time-energy optimization problem, where the discrete task sequence is represented by the ant colony path in the ant colony optimization (ACO) algorithm, and the continuous velocity parameters are encoded by the particle positions in the quantum-behaved particle swarm optimization (QPSO) algorithm. Secondly, based on this dual-layer encoding method, a weighted sum-based multi-objective WMACO-QPSO algorithm is proposed, establishing a parallel optimization mechanism for the hybrid algorithm to achieve co-evolution of dual decision variables. Finally, the proposed algorithm is compared with other algorithms based on Pareto front and weighted sum strategies, and simulation experiments are conducted under different task scenarios. The results demonstrate that the proposed algorithm can adapt to various task scenarios, significantly improving task allocation efficiency and enhancing the overall system performance.