基于量子粒子群算法的近海渔场集中电站选址定容规划

Quantum particle swarm algorithm-based site selection and capacity planning for offshore fishery Centralized power stations

中文关键词: 集中电站  选址定容  近海渔场  量子粒子群算法  Voronoi图

英文关键词: centralized power stations  siting and sizing  offshore fishery farms  Quantum Particle Swarm Optimization (QPSO) algorithm  Voronoi diagram

中文摘要:

      针对近海渔场集中电站微电网供电模式的选址定容规划问题，首先分析了集中电站供电模式工作原理；然后以实现成本最小为目标提出了一个集中电站选址定容规划模型，通过一系列的约束条件，如电站地理位置、电力需求、电站容量等，确保电站选址的合理性和电力系统的稳定运行；并提出采用Voronoi图与量子粒子群算法联合求解最优布局，通过调整算法参数，实现成本效益和电力供应的最优平衡；最后基于近海渔场卫星图像算例得出Voronoi-QPSO联合算法，与标准PSO、GA、SA算法相比，求解精度提升，收敛速度加快；验证了规划模型的合理性与联合算法的有效性，Voronoi图有效实现了负荷的合理分配和区域划分，进一步提升了近海渔场集中式电站规划模型的整体性能。

英文摘要:

      For the siting-and-sizing planning of a centralized power-station micro-grid serving offshore fish farms, the working principle of the centralized supply scheme is first analyzed. A cost-minimization planning model for station location and capac-ity is then formulated, incorporating constraints on geographic position, power demand, station capacity, and other factors to ensure rational siting and stable system operation. To search for the optimal layout, a combined Voronoi-diagram and quantum particle swarm optimization (QPSO) method is proposed; by tuning algorithm parameters, the approach balances cost effi-ciency against power-supply performance. A case study based on satellite imagery of offshore fish-farm sites shows that the Vo-ronoi-QPSO algorithm achieves higher solution accuracy and faster convergence than standard PSO, GA, and SA algorithms. The results verify both the soundness of the planning model and the effectiveness of the hybrid algorithm: the Voronoi diagram enables reasonable load allocation and regional partitioning, fur-ther improving the overall performance of the centralized-station planning model for offshore fish farms.