含分布式电源的多智能体入侵杂草算法配电网规划优化

Distribution Network Planning Optimization with Distributed Generation Based on Multi-agent Invasive Weed Optimization Algorithm

以配电网系统投资费用最小为目标,针对入侵杂草算法缺乏信息共享机制的缺陷,提出一种将入侵杂草算法与多智能体进化思想相结合的新型求解算法。该算法既充分利用了入侵杂草算法参数少、结构简单和鲁棒性强的优点,又通过引入多智能体进化思想改善了入侵杂草算法后期收敛速度慢、易陷入局部最优、收敛精度不高的缺点。以IEEE 33节点配电网系统为例进行仿真分析,并将优化结果与传统的入侵杂草算法优化结果进行比较,结果表明该算法在解决含分布式电源配电网规划优化问题上收敛精度更高,寻优速度更快,能够有效地减少配电网总投资费用。

With distribution network system investment costs to a minimum as the goal, according to the defect of lacking information exchange mechanism in invasive weed optimization （IWO） , this paper proposed a new algorithm which was composed of IWO and multi-agent system. The algorithm made full use of the advantages,like less parameters, simple structure and strong robustness,of IWO. At the same time,it introduced multi-agent evolutionary ideas to improve the disadvantages, like slow convergence speed in the later period, easy to fall into local optimum, low convergence accuracy,of IWO. Finally, comparison with original IWO in IEEE 33-node distribution network system simulation and analysis, the results show that the new hybrid algorithm has higher convergence accuracy and faster search ability and can effectively reduce the investment on distribution network system.