基于智能电网大数据发掘和模拟退火算法的配网重构

Study of Distribution System Reconstruction Based on Smart Grid Big Data Mining and Simulated Annealing Algorithm

为了提高配网电路的经济性及故障情况下快速恢复供电的能力,提出将智能电网大数据发掘和模拟退火算法相结合,即通过模拟退火算法中Metropolis准则的设定来避免在寻优过程中陷入局部最优,基于智能电网大数据发掘,考虑实时环境温度、变压器绕组温度和输电电缆温度情况下进行配网重构,并以美国PG&E 69节点配电系统为例进行仿真验证。结果表明,所提方法可有效降低优化的计算量,能迅速找到全局最优解,并满足所有约束,且配电网络的网损最小。

In order to improve the economy of distribution network circuit and the capacity of quickly restore power under fault conditions,this paper puts forward the combination of large data mining of smart grid and simulated annealing algorithm,that is,to avoid trapping into local optimum in the optimization process by the setting of the Metropolis criterion in the simulated annealing algorithm.Based on smart grid big data mining,the distribution networks is reconstructed by considering real-time environment temperature,transformer winding temperature and transmission cable temperature.Then it takes the American PGE 69-node system as an example for simulation verification.The results show that the proposed method can effectively reduce the optimization computation,quickly find the global optimal solution,and satisfy all constraints and the loss of distribution network are the least.