计及牵引负荷相关性的随机潮流计算  

Probability Load Flow Calculation Considering the Correlation of Traction Load

作　　者：高锋阳[1,2] 乔垚 杜强 强国栋[1] GAO Fengyang;QIAO Yao;DU Qiang;QIANG Guodong(School of Automation and Electrical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China;Gansu Jiaoda Engineering Inspection Co.,Ltd.,Lanzhou 730070,China)

机构地区：[1]兰州交通大学自动化与电气工程学院,甘肃兰州730070 [2]甘肃交达工程检测有限公司,甘肃兰州730070

出　　处：《铁道学报》2018年第10期23-29,共7页Journal of the China Railway Society

基　　金：国家自然科学基金(51767013);甘肃省重点研发计划(18YF1FA058);兰州市人才创新项目(2017-RC-95)

摘　　要：结合随机潮流计算量化系统状态变量的概率信息,构建牵引变电所概率负荷模型,描述牵引负荷的随机性和波动性,对实现系统优化运行具有重要意义。通过蒙特卡洛算法模拟相应数据并结合非线性递减惯性权重与混沌优化的粒子群算法辨识模型参数;针对随机潮流计算输入变量的相关性控制问题,提出一种基于模拟退火算法与拉丁超立方采样的方法。仿真实验结果表明:改进的粒子群算法较普通粒子群算法拟合精度更高;改进的相关性控制方法可以不受随机变量概率密度表达式的约束,实现多个随机变量的相关性控制;计及牵引负荷样本之间的相关性对节点电压越限概率、支路功率的影响较仅考虑普通负荷相关性时更为明显,可指导系统进行概率潮流优化。The probability load model of the traction substation was constructed to describe the randomness and volatility of traction load,combining with probabilistic power flow to calculate the probability information of systemstate variables,which is of great significance to realize optimal operation of the power system.The corresponding data were simulated by the Monte Carlo algorithm and the model parameters were identified by the particle swarm optimization with the nonlinear decreasing inertia weight and the chaos optimization.A method based on simulated annealing algorithm and Latin hypercube sampling was proposed for the correlation control problem of the input variables of the random flow calculation.The simulation results show that the improved particle swarm optimization algorithm is more accurate than the ordinary particle swarm optimization algorithm.The improved correlation control method can realize the correlation control of multiple random variables without the constraint of the probability density expression of random variables.Considering the correlation between traction load samples,the influence of node voltage overshoot probability and branch power is more obvious than that considering only the correlation of ordinary load.This method can be applied to system probabilistic power flow optimization.

关 键 词：牵引变电所 蒙特卡洛模拟 粒子群算法 模拟退火算法 随机潮流计算 

分 类 号：TM92[电气工程—电力电子与电力传动]