配电网无功优化逐层筛选寻优算法

A Hierarchical Screening Algorithm for Reactive Power Optimization in Distribution Networks

利用配电网络具有树状层次结构的特点,提出了一种逐层筛选寻优的配电网无功优化算法。文中将辐射网逐层分解为随电压线性变化的等值负荷,并推导了等值负荷参数递推计算的方法;对含电容器、变压器分接头的控制策略空间也进行逐层分解,将每一个子策略映射到一组等值负荷参数,通过淘汰每一层无功电压负荷参数相似而局部有功网损较大的子策略,有效压缩了策略筛选空间,实现了自底向上的逐层筛选寻优。通过选取合适的参数,能保证算法在实现快速计算的同时具备全局寻优能力。另外,该算法优化结果具有确定性,不存在初值选取和收敛性问题。文中给出了实际配电网18节点系统和IEEE69节点系统的算例仿真,并与传统遗传算法在计算速度和优化效果方面进行了对比,说明该算法适用于含离散变量的大规模辐射网无功优化问题的在线计算。

This paper presents a novel approach to reactive power optimization in the distribution network.By taking advantage of the characteristics of the distribution network with tree hierarchy,the radial network is decomposed into nested linear equivalent loads and a recursive load parameter calculating method is derived.The entire strategy space is also hierarchically decomposed with each sub-strategy mapped to a set of equivalent load parameters.When two sub-strategies of the same node have similar reactive power and voltage load parameters,the one with heavier local active power loss is eliminated.Therefore the strategy space of each layer of the network is greatly reduced.The algorithm proposed is deterministic and free from initial value selection and convergence issues,which helps achieve fast computing and approximate global optimization.An actual 18-bus distribution system and the IEEE 69-bus system simulation results have verified the correctness and effectiveness of the algorithm.