Ensemble Learning based Linear Power Flow
Ensemble Learning based Linear Power Flow
复制标题
DOI：
10.1109/pesgm41954.2020.9281793
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Ren Hu;Qifeng Li
中科院分区：
文献类型：
--
作者：
Ren Hu;Qifeng Li
本文提出了一种基于集成学习的无功潮流线性化方法，该方法首先以多项式回归(PR)作为基本学习器，在直角坐标系下捕捉节点电压作为自变量与有功或无功作为因变量之间的线性关系。然后，引入梯度增强(GB)和袋子学习作为集成学习方法，将所有基本学习器结合起来，以提高模型的性能。将所推导出的线性潮流模型应用于求解著名的最优潮流问题。在IEEE标准电力系统上的仿真结果表明：(1)集成学习方法能显著提高PR算法的效率，且GB算法优于Bging算法；(2)对于最优潮流的求解，数据驱动模型在精度和计算效率上均优于DC模型和SDP松弛模型。
This paper develops an ensemble learning-based linearization approach for power flow with reactive power modeled, where the polynomial regression (PR) is first used as a basic learner to capture the linear relationships between the bus voltages as the independent variables and the active or reactive power as the dependent variable in rectangular coordinates. Then, gradient boosting (GB) and bagging as ensemble learning methods are introduced to combine all basic learners to boost the model performance. The inferred linear power flow model is applied to solve the well-known optimal power flow (OPF) problem. The simulation results on IEEE standard power systems indicate that (1) ensemble learning methods can significantly improve the efficiency of PR, and GB works better than bagging; (2) as for solving OPF, the data-driven model outperforms the DC model and the SDP relaxation in both accuracy, and computational efficiency.