基于潮流引导神经网络的配电网贝叶斯状态估计
Bayesian State Estimation for Distribution Networks Based on Power Flow-informed Neural Networks
梁栋 1刘啸宇 2曾林 3孙智卿 4王守相5
作者信息
- 1. 省部共建电工装备可靠性与智能化国家重点实验室(河北工业大学),天津 300401;石家庄科林电气股份有限公司河北省智能配用电装备产业技术研究院,石家庄 050222
- 2. 省部共建电工装备可靠性与智能化国家重点实验室(河北工业大学),天津 300401
- 3. 康奈尔大学电气与计算机工程学院,纽约 14853
- 4. 国网浙江省电力有限公司杭州供电公司,杭州 310000
- 5. 教育部智能电网重点实验室(天津大学),天津 300072
- 折叠
摘要
针对量测不足条件下配电网状态估计方法精度较低的问题,提出了基于潮流引导神经网络的配电网贝叶斯状态估计方法.首先,基于各节点的历史数据学习注入有功、无功功率的 2维高斯混合概率分布,据此进行蒙特卡洛抽样和潮流计算,以获取用于神经网络训练的丰富样本;其次,以最小化状态估计误差和潮流方程失配量为目标,建立了基于潮流引导神经网络的配电网贝叶斯状态估计模型,通过在损失函数中融入潮流物理损失惩罚项,获取满足电网运行约束的一致解;再次,采用 BOHB(贝叶斯优化+Hyperband)方法对神经网络超参数进行优化,并提出了基于迁移学习的拓扑变化和分接头调整条件下的自适应方法;最后,实际数据和三相平衡/不平衡配电网的测试结果表明,所提方法较基于伪量测的状态估计方法和无潮流引导的贝叶斯估计方法估计精度更高,且在拓扑变化和分接头调整时具有较好的自适应性能.
Abstract
Driven by the low accuracy problem of existing distribution network state estimation(SE)methods when measurements are limited,a Bayesian SE method is proposed for distribution networks based on a novel power flow-informed neural network(PFINN).Firstly,the two-dimensional Gaussian mixture probability distribution of real and reactive power injection is learned for each node using historical data;thereby,abundant samples can be obtained for neural network training by Monte Carlo sampling and power flow calculation.Then,with the goal of minimizing the SE error and power flow equation violation,a Bayesian SE model is established for distribution networks based on the PFINN.Physics loss penalty is introduced into the loss function to constrain the output to be consistent with system oper-ating constraints.Furthermore,the BOHB method is adopted to optimize the hyperparameters of the neural network,while transfer learning is introduced to adapt to changes of network topologies and on-load tap changers.Finally,test re-sults using field data and balanced/unbalanced distribution networks show that the proposed method has better estimation accuracy than the pseudo-measurement-based SE method and the Bayesian SE method without power flow informing.Meanwhile,the proposed method achieves good adaptation performance to topology and tap changes.
关键词
潮流引导/神经网络/贝叶斯状态估计/配电网/迁移学习Key words
power flow informing/neural network/Bayesian state estimation/distribution network/transfer learning引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据