| 引用本文: | 林楠,王怀远,陈启凡.基于后验分布信息的SSAE暂态稳定评估模型倾向性修正方法[J].电力自动化设备,2022,42(3): |
| LIN Nan,WANG Huaiyuan,CHEN Qifan.Tendency correction method of SSAE transient stability assessment model based on posterior distribution information[J].Electric Power Automation Equipment,2022,42(3): |
|
| 摘要: |
| 为了解决样本不平衡带来的评估倾向性问题，从深度学习模型的损失函数出发，分析样本不平衡对评估模型的影响，发现训练过程中的损失函数值能够反映样本的不平衡程度，由此提出基于样本后验分布信息的代价敏感修正方法。通过预先训练获得样本的后验分布信息，引入稳定样本与不稳定样本的损失函数均值比得到修正系数；将修正系数通过代价敏感法修正模型的损失函数，重新对模型进行训练，从而修正模型的评估倾向性。相较于传统方法，该方法从模型的训练机理上量化了样本的不平衡程度，修正系数综合考虑了样本数量与空间分布的不平衡对模型参数的影响，实现了更好的修正效果。IEEE 39节点系统和华东某区域系统的仿真结果验证了所提方法的有效性。 |
| 关键词: 深度学习 暂态稳定评估 代价敏感 后验分布信息 堆叠稀疏自动编码器 不平衡样本 |
| DOI：10.16081/j.epae.202111011 |
| 分类号:TM731 |
| 基金项目:福建省中青年教师教育科研项目(JT180018) |
|
| Tendency correction method of SSAE transient stability assessment model based on posterior distribution information |
|
LIN Nan, WANG Huaiyuan, CHEN Qifan
|
|
Fujian Province University Engineering Research Center of Smart Distribution Grid Equipment, College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350116, China
|
| Abstract: |
| In order to solve the problem of evaluation tendency caused by imbalanced samples, the influence of imbalanced samples on evaluation model is analyzed from the loss function of deep learning model, and it is found that the loss function value in the training process can reflect the imbalance degree of the samples, thus a cost-sensitive correction method based on sample posterior distribution information is proposed. The posterior distribution information of the samples is obtained by the preliminary training, and the correction coefficient is obtained by introducing the mean value ratio of loss function of stable samples to unstable samples. The correction coefficient is used to correct the loss function of the model by the cost sensitive method, and the model is trained again so as to correct the evaluation tendency. Compared with the traditional methods, the proposed method quantifies the imbalance degree of the model from the training mechanism, and the correction coefficient comprehensively considers the influence of the imbalance of sample quantity and spatial distribution on model parameters, which realizes better correction effect. The effectiveness of the proposed method is verified by the simulative results of IEEE 39-bus system and a regional system in East China. |
| Key words: deep learning transient stability assessment cost sensitive posterior distribution information SSAE imbalanced sample |
