ABSTRACT
In the transient stability assessment, machine learning based model has the problem that sample imbalance makes the model have a certain degree of evaluation tendency. From the loss function of the machine learning based model, it is found that the fitting degree to various samples after training can be mirrored by the loss function value of the samples. Therefore, a cost-sensitive strategy based on the imbalance degree of the loss function is proposed. Firstly, the machine learning based model is trained to obtain the mean value of loss functions of various samples. Then, the sample imbalance degree is calculated by the mean ratio of the loss function of unstable samples to that of stable samples. After that, the loss function is modified by the sample imbalance degree combined with the cost-sensitive strategy. Finally, to remedy the assessment inclination, the model is trained once again. When compared to conventional approaches, the suggested method comprehensively considers the impact of the imbalance in quantity and spatial distribution of samples. This model achieves higher global accuracy and greater corrective effect. Simulation findings on IEEE 39-bus and IEEE 145-bus systems are used to confirm the usefulness of the suggested strategy.
- Xiong L S, Liu X K, and Liu Y H. 2022. Modeling and stability issues of voltage-source converter-dominated power systems: a review. CSEE Journal of Power and Energy Systems 8, 6 (2022), 1530–1549. https://doi.org/10.17775/CSEEJPES.2020.03590Google ScholarCross Ref
- Wang H Y, Chen Q F, and Zhang B. 2020. Transient stability assessment combined model framework based on cost-sensitive method. IET generation, transmission and distribution 14, 12 (2020), 2256–2262. https://doi.org/10.1049/iet-gtd.2019.1562Google ScholarCross Ref
- Ahmad T, Zhu H Y, and Zhang D D. 2022. Energetics systems and artificial intelligence: applications of industry 4.0. Energy Reports 8 (2022), 334–361. https://doi.org/10.1016/j.egyr.2021.11.256Google ScholarCross Ref
- Lal M D and Varadarajan R. 2023. A review of machine learning approaches in synchrophasor technology. IEEE Access 11 (2023), 33520–33541. https://doi.org/10.1109/ACCESS.2023.3263547Google ScholarCross Ref
- Kesici M, Mohammadpourfard M, and Aygul K. 2023. Deep learning-based framework for real-time transient stability prediction under stealthy data integrity attacks. Electric Power Systems Research 221 (2023), 33520–33541. https://doi.org/10.1016/j.epsr.2023.109424Google ScholarCross Ref
- Wang H Y and Wu S J. 2022. Transient Stability Assessment with time-adaptive method based on spatial distribution. International Journal of Electrical Power and Energy Systems 143 (2022), 108464. https://doi.org/10.1016/j.ijepes.2022.108464Google ScholarCross Ref
- Du Y X, Hu Z J, and Wang F Z. 2021. A hierarchical power system transient stability assessment method considering sample imbalance. Energy Reports 7 (2021), 224–232. https://doi.org/10.1016/j.egyr.2021.08.052Google ScholarCross Ref
- Wang H Y and Ye W T. 2020. Transient stability evaluation model based on SSDAE with imbalanced correction. IET Generation Transmission and Distribution 14, 11 (2020), 2209–2216. https://doi.org/10.1049/iet-gtd.2019.1388Google ScholarCross Ref
- Huang J Y, Guan L, and Su Y S. 2020. Recurrent graph convolutional network-based multi-task transient stability assessment framework in power system. IEEE Access 8, 11 (2020), 93283–93296. https://doi.org/10.1109/ACCESS.2020.2991263Google ScholarCross Ref
- Zhang R F, Yao W, and Shi Z T. 2022. Recurrent graph convolutional network-based multi-task transient stability assessment framework in power system. International Journal of Electrical Power and Energy Systems 137 (2022), 107783. https://doi.org/10.1016/j.ijepes.2021.107783Google ScholarCross Ref
- Huang J Y, Guan L, and Su Y S. 2021. A topology adaptive high-speed transient stability assessment scheme based on multi-graph attention network with residual structure. International Journal of Electrical Power and Energy Systems 130 (2021), 106948. https://doi.org/10.1016/j.ijepes.2021.106948Google ScholarCross Ref
- Nandanoori S P and Kundu S Guan S. 2022. Graph neural network and koopman models for learning networked dynamics: a comparative study on power grid transients prediction. IEEE Access 10 (2022), 32337–32349. https://doi.org/10.1109/ACCESS.2022.3160710Google ScholarCross Ref
- Mei F, Li X, and Zheng J Y. 2022. A data-driven approach to state assessment of the converter valve based on oversampling and Shapley additive explanations. IET Generation, Transmission and Distribution 16, 8 (2022), 1607–1619. https://doi.org/10.1049/gtd2.12385Google ScholarCross Ref
- Koziarski M. 2020. Radial-based undersampling for imbalanced data classification. Pattern Recognition 102 (2020), 107262. https://doi.org/10.1016/j.patcog.2020.107262Google ScholarDigital Library
- Wang L, Han M, and Li X J. 2021. Review of classification methods on unbalanced data sets. IEEE Access 9 (2021), 64606–64628. https://doi.org/10.1109/ACCESS.2021.3074243Google ScholarCross Ref
- Zheng W J and Zhao H. 2020. Cost-sensitive hierarchical classification for imbalance classes. Applied Intelligence 50, 8 (2020), 2328–2338. https://doi.org/10.1007/s10489-019-01624-zGoogle ScholarDigital Library
- Galar M, Fernández A, and Barrenechea E. 2012. A Review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Transactions on Human-Machine Systems 42, 4 (2012), 463–484. https://doi.org/10.1109/TSMCC.2011.2161285Google ScholarDigital Library
- Zhang H B, Feng L P, and Zhang X H. 2022. Necessary conditions for convergence of CNNs and initialization of convolution kernels. Digital Signal Processing 123 (2022), 103397. https://doi.org/10.1016/j.dsp.2022.103397Google ScholarDigital Library
- Lin C H, Lin Y C, and Tang P W. 2022. ADMM-ADAM: a new inverse imaging framework blending the advantages of convex optimization and deep learning. IEEE Transactions on Geoscience and Remote Sensing 60 (2022), 1–16. https://doi.org/10.1109/TGRS.2021.3111007Google ScholarCross Ref
- Wan J W and Yang M. 2020. Survey on cost-sensitive learning method. Journal of Software 31 (2020), 113–136.Google Scholar
- Ullah A, Javaid N, and Javed M U. 2022. Adaptive data balancing method using stacking ensemble model and its application to non-technical loss detection in smart grids. IEEE Access 10 (2022), 133244–133255. https://doi.org/10.1109/ACCESS.2022.3230952Google ScholarCross Ref
- Duan F and Zhang S. 2022. An oversampling method of unbalanced data for mechanical fault diagnosis based on meanradius-smote. Sensors 22, 14 (2022), 5166. https://doi.org/10.3390/s22145166Google ScholarCross Ref
Index Terms
- Imbalanced correction method for power systems transient stability assessment based on the imbalance degree of image samples
Recommendations
An Improved SMOTE Imbalanced Data Classification Method Based on Support Degree
IIKI '14: Proceedings of the 2014 International Conference on Identification, Information and Knowledge in the Internet of ThingsImbalanced data-set Classification has become a hotspot problem in Data Mining. The essential assumption of the traditional classification algorithms is that the distribution of the classes is balanced, therefore the algorithms used in Imbalanced data-...
A new boundary-degree-based oversampling method for imbalanced data
AbstractImbalanced data constitute a significant challenge in practical applications, as standard classifiers are usually designed to work on data with balanced class label distributions. One of effective methods to solve the imbalanced problem is ...
Imbalanced data enhancement method based on improved DCGAN and its application
Machinery operates well under normal conditions in most cases; far fewer samples are collected in a fault state (minority samples) than in a normal state, resulting in an imbalance of samples. Common machine learning algorithms such as deep neural ...
Comments