Power System Operation Stability Assessment Method Based on Deep Convolutional Neural Network

Jinman Luo; Yuqing Li; Qile Wang; Liyuan Liu

doi:10.4108/ew.7572

Authors

Jinman Luo Dongguan Power Supply Bureau of Guangdong Power Grid
Yuqing Li Dongguan Power Supply Bureau of Guangdong Power Grid
Qile Wang Dongguan Power Supply Bureau of Guangdong Power Grid
Liyuan Liu Dongguan Power Supply Bureau of Guangdong Power Grid

DOI:

https://doi.org/10.4108/ew.7572

Keywords:

Convolutional neural network, power system, stability, Deep learning

Abstract

INTRODUCTION: For the assessment of power system stability, a power system assessment method based on a deep convolutional neural network is studied.

OBJECTIVES: Through the improvement of the integrated convolutional neural network (CNN) network model, the impact of insufficient transient stability assessment caused by sample misjudgment and sample omission is effectively reduced.

METHODS: We adopt the hierarchical real-time prediction model to evaluate the stability and instability of the determined stable samples and unstable samples, thereby improving the timeliness and accuracy of transient evaluation.

RESULTS: Through experimental comparison, the integrated CNN network model in this study has obvious advantages in accuracy compared with the single CNN network. Compared with other algorithm reference models, this model has a higher evaluation accuracy of 98.39%, far exceeding other comparison models.

CONCLUSION: By further evaluating the model’s accuracy, it is proved that the model can provide an effective reference for the follow-up power system stability prevention and has important application value.

Downloads

References

[1] Cui Z, Chang X, Xue Y, et al. Distributed peer-to-peer electricity-heat-carbon trading for multi-energy virtual power plants considering copula-CVaR theory and trading preference[J].International Journal of Electrical Power and Energy Systems, 2024,162110231-110231.

[2] Hossain S M, Shafiullah M, Shahriar S M, et al. Improvement of low-frequency oscillation damping in power systems using a deep learning technique[J].Engineering Applications of Artificial Intelligence,2024,137(PB):109176-109176.

[3] Dassios I, Vaca A, Milano F. On hybrid dynamical systems of differential–difference equations[J]. Chaos, Solitons and Fractals: the interdisciplinary journal of Nonlinear Science, and Nonequilibrium and Complex Phenomena, 2024,187115431-115431.

[4] L P Zhu, C Lu, Z Y Dong, et al. Imbalance learning machine-based power system short-term voltage stability assessment[JJ. IEEE Transactions on Industrial Informatics, 2017,13(5): 2533-2543.

[5] Wang S, Chen H. A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network[J]. Applied Energy, 2019, 235:1126-1140.

[6] Zhu Qiaomu, Dang Jie, Chen Jinfu, et al. Power system transient stability assessment method based on deep confidence network [J]. Proceedings of the Csee, 2018, 38 (3): 753-754.

[7] Li Baoqin，Wu Junyong，Liangliang Hao, et al. Anti-jitter and Refined Power System Transient Stability Assessment Based on Long-short Term Memory Network [J]．IEEE Access，2020，8， 35231-35244．

[8] Purwins H， Li B， Virtanen T， et al．Deep Learning for Audio Signal Processing[J]． IEEE Journal of Selected Topics in Signal Processing，2019，13(2)：206-219．

[9] Mahish P, Pradhan K A, Mishra S. Mitigating the impact of false data in wide area control of power systems[J]. Electric Power Systems Research, 2024,236110912-110912.

[10] Wang X, Ji Y, Sun Z , et al. Improving cyber-physical-power system stability through hardware-in-loop co-simulation platform for real-time cyber attack analysis[J]. Frontiers in Energy Research,2024,121402566-1402566.

[11] Dedović M M , Avdaković S , Musić M , et al. Enhancing power system stability with adaptive under frequency load shedding using synchrophasor measurements and empirical mode decomposition[J]. International Journal of Electrical Power and Energy Systems, 2024,160110133-110133.

[12] Tang M, Li R, Dai X, et al. New Electric Power System Stability Evaluation Based on Game Theory Combination Weighting and Improved Cloud Model[J]. Sustainability, 2024,16(14):6189-6189.

[13] Sancho J, Escobar F, Valverde G. Revisiting the tripping logic of the DERA model for power system stability studies[J]. Electric Power Systems Research, 2024,235110764-110764.

[14] Franke M, Guironnet A, Cardozo C. Comparing IEC and WECC generic dynamic models for type 4 wind turbines[J]. Electric Power Systems Research, 2024,235110806-110806.

[15] Utrilla C, Tafti D H, Kumaresan A, et al. A simplified model of flexible power point tracking algorithms in double-stage photovoltaic systems[J].Mathematics and Computers in Simulation,2024,224(PA):20-33.