Transmission Corridor Stability Margin Prediction Applying Data Mining Criteria and Machine Learning Algorithms
Article Sidebar
Main Article Content
Abstract
Voltage Stability refers to the ability of the system to maintain acceptable voltages in all busbars, considering normal operating conditions and after being subjected to a disturbance. The present work predicts the critical parameters of the system based on the P-V Curve determined by the Thévenin's Equivalent in a transmission corridor. A dataset is obtained via Monte Carlo simulations performed on the 39-bus test system model in PowerFactory controlled by Python. Given an operating condition, N simulations are performed to establish different system operating conditions under variations in the values of each of the system loads. From the obtained dataset, Data Mining is applied to train regression models based on artificial neural networks and support vector machines to predict the maximum power transfer condition. Afterwards, the MSE (Mean-squared error) is used to analyze the performance of the regression models. The proposed methodology can be applied in control centers to predict the maximum transfer power point of a congested transmission corridor. This prediction offers early warning signs in operations and might allow structuring criteria for security constrained dispatch in planning.
Downloads
Article Details
Aviso de Derechos de Autor
La Revista Técnica "energía" está bajo licencia internacional Creative Commons Reconocimiento-NoComercial 4.0.
References
[2] M. Larsson, C. Rehtanz y J. Bertsch, «Monitoring and operation of transmission corridors,» IEEE Power Tech Conference Proceedings, vol. 3, 2003.
[3] J. Cepeda y D. Colome, «Vulnerability Assesment of Electric Power Systems Through Identification and Ranking of Vulnerable Areas,» International Journal of Emerging Electric Power Systems, vol. 13, nº 1, 2006.
[4] «Neural Network models (supervised),» scikit learn, 2020. [En línea]. Available: https://scikit-learn.org/stable/modules/neural_networks_supervised.html.
[5] ICHI.PRO, «Funciones de activación en DNN,» 2021. [En línea].
[6] A. Ben-Hur y J. Weston, « A user’s guide to support vector machines,» Methods in Molecular Biology, vol. 609, pp. 223-239, 2010.
[7] R. Batuwita y V. Palade, «Class imbalance learning methods for support vector,» Imbalanced Learning: Foundations, Algorithms, Applications, pp. 83-100, 2013.
[8] S. Khalid, T. Khalil y S. Nasreen, «A Survey of Feature Selection and Feature Extraction Techniques in Machine Learning,» Science and Information Conference, 2014.
[9] A. Olalekan y S. Jain, «Feature Extraction: A Survey of the Types, Techniques, Applications,» International Conference on Signal Processing and Communication (ICSC), 2019.
[10] P. Prathusha y S. Jyothi, «Feature Extraction Methods: A Review,» International Journal of Innovative Research in Science, Engineering and Technology, vol. 6, nº 12, 2017.
[11] C. Syms, «Principal Components Analysis,» de Encyclopedia of Ecology, 2019, pp. 566-573.
[12] S. Brown, «Machine learning, explained,» 21 April 2021. [En línea].
[13] D. A. Pisner y D. M. Schnyer, «Support vector machine,» de Machine Learning, 2020, pp. 101-121.
[14] R. Bhaumik, L. M. Jenkins, J. R. Gowins, R. H. Jacobs, A. Barba y D. K. Bhaumik, «Multivariate pattern analysis strategies in detection of remitted major depressive disorder using resting state functional connectivity,» NeuroImage: Clinical, vol. 16, pp. 390-398, 2017.
[15] «Support Vector Machines,» scikit learn, 2020. [En línea]. Available: https://scikit-learn.org/stable/modules/svm.html#svm-regression.
[16] «SVM Hyperparameter Tuning using GridSearchCV,» Velocity Business, 2020. [En línea]. Available: https://www.vebuso.com/2020/03/svm-hyperparameter-tuning-using-gridsearchcv/
