The Use of AutoEncoders as a Measurements Generator in Distribution System

• Luiz Phillip Q. da Silva UFF
• Julio Cesar S. de Souza UFF
• Milton Brown Do C. Filho UFF

DOI: https://doi.org/10.5753/semish.2022.223145

Abstract

The success of the automation and control functions envisaged for smart distribution grids depends on a reliable real-time distribution system monitoring. This task is performed by the distribution system state estimator, responsible for processing a set of measurements obtained through the data acquisition system. The smart grid advanced metering infrastructure (AMI) can collect voltage and power measurements readings in a regular basis, which may complement the few SCADA measurements usually available in distribution networks and benefit the state estimation process. However, due to bottlenecks in the communications infrastructure, the refresh rates of SCADA and AMI measurements are not the same. This work presents a methodology that employs an AutoEncoder to generate AMI pseudomeasurements to complement SCADA measurements when only the latter are available. Simulations carried out with a 34-bus distribution system illustrate the proposed methodology and the obtained results confirm its potential to generate pseudomeasurements.

Keywords: Smart grids, State estimation, Autoencoder, Redundancy, Real-time monitoring

References

Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019). Optuna: A nextgeneration hyperparameter optimization framework. In Proceedings of the 25rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.

Bergstra, J., Bardenet, R., Bengio, Y., and Kégl, B. (2011). Algorithms for hyperparameter optimization. In Shawe-Taylor, J., Zemel, R., Bartlett, P., Pereira, F., and Weinberger, K. Q., editors, Advances in Neural Information Processing Systems, volume 24. Curran Associates, Inc.

Dahale, S., Karimi, H. S., Lai, K., and Natarajan, B. (2020). Sparsity based approaches for distribution grid state estimation-a comparative study. IEEE Access, 8:198317–198327.

Dehghanpour, K., Yuan, Y., Wang, Z., and Bu, F. (2019). A game-theoretic data-driven approach for pseudo-measurement generation in distribution system state estimation. IEEE Transactions on Smart Grid, 10(6):5942–5951.

He, Z., Hong, K., Zhou, J., Liang, D., Wang, Y., and Liu, Q. (2022). Deep frequencyrecurrent priors for inverse imaging reconstruction. Signal Processing, 190:108320.

Hinton, G. E. and Zemel, R. (1994). Autoencoders, minimum description length and helmholtz free energy. In Cowan, J., Tesauro, G., and Alspector, J., editors, Advances in Neural Information Processing Systems, volume 6. Morgan-Kaufmann.

Huang, S.-C., Lu, C.-N., and Lo, Y.-L. (2015). Evaluation of ami and scada data synergy for distribution feeder modeling. IEEE Transactions on Smart Grid, 6(4):1639–1647.

Jabbar, A., Li, X., and Omar, B. (2020). A survey on generative adversarial networks: Variants, applications, and training.

Ko, J. U., Na, K., Oh, J.-S., Kim, J., and Youn, B. D. (2021). A new auto-encoder-based dynamic threshold to reduce false alarm rates for anomaly detection of steam turbines. Expert Systems with Applications, page 116094.

Krstulovic, J., Miranda, V., Costa, A. J. S., and Pereira, J. (2013). Towards an autoassociative topology state estimator. IEEE transactions on power systems, 28(3):3311–3318.

Lefebvre, S., Prévost, J., and Lenoir, L. (2014). Distribution state estimation: A necessary requirement for the smart grid. In 2014 IEEE PES General Meeting — Conference Exposition, pages 1–5.

Li, H., Lai, L., and Zhang, W. (2011). Communication requirement for reliable and secure state estimation and control in smart grid. IEEE Transactions on Smart Grid, 2(3):476–486.

Liu, W., Wang, Z., Liu, X., Zeng, N., Liu, Y., and Alsaadi, F. E. (2017). A survey of deep neural network architectures and their applications. Neurocomputing, 234:11–26.

Mestav, K. R., Luengo-Rozas, J., and Tong, L. (2019). Bayesian state estimation for IEEE Transactions on Power unobservable distribution systems via deep learning. Systems, 34(6):4910–4920.

Miranda, V., Krstulovic, J., Keko, H., Moreira, C., and Pereira, J. (2011). Reconstructing missing data in state estimation with autoencoders. IEEE Transactions on power systems, 27(2):604–611.

Singh, R., Pal, B., and Jabr, R. (2009). Choice of estimator for distribution system state estimation. IET generation, transmission & distribution, 3(7):666–678.

Soares, W., de Souza, J. C. S., Do Coutto Filho, M. B., and Augusto, A. A. (2019). Distribution system state estimation with real-time pseudo-measurements. In 2019 IEEE PES Innovative Smart Grid Technologies Conference-Latin America (ISGT Latin America), pages 1–5. IEEE.

Vijayalakshmi, G. and Shanthakumar, M. (2019). Image restoration on fusion of mammographs and mri breast images using dual tree complex wavelet transform. International Journal of Advanced Science and Technology, 28(17):842–857. cited By 0.

Xu, W., Zhang, J., Li, X., Yuan, S., Ma, G., Xue, Z., Jing, X., and Cao, J. (2022). Intelligent denoise laser ultrasonic imaging for inspection of selective laser melting components with rough surface. NDT & E International, 125:102548.

Yilmaz, C. S., Yilmaz, V., and Gungor, O. (2022). A theoretical and practical survey of image fusion methods for multispectral pansharpening. Information Fusion, 79:1–43.

Zhang, X., Mu, J., Zhang, X., Liu, H., Zong, L., and Li, Y. (2022). Deep anomaly detection with self-supervised learning and adversarial training. Pattern Recognition, 121:108234.

Zhao, J., Huang, C., Mili, L., Zhang, Y., and Min, L. (2020). Robust medium-voltage distribution system state estimation using multi-source data. In 2020 IEEE Power Energy Society Innovative Smart Grid Technologies Conference (ISGT), pages 1–5.