Estimasi Loss Of Life Tranformator Berdasarkan Loading dan Temperature Menggunakan LSTM di Gardu Induk 150KV Buduran

Anjar Novian Piyan

doi:10.59086/jti.v2i2.312

Authors

Anjar Novian Piyan -

DOI:

https://doi.org/10.59086/jti.v2i2.312

Keywords:

LSTM, Transformer

Abstract

Transformers are crucial equipment in substations, performing important tasks such as voltage transformation, current adjustment, and power quality maintenance. However, various factors over time, such as increased operating temperature, loading conditions, and maintenance schedules, can impact transformer performance and lead to a reduction in its lifespan. This research focuses on the effective and accurate estimation of age loss employ the Long Short Term Memory (LSTM) skill. LSTM means a deep neural network that processes sequential data and retains historical information. Data utilized in this research is sourced from transformer 6 at the Buduran 150 kV substation, including load and oil temperature data for 2021 and 2022. The performance of LSTM is assessed using Mean Squared Error (MSE) cum Root Mean Squared Error (RMSE). The estimation results demonstrate the favorable performance of the LSTM method, with an MSE error value of 0.0002 and an RMSE of 0.014. The projected age loss for 2023 is estimated to be 17.89% or 0.1789 pu.

References

Ardianto, D., & Kartini, U. T. (2019). Peramalan Daya Listrik Jangka Sangat Pendek Pembangkit Termal Berdasarkan Data Meteorologi Menggunakan Metode k-Nearest Neighbor-Artificial Neural …. Jurnal Teknik Elektro, 101–109. https://jurnalmahasiswa.unesa.ac.id/index.php/JTE/article/view/25792

Ayturan, Y. A., Ayturan, Z. C., & Altun, H. O. (2018). Air Pollution Modelling with Deep Learning: A Review. Int. J. of Environmental Pollution & Environmental Modelling, 1(3), 58–62. https://ijepem.com/doc/ijepem-18-03-01.pdf

Biçen, Y., Aras, F., & Kirkici, H. (2014). Lifetime estimation and monitoring of power transformer considering annual load factors. IEEE Transactions on Dielectrics and Electrical Insulation, 21(3), 1360–1367. https://doi.org/10.1109/TDEI.2014.6832284

Diahovchenko, I., Petrichenko, R., Petrichenko, L., Mahnitko, A., Korzh, P., Kolcun, M., & Čonka, Z. (2022). Mitigation of transformers’ loss of life in power distribution networks with high penetration of electric vehicles. Results in Engineering, 15(August). https://doi.org/10.1016/j.rineng.2022.100592

Hajeforosh, S. F., Khatun, A., & Bollen, M. (2022). Enhancing the hosting capacity of distribution transformers for using dynamic component rating. International Journal of Electrical Power and Energy Systems, 142(PA), 108130. https://doi.org/10.1016/j.ijepes.2022.108130

Ibrahim, K., Sharkawy, R. M., Temraz, H. K., & Salama, M. M. A. (2022). Reliability calculations based on an enhanced transformer life expectancy model. Ain Shams Engineering Journal, 13(4), 101661. https://doi.org/10.1016/j.asej.2021.101661

Kumar, K., Kumbhar, B. G., & Satsangi, S. (2018). Assessment of Effect of Load Models on Loss-of-Life Calculation of a Transformer Using a Point Estimation Method. Electric Power Components and Systems, 46(16–17), 1808–1819. https://doi.org/10.1080/15325008.2018.1511874

Liu, H., & Lang, B. (2019). Machine learning and deep learning methods for intrusion detection systems: A survey. Applied Sciences (Switzerland), 9(20). https://doi.org/10.3390/app9204396

Meshkatodd, M. R. (2008). Aging Study and Lifetime Estimation of Transformer Mineral Oil. American Journal of Engineering and Applied Sciences, 1(4), 384–388. https://doi.org/10.3844/ajeassp.2008.384.388

Ningrum, A. A., Syarif, I., Gunawan, A. I., Satriyanto, E., & Muchtar, R. (2021). Algoritma Deep Learning-LSTM untuk Memprediksi Umur Transformator. Jurnal Teknologi Informasi Dan Ilmu Komputer, 8(3), 539. https://doi.org/10.25126/jtiik.2021834587

Rommel, D. P., Di Maio, D., & Tinga, T. (2021). Transformer hot spot temperature prediction based on basic operator information. International Journal of Electrical Power and Energy Systems, 124(June 2020), 106340. https://doi.org/10.1016/j.ijepes.2020.106340

Roza, I., Ananda, Y., Siregar, L. A., Dharmawati, D., & Junaidi, J. (2021). Analysis of Age Transformer Due to Annual Load Growth in 20 kV Distribution Network. Journal of Renewable Energy, Electrical, and Computer Engineering, 1(1), 42. https://doi.org/10.29103/jreece.v1i1.3685

Science, N., Phenomena, C., Arunkumar, K. E., Kalaga, D. V, Mohan, C., Kumar, S., Kawaji, M., & Brenza, T. M. (2021). Chaos , Solitons and Fractals Forecasting of COVID-19 using deep layer Recurrent Neural Networks ( RNNs ) with Gated Recurrent Units ( GRUs ) and Long Short-Term Memory ( LSTM ) cells. Chaos, Solitons and Fractals: The Interdisciplinary Journal of Nonlinear Science, and Nonequilibrium and Complex Phenomena, 146, 110861. https://doi.org/10.1016/j.chaos.2021.110861

Setiawati, N. E., Munir, M., Wati, T., & Masfufiah, I. (2021). Prediksi Sisa Umur Transformator Menggunakan Metode Backpropagation. Cyclotron, 4(1), 1–6.

Shang, Y., Wu, W., Huai, X., Guo, J., Su, J., Liu, W., Huang, Y., & Zhou, L. (2021). Loss of life estimation of distribution transformers considering corrupted AMI data recovery and field verification. IEEE Transactions on Power Delivery, 36(1), 180–190. https://doi.org/10.1109/TPWRD.2020.2978809