The ANN Design Based On PMU Readings For Fault Location Detection

A fault diagnosis of an electric power transmission systems is sensitive to power outages and this has led to the introduction of several recycling techniques to find faults in transmission lines. The system-based measurement known as the Phasor Measurement Unit (PMU) is designed to monitor large systems over a large area as well as to regulate related applications. Therefore, this research was conducted to improve the PMU and Wide Area Protection (WAP) IEEE 9-bus and 14-bus systems. PMU is used to convert voltage and current waves into phasors, magnitude, and angles of energy and current to protect the fault site from a three-phase short circuit. All lines of the IEEE 9-bus and 14-bus systems are simulated with distance variations of 10%, 30%, 50%, 70%, and 90% and the results serve as a contribution to infer fault points in the system. In addition, an analysis of the PMU and Artificial Neural Networks (ANN) for inaccuracy, RMSE, MAE, and MSE values was also analyzed from three-phase faults on each networks of IEEE 9-bus & 14-bus tests, respectively. The simulation is validated through variations in the ANN data input consisting of current and voltage.

REFERENCES

[1] F. Zhou, “Architecture Design for Integrated Wide Area Protection and Control Systems,” J. Power Energy Eng., 2014.
[2] S. Talpur and T. T. Lie, “PMU based WAMC application in multi-modular HVDC based large scale solar system,” 2017 IEEE Innov. Smart Grid Technol. - Asia Smart Grid Smart Community, ISGT-Asia 2017, pp. 1–3, 2018, doi: 10.1109/ISGT-Asia.2017.8378460.
[3] X. Zhao, H. Zhou, D. Shi, H. Zhao, C. Jing, and C. Jones, “On-line PMU-based transmission line parameter identification,” CSEE J. Power Energy Syst., vol. 1, no. 2, pp. 68–74, 2015, doi: 10.17775/cseejpes.2015.00021.
[4] Z. Wu et al., “Optimal PMU Placement Considering Load Loss and Relaying in Distribution Networks,” IEEE Access, vol. 6, pp. 33645–33653, 2018, doi: 10.1109/ACCESS.2018.2841891.
[5] A. A. Zakri, M. W. Mustafa, H. Syaibi, and I. Sofimieari, “Monitoring Fault Diagnosis Based on Phasor Measurement Unit at Wide Area Systems,” IEEE Xplore, pp. 245–249, 2020, doi: 10.1109/cencon47160.2019.8974748.
[6] J. Reyes, R.A. and Guardado, “A PMU Model for Wide Area Protection in ATP / EMTP,” Trans. Power Deliv., pp. 1–6, 2015.
[7] D. Mallikarjuna, B., Reddy, M.J.B. and Mohanta, “A Case Study on Optimal Phasor Measurement Unit Placement for Emerging Indian National Smart Grid,” IEEE, pp. 1956–1960, 2016.
[8] V. Mohammed Mahdi, “Artificial Neural Network Based Algorithm for Early Prediction of Transient Stability Using Wide Area Measurements,” IEEE, pp. 1–5, 2017.
[9] H. S. Saeed Asgharigoavr, “Development of PMU-based backup wide area protection for power systems considering HIF detection,” Turkish J. Electr. Eng. Comput. Sci., 2017.
[10] J. W. Lee, “Fault area estimation using traveling wave for wide area Protection,” 2016.
[11] M. Qiu, H. Su, M. Chen, and Z. Ming, “Balance of Security Strength and Energy for a PMU Monitoring System in Smart Grid,” no. May, pp. 142–149, 2012.
[12] A. S. Dobackhshari, “Transmission Grid Fault Diagnosis by Wide Area Measurement System,” IEEE, pp. 1–7, 2013.
[13] M. Shahraeini and M. H. Javidi, “Wide Area Measurement Systems,” Adv. Top. Meas., pp. 304–321, 2012.
[14] A. Waqar, Z. Khurshid, J. Ahmad, M. Aamir, M. Yaqoob, and I. Alam, “Modeling and Simulation of Phasor Measurement Unit ( PMU ) for Early Fault Detection in Interconnected Two-Area Network,” 2018 1st Int. Conf. Power, Energy Smart Grid, pp. 1–6, 2018.
[15] K. Zimmerman and David Costello, “Impedance-Based Fault Location Experience,” SEL J. Reliab. Power, vol. 1, no. 1, pp. 1–27, 2005.
[16] H. Yin, “PMU data-based fault location techniques,” IEEE, 2010.
[17] S. Ben Hessine, Moez Ben., Saber, Accurate Fault Clasifier and Locator for EHV Transmission Lines Based on Artificial Neural Networks. 2014.
[18] A. A. Zakri and S. Tua, “Recurrent Neural Networks to Identify Fault in Transmission Line,” vol. 62, no. 03, pp. 733–742, 2020.
[19] A. Narwan, M. W. Mustafa, D. Y. Sukma, and M. E. Dame, “Backpropagation Neural Network Modeling for Fault Location in Transmission Line 150 kV,” Indones. J. Electr. Eng. Informatics, vol. 2, no. 1, pp. 1–12, 2014, doi: 10.11591/ijeei.v2i1.92.
[20] M. Raoofat, A. Mahmoodian, and A. Abunasri, “Fault location in transmission lines using neural network and wavelet transform,” 2015 Int. Congr. Electr. Ind. Autom. ICEIA 2015, pp. 1–6, 2015, doi: 10.1109/ICEIA.2015.7165837.
[21] A. A. Zakri, S. Darmawan, J. Usman, I. H. Rosma, and B. Ihsan, “Extract fault signal via DWT and penetration of SVM for fault classification at power system transmission,” Proc. - 2018 2nd Int. Conf. Electr. Eng. Informatics Towar. Most Effic. W. Mak. Deal. with Futur. Electr. Power Syst. Big Data Anal. ICon EEI 2018, no. October, pp. 191–196, 2018, doi: 10.1109/ICon-EEI.2018.8784320.
[22] E. K. Sai Sowmya Nagam, “Artificial Neural Network Based Fault Locator for Three Phase Transmission Line with STATCOM,” 2017.
[23] T. Chai and R. R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature,” Geosci. Model Dev., vol. 7, no. 3, pp. 1247–1250, Jun. 2014.