EVALUATING OPERATIONAL CONDITION RELIABILITY THROUGH LOAD CONDITION FORECASTING
Keywords:
Transformer load forecasting, Feed Forward Neural Network (FNN), load distribution, operational reliability, Qibray substation, digital twin, load management, critical load thresholds.Abstract
This research investigates the operational reliability of transformers in the Qibray 35/6 substation by forecasting load conditions using Feed Forward Neural Networks (FNN). The study focuses on analyzing transformer load behavior over time and predicts when the load will exceed critical thresholds. Using primary data from 2021 to 2023, the study develops a forecasting algorithm based on FNN, which is used to predict when transformer loads exceed 85% of their nominal capacity. Results indicate that in the near future, the transformer load will enter a hazardous zone, reaching over 0.8 after 8 years and fully entering the critical range after 12 years. The study emphasizes the importance of load redistribution and the installation of new equipment to ensure the continuous and reliable operation of the electrical grid
References
ABB Group. (n.d.). Feeder Protection and Control REF620 IEC. ABB. Retrieved from https://new.abb.com/medium-voltage/digital-substations/protection-relays/feeder-protection-and-control/feeder-protection-and-control-ref620-iec
Siemens AG. (n.d.). SIPROTEC 5 Digital Protection Relays and Control. Siemens. Retrieved from https://www.siemens.com/global/en/products/energy/energy-automation-and-smart-grid/protection-relays-and-control/siprotec-5.html
Bhattar, C., & Chaudhari, M. (2023). Centralized energy management scheme for grid-connected DC microgrid. IEEE Systems Journal, PP(1-11). https://doi.org/10.1109/JSYST.2022.3231898
Cho, J., Yoon, Y., Son, Y., Kim, H., Ryu, H., & Jang, G. (2022). A study on load forecasting of distribution line based on ensemble learning for mid- to long-term distribution planning. Energies, 15(9), 2987. https://doi.org/10.3390/en15092987
Yan, S., & Hu, M. (2022). A multi-stage planning method for distribution networks based on ARIMA with error gradient sampling for source–load prediction. Sensors, 22(21), 8403. https://doi.org/10.3390/s22218403
Nayak, S., Chandan, M., Ambiger, P., & Patil, S. (2023). Development and implementation of transformer breather health monitoring system using IoT. Proceedings of the International Journal for Research in Applied Science & Engineering Technology. https://doi.org/10.22214/ijraset.2023.55632
General Electric Company. (n.d.). Multilin 750/760 Feeder Protection Systems. GE Grid Solutions. Retrieved from https://www.gegridsolutions.com/products/brochures/750760_gea31955.pdf
IEC. (2020). IEC 61850: Communication Networks and Systems for Power Utility Automation. International Electrotechnical Commission.
National Fire Protection Association (NFPA). (2021). NFPA 70E: Standard for Electrical Safety in the Workplace. NFPA.
Zhang, X., & Sun, Z. (2023). Application of improved probabilistic neural network (PNN) in transformer fault diagnosis. Processes, 11(2), 474. https://doi.org/10.3390/pr11020474
Wang, L., Fan, Y., Yang, X., Li, B., Li, W., Xue, J., Wang, H., Wang, G., & Guo, X. (2023). Exploration of transformer operation and maintenance technology and realization of transformer condition monitoring system. In Advances in Power and Energy Engineering (pp. 875-890). Springer. https://doi.org/10.1007/978-981-99-1439-5_75
Faqih, M., Binti Omar, M., & Ibrahim, R. (2023). Prediction of dry-low emission gas turbine operating range from emission concentration using semi-supervised learning. Sensors, 23(8), 3863. https://doi.org/10.3390/s23083863
Svozil, D., Kvasnicka, V., & Pospíchal, J. (1997). Introduction to multi-layer feed-forward neural networks. Chemometrics and Intelligent Laboratory Systems, 39(1), 43-62. https://doi.org/10.1016/S0169-7439(97)00061-0
Balanta, J. Z., Rivera, S., Romero, A. A., & Coria, G. (2023). Planning and optimizing the replacement strategies of power transformers: A literature review. Energies, 16(11), 4448. https://doi.org/10.3390/en16114448
