ارائه یک شاخص تشخیص جزیره‌ای شدن برای شبکه توزیع با منابع تولید پراکنده دیزلی و اینورتری
محورهای موضوعی : مهندسی برق و کامپیوتر
امیرحسین علیزاده
1
,
سید فریبرز زارعی
2
1 - دانشکده مهندسی برق و کامپیوتر، دانشگاه صنعتی قم، قم، ايران
2 - دانشکده مهندسی برق و کامپیوتر، دانشگاه صنعتی قم، قم، ايران
کلید واژه: جزیره‌ای شدن, تشخیص جزیره‌ای شدن, الکترونیک قدرت برای سیستم‌های انرژی تجدیدپذیر, D CNN- 1,
چکیده مقاله :
در این مقاله، یک شاخص مبتنی بر مؤلفه‌های توالی صفر پیشنهاد شده که می‌تواند به عنوان تک‌شاخص برای تشخیص جزیرهایشدن استفاده شود. شاخص پیشنهادی نتایج مطلوبی به میزان 97.84% را با استفاده از یک مدل تنظیم آستانه ساده نشان می‌دهد. علاوه بر این، شاخص پیشنهادی می‌تواند در روش‌های مبتنی بر هوش مصنوعی برای دستیابی به دقت‌های بالاتر استفاده شود. بر اساس نتایج به‌دست‌آمده، استفاده از شاخص پیشنهادی به عنوان تک‌شاخص در یک مدل شبکه عصبی کانولوشنی یک‌بعدی (D CNN- 1) نتیجه رقابتی 99.78% را به دست می‌دهد. این نتیجه در مقایسه با نتایج روش‌های پیشرفته‌تر هوش مصنوعی مانند شبکه‌های عصبی حافظه کوتاه‌مدت پیشرفته (LSTM) که از تعداد بیشتری ویژگی مختلف استفاده می‌کنند قابل توجه است. جمع‌آوری داده‌ها برای آزمایش‌ها شامل شرایط مختلف جزیره‌ای/ غیرجزیرهای است؛ مانند جزیرهایشدن تحت شرایط بارگذاری مختلف و ضرایب توان متفاوت، جزیرهایشدن تحت مقادیر مختلف ضریب کیفیت و غیر جزیرهایشدن شامل روشن/ خاموش‌کردن بارهای بزرگ، روشن/ خاموش‌کردن بانک‌های خازنی و اعمال انواع خطاهای اتصال کوتاه در مکان‌های مختلف با مقاومت‌های اتصال کوتاه متفاوت می‌شود. نتایج همه آزمایش‌ها نشان از برتری روش و شاخص پیشنهادی است.
This paper proposes an index based on zero-sequence components that serves as a single indicator for islanding detection. The proposed index demonstrates satisfactory performance, achieving an accuracy of 97.84% using a simple threshold adjustment model. Additionally, this index can be integrated into artificial intelligence-based methods to enhance accuracy further. The results indicate that utilizing the proposed index as a single indicator within a one-dimensional convolutional neural network (1D-CNN) model yields a competitive accuracy of 99.78%. This outcome is noteworthy when compared to more advanced artificial intelligence methods, such as long short-term memory (LSTM) neural networks, which rely on a larger set of features. The data collection for testing encompasses various islanding and non-islanding conditions, including islanding under different loading conditions and power factors, as well as varying quality factor values. Non-islanding scenarios include the activation and deactivation of large loads and capacitor banks, along with the application of various short-circuit faults at different locations and resistances. The results from all tests demonstrate the superiority of the proposed method and index.
[1] D. Gielen, et al., "The role of renewable energy in the global energy transformation," Energy Strategy Reviews, vol. 24, pp. 38-50, Apr. 2019.
[2] S. F. Zarei, H. Mokhtari, and M. A. Ghasemi, "Enhanced control of grid forming VSCs in a micro-grid system under unbalanced conditions," in Proc. 9th Annual Power Electronics, Drives Systems and Technologies Conf., pp. 380-385, Tehran, Iran, 13-15 Feb. 2018.
[3] J. L. Holechek, H. M. Geli, M. N. Sawalhah, and R. Valdez, "A global assessment: can renewable energy replace fossil fuels by 2050?" Sustainability, vol. 14, no. 8, Article ID: 4792, Apr-2. 2022.
[4] M. Mishra, S. Chandak, and P. K. Rout, "Taxonomy of islanding detection techniques for distributed generation in microgrid," Renewable Energy Focus, vol. 31, pp. 9-30, Dec. 2019.
[5] S. F. Zarei, H. Mokhtari, and F. Blaabjerg, "Fault detection and protection strategy for islanded inverter-based microgrids," IEEE J. of Emerging and Selected Topics in Power Electronics, vol. 9, no. 1, pp. 472-484, Feb. 2019.
[6] P. Fernández‐Porras, M. Panteli, and J. Quirós‐Tortós, "Intentional controlled islanding: when to island for power system blackout prevention," IET Generation, Transmission & Distribution, vol. 12, no. 14, pp. 3542-3549, Aug. 2018.
[7] M. S. Kim, et al., "Comprehensive review of islanding detection methods for distributed generation systems," Energies, vol. 12, no. 5, Article ID: 0837, Mar. 2019.
[8] M. Alobaid and A. G. Abo-Khalil, "A comprehensive review and assessment of islanding detection techniques for PV systems," International J. of Thermofluids, vol. 18, Article ID: 100353, May 2023.
[9] S. F. Zarei and M. Parniani, "A comprehensive digital protection scheme for low-voltage microgrids with inverter-based and conventional distributed generations," IEEE Trans. on Power Delivery, vol. 32, no. 1, pp. 441-452, Feb. 2016.
[10] R. A. Mastromauro, "Grid synchronization and islanding detection methods for single-stage photovoltaic systems," Energies, vol. 13, no. 13, Article ID: 3382, Jul.-12020.
[11] B. K. Chaitanya, A. Yadav, and M. Pazoki, "An advanced signal decomposition technique for islanding detection in DG system," IEEE Systems J., vol. 15, no. 3, pp. 3220-3229, Sept. 2021.
[12] A. A. Abdelsalam, A. A. Salem, E. S. Oda, and A. A. Eldesouky, "Islanding detection of microgrid incorporating inverter based DGs using long short-term memory network," IEEE Access, vol. 8, pp. 106471-106486, 2020.
[13] N. B. Hartmann, R. C. dos Santos, A. P. Grilo, and J. C. M. Vieira, "Hardware implementation and real-time evaluation of an ANN-based algorithm for anti-islanding protection of distributed generators," IEEE Trans. on Industrial Electronics, vol. 65, no. 6, pp. 5051-5059, Jun. 2018.
[14] S. R. Samantaray, B. C. Babu, and P. K. Dash, "Probabilistic neural network based islanding detection in distributed generation," Electric Power Components and Systems, vol. 39, no. 3, pp. 191-203, Jan. 2011.
[15] S. Adari and B. R. Bhalja, "Islanding detection of distributed generation using random forest technique," in Proc. IEEE 6th Int. Conf. on Power Systems, 6 pp., New Delhi, India, 4-6 Mar. 2016.
[16] A. H. Alizadeh, S. F. Zarei, and M. H. Shateri, "A sequence component-based feature for passive and artificial-intelligence-based islanding detection," in Proc. The Power Electronics and Drives: Systems and Technologies Conf., 7 pp., Tehran, Iran, 30 Jan.-1 Feb. 2024. [Online]. Available: https://sid.ir/paper/1132488/en
[17] Y. Yang, Elements of Information Theory, Ed: Taylor & Francis, 2008.
[18] T. Saito and M. Rehmsmeier, "The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets," PLOS One, vol. 10, no. 3, Article ID: e0118432, 2015.
[19] M. Pourmirasghariyan, S. F. Zarei, M. Hamzeh, and F. Blaabjerg, "A power routing-based fault detection strategy for multi-terminal VSC-HVDC grids," IEEE Trans. on Power Delivery, vol. 38, no. 1, pp. 528-540, Feb. 2022.
[20] Y. LeCun and Y. Bengio, "Convolutional networks for images, speech, and time series," In M. C. Arbib (Ed.), The Handbook of Brain Theory and Neural Networks, Cambridge: MIT Press, 1998.
[21] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors," Nature, vol. 323, pp. 533-536, 1986. [22] K. P. Murphy, Probabilistic Machine Learning: An Introduction, MIT Press, 2022.
[23] Y. Xia, F. Yu, X. Xiong, Q. Huang, and Q. Zhou, "A novel microgrid islanding detection algorithm based on a multi-feature improved LSTM," Energies, vol. 15, no. 8, Article ID: 2810, Apr.-2 2022.
[24] N. A. Larik, M. F. Tahir, Z. S. Elbarbary, M. Z. Yousaf, and M. A. Khan, "A comprehensive literature review of conventional and modern islanding detection methods," Energy Strategy Reviews, vol. 44, Article ID: pp. 101007, Nov. 2022.
