Abstract: Due to nonlinear grid behaviour, varying operation condition and availability of efficient settlement process. Traditional power loss allocation models often utilizes fixed percentage based methods and is incapable of capturing inherent loss contribution of market players which lead to disparity in the cost to be assigned and market efficiency. This study aims at an in-depth study that utilizes Support Vector machine based data driven approach to efficiently allocate, forecast and minimize the power losses that occurs in a deregulated power market. The network connectivity, market and equipment related data and the real-time network measurements are utilized along with past power losses data for developing the model that mimics the nonlinear loss behavior and allocate losses based on market...
Keywords: Support Vector Machine, Deregulated Power Market, Loss Allocation, Artificial Intelligence, Transmission Loss Prediction.
[1] M. S. Seheda, O. S. Beshta, P. F. Gogolyuk, Y. V. Blyznak, R. D. Dychkovskyi, and A. Smoliński, “Mathematical model for the management of wave processes in three-winding transformers with consideration of the main magnetic flux in mining industry,” Journal of Sustainable Mining, vol. 23, pp. 20–39, 2024, doi: 10.46873/2300-3960.1390.
[2] I. Bashynska, L. Niekrasova, D. Ivliev, M. Dudek, V. Kosenkov, and A. Yakimets, “Justification for transitioning equipment to direct current for smart small enterprises with sustainable solar power autonomy,” in Proc. IEEE KhPI Week on Advanced Technology, Oct. 7–11, 2024, pp. 1–6, doi: 10.1109/KhPIWeek64252.2024.10655201.
[3] O. S. Beshta, O. O. Beshta, and S. S. Khudolii, “Electric vehicle energy consumption taking into account the route topology,” Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, no. 2, pp. 104–112, 2024, doi: 10.33271/nvngu/2024-2/104.
[4] Z. A. Styczynski, K. Rudion, O. Orths, and K. Strunz, “Design of benchmark of medium voltage distribution network for investigation of DG integration,” in Proc. IEEE Power Engineering Society General Meeting, 2022.
[5] L. J. Lepolesa, S. Achari, and L. Cheng, “Electricity theft detection in smart grids based on deep neural network,” IEEE Access, vol. 10, pp. 39638–39655, 2022, doi: 10.1109/ACCESS.2022.3163579.