Probabilistic Available Transfer Capacity Calculation Using Broad Learning System and Gaussian Mixture Model-Based Clustering
DOI:
https://doi.org/10.52152/4414Keywords:
probabilistic available transfer capacity, broad learning system, Gaussian mixture model, clustering, large-scale power systemsAbstract
This paper proposes a probabilistic available transfer capacity (ATC) calculation method by integrating a broad learning system (BLS) with Gaussian mixture model-based clustering. The key feature of this method is the development of a surrogate model for ATC calculation based on BLS. First, the deterministic ATC problem is formulated as an optimal power flow problem aimed at maximizing transmission power. Second, the joint probability distribution of uncertain renewable power generation and loads is modeled based on Copula theory, which is a powerful tool to capture their correlations. Third, an improved Gaussian mixture model-based clustering method, which combines kernel density estimation with a Gaussian component reduction strategy, is employed to generate high-quality training samples. It overcomes numerical issues encountered when using GMM to generate a sufficiently large number of training samples, which are then used to construct the BLS-based surrogate model for ATC calculation. Finally, a large number of ATC samples are efficiently generated through Monte Carlo simulation on the BLS-based surrogate model, from which the probability distribution and statistical characteristics of the ATC are derived. The proposed method is validated on the 118-bus, 300-bus, and 1354-bus systems with integrated wind and photovoltaic generation, and compared with surrogate models based on polynomial chaos expansion (PCE) and Gaussian process regression (GPR). For the 118-bus and 300-bus systems, the proposed method reduces distribution function errors to less than 50% of those from PCE and GPR methods, while maintaining high computational efficiency similar to the GPR method. For the 1354-bus system, the PCE method fails to train the model due to memory constraints, and the GPR method produces large errors. In contrast, the proposed method remains accurate and efficient, demonstrating strong scalability for large-scale probabilistic ATC problems.
References
G. C. Ejebe, J. Tong, J. G. Waight, J. G. Frame, X. Wang, and W. F. Tinney, “Available transfer capability calculations,” IEEE Transactions on Power Systems, vol. 13, no. 4, pp. 1521–1527, Nov. 1998, doi: 10.1109/59.736300.
H. Zhang et al., “How does load-side re-electrification help carbon neutrality in energy systems: cost competitiveness analysis and life-cycle deduction,” Renewable and Sustainable Energy Reviews, vol. 187, p. 113745, Nov. 2023, doi: 10.1016/j.rser.2023.113745.
X. Kou and F. Li, “Interval optimization for available transfer capability evaluation considering wind power uncertainty,” IEEE Transactions on Sustainable Energy, vol. 11, no. 1, pp. 250–259, Jan. 2020, doi: 10.1109/TSTE.2018.2890125.
J. W. Stahlhut and G. T. Heydt, “Stochastic-algebraic calculation of available transfer capability,” IEEE Transactions on Power Systems, vol. 22, no. 2, pp. 616–623, May 2007, doi: 10.1109/TPWRS.2007.894865.
A. B. Rodrigues and M. G. Da Silva, “Probabilistic assessment of available transfer capability based on Monte Carlo method with sequential simulation,” IEEE Transactions on Power Systems, vol. 22, no. 1, pp. 484–492, Feb. 2007, doi: 10.1109/TPWRS.2006.887958.
A. B. Khairuddin, S. S. Ahmed, M. W. Mustafa, A. A. M. Zin, and H. Ahmad, “A novel method for ATC computations in a large-scale power system,” IEEE Transactions on Power Systems, vol. 19, no. 2, pp. 1150–1158, May 2004, doi: 10.1109/TPWRS.2004.825933.
Transmission Transfer Capability Task Force, “Available transfer capability definitions and determination,” North American Electric Reliability Council, Princeton, NJ, USA, Jun. 1996.
P. W. Pande, S. Kumar, and A. K. Sinha, “Total transfer capability calculation using modified repeated power flow method,” in 2015 Annual IEEE India Conference (INDICON), Dec. 2015, pp. 1–6. doi: 10.1109/INDICON.2015.7443378.
H.-D. Chiang, A. J. Flueck, K. S. Shah, and N. Balu, “CPFLOW: a practical tool for tracing power system steady-state stationary behavior due to load and generation variations,” IEEE Transactions on Power Systems, vol. 10, no. 2, pp. 623–634, May 1995, doi: 10.1109/59.387897.
G. Hamoud, “Assessment of available transfer capability of transmission systems,” IEEE Transactions on Power Systems, vol. 15, no. 1, pp. 27–32, Feb. 2000, doi: 10.1109/59.852097.
X. Wang, X. Wang, H. Sheng, and X. Lin, “A data-driven sparse polynomial chaos expansion method to assess probabilistic total transfer capability for power systems with renewables,” IEEE Transactions on Power Systems, vol. 36, no. 3, pp. 2573–2583, May 2021, doi: 10.1109/TPWRS.2020.3034520.
X. Sun, Z. Tian, Y. Rao, Z. Li, and P. Tricoli, “Probabilistic available transfer capability assessment in power systems with wind power integration,” IET Renewable Power Generation, vol. 14, no. 11, pp. 1912–1920, 2020, doi: 10.1049/iet-rpg.2019.1383.
B. Sudret, S. Marelli, and J. Wiart, “Surrogate models for uncertainty quantification: an overview,” in 2017 11th European Conference on Antennas and Propagation (EUCAP), Mar. 2017, pp. 793–797. doi: 10.23919/EuCAP.2017.7928679.
T. Crestaux, O. Le Maıˆtre, and J.-M. Martinez, “Polynomial chaos expansion for sensitivity analysis,” Reliability Engineering & System Safety, vol. 94, no. 7, pp. 1161–1172, Jul. 2009, doi: 10.1016/j.ress.2008.10.008.
E. Schulz, M. Speekenbrink, and A. Krause, “A tutorial on Gaussian process regression: modelling, exploring, and exploiting functions,” Journal of Mathematical Psychology, vol. 85, pp. 1–16, Aug. 2018, doi: 10.1016/j.jmp.2018.03.001.
S. Marelli and B. Sudret, “UQLab: a framework for uncertainty quantification in MATLAB,” presented at the 2nd International Conference on Vulnerability and Risk Analysis and Management, Liverpool, U.K., 2014, pp. 2554–2563. doi: 10.1061/9780784413609.257.
A. Wächter and L. T. Biegler, “On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming,” Math. Program., vol. 106, no. 1, pp. 25–57, Mar. 2006, doi: 10.1007/s10107-004-0559-y.
H. Sheng and X. Wang, “Probabilistic power flow calculation using non-intrusive low-rank approximation method,” IEEE Transactions on Power Systems, vol. 34, no. 4, pp. 3014–3025, 2019, doi: 10.1109/TPWRS.2019.2896219.
C. L. P. Chen and Z. Liu, “Broad learning system: an effective and efficient incremental learning system without the need for deep architecture,” IEEE Trans. Neural Netw. Learning Syst., vol. 29, no. 1, pp. 10–24, Jan. 2018, doi: 10.1109/TNNLS.2017.2716952.
F. Chu, T. Liang, C. L. P. Chen, X. Wang, and X. Ma, “Weighted broad learning system and its application in nonlinear industrial process modeling,” IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 8, pp. 3017–3031, Aug. 2020, doi: 10.1109/TNNLS.2019.2935033.
X. Gong, T. Zhang, C. L. P. Chen, and Z. Liu, “Research review for broad learning system: algorithms, theory, and applications,” IEEE Transactions on Cybernetics, vol. 52, no. 9, pp. 8922–8950, Sep. 2022, doi: 10.1109/TCYB.2021.3061094.
N. Zhou, X. Xu, Z. Yan, and M. Shahidehpour, “Spatio-temporal probabilistic forecasting of photovoltaic power based on monotone broad learning system and copula theory,” IEEE Trans. Sustain. Energy, vol. 13, no. 4, pp. 1874–1885, Oct. 2022, doi: 10.1109/TSTE.2022.3174012.
M. Gong, J. Liu, H. Li, Q. Cai, and L. Su, “A multiobjective sparse feature learning model for deep neural networks,” IEEE Transactions on Neural Networks and Learning Systems, vol. 26, no. 12, pp. 3263–3277, Dec. 2015, doi: 10.1109/TNNLS.2015.2469673.
L. Yu, T. Yang, and A. B. Chan, “Density-preserving hierarchical EM algorithm: simplifying Gaussian mixture models for approximate inference,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 6, pp. 1323–1337, 2019, doi: 10.1109/TPAMI.2018.2845371.
Y. Gao, X. Xu, Z. Yan, and M. Shahidehpour, “Gaussian mixture model for multivariate wind power based on kernel density estimation and component number reduction,” IEEE Transactions on Sustainable Energy, vol. 13, no. 3, pp. 1853–1856, Jul. 2022, doi: 10.1109/TSTE.2022.3159391.
R. D. Zimmerman, C. E. Murillo-Sánchez, and R. J. Thomas, “MATPOWER: steady-state operations, planning, and analysis tools for power systems research and education,” IEEE Transactions on Power Systems, vol. 26, no. 1, pp. 12–19, Feb. 2011, doi: 10.1109/TPWRS.2010.2051168.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Xiongguang Zhao, Xu Ling, Jianghui Xi, Weigang Jin, Ying Wang, Peng Yuan, Xiaodong Yu (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
