AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home CSEE Journal of Power and Energy Systems Article
PDF (27.1 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Special Section Paper | Open Access

Constraint Learning-based Optimal Power Dispatch for Active Distribution Networks with Extremely Imbalanced Data

Yonghua Song1, Ge Chen2 ( ), Hongcai Zhang1
State Key Laboratory of Internet of Things for Smart City and Department of Electrical and Computer Engineering, University of Macau, Macao 999078, China
School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907 USA
Show Author Information

Abstract

Transition towards carbon-neutral power systems has necessitated optimization of power dispatch in active distribution networks (ADNs) to facilitate integration of distributed renewable generation. Due to unavailability of network topology and line impedance in many distribution networks, physical model-based methods may not be applicable to their operations. To tackle this challenge, some studies have proposed constraint learning, which replicates physical models by training a neural network to evaluate feasibility of a decision (i.e., whether a decision satisfies all critical constraints or not). To ensure accuracy of this trained neural network, training set should contain sufficient feasible and infeasible samples. However, since ADNs are mostly operated in a normal status, only very few historical samples are infeasible. Thus, the historical dataset is highly imbalanced, which poses a significant obstacle to neural network training. To address this issue, we propose an enhanced constraint learning method. First, it leverages constraint learning to train a neural network as surrogate of ADN's model. Then, it introduces Synthetic Minority Oversampling Technique to generate infeasible samples to mitigate imbalance of historical dataset. By incorporating historical and synthetic samples into the training set, we can significantly improve accuracy of neural network. Furthermore, we establish a trust region to constrain and thereafter enhance reliability of the solution. Simulations confirm the benefits of the proposed method in achieving desirable optimality and feasibility while maintaining low computational complexity.

Keywords

Deep learningdemand responsedistribution networksimbalanced dataoptimal power flow

References

[1]

P. J. Heptonstall and R. J. K. Gross, “A systematic review of the costs and impacts of integrating variable renewables into power grids,” Nature Energy, vol. 6, no. 1, pp. 72–83, Nov. 2021.
Google Scholar
[2]

X. D. Yang, C. B. Xu, H. B. He, W. Yao, J. Y. Wen, and Y. B. Zhang, “Flexibility provisions in active distribution networks with uncertainties,” IEEE Transactions on Sustainable Energy, vol. 12, no. 1, pp. 553–567, Jan. 2021.
Google Scholar
[3]

Y. F. Guo, Q. W. Wu, H. L. Gao, X. Y. Chen, J. Østergaard, and H. H. Xin, “MPC-based coordinated voltage regulation for distribution networks with distributed generation and energy storage system,” IEEE Transactions on Sustainable Energy, vol. 10, no. 4, pp. 1731–1739, Oct. 2019.
Crossref Google Scholar
[4]

K. Oikonomou, M. Parvania, and R. Khatami, “Deliverable energy flexibility scheduling for active distribution networks,” IEEE Transactions on Smart Grid, vol. 11, no. 1, pp. 655–664, Jan. 2020.
Crossref Google Scholar
[5]

G. Chen, H. C. Zhang, H. X. Hui, and Y. H. Song, “Fast wasserstein-distance- based distributionally robust chance-constrained power dispatch for multi-zone HVAC systems,” IEEE Transactions on Smart Grid, vol. 12, no. 5, pp. 4016–4028, Sep. 2021.
Crossref Google Scholar
[6]

W. Q. Sun, W. Liu, J. Zhang, and K. P. Tian, “Bi-level optimal operation model of mobile energy storage system in coupled transportation-power networks,” Journal of Modern Power Systems and Clean Energy, vol. 10, no. 6, pp. 1725–1737, Nov. 2022.
Crossref Google Scholar
[7]

Y. Y. Chai, L. Guo, C. S. Wang, Y. X. Liu, and Z. Z. Zhao, “Hierarchical distributed voltage optimization method for HV and MV distribution networks,” IEEE Transactions on Smart Grid, vol. 11, no. 2, pp. 968–980, Mar. 2020.
Crossref Google Scholar
[8]

Z. G. Li, W. J. Huang, J. H. Zheng, and Q. H. Wu, “Dispatchable region for active distribution networks using approximate second-order cone relaxation,” CSEE Journal of Power and Energy Systems, vol. 9, no. 6, pp. 1999–2007, Nov. 2023.
Google Scholar
[9]

J. W. Zhang, Y. Wang, Y. Weng, and N. Zhang, “Topology identification and line parameter estimation for non-PMU distribution network: a numerical method,” IEEE Transactions on Smart Grid, vol. 11, no. 5, pp. 4440–4453, Sep. 2020.
Crossref Google Scholar
[10]

L. Ma, L. F. Wang, and Z. X. Liu, “Topology identification of distribution networks using a split-EM based data-driven approach,” IEEE Transactions on Power Systems, vol. 37, no. 3, pp. 2019–2031, May 2022.
Google Scholar
[11]

V. L. Srinivas and J. Z. Wu, “Topology and parameter identification of distribution network using smart meter and µpmu measurements,” IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1–14, Jan. 2022.
Google Scholar
[12]

M. Khodayar, G. Y. Liu, J. H. Wang, and M. E. Khodayar, “Deep learning in power systems research: a review,” CSEE Journal of Power and Energy Systems, vol. 7, no. 2, pp. 209–220, Mar. 2021.
Google Scholar
[13]

M. S. Gao, J. Yu, Z. F. Yang, and J. B. Zhao, “A physics-guided graph convolution neural network for optimal power flow,” IEEE Transactions on Power Systems, 2023, doi: 10.1109/TPWRS.2023.3238377.
Crossref Google Scholar
[14]

R. Nellikkath and S. Chatzivasileiadis, “Physics-informed neural networks for AC optimal power flow,” Electric Power Systems Research, vol. 212, pp. 108412, Nov. 2022.
Crossref Google Scholar
[15]
F. Fioretto, T. W. K. Mak, and P. Van Hentenryck, “Predicting AC optimal power flows: combining deep learning and lagrangian dual methods,” in Proceedings of the 34th AAAI Conference on Artificial Intelligence, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, 2020, pp. 630–637.
[16]
S. Park and P. Van Hentenryck, “Self-supervised primal-dual learning for constrained optimization,” in Proceedings of the 37th AAAI Conference on Artificial Intelligence Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, Thirteenth Symposium on Educational Advances in Artificial Intelligence, 2023, pp. 4052–4060.
[17]
L. Zhang and B. S. Zhang, “Learning to solve the AC optimal power flow via a lagrangian approach,” in Proceedings of 2022 North American Power Symposium (NAPS), 2022, pp. 1–6.
[18]

M. Zhou, M. H. Chen, and S. H. Low, “DeepOPF-FT: one deep neural network for multiple AC-OPF problems with flexible topology,” IEEE Transactions on Power Systems, vol. 38, no. 1, pp. 964–967, Jan. 2023.
Crossref Google Scholar
[19]

S. Bahrami, Y. C. Chen, and V. W. S. Wong, “Deep reinforcement learning for demand response in distribution networks,” IEEE Transactions on Smart Grid, vol. 12, no. 2, pp. 1496–1506, Mar. 2021.
Crossref Google Scholar
[20]

H. P. Li and H. B. He, “Learning to operate distribution networks with safe deep reinforcement learning,” IEEE Transactions on Smart Grid, vol. 13, no. 3, pp. 1860–1872, May 2022.
Crossref Google Scholar
[21]
J. H. Wang, W. K. Xu, Y. J. Gu, W. B. Song, and T. C. Green, “Multi-agent reinforcement learning for active voltage control on power distribution networks,” in Proceedings of the 35th Conference on Neural Information Processing Systems, 2021, pp. 3271–3284.
[22]

Y. Xiang, Y. Lu, and J. Y. Liu, “Deep reinforcement learning based topology-aware voltage regulation of distribution networks with distributed energy storage,” Applied Energy, vol. 332, pp. 120510, Feb. 2023.
Crossref Google Scholar
[23]

D. Cao, J. B. Zhao, J. X. Hu, Y. S. Pei, Q. Huang, Z. Chen, and W. H. Hu, “Physics- informed graphical representation-enabled deep reinforcement learning for robust distribution system voltage control,” IEEE Transactions on Smart Grid, vol. 15, no. 1, pp. 233–246, Jan. 2024.
Crossref Google Scholar
[24]

A. Venzke and S. Chatzivasileiadis, “Verification of neural network behaviour: Formal guarantees for power system applications,” IEEE Transactions on Smart Grid, vol. 12, no. 1, pp. 383–397, Jan. 2021.
Crossref Google Scholar
[25]
A. Venzke, G. N. Qu, S. Low, and S. Chatzivasileiadis, “Learning optimal power flow: Worst-case guarantees for neural networks,” in Proceedings of 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), 2020, pp. 1–7.
[26]

G. Chen, H. C. Zhang, H. X. Hui, N. Y. Dai, and Y. H. Song, “Scheduling thermostatically controlled loads to provide regulation capacity based on a learning-based optimal power flow model,” IEEE Transactions on Sustainable Energy, vol. 12, no. 4, pp. 2459–2470, Oct. 2021.
Crossref Google Scholar
[27]

A. Kody, S. Chevalier, S. Chatzivasileiadis, and D. Molzahn, “Modeling the AC power flow equations with optimally compact neural networks: application to unit commitment,” Electric Power Systems Research, vol. 213, pp. 108282, Dec. 2022.
Crossref Google Scholar
[28]

G. Chen, H. C. Zhang, and Y. H. Song, “Efficient constraint learning for data- driven active distribution network operation,” IEEE Transactions on Power Systems, 2023, doi: 10.1109/TPWRS.2023.3251724.
Crossref Google Scholar
[29]

G. Chen, H. C. Zhang, H. X. Hui, and Y. H. Song, “Deep-quantile-regression- based surrogate model for joint chance-constrained optimal power flow with renewable generation,” IEEE Transactions on Sustainable Energy, vol. 14, no. 1, pp. 657–672, Jan. 2023.
Crossref Google Scholar
[30]

A. Alcántara and C. Ruiz, “On data-driven chance constraint learning for mixed-integer optimization problems,” Applied Mathematical Modelling, vol. 121, pp. 445–462, Sep. 2023.
Crossref Google Scholar
[31]

L. W. Sang, Y. L. Xu, and H. B. Sun, “Encoding carbon emission flow in energy management: a compact constraint learning approach,” IEEE Transactions on Sustainable Energy, vol. 15, no. 1, pp. 1–13, Jan. 2024.
Crossref Google Scholar
[32]

D. R. Morrison, S. H. Jacobson, J. J. Sauppe, and E. C. Sewell, “Branch- and-bound algorithms: a survey of recent advances in searching, branching, and pruning,” Discrete Optimization, vol. 19, pp. 79–102, Feb. 2016.
Crossref Google Scholar
[33]

F. X. Li, “Successful applications and future challenges of machine learning for power systems: A summary of recent activities by the IEEE WG on machine learning for power systems[what's popular],” IEEE Electrification Magazine, vol. 10, no. 4, pp. 90–96, Dec. 2022.
Crossref Google Scholar
[34]

D. Yang, P. Balaprakash, and S. Leyffer, “Modeling design and control problems involving neural network surrogates,” Computational Optimization and Applications, vol. 83, no. 3, pp. 759–800, Nov. 2022.
Crossref Google Scholar
[35]

X. Chen, E. Dall'Anese, C. H. Zhao, and N. Li, “Aggregate power flexibility in unbalanced distribution systems,” IEEE Transactions on Smart Grid, vol. 11, no. 1, pp. 258–269, Jan. 2020.
Crossref Google Scholar
[36]

M. Baran and F. F. Wu, “Optimal sizing of capacitors placed on a radial distribution system,” IEEE Transactions on Power Delivery, vol. 4, no. 1, pp. 735–743, Jan. 1989.
Crossref Google Scholar
[37]

A. Fernandez, S. Garcia, F. Herrera, and N. V. Chawla, “SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary,” Journal of Artificial Intelligence Research, vol. 61, no. 1, pp. 863–905, Jan. 2018.
Google Scholar
[38]

H. M. Nguyen, E. W. Cooper, and K. Kamei, “Borderline over-sampling for imbalanced data classification,” International Journal of Knowledge Engineering and Soft Data Paradigms, vol. 3, no. 1, pp. 4–21, Apr. 2011.
Crossref Google Scholar
[39]

M. Bicego and M. A. T. Figueiredo, “Soft clustering using weighted one- class support vector machines,” Pattern Recognition, vol. 42, no. 1, pp. 27–32, Jan. 2009.
Google Scholar
[40]

L. Thurner, A. Scheidler, F. Schäfer, J. H. Menke, J. Dollichon, F. Meier, S. Meinecke, and M. Braun, “Pandapower—an open-source python tool for convenient modeling, analysis, and optimization of electric power systems,” IEEE Transactions on Power Systems, vol. 33, no. 6, pp. 6510–6521, Nov. 2018.
Google Scholar
[41]

S. H. Low, “Convex relaxation of optimal power flow—part Ⅱ: exactness,” IEEE Transactions on Control of Network Systems, vol. 1, no. 2, pp. 177–189, Jun. 2014.
Google Scholar
CSEE Journal of Power and Energy Systems
Volume 10 Issue 1,
January 2024
Pages 51-65
DOI: 10.17775/CSEEJPES.2023.05970
Cite this article:
Song Y, Chen G, Zhang H. Constraint Learning-based Optimal Power Dispatch for Active Distribution Networks with Extremely Imbalanced Data. CSEE Journal of Power and Energy Systems, 2024, 10(1): 51-65. https://doi.org/10.17775/CSEEJPES.2023.05970

256

Views

9

Downloads

0

Crossref

0

Web of Science

1

Scopus

0

CSCD

Altmetrics
Received: 16 January 2023
Revised: 24 October 2023
Accepted: 30 November 2023
Published: 28 December 2023
© 2023 CSEE.

This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Return