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 (2.9 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

Parallel System Based Quantitative Assessment and Self-evolution for Artificial Intelligence of Active Power Corrective Control

Tianyun Zhang1, Jun Zhang1 ( ), Feiyue Wang2, Peidong Xu1, Tianlu Gao1, Haoran Zhang1, Ruiqi Si1
School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, Hubei, China
State Key Laboratory for Management and Control of Complex System, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
Show Author Information

Abstract

In artificial intelligence (AI) based-complex power system management and control technology, one of the urgent tasks is to evaluate AI intelligence and invent a way of autonomous intelligence evolution. However, there is, currently, nearly no standard technical framework for objective and quantitative intelligence evaluation. In this article, based on a parallel system framework, a method is established to objectively and quantitatively assess the intelligence level of an AI agent for active power corrective control of modern power systems, by resorting to human intelligence evaluation theories. On this basis, this article puts forward an AI self-evolution method based on intelligence assessment through embedding a quantitative intelligence assessment method into automated reinforcement learning (AutoRL) systems. A parallel system based quantitative assessment and self-evolution (PLASE) system for power grid corrective control AI is thereby constructed, taking Bayesian Optimization as the measure of AI evolution to fulfill autonomous evolution of AI under guidance of their intelligence assessment results. Experiment results exemplified in the power grid corrective control AI agent show the PLASE system can reliably and quantitatively assess the intelligence level of the power grid corrective control agent, and it could promote evolution of the power grid corrective control agent under guidance of intelligence assessment results, effectively, as well as intuitively improving its intelligence level through self-evolution.

Keywords

AI quantitative intelligence assessment and self-evolutionautomated reinforcement learningBayesian optimizationcorrective controlparallel system

References

[1]
F. Chollet. (2019 Nov.). On the measure of intelligence[Online]. Available: https://arxiv.org/abs/1911.01547.
[2]
A. Boggust, B. Hoover, A. Satyanarayan, and H. Strobelt, “Shared interest: measuring human-AI alignment to identify recurring patterns in model behavior,” in Proceedings of 2022 CHI Conference on Human Factors in Computing Systems, 2022, pp. 10, doi: 10.1145/3491102.3501965.
Crossref
[3]

J. Parker-Holder, R. Rajan, X. Y. Song, A. Biedenkapp, Y. J. Miao, T. Eimer, B. H. Zhang, V. Nguyen, R. Calandra, A. Faust, F. Hutter, and M. Lindauer, “Automated reinforcement learning (AutoRL): A survey and open problems,” Journal of Artificial Intelligence Research, vol. 74, pp. 517–568, Jun. 2007.
Crossref Google Scholar
[4]
J. D. Morales, P. N. Papadopoulos, and J. V. Milanović, “Feasibility of different corrective control options for the improvement of transient stability,” in 2017 IEEE Manchester PowerTech, 2017, pp. 1–6, doi: 10.1109/PTC.2017.7981015.
Crossref
[5]

R. Moreno, D. Pudjianto, and G. Strbac, “Transmission network investment with probabilistic security and corrective control,” IEEE Transactions on Power Systems, vol. 28, no. 4, pp. 3935–3944, Nov. 2013, doi: 10.1109/TPWRS.2013.2257885.
Crossref Google Scholar
[6]

L. Roald, S. Misra, T. Krause, and G. Andersson, “Corrective control to handle forecast uncertainty: a chance constrained optimal power flow,” IEEE Transactions on Power Systems, vol. 32, no. 2, pp. 1626–1637, Mar. 2017, doi: 10.1109/TPWRS.2016.2602805.
Crossref Google Scholar
[7]
A. Kelly, A. O’Sullivan, P. de Mars, and A. Marot. (2020, Mar.). Reinforcement learning for electricity network operation[Online]. Available: https://arxiv.org/abs/2003.07339.
[8]

P. D. Xu, J. J. Duan, J. Zhang, Y. Z. Pei, D. Shi, Z. W. Wang, X. Z. Dong, and Y. Z. Sun, “Active power correction strategies based on deep reinforcement learning—part Ⅰ: a simulation-driven solution for robustness,” CSEE Journal of Power and Energy Systems, vol. 8, no. 4, pp. 1122–1133, Jul. 2022, doi: 10.17775/CSEEJPES.2020.07090.
Crossref Google Scholar
[9]

S. Y. Chen, J. J. Duan, Y. Y. Bai, J. Zhang, D. Shi, Z. W. Wang, X. Z. Dong, and Y. Z. Sun, “Active power correction strategies based on deep reinforcement learning—part Ⅱ: a distributed solution for adaptability,” CSEE Journal of Power and Energy Systems, vol. 8, no. 4, pp. 1134–1144, Jul. 2022, doi: 10.17775/CSEEJPES.2020.07070.
Crossref Google Scholar
[10]
S. Y. Chen, Y. Y. Bai, and Z. Jun, “Dynamic load shedding strategy using distributional deep reinforcement learning in power system emergency control,” in 2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2), 2020, pp. 248–253, doi: 10.1109/EI250167.2020.9346749.
Crossref
[11]

M. S. Li, H. M. Zhang, T. Y. Ji, and Q. H. Wu, “Fault identification in power network based on deep reinforcement learning”, CSEE Journal of Power and Energy Systems, vol. 8, no. 3, pp. 721–731. May 2022, doi: 10.17775/CSEEJPES.2020.04520.
Crossref Google Scholar
[12]

J. M. L. Asensio, J. Peralta, R. Arrabales, M. G. Bedia, P. Cortez, and A. L. Peña, “Artificial intelligence approaches for the generation and assessment of believable human-like behaviour in virtual characters”, Expert Systems with Applications, vol. 41, no. 16, pp. 7281–7290, Nov. 2014.
Crossref Google Scholar
[13]
J. Insa-Cabrera, D. L. Dowe, S. España-Cubillo, M. Hernández-Lloreda, and J. Hernández-Orallo, “Comparing humans and AI agents,” in 4th International Conference on Artificial General Intelligence, 2011, pp. 122–132.
Crossref
[14]
M. J. Kim, K. J. Kim, S. Kim, and A. K. Dey, “Evaluation of StarCraft artificial intelligence competition bots by experienced human players,” in Proceedings of 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems, 2016, pp. 1915–1921, doi: 10.1145/2851581.2892305.
Crossref
[15]
T. Schaul, J. Togelius, J. Schmidhuber. (2011, Sep.). Measuring intelligence through games[Online]. Available: https://arxiv.org/abs/1109.1314.
[16]
T. Y. Zhang, T. L. Gao, P. D. Xu, and J. Zhang, “A review of AI and AI intelligence assessment,” in 2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2), 2020, pp. 3039–3044, doi: 10.1109/EI250167.2020.9347303.
Crossref
[17]

X. He, K. Y. Zhao, and X. W. Chu, “AutoML: a survey of the state-of-the-art”, Knowledge-Based Systems, vol. 212, pp. 106622, Jan. 2021, doi: 10.1016/j.knosys.2020.106622.
Crossref Google Scholar
[18]
M. Feurer, A. Klein, K. Eggensperger, J. T. Springenberg, M. Blum, and F. Hutter, “Methods for improving Bayesian optimization for AutoML,” presented at Workshop and Conference Proceedings 2015, 2015.
[19]
H. F. Jin, Q. Q. Song, and X. Hu, “Auto-Keras: an efficient neural architecture search system,” in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, pp. 1946–1956.
Crossref
[20]
J. Liang, E. Meyerson, B. Hodjat, D. Fink, K. Mutch, and R. Miikkulainen, “Evolutionary neural AutoML for deep learning,” in Proceedings of Genetic and Evolutionary Computation Conference, 2019, pp. 401–409, doi: 10.1145/3321707.3321721.
Crossref
[21]
R. S. Olson and J. H. Moore, “TPOT: A tree-based pipeline optimization tool for automating machine learning,” in Proceedings of the Workshop on Automatic Machine Learning, New York, USA, 2016, pp. 66–74.
[22]
E. Real, C. Liang, D. R. So, and Q. V. Le, “AutoML-Zero: evolving machine learning algorithms from scratch,” in Proceedings of the 37th International Conference on Machine Learning, 2020, pp. 742.
[23]
A. M. Alaa and M. van der Schaar. “AutoPrognosis: automated clinical prognostic modeling via Bayesian optimization with structured kernel learning,” in Proceedings of the 35th International Conference on Machine Learning, 2018, pp. 139–148.
[24]
Y. T. Chen, A. Huang, Z. Y. Wang, I. Antonoglou, J. Schrittwieser, D. Silver, and N. de Freitas. (2018, Dec.). Bayesian optimization in AlphaGo[Online]. Available: https://arxiv.org/abs/1812.06855.
[25]

J. M. Hernández-Lobato, M. A. Gelbart, R. P. Adams, M. W. Hoffman, and Z. Ghahramani, “A general framework for constrained Bayesian optimization using information-based search,” Journal of Machine Learning Research, vol. 17, no. 160, pp. 1–53, Sep. 2016.
Google Scholar
[26]
J. C. Lévesque, C. Gagné, and R. Sabourin, “Bayesian hyperparameter optimization for ensemble learning,” in Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence, 2016, pp. 437–446.
[27]
J. C. Lévesque, A. Durand, C. Gagné, and R. Sabourin, “Bayesian optimization for conditional hyperparameter spaces,” in 2017 International Joint Conference on Neural Networks (IJCNN), 2017, pp. 286–293, doi: 10.1109/IJCNN.2017.7965867.
[28]
Z. Wang, C. Gehring, P. Kohli, and S. Jegelka, “Batched large-scale Bayesian optimization in high-dimensional spaces,” in Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, 2018, pp. 745–754.
[29]

J. Zhang, P. D. Xu, and F. Y. Wang, “Parallel systems and digital twins: a data-driven mathematical representation and computational framework,” Acta Automatica Sinica, vol. 46, no. 7, pp. 1346–1356, Jul. 2020.
Google Scholar
[30]
P. I. Frazier. (2018, Jul.). A tutorial on Bayesian optimization[Online]. Available: https://arxiv.org/abs/1807.02811.
[31]

H. Morgan, “An analysis of Gardner’s theory of multiple intelligence,” Roeper Review, vol. 18, no. 4, pp. 263–269, Feb. 1996, doi: 10.1080/02783199609553756.
Crossref Google Scholar
[32]
Y. F. Feis, “Raven’s progressive matrices,” in Encyclopedia of Cross-Cultural School Psychology, C. S. Clauss-Ehlers, Ed. New York: Springer, 2010, pp. 787, doi: 10.1007/978-0-387-71799-9_344.
Crossref
[33]

S. S. Cai and X. D. Xue, “Artificial intelligence and human intelligence: a view on human-computer competition from the five-level theory of cognitive science,” Journal of Peking University (Philosophy and Social Sciences), vol. 53, no. 4, pp. 145–154, Jul. 2016.
Google Scholar
[34]
W. Lin and L. B. Shao. (2013, Dec.). Evaluation on the financial competitiveness of Chinese listed real estate companies based on entropy method[Online]. Available: https://arxiv.org/abs/1302.2493.
[35]
RTE-France. (2021). Grid2Op[Online]. Available: https://github.com/rte-france/Grid2Op.
[36]
A. Marot, B. Donnot, G. Dulac-Arnold, A. Kelly, A. O’Sullivan, J. Viebahn, M. Awad, I. Guyon, P. Panciatici, and C. Romero, “Learning to run a power network challenge: a retrospective analysis,” in Proceedings of NeurIPS 2020 Competition and Demonstration Track, 2021, pp. 112–132.
CSEE Journal of Power and Energy Systems
Volume 10 Issue 1,
January 2024
Pages 13-28
DOI: 10.17775/CSEEJPES.2023.00190
Cite this article:
Zhang T, Zhang J, Wang F, et al. Parallel System Based Quantitative Assessment and Self-evolution for Artificial Intelligence of Active Power Corrective Control. CSEE Journal of Power and Energy Systems, 2024, 10(1): 13-28. https://doi.org/10.17775/CSEEJPES.2023.00190

286

Views

21

Downloads

0

Crossref

2

Web of Science

3

Scopus

0

CSCD

Altmetrics
Received: 13 January 2023
Revised: 01 June 2023
Accepted: 03 August 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