Explainable artificial intelligence in electrical systems: methods, applications and emerging challenges
Keywords:
explainable artificial intelligence, power systems, interpretability, transparency, decision supportAbstract
Introduction: Artificial intelligence is increasingly used for forecasting, control and diagnosis in electrical systems, creating a need for explanations that make model behavior understandable to engineers, operators and other decision makers. Objective: To systematically synthesize evidence from 2018 to 2022 on explainable artificial intelligence methods, applications and emerging challenges in electrical systems, distinguishing technical explainability, model interpretability and user-oriented explanation needs. Method: A systematic review followed sequential identification, duplicate removal, title and abstract screening, full-text eligibility assessment and final inclusion. Eligible publications were within the review window, had a DOI, addressed XAI or interpretable machine learning with clear relevance to energy or electrical applications, and provided sufficient technical detail. Twenty-six studies were included. Results: The corpus combines domain-specific energy applications with methodological contributions on interpretability. Forecasting, stability analysis, photovoltaic control and energy-consumption modeling are prominent applications. Feature attribution, interpretable models and post hoc explanations recur, but evaluation of explanation quality remains less standardized than predictive performance. Conclusions: XAI can improve transparency in data-driven electrical applications, yet technical explanations do not automatically guarantee operational usefulness. Progress requires user-centered evaluation, clearer reporting of explanation objectives, robustness analysis and validation with domain experts under realistic decision conditions. The evidence also emphasizes the importance of aligning explanations with operational decision requirements.
Downloads
References
1. Ram Machlev, Leena Heistrene, M. Perl, Kfir Y. Levy, Juri Belikov, Shie Mannor, Yoash Levron. Explainable Artificial Intelligence (XAI) techniques for energy and power systems: Review, challenges and opportunities. Energy AI. 2022;9:100169. https://doi.org/10.1016/j.egyai.2022.100169.
2. Johannes Kruse, Benjamin Schäfer, Dirk Witthaut. Revealing drivers and risks for power grid frequency stability with explainable AI. Patterns. 2021;2(11):100365. https://doi.org/10.1016/j.patter.2021.100365.
3. Utama C, Meske C, Schneider J, Ulbrich C. Reactive power control in photovoltaic systems through (explainable) artificial intelligence. Appl Energy. 2022;328:120004. https://doi.org/10.1016/j.apenergy.2022.120004.
4. Haoqi Huang, Yue Hong, Huaizhi Wang. Probabilistic Prediction Intervals of Wind Speed Based on Explainable Neural Network. Front Energy Res. 2022;10:https://doi. org/https://doi.org/10.3389/fenrg.2022.934935.
5. Jihoon Moon, Sungwoo Park, Seungmin Rho, Eenjun Hwang. Interpretable Short-Term Electrical Load Forecasting Scheme Using Cubist. Comput Intell Neurosci. 2022;2022(1):6892995. https://doi.org/10.1155/2022/6892995.
6. Peng Han, Wei He, You Cao, YingMei Li, YunYi Zhang. Deep belief rule based photovoltaic power forecasting method with interpretability. Sci Rep. 2022;12(1):https://doi. org/https://doi.org/10.1038/s41598-022-18820-6.
7. Chakraborty D, Alam A, Chaudhuri S, Basagaoglu H, Sulbaran T, Langar S. Scenario-based prediction of climate change impacts on building cooling energy consumption with explainable artificial intelligence. Appl Energy. 2021;291:116807. https://doi.org/10.1016/j.apenergy.2021.116807.
8. Abdul Khalique Shaikh, Amril Nazir, Imran Khan, Abdul Salam Shah. Short term energy consumption forecasting using neural basis expansion analysis for interpretable time series. Sci Rep. 2022;12(1):https://doi. org/https://doi.org/10.1038/s41598-022-26499-y.
9. Alejandro Barredo Arrieta et al. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Inf Fusion. 2020;58:82-115. https://doi.org/10.1016/j.inffus.2019.12.012.
10. Pantelis Linardatos, Vasilis Papastefanopoulos, Sotiris Kotsiantis. Explainable AI: A Review of Machine Learning Interpretability Methods. Entropy. 2021;23(1):18. https://doi.org/10.3390/e23010018.
11. Plamen P. Angelov et al. Explainable artificial intelligence: an analytical review. WIREs Data Min Knowl Discov. 2021;11(5):e1424. https://doi.org/10.1002/widm.1424.
12. Dang Minh, H. Wang, Y.F. Li, T.N. Nguyen. Explainable artificial intelligence: a comprehensive review. Artif Intell Rev. 2022;55(8):6341-6400. https://doi.org/10.1007/s10462-021-10088-y.
13. Xiao Bai, Xiang Wang, Xianglong Liu, Qiang Liu, Jingkuan Song, Nicu Sebe, Been Kim. Explainable deep learning for efficient and robust pattern recognition: A survey of recent developments. Pattern Recognit. 2021;120:108102. https://doi.org/10.1016/j.patcog.2021.108102.
14. Ding W, Abdel-Basset M, Hawash H, Ali AMA. Explainability of artificial intelligence methods, applications and challenges: A comprehensive survey. Inf Sci. 2022;615:238-292. https://doi.org/10.1016/j.ins.2022.10.013.
15. W. James Murdoch, Chandan Singh, Karl Kumbier, Reza Abbasi-Asl, Bin Yu. Definitions, methods, and applications in interpretable machine learning. Proc Natl Acad Sci U S A. 2019;116(44):22071-22080. https://doi.org/10.1073/pnas.1900654116.
16. Joaquín Borrego-Díaz, Juan Galán-Páez. Explainable Artificial Intelligence in Data Science. Minds Mach. 2022;32(3):485-531. https://doi.org/10.1007/s11023-022-09603-z.
17. Meske C, Bunde E, Schneider J, Gersch M. Explainable Artificial Intelligence: Objectives, Stakeholders, and Future Research Opportunities. Inf Syst Manag. 2022;39(1):53-63. https://doi.org/10.1080/10580530.2020.1849465.
18. Fabien Charmet et al. Explainable artificial intelligence for cybersecurity: a literature survey. Ann Telecommun. 2022;77(11-12):789-812. https://doi.org/10.1007/s12243-022-00926-7.
19. Haque AKMB, Islam AKMN, Mikalef P. Explainable Artificial Intelligence (XAI) from a user perspective: A synthesis of prior literature and problematizing avenues for future research. Technol Forecast Soc Change. 2023;186:122120. https://doi.org/10.1016/j.techfore.2022.122120.
20. Amiri SS, Mottahedi S, Lee EE, Hoque S. Peeking inside the black-box: Explainable machine learning applied to household transportation energy consumption. Comput Environ Urban Syst. 2021;88:101647. https://doi.org/10.1016/j.compenvurbsys.2021.101647.
21. Loh HW, Ooi CP, Seoni S, Barua PD, Molinari F, Acharya UR. Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011-2022). Comput Methods Programs Biomed. 2022;226:107161. https://doi.org/10.1016/j.cmpb.2022.107161.
22. Di Martino F, Delmastro F. Explainable AI for clinical and remote health applications: a survey on tabular and time series data. Artif Intell Rev. 2023;56(6):5261-5315. https://doi.org/10.1007/s10462-022-10304-3.
23. Payrovnaziri SN, Chen Z, Rengifo-Moreno P, Miller T, Bian J, Chen JH, Liu X, He Z. Explainable artificial intelligence models using real-world electronic health record data: a systematic scoping review. J Am Med Inform Assoc. 2020;27(7):1173-1185. https://doi.org/10.1093/jamia/ocaa053.
24. Miruna-Adriana Clinciu, Helen Hastie. A Survey of Explainable AI Terminology. Proceedings of NL4XAI 2019 / ACL. 2019. https://doi.org/10.18653/v1/W19-8403
25. David S. Watson, Luciano Floridi. The explanation game: a formal framework for interpretable machine learning. Synthese. 2021;198(10):9211-9242. https://doi.org/10.1007/s11229-020-02629-9.
26. Tim Miller. Explanation in artificial intelligence: Insights from the social sciences. Artif Intell. 2019;267:1-38. https://doi.org/10.1016/j.artint.2018.07.007.
27. ETHICAL CONSIDERATIONS
28. Not applicable. This study is a review of published literature and did not involve direct participation of human beings, animals, interventions, or collection of identifiable personal data.
29. ARTIFICIAL INTELLIGENCE (AI) USE STATEMENT
30. The authors declare that the generative artificial intelligence tool ChatGPT (OpenAI) was used exclusively to support the organization of the article and translation of text. Its use did not determine the scientific content, study design, source selection, data analysis, interpretation of results, or conclusions. Full responsibility for the content remains with the authors.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Danner Anderson Figueroa Guerra
This work is licensed under a Creative Commons Attribution 4.0 International License.
