Methods of Explainable Artificial Intelligence (XAI), Trustworthy Artificial Intelligence (TAI) and Interpretable Machine Learning (IML) in Renewable Energy

Betul Ersoz, Seref Sagiroglu, Halil Ibrahim Bulbul

Abstract


In recent years, tendency to renewable energy resources has increased considerably in order to obtain cleaner energy. The effect of the decisions taken by artificial intelligence models on energy efficiency is very important in the transformation of these resources. With eXplainable Artificial Intelligence (XAI), various methods have been developed for trust, transparency and decision making by artificial intelligence models, but more models need to be developed in this area in order for decision-making mechanisms to increase confidence in performance, evaluation and explanations. The aims of the study are to review and analyze how RE systems can benefit from XAI applications with some criticisms. The results have shown that XAI in a new topic in RE and requires more attentions to be applied in critical systems to improve the trust and transparency.

Keywords


Explainable Artificial Intelligence (XAI); b) Trustworthy Artificial Intelligence (TAI); Renewable Energy (RE); Interpretable Machine Learning; Energy systems;

Full Text:

PDF

References


M. Ridley, "Explainable Artificial Intelligence (XAI)," Information Technology and Libraries, vol. 41, no. 2, 2022.

Entes, "The Role of Artificial Intelligence in the Energy Sector of the Future," 2021. [Online]. Available: https://www.entes.com.tr/gelecegin-enerji-sektorunde-yapay-zekanin-rolu/.

D. Ta?ba??, "Artificial intelligence in the renewable energy industry will exceed $75 billion," https://temizenerji.org/, 2022.

IRENA, Future Energy Systems Need Clear AI Boundaries, 2020. [Online]. Available: https://www.irena.org/news/expertinsights/2020/Dec/Future-Energy-Systems-Need-Clear-AI-Boundaries.

A. Singh, S. Sengupta, and V. Lakshminarayanan, "Explainable deep learning models in medical image analysis," Journal of Imaging, vol. 6, no. 6, p. 52, 2020.

A. Das and P. Rad, "Opportunities and challenges in explainable artificial intelligence (xai): A survey," arXiv preprint arXiv:2006.11371, 2020.

D. Gunning and D. Aha, "DARPA’s explainable artificial intelligence (XAI) program," AI magazine, vol. 40, no. 2, pp. 44-58, 2019.

Microsoft, "Concept Responsible AI," 2022. [Online]. Available: https://learn.microsoft.com/tr-tr/azure/machine-learning/concept-responsible-ai.

H. Liu et al., "Trustworthy ai: A computational perspective," ACM Transactions on Intelligent Systems and Technology, vol. 14, no. 1, pp. 1-59, 2022.

S. Thiebes, S. Lins, and A. Sunyaev, "Trustworthy artificial intelligence," Electronic Markets, vol. 31, no. 2, pp. 447-464, 2021/06/01 2021, doi: 10.1007/s12525-020-00441-4.

A. Kizrak, "Trustworthy AI," Medium, 2020. [Online]. Available: https://ayyucekizrak.medium.com/a%C3%A7%C4%B1klanabilir-sorumlu-ve-g%C3%BCvenilir-yapay-zeka-bece897c5ea9.

S. Das, N. Agarwal, D. Venugopal, F. T. Sheldon, and S. Shiva, "Taxonomy and Survey of Interpretable Machine Learning Method," in 2020 IEEE Symposium Series on Computational Intelligence (SSCI), 1-4 Dec. 2020 2020, pp. 670-677, doi: 10.1109/SSCI47803.2020.9308404.

M. E. Morocho-Cayamcela, H. Lee, and W. Lim, "Machine Learning for 5G/B5G Mobile and Wireless Communications: Potential, Limitations, and Future Directions," IEEE Access, vol. 7, pp. 137184-137206, 09/01 2019, doi: 10.1109/ACCESS.2019.2942390.

Microsoft, "How to Machine Learning Interpretability," 2022. [Online]. Available: https://learn.microsoft.com/tr-tr/azure/machine-learning/how-to-machine-learning-interpretability.

W. Shin, J. Han, and W. Rhee, "AI-assistance for predictive maintenance of renewable energy systems," Energy, vol. 221, p. 119775, 2021.

F. Conte, F. D’Antoni, G. Natrella, and M. Merone, "A new hybrid AI optimal management method for renewable energy communities," Energy and AI, vol. 10, p. 100197, 2022.

J. Moraga, H. S. Duzgun, M. Cavur, and H. Soydan, "The Geothermal Artificial Intelligence for geothermal exploration," Renewable Energy, vol. 192, pp. 134-149, 2022/06/01/ 2022, doi: https://doi.org/10.1016/j.renene.2022.04.113.

H. Salem, I. M. El-Hasnony, A. Kabeel, E. M. El-Said, and O. M. Elzeki, "Deep Learning model and Classification Explainability of Renewable energy-driven Membrane Desalination System using Evaporative Cooler," Alexandria Engineering Journal, vol. 61, no. 12, pp. 10007-10024, 2022.

S. Heo, J. Ko, S. Kim, C. Jeong, S. Hwangbo, and C. Yoo, "Explainable AI-driven net-zero carbon roadmap for petrochemical industry considering stochastic scenarios of remotely sensed offshore wind energy," Journal of Cleaner Production, p. 134793, 2022.

T. Sim et al., "eXplainable AI (XAI)-Based Input Variable Selection Methodology for Forecasting Energy Consumption," Electronics, vol. 11, no. 18, p. 2947, 2022.

S. Sairam, S. Seshadhri, G. Marafioti, S. Srinivasan, G. Mathisen, and K. Bekiroglu, "Edge-based Explainable Fault Detection Systems for photovoltaic panels on edge nodes," Renewable Energy, vol. 185, pp. 1425-1440, 2022.

T. Tsoka, X. Ye, Y. Chen, D. Gong, and X. Xia, "Explainable artificial intelligence for building energy performance certificate labelling classification," Journal of Cleaner Production, vol. 355, p. 131626, 2022.

D. A. Bolstad, U. Cali, M. Kuzlu, and U. Halden, "Day-ahead Load Forecasting using Explainable Artificial Intelligence," in 2022 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 24-28 April 2022 2022, pp. 1-5, doi: 10.1109/ISGT50606.2022.9817538.

Y. Lu, I. Murzakhanov, and S. Chatzivasileiadis, "Neural network interpretability for forecasting of aggregated renewable generation," in 2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), 25-28 Oct. 2021 2021, pp. 282-288, doi: 10.1109/SmartGridComm51999.2021.9631993.

E. Henriksen, U. Halden, M. Kuzlu, and U. Cali, "Electrical Load Forecasting Utilizing an Explainable Artificial Intelligence (XAI) Tool on Norwegian Residential Buildings," in 2022 International Conference on Smart Energy Systems and Technologies (SEST), 5-7 Sept. 2022 2022, pp. 1-6, doi: 10.1109/SEST53650.2022.9898500.

M. Langer et al., "What do we want from Explainable Artificial Intelligence (XAI)? – A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI research," Artificial Intelligence, vol. 296, p. 103473, 2021/07/01/ 2021, doi: https://doi.org/10.1016/j.artint.2021.103473.

J. T. Dellosa and E. C. Palconit, "Artificial Intelligence (AI) in Renewable Energy Systems: A Condensed Review of its Applications and Techniques," in 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe), 2021: IEEE, pp. 1-6.




DOI (PDF): https://doi.org/10.20508/ijsmartgrid.v6i4.256.g250

Refbacks

  • There are currently no refbacks.


www.ijsmartgrid.com; www.ijsmartgrid.org

iilhcol@gmail.com; ijsmartgrid@nisantasi.edu.tr

Online ISSN: 2602-439X

Publisher: ilhami COLAK (istanbul Nisantasi Univ)

Cited in Google Scholar and CrossRef