Explainable AI (XAI) in Smart Grids for Predictive Maintenance: A survey

被引：0

作者：

Onu, Peter ^{[1
]}

Pradhan, Anup ^{[1
]}

Madonsela, Nelson Sizwe ^{[1
]}

机构：

[1] Univ Johannesburg, Dept Qual & Operat Management, Johannesburg, South Africa

来源：

2024 1ST INTERNATIONAL CONFERENCE ON SMART ENERGY SYSTEMS AND ARTIFICIAL INTELLIGENCE, SESAI 2024 | 2024年

关键词：

explainable AI; smart grid; predictive maintenance; challenges; and opportunities;

D O I：

10.1109/SESAI61023.2024.10599403

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The dynamic trend of modern energy infrastructure demands proactive and transparent solutions, especially in predictive maintenance for smart grids. This research discusses the integration of Explainable AI ( XAI) to augment the reliability and trustworthiness of predictive maintenance strategies within smart grids. As such, the present study explores how XAI can be better understood based on predictive maintenance procedures and delignates the factors influencing maintenance decisions. In addition, the paper highlights the implications of two XAI techniques (LIME and SHAP) and then surveys recent literature on the subject matter. The authors are optimistic that this paper will spark a new turn towards, as per stakeholders' commitment to enhance the operational efficiency of energy infrastructure with emphasis on the decision-making processes that drive these critical systems.

引用

页码：12 / 17

页数：6

共 44 条

[1] A machine-learning approach to predicting Africa's electricity mix based on planned power plants and their chances of success
Alova, Galina
Trotter, Philipp A.
Money, Alex
[J]. NATURE ENERGY, 2021, 6 (02) : 158 - 166
[2] EnergyStar plus plus : Towards more accurate and explanatory building energy benchmarking
Arjunan, Pandarasamy
Poolla, Kameshwar
Miller, Clayton
[J]. APPLIED ENERGY, 2020, 276
[3] An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction
Chaibi, Mohamed
Benghoulam, El Mahjoub
Tarik, Lhoussaine
Berrada, Mohamed
El Hmaidi, Abdellah
[J]. ENERGIES, 2021, 14 (21)
[4] Scenario-based prediction of climate change impacts on building cooling energy consumption with explainable artificial intelligence
Chakraborty, Debaditya
Alam, Arafat
Chaudhuri, Saptarshi
Basagaoglu, Hakan
Sulbaran, Tulio
Langar, Sandeep
[J]. APPLIED ENERGY, 2021, 291
[5] Chang XM, 2020, INT CONF ACOUST SPEE, P8981, DOI [10.1109/ICASSP40776.2020.9054088, 10.1109/icassp40776.2020.9054088]
[6] XGBoost-Based Algorithm Interpretation and Application on Post-Fault Transient Stability Status Prediction of Power System
Chen, Minghua
Liu, Qunying
Chen, Shuheng
Liu, Yicen
Zhang, Chang-Hua
Liu, Ruihua
[J]. IEEE ACCESS, 2019, 7 : 13149 - 13158
[7] A novel methodology to explain and evaluate data-driven building energy performance models based on interpretable machine learning
Fan, Cheng
Xiao, Fu
Yan, Chengchu
Liu, Chengliang
Li, Zhengdao
Wang, Jiayuan
[J]. APPLIED ENERGY, 2019, 235 : 1551 - 1560
[8] Ikumapayi O. M., 2020, Lecture Notes in Mechanical Engineering, DOI [10.1007/978-981-15-5753-8_15, DOI 10.1007/978-981-15-5753-8_15]
[9] Ke Zhang, 2020, 2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2), P711, DOI 10.1109/EI250167.2020.9347147
[10] Kruse Johannes, 2021, 2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), P133, DOI 10.1109/SmartGridComm51999.2021.9632335

← 1 2 3 4 5 →