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

作者：Peter Onu, Anup Pradhan, N. Madonsela · 发表于：2024 1st International Conference on Smart Energy Systems and Artificial Intelligence (SESAI) · 年份：2024 · DOI：10.1109/sesai61023.2024.10599403 · 被引用次数：11

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.