International Journal of Multidisciplinary Research and Growth Evaluation  |  ISSN (Online): 2582-7138  |  Double-Blind Peer Review  |  Open Access  |  CC BY 4.0

Current Issues
     2026:7/3

International Journal of Multidisciplinary Research and Growth Evaluation

ISSN (Online): 2582-7138 | Open Access

Interpretable Machine Learning for Early Failure Prediction in Distributed Renewable Energy Assets

Full Text (PDF)

Open Access - Free to Download

Download Full Article (PDF)

Alternative download link

Abstract

This paper develops a conceptual framework for predictive maintenance of distributed renewable assets that treats engineering innovation and socio-technical analysis as a single integrated design problem rather than as separate concerns addressed in sequence. The framework is motivated by a persistent pattern in which technically sound interventions falter in the field because the social and institutional conditions that govern their durability are neither measured nor designed for. In response, this paper articulates a model in which social variables, centrally the gap between model accuracy and technician adherence, where interpretable models produce greater net benefit than opaque ones, are rendered explicit and brought into the design problem on the same footing as technical parameters. The contribution is conceptual: this paper sets out the foundations of the framework, specifies its components and the relationships among them, illustrates its reasoning, and derives design and policy implications, with the aim of supporting energy systems that are simultaneously technically efficient, economically accessible, socially responsive, and adaptable to developing and resource-dependent regions

How to Cite This Article

Nenubari Marvin Komi, Azeez Adamolekun (2021). Interpretable Machine Learning for Early Failure Prediction in Distributed Renewable Energy Assets . International Journal of Multidisciplinary Research and Growth Evaluation (IJMRGE), 2(6), 1015-1038. DOI: https://doi.org/10.54660/.IJMRGE.2021.2.6.1015-1038

Export Citation:

BibTeX RIS EndNote

Share This Article: