Abstract
This thesis presents a systematic literature review to investigate the application of big data analytics (BDA) in energy management, with a focus on three key objectives: identifying challenges such as data security, interoperability, and model precision; investigating the sustainability, legal, and ethical implications; and evaluating methods for integrating diverse data sources, methodologies, and algorithms. The assessment covers research from 2019 to 2023 and identifies substantial challenges to BDA adoption, such as privacy concerns, a lack of defined data standards, and the complexities of maintaining big, heterogeneous datasets. Proposed solutions are assessed, such as blockchain for safe data sharing and machine learning for increased predictive accuracy. Ethical considerations, including algorithmic fairness and data ownership, are also discussed. The findings suggest that, while BDA has the potential to improve operational efficiency, optimize resource use, and allow renewable energy integration, technical and legal barriers must be overcome. The study provides practical insights, including hybrid models that integrate machine learning and classical statistical methods, improved data integration frameworks, and robust cybersecurity safeguards to support future smart grid systems.