The rapid digitalization, decentralization, and integration of renewable energy in electricity markets have heightened the demand for advanced data analytics to manage their complexity and ensure sustainability. This systematic review explores the transformative role of data analytics, machine learning and artificial intelligence in enhancing efficiency across key areas of smart electricity markets. These include forecasting (price, demand, load, carbon emissions, and supply), trading, security, bidding, and the impact of renewable energy on pricing. Following PRISMA guidelines to conduct this systematic literature review (SLR), a rigorous selection process narrowed 504 initial articles to 23 high-impact studies from 2014 to 2024, offering a focused analysis of emerging techniques such as hybrid models, neural networks, blockchain, and explainable AI. The review identifies advancements in predictive accuracy, adaptive decision-making, and decentralized trading mechanisms, emphasizing their ability to address market volatility and enhance operational stability. Furthermore, the findings highlight gaps in existing approaches and propose future research directions, including the integration of real-time analytics, reinforcement learning, and decentralized frameworks. By providing a structured overview, this study serves as a resource for researchers and practitioners, underscoring the critical role of data-driven solutions in the evolving landscape of smart electricity markets.
Asim et al. (Sun,) studied this question.