Deep Neural Networks in Smart Grid Digital Twins: Evolution, Challenges, and Future Outlooks
Shewit Tsegaye, Kifle Godana Heyi, Mimi Tsegaye Endaylalu, Zemenu Addis Melaku, Kasech Tsegaye Turufi
Abstract
The increasing demand for reliable, sustainable, and efficient energy systems is accelerating the adoption of innovative technologies in the power sector. Among these advancements, the integration of Deep Neural Networks (DNNs) with Digital Twins (DTs) emerged as a groundbreaking innovation, particularly in smart grids (SGs). DNNs, subset of artificial intelligence, process complex datasets and are able to identify intricate patterns, proving invaluable for predictive analytics, optimization, and real-time decision-making. DTs serve as dynamic virtual representations of physical grid systems, enabling engineers to monitor, simulate, and optimize grid performance with outstanding precision. This strategic review presents the evolution of DNNs in Smart Grid DTs (SGDTs), highlighting their transformative role in enhancing grid operations, outlining the significant challenges that hindered their widespread adoption, and providing a forward-looking perspective on their future potential in revolutionizing energy systems. The scope of this study encompasses exploring evolution of smart grids, the advancements in communication systems within SGDTs, and the integration of DNNs in SGDTs by taking lessons from existing DT architectures and case studies. It also categorized challenges into physical, intelligent, and virtual layers, to emphasize hybrid DNNs’ role in addressing big data and intermittent energy issues.