Chirag B A, Chandana M Rao, Chaithra S, Rohini M, Robin Rohit Vincent, Prashanth Kannadaguli "Digital Twin for Smart Factory Energy Optimisation "

Paper_id: 21_5

Abstract

The demand for energy, efficient measures in smart manufacturing has significantly contributed to the integration of digital twin (DT) technologies. Such innovations entail the coupling of the physical and virtual models, thereby enabling prompt monitoring, forecasting, and optimizing. The article provides an overview of the energizing optimization digital twin framework that employs a hybrid agent, based and discrete, event simulation model realized through AnyLogic. The energy management model in the factory is based on real, time energy supply and demand models. The method in question involves IoT, enabled data collection, predictive analytics, and reinforcement learning optimization. The energy efficiency measures have an impact on energy cost, and environmental protection, too. The energy measures have been simulated and studied through case studies and show energy consumption to be reduced by 15 to 20%, the costs to be decreased by 16 to 18%, and the CO₂ emissions to be lowered by 10 to 15%. The findings indicate the use of digital twins as an adaptable means of achieving energy optimization in real, time and comply with standards such as IEC 62832, OPC UA, and ISO 50001.