부산대학교 도서관

Discrete Event Simulations (DES) are the most commonplace tools for modelling today's manufacturing factories and their processes. DES are becoming steadfastly integrated into their corresponding physical counterparts to administer greater avenues for their analysis, control, forecasts and optimisations in real-time. However, this growth does not materialise without a penalty in the form of computational burden. The demand for flexible and alternate approaches to accelerate DES is made necessary. Hence, the utilisation of GPUs to comply with such acceleration presents a research topic of growing interest. This work investigates the use of the Machine Learning platform TensorFlow with GPUs to accelerate a variety of manufacturing-domain DES using the SimPy simulation framework. A range of results were gathered, of speed-ups spanning between x1.4 and x3.21, paving the way for further enhancements towards the vision of real-time communication between simulation and physical system in the form of a complete Digital Twin.