Multi-Threaded Distributed System Simulations Using Transmission Line Modelling
(English)Manuscript (preprint) (Other academic)
This paper presents an automatic algorithm for partitioning and running distributed system simulations on multi-core computers. Methods for sorting and distributing components for good load balancing have been developed. Mathematical correctness during simulation is maintained by a thread synchronisation algorithm. Independence between system components is achieved by using the transmission line element method. In contrast tothe more commonly used centralised solvers, this method uses distributed solvers with physically motivated time delays, making simulations inherently parallel. Results show that simulation speed increases almost proportionally to the number of processor cores in the case of large models. However, overhead time costs mean that models need to be over a certain size to benefit from parallelisation.
Distributed Solvers, Parallelism, Problem Partitioning, Transmission Line Modelling, System Simulation
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-88024OAI: oai:DiVA.org:liu-88024DiVA: diva2:601337