Parallel and distributed simulation: managing external workload with BSP time warp
Proceedings of the 34th conference on Winter simulation: exploring new frontiers
A Flexible Dynamic Partitioning Algorithm for Optimistic Distributed Simulation
Proceedings of the 21st International Workshop on Principles of Advanced and Distributed Simulation
An Efficient Dynamic Load Balancing Scheme for Distributed Simulations on a Grid Infrastructure
DS-RT '08 Proceedings of the 2008 12th IEEE/ACM International Symposium on Distributed Simulation and Real-Time Applications
A grid-based DEVS approach to dynamic load balancing for large scale distributed simulations
SpringSim '09 Proceedings of the 2009 Spring Simulation Multiconference
DS-RT '09 Proceedings of the 2009 13th IEEE/ACM International Symposium on Distributed Simulation and Real Time Applications
Journal of Parallel and Distributed Computing
Automating the runtime performance evaluation of simulation algorithms
Winter Simulation Conference
Predictive Dynamic Load Balancing for Large-Scale HLA-based Simulations
DS-RT '11 Proceedings of the 2011 IEEE/ACM 15th International Symposium on Distributed Simulation and Real Time Applications
Migration Delay Awareness in a Self-Adaptive Balancing Scheme for HLA-Based Simulations
DS-RT '12 Proceedings of the 2012 IEEE/ACM 16th International Symposium on Distributed Simulation and Real Time Applications
Load Prediction in HLA-Based Distributed Simulation Using Holt's Variants
DS-RT '13 Proceedings of the 2013 IEEE/ACM 17th International Symposium on Distributed Simulation and Real Time Applications
Autonomous Configuration Scheme in a Distributed Load Balancing System for HLA-Based Simulations
DS-RT '13 Proceedings of the 2013 IEEE/ACM 17th International Symposium on Distributed Simulation and Real Time Applications
| Hi-index | 0.00 |
The performance of a parallel simulation system depends very much on partitioning simulation workload evenly among the set of processors in the computing environment to ensure load-balance between processors. Most parallel simulation systems employ user-defined static partitioning. However, static partitioning requires in-depth domain knowledge of the specific simulation model in study. It is not effective if the workload of a simulation model could not be quantified accurately or changes over time during a simulation run.Dynamic load-balancing allows the simulation system to automatically balance the workload of different simulation models without user's input. In this paper, the use of dynamic load-balancing in the context of BSP Time Warp optimistic protocol is examined. Based on the BSP cost model, a dynamic load-balancing algorithm for the BSP Time Warp protocol is developed. Using different simulation models, we show that to achieve consistent performance, the dynamic load-balancing algorithm for BSP Time Warp needs to consider both computation and communication workload, as well as lookaheads between processors.