Distributed Execution of an Inherently Sequential Network Simulator

Network simulators play a vital role in research and development of networks. Simulations are usually computationally intensive where distributed execution can improve performance significantly. However, due to the sequential nature of the communication process modeled by network simulators and limitations in access to source code it is not possible to completely isolate the sub-processes for distributed execution. An alternate solution in this case is to classify independent modules within a sequential simulation environment and execute the modules in parallel. This paper presents a similar mechanism for OPNET by enabling distributed execution of network simulation scenarios on a cluster of PCs using Sun Grid Engine. The proposed framework provides a demarcation between local configuration of software simulators and their remote execution. Such a demarcation gives a lead into future possibilities where computationally intensive tasks can be configured using devices with insufficient computational resources and executed remotely. Extensive experimental results in a Sun Grid Engine cluster environment using a variety of OPNET simulation scenarios show substantial efficiency in simulation run-time.