Parallel Distributed Discrete Event Simulation Optimization Using Complexity and Deep Learning

Parallel distributed discrete event simulation (PDDES) is the execution of a discrete event simulation on a tightly or loosely coupled computer system with multiple processors. The discrete-event simulation model is decomposed into several logical processors (LPs) or simulation objects that can be executed concurrently using partitioning types such as spatial and temporal. PDDES is exceedingly important for the reduction of the simulation time, increase of model size, intellectual property issue mitigation in multi-enterprise simulations, and the sharing of resources. One of the problems with PDDES is the time management to provide flow control over event processing, the process flow, and the coordination of different logical processors to take advantage of parallelism. Time Warp (TW), Breathing Time Buckets (BTB), and Breathing Time Warp (BTW) are three time management schemes studied by this research. For a particular PDDES problem, unfortunately, there is no clear methodology to decide a priori a time management scheme to achieve higher system and simulation performance. This dissertation shows a new approach for selecting the optimal time synchronization technique class that corresponds to a particular parallel distributed and discrete simulation with different levels of simulation logic complexity. Simulation complexities such as branching, parallelism, function calls, concurrency, iterations, mathematical computations, messaging frequency, event processing, and number of simulation objects interactions were given a weighted parameter value based on the cognitive weight approach. Deep belief neural networks were then used to perform deep learning from the simulation complexity parameters and their corresponding optimal time synchronization scheme value as measured by speedup performance.