HLA-based simulation systems are prone to load imbalances due to lack management of shared resources in distributed environments. Such imbalances lead these simulations to exhibit performance loss in terms of execution time. As a result, many dynamic load balancing systems have been introduced to manage distributed load. These systems use specific methods, depending on load or application characteristics, to perform the required balancing. Load prediction is a technique that has been used extensively to enhance load redistribution heuristics towards preventing load imbalances. In this paper, several efficient Time Series model variants are presented and used to enhance prediction precision for large-scale distributed simulation-based systems. These variants are proposed to extend and correct the issues originating from the implementation of Holt's model for time series in the predictive module of a dynamic load balancing system for HLA-based distributed simulations. A set of migration decision-making techniques is also proposed to enable a prediction-based load balancing system to be independent of any prediction model, promoting a more modular construction.

HLA-based distributed simulations tend to suffer from load imbalances and degradation in performance as a result of running on distributed environment. High-Level Architecture (HLA) is a general purpose framework that eases the implementation of distributed simulations on top of dedicated resources without worrying about the computing infrastructure. Due to the high cost of hardware and other factors, some companies have ditched the concept of dedicated resources and shifted towards shared ones which revealed some HLA weaknesses, out of which, dynamic reaction to load imbalances and managing federates on the shared resources. Therefore, different efforts have proposed numerous dynamic load balancing systems to offer a balancing feature to running distributed simulations. In order to perform the load balancing task, these proposed systems gather and make use of a number of simulation and load metrics. Load prediction is a metric that is computed to provide load projections and prevent any prospective load imbalances by migrating federates from an overloaded shared resource to an underloaded shared resource. This work touches the federate migration decision-making process, which is the last step of the balancing task. The proposed federate migration decision-making methods are to overcome the dependency on predefined thresholds in previous work and offer dynamic decisions to migrate federates.

Due to the dependency of HLA-Based distributed simulations on the resources of distributed environments, simulations can face load imbalances and can suffer from low performance in terms of execution time. High-Level Architecture (HLA) is a framework that simplifies the implementation of distributed simulations, and, it has been built with dedicated resources in mind. As technology is nowadays shifting towards shared resources, the following two weaknesses have become apparent in HLA: managing federates and reacting towards load imbalances on shared resources. Moreover, a number of dynamic load management systems have been designed in order to provide a solution to enable a balanced simulation environment on shared resources. These systems use some specific techniques depending on certain simulation or load aspects, to perform the balancing task. Load prediction is one such technique that improves load redistribution heuristics by preventing load imbalances. In this work, we present a number of enhancements for a prediction technique and compare their efficiency. The proposed enhancements solve observed problems with Holt's implementations on dynamic load balancing systems for HLA-Based distributed simulations and provide better forecasting. As a result, these enhancements provide better forecasting for the load of the shared resources.