“…1, which shows the effect on efficiency and execution time of a largest processing time first (LPTF) policy. These results were obtained in a simulation study comparing different scheduling strategies for master-worker applications, which can be found in [10]. In general, our results showed that for any given workload distribution, a similar scenario to the one depicted in Fig.…”
Section: Self-adjusting Scheduling For Master-worker Applicationssupporting
confidence: 64%
“…The first of these controls the assignment of tasks to workers according to an algorithm that keeps a running average of each task (a detailed description could be found in [10]). Tasks are sorted in decreasing order of this average execution time and, at each iteration, were assigned to workers according to the sorted list.…”
Section: Self-adjusting Scheduling Strategy For Homogeneous Systemsmentioning
“…1, which shows the effect on efficiency and execution time of a largest processing time first (LPTF) policy. These results were obtained in a simulation study comparing different scheduling strategies for master-worker applications, which can be found in [10]. In general, our results showed that for any given workload distribution, a similar scenario to the one depicted in Fig.…”
Section: Self-adjusting Scheduling For Master-worker Applicationssupporting
confidence: 64%
“…The first of these controls the assignment of tasks to workers according to an algorithm that keeps a running average of each task (a detailed description could be found in [10]). Tasks are sorted in decreasing order of this average execution time and, at each iteration, were assigned to workers according to the sorted list.…”
Section: Self-adjusting Scheduling Strategy For Homogeneous Systemsmentioning
“…The Condor project [14] develops a software infrastructure so that heterogeneous resources with distributed ownerships can be utilized to provide large amounts of processing capacity over long periods of time. Master-slave paradigm is widely used in the Condor systems and has been exploited by various research efforts ( [6,13]) to maximize the throughput. The multi-level master-slave paradigm is studied in [1], where a bandwidth-centric approach was proposed to maximize system throughput.…”
“…However, our optimization framework is based on an iterative way of working. For this purpose, we have developed our optimization framework based on an extended version of MW [7], which allows MW to iterate a predetermined number of times.…”
Abstract. Optimization of complex objective functions such as environmental models is a compute-intensive task, difficult to achieve by classical optimization techniques. Evolutionary techniques such as genetic algorithms present themselves as the best alternative to solving this problem. We present a friendly optimization framework for complex objective function on a computational grid platform, which allows easy incorporation of new optimization strategies. This framework was developed using the MW library and the Condor system. The framework architecture is described, and a case study of a forest-fire propagation simulator is then analyzed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.