Hybrid Genetic Algorithms for Scheduling High-Speed Multimedia Systems
It has been observed that most conventional operating systems could not cope with the scheduling of multimedia tasks owing to the large size of these files. For instance, processing of multimedia tasks using the traditional operating systems are fraught with problems such as low quality of service and delay jitters. In order to address these problems, a scheduling algorithm christened hybrid genetic algorithm for multimedia task scheduling (HGAMTS) was developed. It employed heuristic knowledge of the problem domain to model a hybrid genetic algorithm in a multiprocessor environment. The system is made up of the scheduler model and the task model. The scheduler model consist a centralized dynamic scheduling scheme. In this scheme, all tasks arrive at a central processor (scheduler). The model has a minimum of five and maximum of ten processors. Attached to each processor is a dispatch queue.
