Neural Network Based Priority Assignment for Job Scheduler

This paper describes the design and implementation of a neural network-based job priority assigner system for a job scheduling environment. Scheduling deals with the allocation of resources over time to perform a collection of tasks. Scheduling problems arise in domains as diverse as manufacturing, computer processing, transportation, health care, space exploration, and education. In the case of a neural network (NN) based scheduler, once the job attributes are properly trained for a specified schedule, it will never miss that related scheduling pattern for that particular job. An NN based scheduling procedure can successfully overcome the local minima of its error surface. This paper reports on research which established that a back propagation neural network-based priority procedure would recognize jobs from a job queue by estimating each job’s priority. Once the priorities are assigned, it is not possible to alter the priorities under any circumstances.