Dynamic task scheduling using a directed neural network

• Development of the learning method for ANN.
• Development of a method for optimization of RBFNN.
• Use of DSO in task scheduling.
• Use of DSO trained ANN in task scheduling.
• Use of DSO trained RBFNN in task scheduling.

This article is based on the problem of work flow scheduling in grid environment of multi-processors. We, in this paper, introduce three novel approaches for the task scheduling problem using recently proposed Directed Search Optimization (DSO). In the first attempt, task scheduling is framed as an optimization problem and solved by DSO. Next, this paper makes use of DSO as a training algorithm to train (a) a three layer Artificial Neural Network (ANN) and then (b) Radial Basis Function Neural Networks (RBFNN). These DSO trained networks are used for task scheduling and interestingly yield better performance than contemporary algorithms as evidenced by simulation results.