Particle Swarm Optimization Technique for Task-Resource Scheduling for Robotic Clouds

Abstract

The task-resource scheduling problem is one of the fundamental problems for cloud computing. There are a large number of heuristics based approaches to various scheduling workflow applications. In this paper, we consider the problem for robotic clouds. We propose new method of selection of parameters of a particle swarm optimization algorithm for solution of the task-resource scheduling problem for robotic clouds. In particular, for the prediction of values of the inertia weight we consider genetic algorithms, multilayer perceptron networks with gradient learning algorithm, recurrent neural networks with gradient learning algorithm, and 4-order Runge Kutta neural networks with different learning algorithms. Also, we present experimental results for different intelligent algorithms.