Competitive Neural Network to Solve Real-Time Scheduling

Abstract

The Hopfield neural network is widely applied to obtain an optimal solution in a variety of different scheduling applications. A competitive learning rule provides a highly effective means of attaining a sound solution and is capable of reducing the time-consuming effort of obtaining coefficients. Restated, the competitive mechanism simplifies the network complexity. This important feature is applied to Hopfield neural network to derive a new technique, i.e. competitive Hopfield neural network. This investigation utilizes the competitive Hopfield neural network to resolve a multiprocessor real-time scheduling problem with constrained times (execution time and deadline). Simulation results demonstrate that the competitive Hopfield neural network imposed on the proposed energy function ensures an appropriate approach of solving this class of real-time scheduling problems.