MLP-ANN-Based Execution Time Prediction Model and Assessment of Input Parameters Through Structural Modeling

Abstract

Listen

Translate article

A multilayer perceptron–artificial neural network (MLP-ANN)-based prediction model is proposed to predict the execution time of tasks in cloud environment. Significant input parameters are identified and selected through interpretive structural modeling (ISM) approach. A prediction model is proposed for predicting the task execution time for varying number of inputs. The proposed model is validated and provides 21.7% reduction in mean relative error compared to other state-of-the-art methods.