Real time data modeling for forecasting fuel consumption of construction equipment using integral approach of IoT and ML techniques

Abstract

The Internet of Things (IoT) plays a vital role in the automation of Construction Industry. The real time data of the construction equipment is monitored using IoT devices. An integral approach of IoT based sensing data and Machine Learning (ML) models helps to predict the fuel consumed by the equipment. This paper presents the real time data modeling to estimate the fuel consumption for a trip travelled by the construction equipment using IoT enabled remote data along with machine learning algorithms. The Random Forest, Extreme Gradient Boosting (XGBoost) ensemble methods and Lasso Cross Validation (LassoCV), Support Vector Machines Regression models are used in this study. These models are fitted on dataset and splits the data into training and testing data. Based on the comparative analysis of coefficient of determination, LassoCV technique produces more accurate results along with the other models using Models’ accuracy measures. This study would help the decision makers for cost estimation of the construction project which includes fuel consumption as major component of cost.