On the Assessment of Ensemble Models for Propagation Loss Forecasts in Rural Environments

Abstract

This letter assesses different ensemble models, exploited to forecast propagation loss in rural environments. Stacking, voting, bagging, and gradient boosted trees ensemble techniques are evaluated using path loss data recorded in various rural locations all over Greece. According to the numerical results all the introduced ensemble models increase their prediction efficacy and outperform all the single-model-based methods. Furthermore, stacking technique with 5 base learners and a customized deep neural network (DNN), as meta-learner, exhibits the best performance. Finally, it is shown that the forecast precision is gradually enhanced by increasing the number of the training features, yet under penalty of time complexity.