Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption

TLDR

Energy prediction models are used in buildings for performance evaluation, advanced control, and decision‑making, and simplified data‑driven models are preferred when detailed simulation data are lacking or rapid responses are needed, with ensemble methods offering advantages for handling complex, categorical data. The study compared the performance of a feed‑forward back‑propagation artificial neural network and a random forest model for hourly HVAC energy consumption prediction in a Madrid hotel. The authors employed a feed‑forward back‑propagation ANN and a random forest, the latter using internal cross‑validation with out‑of‑bag samples and few tuning parameters, to predict hourly HVAC energy consumption. Adding social parameters slightly improved accuracy for both models; overall the ANN achieved a marginally lower RMSE (4.97 vs 6.10) than the RF, but both models displayed comparable predictive power and are similarly applicable to building energy applications.

Abstract

Energy prediction models are used in buildings as a performance evaluation engine in advanced control and optimisation, and in making informed decisions by facility managers and utilities for enhanced energy efficiency. Simplified and data-driven models are often the preferred option where pertinent information for detailed simulation are not available and where fast responses are required. We compared the performance of the widely-used feed-forward back-propagation artificial neural network (ANN) with random forest (RF), an ensemble-based method gaining popularity in prediction – for predicting the hourly HVAC energy consumption of a hotel in Madrid, Spain. Incorporating social parameters such as the numbers of guests marginally increased prediction accuracy in both cases. Overall, ANN performed marginally better than RF with root-mean-square error (RMSE) of 4.97 and 6.10 respectively. However, the ease of tuning and modelling with categorical variables offers ensemble-based algorithms an advantage for dealing with multi-dimensional complex data, typical in buildings. RF performs internal cross-validation (i.e. using out-of-bag samples) and only has a few tuning parameters. Both models have comparable predictive power and nearly equally applicable in building energy applications.