A decision tree method for building energy demand modeling

Abstract

This paper reports the development of a building energy demand predictive model based on the decision tree method. The developed model estimates the building energy performance indexes in a rapid and easy way. This method is appropriate to classify and predict categorical variables: its competitive advantage over other widely used modeling techniques, such as regression method and ANN method, lies in the ability to generate accurate predictive models with interpretable flowchart-like tree structures that enable users to quickly extract useful information. To demonstrate its applicability, the method is applied to estimate residential building energy performance indexes by modeling building energy use intensity (EUI) levels (either high or low). The results demonstrate that the use of decision tree method can classify and predict building energy demand levels accurately (93% for training data and 92% for test data), identify and rank significant factors of building EUI automatically. The method can provide the combination of significant factors as well as the threshold values that will lead to high building energy performance. Moreover, the average EUI value of data records in each classified data subsets can be used for reference when performing prediction. The outcomes of this methodology could benefit architects, building designers and owners greatly in the building design and operation stage. One crucial benefit is improving building energy performance and reducing energy consumption. Another advantage of this methodology is that it can be utilized by users without requiring much computation knowledge.

Data science for building energy management: A review

“…hierarchical, k -means, fuzzy k -means, follow the leader and fuzzy relation) and compared their effectiveness in the classification of customers and the generation of electricity load profiles (in terms of average retail price and net generation). In contrast, Yu et al [26] proposed the use of decision trees to develop predictive models for building energy demand since they are more easily interpreted than other classification techniques.…”

An application of data mining in district heating substations for improving energy performance

“…In the past several decades, it has been successfully applied in economics, retails, telecommunication, and financial services [4]. Recently, efforts have also been made to investigate the application of data mining in HVAC field, including building energy consumption prediction [5,6], building energy management [7,8], fault detection and diagnosis [9,10], and occupant behaviour [11,12].…”

Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model

“…It comprises root nodes, internal nodes and leaf nodes. Each root node and internal node represents a test on attribute of cases, while each leaf node represents an outcome of classification [45]. Learning is performed so that data are divided into a train set and a test set before the generation algorithm takes train data as input [45].…”