Accuracy analyses and model comparison of machine learning adopted in building energy consumption prediction

Abstract

It is of great significance to achieve the prediction of building energy consumption. However, machine learning, as a promising technique for many practical applications, was rarely utilized in this field. The most important reason is that the predictive structure with best performance is difficult to be determined. To fill the gap, this paper offers one in-depth review, which focuses on the accuracy analyses and model comparisons. Specifically, the accuracy analyses were conducted based on different types of buildings (e.g. residential building, commercial building, government building or educational building), different type of temporal granularity (e.g. sub-hourly, hourly, daily or annual), as well as input/output variables and historical data collections. Further, artificial neural network (ANN) and support vector machine (SVM), as the epidemic models, were compared in terms of their complexity of prediction processes, accuracies of results, the amounts of required historical data, the numbers of inputs, etc. Then the hybrid and single machine learning methods were outlined and compared in terms of their strengths and weaknesses. In addition, several vital defects and further research directions are presented from a multivariate perspective. We hope

Optimization method for prefabricated restroom envelope energy saving characteristics in hot summer and cold winter zone

“…New wall materials, using more environmentally friendly materials or waste materials in raw materials, can not only provide thermal insulation function but also can reduce building energy consumption. The utilization of raw materials and the construction process are energy-saving, but the produced building materials have excellent properties, such as excellent insulation, fire resistance, and durability (Liu et al, 2019b). Since the external wall plays an important role in the insulation function, the wall with only the structural layer cannot meet the requirements of heat preservation and heat insulation.…”

Simulation and experimental verification of energy saving effect of passive preheating natural ventilation double skin façade

“…However, although people are more and more interested in the environmental and energy benefits of building natural ventilation with DSF, on the one hand, the research variables are single, and there is no comprehensive method to evaluate the effect of DSF; on the other hand, due to the lack of simulation verification and performance prediction(Liu et al., 2019), especially in the use of climate driven functions, it has become a key obstacle to the implementation of DSF (Darkwa et al., 2014). Some studies (Hanby et al., 2008; Høseggen et al., 2008; Jiru and Haghighat, 2008; Park, 2003) have been carried out and reported on the thermal performance of DSF, but the real and effective information about passive preheating of DSF in cold season is still insufficient.…”

Prediction of coal and gas outbursts by a novel model based on multisource information fusion

“…SVM, a promising machine learning technique that analyses data for classification and regression, performs very well in some small sample data processing, which may become more complicated by deep learning models; therefore, it is very suitable for gas data. SVM has been successfully applied in many research fields, such as text categorization (Manochandar and Punniyamoorthy, 2018), image classification (Jac Fredo et al., 2019; Rahmani et al., 2019), health care (Cai et al., 2002; Hua and Sun, 2001), and other engineering fields (Dou et al., 2018; Dou and Yang, 2018; Liu et al., 2019; Zuo & Carranza, 2011). D-S evidence theory is a mathematical framework for analysing uncertain and partial information.…”