Research on the Combined Prediction Model of Residential Building Energy Consumption Based on Random Forest and BP Neural Network

Xuenan Zhang,Jinhua Zhang,Jinxin Zhang,Yuchuan Zhang,Zhang Xudong

doi:10.1155/2021/7271383

Xuenan Zhang, Jinhua Zhang + Show 3 more

Open Access

https://doi.org/10.1155/2021/7271383

Copy DOI

Journal: Geofluids	Publication Date: Sep 25, 2021
Citations: 2	License type: CC BY 4.0

Affiliation: Fuzhou University, Hubei University

Abstract

As the energy consumption of residential building takes a large part in the building energy consumption, it is important to promote energy efficiency in residential building for green development. In order to evaluate the energy consumption of residential building more effectively, this paper proposes a combined prediction model based on random forest and BP neural network (RF-BPNN). To verify the prediction effect of the RF-BPNN combined model, experiments were performed by using the energy efficiency data set in the UCI database, and the model was evaluated with five indicators: mean absolute error, root mean square deviation, mean absolute percentage error, correlation coefficient, and coincidence index. Compared with the random forest, BP neural network model, and other existing models, respectively, it is proven by the experimental results that the RF-BPNN model possesses higher prediction accuracy and better stability.

Highlights

Global warming has become an important environmental problem that needs to be solved urgently worldwide
To verify the effectiveness of the proposed random forest and BP neural network (RF-BP neural network (BPNN)) combined model for predicting energy consumption in residential buildings, the energy efficiency data set from the UCI, an authoritative database for machine learning, was used for the experiments
This paper predicts the heating and cooling energy consumption of different residential buildings in the energy efficiency data set of the UCI database by proposing the random forest (RF)-BPNN combined model

Summary

Introduction

Global warming has become an important environmental problem that needs to be solved urgently worldwide. The main cause of climate change is that human beings emit a large amount of greenhouse gases into the air, and the sources of these gases are mainly the energy consumption of transportation, industry, and building. With the development of urbanization, the energy consumption of construction has increased significantly. According to the report Buildings and Climate Change: Summary for DecisionMakers published by the United Nations Environment Programme in 2009, building energy consumption accounts for 40% of all global energy consumption, and one-third of global greenhouse gas emission is related to building energy consumption [2]. It is reported that building energy consumption in Europe and North America has increased at a rate of 1.5% and 1.9%, respectively, from 1999 to 2004 [3]. In The 13th Five-Year Plan for Economic and Social Development of the People’s Republic of China, China has determined that the green building area will be increased by more than 2 billion square meters at the end of the period of 2016 to 2020; the building industry, which is one of the largest energy-consuming industries, is facing a great challenge [5]

Methods

Results

Conclusion