Forecasting Time-Series Energy Data in Buildings Using an Additive Artificial Intelligence Model for Improving Energy Efficiency.

Ngoc-Son Truong,Ngoc-Tri Ngo,Anh-Duc Pham,Yu-Ting Bai

doi:10.1155/2021/6028573

Ngoc-Son Truong, Ngoc-Tri Ngo + Show 2 more

Open Access

https://doi.org/10.1155/2021/6028573

Copy DOI

Abstract

Building energy efficiency is important because buildings consume a significant energy amount. The study proposed additive artificial neural networks (AANNs) for predicting energy use in residential buildings. A dataset in hourly resolution was used to evaluate the AANNs model, which was collected from a residential building with a solar photovoltaic system. The proposed AANNs model achieved good predictive accuracy with 14.04% in mean absolute percentage error (MAPE) and 111.98 Watt-hour in the mean absolute error (MAE). Compared to the support vector regression (SVR), the AANNs model can significantly improve the accuracy which was 103.75% in MAPE. Compared to the ANNs model, accuracy improvement percentage by the AANNs model was 4.6% in MAPE. The AANNs model was the most effective forecasting model among the investigated models in predicting energy consumption, which provides building managers with a useful tool to improve energy efficiency in buildings.

Highlights

National development, urbanization, and population growth require a growing energy demand
Results and Discussion. e investigated artificial intelligence (AI) models in this study include the support vector regression (SVR)-PL, SVR-radial basis function (RBF), linear regression (LR), M5Rules, artificial neural networks (ANNs), and artificial neural networks (AANNs) models. eir performance was assessed using a dataset that was recorded from a residential building with renewable energy
The mean absolute error (MAE) and root-mean-square error (RMSE) values obtained by the SVR model with the PL kernel (SVR-PL) model were relatively high, up to 236.83 Wh and 430.69 Wh, respectively, for predicting residential building energy use profiles. e results of these statistical indices indicated that the SVR-PL was not effective in energy use prediction in residential buildings with renewable energy

Summary

Introduction

Urbanization, and population growth require a growing energy demand. Buildings account for remarkable energy consumption during their operational stages and are responsible for carbon emissions and global warming. Energy performance in buildings is of prime importance all over the world. Us, energy efficiency is one of the most concerning topics among academic researchers and decision-makers in the energy sector. It plays a remarkable role in targeting a low-carbon economy [1]. National governments have recognized the benefits of efficient uses of energy in the building sector. E efficient use of energy in buildings strongly affects the building’s capability to meet the building green certificates in the green building rating system to reduce carbon emission and greenhouse effects. National governments have recognized the benefits of efficient uses of energy in the building sector. e efficient use of energy in buildings strongly affects the building’s capability to meet the building green certificates in the green building rating system to reduce carbon emission and greenhouse effects. us, energy usage prediction in buildings is necessary for energy planning, management, and conservation

Methods

Results

Conclusion