Impacts of data preprocessing and selection on energy consumption prediction model of HVAC systems based on deep learning

Xiao, Zhihua; Gang, Wenjie; Yuan, Jiaqi; Chen, Zhuolun; Ji, Li; Wang, Xuan; Feng, Xiao

doi:10.1016/j.enbuild.2022.111832

Cited by 51 publications

(7 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…146,147 Standardization changes the data to give a zero mean and unit variance, which allows the algorithms to achieve convergence more easily during training. 148,149 Feature engineering is a vital aspect of data preparation that requires subject expertise and ingenuity. The objectives are to extract useful information from basic data and to develop new features that will enhance the prediction potential of the model.…”

Section: Data Preprocessing and Feature Engineeringmentioning

confidence: 99%

“…Normalization ensures that all characteristics have the same scale, which prevents specific features from overwhelming the learning process due to their greater magnitudes 146,147 . Standardization changes the data to give a zero mean and unit variance, which allows the algorithms to achieve convergence more easily during training 148,149 …”

Section: Fundamentals Of MLmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning for the management of biochar yield and properties of biomass sources for sustainable energy

Nguyen,

Sharma,

Ağbulut

et al. 2024

Biofuels Bioprod Bioref

View full text Add to dashboard Cite

Biochar is emerging as a potential solution for biomass conversion to meet the ever increasing demand for sustainable energy. Efficient management systems are needed in order to exploit fully the potential of biochar. Modern machine learning (ML) techniques, and in particular ensemble approaches and explainable AI methods, are valuable for forecasting the properties and efficiency of biochar properly. Machine‐learning‐based forecasts, optimization, and feature selection are critical for improving biomass management techniques. In this research, we explore the influences of these techniques on the accurate forecasting of biochar yield and properties for a range of biomass sources. We emphasize the importance of the interpretability of a model, as this improves human comprehension and trust in ML predictions. Sensitivity analysis is shown to be an effective technique for finding crucial biomass characteristics that influence the synthesis of biochar. Precision prognostics have far‐reaching ramifications, influencing industries such as biomass logistics, conversion technologies, and the successful use of biomass as renewable energy. These advances can make a substantial contribution to a greener future and can encourage the development of a circular biobased economy. This work emphasizes the importance of using sophisticated data‐driven methodologies such as ML in biochar synthesis, to usher in ecologically friendly energy solutions. These breakthroughs hold the key to a more sustainable and environmentally friendly future.

show abstract

Section: Data Preprocessing and Feature Engineeringmentioning

confidence: 99%

Section: Fundamentals Of MLmentioning

confidence: 99%

Machine learning for the management of biochar yield and properties of biomass sources for sustainable energy

Nguyen,

Sharma,

Ağbulut

et al. 2024

Biofuels Bioprod Bioref

View full text Add to dashboard Cite

show abstract

“…In January 2022, Xiao et al [110] proposed an LSTM model to predict the day-ahead energy consumption. Two data smoothing methods, Gaussian kernel density estimation and Savitzky-Golay filter, were selected and compared.…”

Section: Commercial Building Loadmentioning

confidence: 99%

A Survey on Deep Learning for Building Load Forecasting

Patsakos

Vrochidou

Papakostas

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Energy consumption forecasting is essential for efficient resource management related to both economic and environmental benefits. Forecasting can be implemented through statistical analysis of historical data, application of Artificial Intelligence (AI) algorithms, physical models, and more, and focuses on two directions: the required load for a specific area, e.g., a city, and the required load for a building. Building power forecasting is challenging due to the frequent fluctuation of the required electricity and the complexity and alterability of each building’s energy behavior. This paper focuses on the application of Deep Learning (DL) methods to accurately predict building (residential, commercial, or multiple) power consumption, by utilizing the available historical big data. Research findings are compared to state-of-the-art statistical models and AI methods of the literature to comparatively evaluate their efficiency and justify their future application. The aim of this work is to review up-to-date proposed DL approaches, to highlight the current research status, and to point out emerging challenges and future potential directions. Research revealed a higher interest in residential building load forecasting covering 47.5% of the related literature from 2016 up to date, focusing on short-term forecasting horizon in 55% of the referenced papers. The latter was attributed to the lack of available public datasets for experimentation in different building types, since it was found that in the 48.2% of the related literature, the same historical data regarding residential buildings load consumption was used.

show abstract

“…Furthermore, in line with the International Energy Agency (IEA), building activity is responsible for 36% of global CO 2 emissions 2,3 . In this sector, the heating, ventilation, and air conditioning (HVAC) equipment energy consumption represents 40%‐60% of the total 4,5 . For example, in residential buildings, domestic hot water production, and heating energy consumption reaches 70% in the IEA member countries, resulting in considerable CO 2 emissions 6 …”

Section: Introductionmentioning

confidence: 99%

“…2,3 In this sector, the heating, ventilation, and air conditioning (HVAC) equipment energy consumption represents 40%-60% of the total. 4,5 For example, in residential buildings, domestic hot water production, and heating energy consumption reaches 70% in the IEA member countries, resulting in considerable CO 2 emissions. 6 Nowadays, the energy consumption of HVAC systems has also increased due to the COVID-19 pandemic since, to avoid COVID-19 infections, it is necessary to increase the air infiltration rate.…”

Section: Introductionmentioning

confidence: 99%

Numerical prediction of the solidification and melting of encapsulated nano‐enhanced phase change materials

Cofré‐Toledo,

Muñoz‐Cuevas,

Jofré‐Severino

et al. 2023

Energy Storage

View full text Add to dashboard Cite

The thermal properties of Octadecane vary due to the addition of copper oxide (CuO) nanoparticles. The synthesis of two nano‐enhanced phase change material (NEPCM) required the implementation of the two‐step method, using Octadecane as the base phase change material and CuO nanoparticles at 2.5 and 5.0 wt%. The experimental characterization determined the specific heat capacity, and thermal conductivity of the NEPCMs solid phase, including phase change enthalpy and temperature. These experimental results were then utilized for computational simulation of the thermal charging (solidification) and discharging (melting) processes of NEPCMs within a spherical enclosure, employing the ANSYS/Fluent software. The incorporation of CuO nanoparticles led to an increase in thermal conductivity while causing a decrease in specific heat capacity, enthalpy, and phase change temperature of Octadecane. The computational results revealed a reduction in the melting period and an improvement in the solidification of both NEPCMs. In terms of melting, the convective heat transfer coefficient increased by approximately 27.4% and 3.2% for the NEPCM at 2.5 and 5.0 wt% CuO, respectively. During the solidification process, the overall heat transfer coefficient experienced a significant increase of 43.8% and 59.8% for the NEPCM at 2.5 and 5.0 wt%, respectively.

show abstract

Impacts of data preprocessing and selection on energy consumption prediction model of HVAC systems based on deep learning

Cited by 51 publications

References 63 publications

Machine learning for the management of biochar yield and properties of biomass sources for sustainable energy

Machine learning for the management of biochar yield and properties of biomass sources for sustainable energy

A Survey on Deep Learning for Building Load Forecasting

Numerical prediction of the solidification and melting of encapsulated nano‐enhanced phase change materials

Contact Info

Product

Resources

About