A short-term building cooling load prediction method using deep learning algorithms

By C. Fan, F. Xiao, Yang Zhao. 2017

646 citations recorded by the source corpus.

Short-term building cooling load prediction is the essential foundation for many building energy management tasks, such as fault detection and diagnosis, demand-side management and control optimization. Conventional methods, which heavily rely on physical principles, have limited power in practice as their performance is subject to many physical assumptions. By contrast, data-driven methods have gained huge interests due to their flexibility in model development and the rich data available in modern buildings. The rapid development in data science has provided advanced data analytics to tackle prediction problems in a more convenient, efficient and effective way.

Subfields: Building and Construction, Electrical and Electronic Engineering, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/7c63c8b15acdecce78e4499fa624b4e8963e5f18

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

1. Saifur Rahman
2. Manisa Pipattanasomporn
3. Benjamin C. M. Fung
4. Ying Sun
5. F. Haghighat
6. Mengmeng Cai

In Electrical and Electronic Engineering

1. Saifur Rahman
2. Manisa Pipattanasomporn
3. Benjamin C. M. Fung
4. Ying Sun
5. F. Haghighat
6. Mengmeng Cai

In Environmental Engineering

1. Saifur Rahman
2. Manisa Pipattanasomporn
3. Benjamin C. M. Fung
4. Ying Sun
5. F. Haghighat
6. Mengmeng Cai

Citations in the corpus

• Modeling and forecasting building energy consumption: A review of data-driven techniques (2019, methodology): “For building energy studies, it would mean that inputs used to assess the energy consumption of a building have been related to their tangible physical meaning (Fan et al., 2017).”
• Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks (2018, background): “[26] in the context of short-term load forecasting.”
• A research agenda for augmented and virtual reality in architecture, engineering and construction (2020, background): “Predictive analytics have been employed for a wide range of applications in the AEC sectors from predicting cooling loads [61], occupational hazards [154] to construction costs [46].”
• Day-ahead building-level load forecasts using deep learning vs. traditional time-series techniques (2019, methodology): “The application of deep learning on feature extraction was also discussed in [35], indicating a signi fi cant improvement in prediction accuracy after applying an un-supervised deep learning model.”
• A review of the-state-of-the-art in data-driven approaches for building energy prediction (2020, methodology): “[132] 11054 2369 - 1 Meteorological information, time index, historical data (previous 24hours’ cooling load, exterior temperature and humidity) MLR, RF, GBM, SVR, XGB, DNN, elastic net Educational Cooling load Building 30min 24hour 48 MAE, RMSE, CV(RMSE)”