Systematic Review of Deep Learning and Machine Learning for Building Energy DOI Creative Commons
Sina Ardabili,

Leila Abdolalizadeh,

Csaba Makó

et al.

Frontiers in Energy Research, Journal Year: 2022, Volume and Issue: 10

Published: March 18, 2022

The building energy (BE) management has an essential role in urban sustainability and smart cities. Recently, the novel data science data-driven technologies have shown significant progress analyzing consumption demand sets for a smarter management. machine learning (ML) deep (DL) methods applications, particular, been promising advancement of accurate high-performance models. present study provides comprehensive review ML DL-based techniques applied handling BE systems, it further evaluates performance these techniques. Through systematic taxonomy, advances are carefully investigated, models introduced. According to results obtained forecasting, hybrid ensemble located high robustness range, SVM-based good limitation, ANN-based medium limitation linear regression low limitations. On other hand, DL-based, hybrid, ensemble-based provided highest score. ANN, SVM, single LR-based lower In addition, load higher score

Language: Английский

A survey on deep learning methods for power load and renewable energy forecasting in smart microgrids DOI
Sheraz Aslam, Herodotos Herodotou, Syed Muhammad Mohsin

et al.

Renewable and Sustainable Energy Reviews, Journal Year: 2021, Volume and Issue: 144, P. 110992 - 110992

Published: April 3, 2021

Language: Английский

Citations

407
A review of the-state-of-the-art in data-driven approaches for building energy prediction DOI
Ying Sun, Fariborz Haghighat, Benjamin C. M. Fung

et al.

Energy and Buildings, Journal Year: 2020, Volume and Issue: 221, P. 110022 - 110022

Published: April 30, 2020

Language: Английский

Citations

382
Machine learning driven smart electric power systems: Current trends and new perspectives DOI
Muhammad Sohail Ibrahim, Wei Dong, Qiang Yang

et al.

Applied Energy, Journal Year: 2020, Volume and Issue: 272, P. 115237 - 115237

Published: June 2, 2020

Language: Английский

Citations

305
Improving Electric Energy Consumption Prediction Using CNN and Bi-LSTM DOI Creative Commons
Tuong Le, Minh Thanh Vo, Bay Vo

et al.

Applied Sciences, Journal Year: 2019, Volume and Issue: 9(20), P. 4237 - 4237

Published: Oct. 10, 2019

The electric energy consumption prediction (EECP) is an essential and complex task in intelligent power management system. EECP plays a significant role drawing up national development policy. Therefore, this study proposes Electric Energy Consumption Prediction model utilizing the combination of Convolutional Neural Network (CNN) Bi-directional Long Short-Term Memory (Bi-LSTM) that named EECP-CBL to predict consumption. In framework, two CNNs first module extract important information from several variables individual household (IHEPC) dataset. Then, Bi-LSTM with layers uses above as well trends time series directions including forward backward states make predictions. obtained values will be passed last consists fully connected for finally predicting future. experiments were conducted compare performances proposed state-of-the-art models IHEPC dataset variants. experimental results indicate framework outperforms approaches terms performance metrics on variations real-time, short-term, medium-term long-term timespans.

Language: Английский

Citations

221
Robust short-term electrical load forecasting framework for commercial buildings using deep recurrent neural networks DOI
Gopal Chitalia, Manisa Pipattanasomporn, Vishal Garg

et al.

Applied Energy, Journal Year: 2020, Volume and Issue: 278, P. 115410 - 115410

Published: Aug. 5, 2020

Language: Английский

Citations

171
Building energy prediction using artificial neural networks: A literature survey DOI
Chujie Lu, Sihui Li,

Zhengjun Lu

et al.

Energy and Buildings, Journal Year: 2021, Volume and Issue: 262, P. 111718 - 111718

Published: Nov. 26, 2021

Language: Английский

Citations

148
Machine Learning and Deep Learning Methods for Enhancing Building Energy Efficiency and Indoor Environmental Quality – A Review DOI Creative Commons
Paige Wenbin Tien, Shuangyu Wei, Jo Darkwa

et al.

Energy and AI, Journal Year: 2022, Volume and Issue: 10, P. 100198 - 100198

Published: Aug. 8, 2022

The built environment sector is responsible for almost one-third of the world's final energy consumption. Hence, seeking plausible solutions to minimise building demands and mitigate adverse environmental impacts necessary. Artificial intelligence (AI) techniques such as machine deep learning have been increasingly successfully applied develop environment. This review provided a critical summary existing literature on methods over past decade, with special reference holistic approaches. Different AI-based employed resolve interconnected problems related heating, ventilation air conditioning (HVAC) systems enhance performances were reviewed, including forecasting management, indoor quality occupancy comfort/satisfaction prediction, detection recognition, fault diagnosis. present study explored focusing framework, methodology, performance. highlighted that selecting most suitable model solving problem could be challenging. recent explosive growth experienced by research area has led hundreds algorithms being performance-related studies. showed studies considered wide range scope/scales (from an HVAC component urban areas) time scales (minute year). makes it difficult find optimal algorithm specific task or case. also evaluation metrics, adding challenge. Further developments more guidelines are required field encourage best practices in evaluating models. while had efficiency research, still at experimental testing stage, there limited which implemented strategies actual buildings conducted post-occupancy evaluation.

Language: Английский

Citations

141
Load Forecasting Techniques for Power System: Research Challenges and Survey DOI Creative Commons

Naqash Ahmad,

Yazeed Yasin Ghadi,

Muhammad Adnan

et al.

IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 71054 - 71090

Published: Jan. 1, 2022

The main and pivot part of electric companies is the load forecasting. Decision-makers think tank power sectors should forecast future need electricity with large accuracy small error to give uninterrupted free shedding consumers. demand can be forecasted amicably by many Machine Learning (ML), Deep (DL) Artificial Intelligence (AI) techniques among which hybrid methods are most popular. present technologies forecasting work regarding combination various ML, DL AI algorithms reviewed in this paper. comprehensive review single models functions; advantages disadvantages discussed comparison between performance terms Mean Absolute Error (MAE), Root Squared (RMSE), Percentage (MAPE) values compared literature different support researchers select best model for prediction. This validates fact that will provide a more optimal solution.

Language: Английский

Citations

138
Forecasting short-term electricity load using hybrid support vector regression with grey catastrophe and random forest modeling DOI
Guo‐Feng Fan, Meng Yu,

Song-Qiao Dong

et al.

Utilities Policy, Journal Year: 2021, Volume and Issue: 73, P. 101294 - 101294

Published: Sept. 2, 2021

Language: Английский

Citations

128
Energy consumption and carbon emissions forecasting for industrial processes: Status, challenges and perspectives DOI
Yusha Hu, Yi Man

Renewable and Sustainable Energy Reviews, Journal Year: 2023, Volume and Issue: 182, P. 113405 - 113405

Published: May 25, 2023

Language: Английский

Citations

85