Energy demand forecasting is crucial for planning and optimizing the use of energy resources in building facilities. However, integrating digital solutions and learning techniques into legacy buildings presents significant challenges due to limited or outdated resources, hampering predictive analytics in these buildings and their circuits. To fill this gap, this article proposes an innovative demand forecasting strategy using an AIoT retrofit architecture based on the SmartLVGrid metamodel. This architecture allows remote monitoring of legacy building circuits, facilitating the collection, processing and storage of data in the cloud. We use several learning algorithms, including linear regression, support vector regressor, random forest regressor, XGBoost regressor, and long short-term memory (LSTM) neural network, to predict energy demand 15 min ahead, identifying potential overruns of contracted demand in accordance with Brazilian regulations. After Bayesian optimization, the LSTM neural network outperformed other models for most of the selected datasets and detected 32 out of 38 demand overruns on the test set. XGBoost and random forest followed closely, detecting 30 demand overruns. Overall, our cost-effective solution optimizes energy usage and efficiently mitigates potential demand exceedances in building installations. This is achieved through a step-by-step approach to upgrading existing aging facilities, which promotes energy efficiency and sustainability.

More from our Archive

• DOI: 10.3390/su151310543 2023

  The State of the Art in Deep Learning Applications, Challenges, and Future Prospects: A Comprehensive Review of Flood Forecasting and Management

  Vijendra Kumar, Hazi Md. Azamathulla, Kul Vaibhav Sharma, Darshan J. Mehta, Kiran Tota Maharaj

• DOI: 10.3390/su151410821 2023

  Microplastics as an Emerging Threat to the Global Environment and Human Health

  Shampa Ghosh, Jitendra Kumar Sinha, Soumya Ghosh, Kshitij Vashisth, Sungsoo Han, Rakesh Bhaskar

• DOI: 10.3390/su151310663 2023

  Unraveling the Interrelationship of Digitalization, Renewable Energy, and Ecological Footprints within the EKC Framework: Empirical Insights from the United States

  Najia Saqib, Ivan A. Duran, Ilhan Ozturk

• DOI: 10.3390/su151310645 2023

  Green Environmental Management System to Support Environmental Performance: What Factors Influence SMEs to Adopt Green Innovations?

  Abdalwali Lutfi, Hamza Alqudah, Mahmaod Alrawad, Ahmad Farhan Alshira’h, Malek Hamed Alshirah, Mohammed Amin Almaiah, Adi Alsyouf, Mohammed Faisal Hassan

• DOI: 10.3390/su151411065 2023

  Green Finance, Enterprise Energy Efficiency, and Green Total Factor Productivity: Evidence from China

  Hepei Li, Chen Chen, Muhammad Umair

• DOI: 10.3390/su151310729 2023

  Innovations and the CO2 Emissions Nexus in the MENA Region: A Spatial Analysis

  Haider Mahmood, Maham Furqan, Najia Saqib, Anass Hamadelneel Adow, Muzaffar Abbas

• DOI: 10.3390/su151310442 2023

  Sustainable Potato Growth under Straw Mulching Practices

  Abdul Waheed, Chuang Li, Murad Muhammad, Mushtaq Ahmad, Khalid Ali Khan, Hamed A. Ghramh, Zhongwei Wang, Daoyuan Zhang

• DOI: 10.3390/su151310329 2023

  From Neglect to Progress: Assessing Social Sustainability and Decent Work in the Tourism Sector

  Eleonora Santos

• DOI: 10.3390/su151410976 2023

  Driving Sustainable Disaster Risk Reduction: A Rapid Review of the Policies and Strategies in Saudi Arabia

  Ahmed M. Al-Wathinani, Dennis G. Barten, Marta Borowska-Stefańska, Paweł Gołda, Noora A. AlDulijan, Mohammad A. Alhallaf, Lujain O. Samarkandi, Abdullah S. Almuhaidly, Mariusz Goniewicz, Waleed O. Samarkandi, Krzysztof Goniewicz

• DOI: 10.3390/su151410940 2023

  Wastewater Treatment and Reuse for Sustainable Water Resources Management: A Systematic Literature Review

  Jorge Alejandro Silva