Deep learning for time series forecasting: Advances and open problems

A Casolaro, V Capone, G Iannuzzo, F Camastra - Information, 2023 - mdpi.com
A time series is a sequence of time-ordered data, and it is generally used to describe how a
phenomenon evolves over time. Time series forecasting, estimating future values of time …

[HTML][HTML] Urban building energy performance prediction and retrofit analysis using data-driven machine learning approach

U Ali, S Bano, MH Shamsi, D Sood, C Hoare, W Zuo… - Energy and …, 2024 - Elsevier
Stakeholders such as urban planners and energy policymakers use building energy
performance modeling and analysis to develop strategic sustainable energy plans with the …

[HTML][HTML] Federated-WDCGAN: A federated smart meter data sharing framework for privacy preservation

Z Chen, J Li, L Cheng, X Liu - Applied Energy, 2023 - Elsevier
Energy consumption data are crucial for various smart energy management applications,
such as demand forecasting, customer segmentation, and energy efficiency analysis …

Filling time-series gaps using image techniques: Multidimensional context autoencoder approach for building energy data imputation

C Fu, M Quintana, Z Nagy, C Miller - Applied Thermal Engineering, 2024 - Elsevier
Building energy prediction and management has become increasingly important in recent
decades, driven by the growth of Internet of Things (IoT) devices and the availability of more …

[HTML][HTML] Building simulation in adaptive training of machine learning models

H Amini, K Alanne, R Kosonen - Automation in Construction, 2024 - Elsevier
Combining building performance simulation (BPS) and artificial intelligence (AI) provides
smart buildings with the ability to adapt by utilizing BPS's data synthesis and training …

Creating synthetic energy meter data using conditional diffusion and building metadata

C Fu, H Kazmi, M Quintana, C Miller - Energy and Buildings, 2024 - Elsevier
Advances in machine learning and increased computational power have driven progress in
energy-related research. However, limited access to private energy data from buildings …

Fast prediction of indoor airflow distribution inspired by synthetic image generation artificial intelligence

CA Faulkner, DS Jankowski, JE Castellini Jr, W Zuo… - Building simulation, 2023 - Springer
Prediction of indoor airflow distribution often relies on high-fidelity, computationally intensive
computational fluid dynamics (CFD) simulations. Artificial intelligence (AI) models trained by …

A data transfer method based on one dimensional convolutional neural network for cross-building load prediction

Y Zhang, Z Zhou, Y Du, J Shen, Z Li, J Yuan - Energy, 2023 - Elsevier
Load prediction is one of the basic tasks in energy system operation and management. With
the development of data mining and artificial intelligence, data driven-based prediction …

A scenario framework for electricity grid using Generative Adversarial Networks

B Yilmaz - Sustainable Energy, Grids and Networks, 2023 - Elsevier
This study proposes a synthetic data framework to decrease the cost of smart metering. It
offers clustering of real-time buses based on their electricity consumption levels and …

Performance comparison on improved data-driven building energy prediction under data shortage scenarios in four perspectives: data generation, incremental …

G Li, L Zhan, X Fang, J Gao, C Xu, X He, J Deng… - Energy, 2024 - Elsevier
Accurate building energy predictions (BEPs) are crucial for maintaining a built environment's
sustainability and energy systems. Many data-driven BEPs rely heavily on sufficient data …