Deep learning for prediction of energy consumption: an applied use case in an office building
Problem
Building operators need accurate estimates of office building energy consumption to identify inefficiencies and optimize energy management.
Why it matters
Non-residential buildings account for more than a third of global energy consumption, per the abstract.
What the AI did
Feed-forward and recurrent neural networks (MLPs, LSTMs, CNNs) were trained on multisource sensor data from a real office building to predict energy consumption.
Results
LSTMs outperformed stateless MLPs; insufficient usable data limited Seq2Seq; no numeric accuracy metrics stated
Impact
Shows memory-based LSTMs are preferable for building energy prediction with limited data.
Record
| Venue | Applied Intelligence |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | Roberto Morcillo-Jiménez, Jesús Mesa, Juan Gómez‐Romero, M.A. Vila, Marı́a J. Martı́n-Bautista |
| Citations | 37 (OpenAlex, at import time) |
| References | 38 |
| Model or method | MLP, LSTM, CNN, Seq2Seq |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1007/s10489-024-05451-9 |
| Open access | hybrid |
| Keywords | energy prediction, deep learning, LSTM, office building, time series |
Importance rating
significant — thousands to millions affected
Abstract states non-residential buildings account for over a third of global energy consumption; better consumption estimation supports efficiency, though this case addresses a single office building.
More in Climate & Environment
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Learning skillful medium-range global weather forecasting | 2023 | 1,416 |
8
|
| 2 | Accurate medium-range global weather forecasting with 3D neural networks | 2023 | 1,631 |
8
|
| 3 | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast | 2023 | 355 |
8
|
| 4 | Skilful nowcasting of extreme precipitation with NowcastNet | 2023 | 451 |
8
|
| 5 | Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects | 2023 | 378 |
8
|