Research on building energy consumption prediction algorithm based on customized deep learning model
Problem
Building energy consumption is hard to forecast accurately due to uncertainty and noise, hindering energy-saving measures.
Why it matters
Accurate forecasts are stated as essential for implementing energy-saving measures in buildings.
What the AI did
Proposes CCNN-QL, a customized convolutional neural network combined with Q-learning reinforcement learning, that auto-learns and is claimed to continually improve energy-consumption predictions, evaluated on multi-city Chinese building data.
Results
Claimed low MAE and RMSE; exact values and baselines not stated in source
Impact
Evidence supports a proposed prediction method with claimed low error; no independent verification stated.
Record
| Venue | Energy Informatics |
|---|---|
| Published | 2025 |
| Work type | article |
| Authors | Zheng Liang, Junjie Chen |
| Citations | 11 (OpenAlex, at import time) |
| References | 37 |
| Model or method | CCNN-QL (customized CNN with Q-Learning) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1186/s42162-025-00483-y |
| Open access | gold |
| Keywords | building energy, deep learning, CNN, Q-learning, prediction |
Importance rating
real but narrower advance
Abstract states forecasting building energy use is essential for implementing energy-saving measures; a broad sector, but the abstract gives no quantified impact, energy figures, or affected-population scale.
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
|