Prediction of electricity carbon emission peak in intelligent buildings with discrete second-order differential and time-sharing carbon measurement
Abstract To achieve intelligent building energy management, predict the peak carbon emissions of intelligent building energy. A prediction model integrating discrete second-order difference and time-sharing carbon measurement is proposed. Considering peak and valley habits of building users, the car...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-04-01
|
| Series: | Sustainable Energy Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40807-025-00163-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract To achieve intelligent building energy management, predict the peak carbon emissions of intelligent building energy. A prediction model integrating discrete second-order difference and time-sharing carbon measurement is proposed. Considering peak and valley habits of building users, the carbon emissions cycle is divided into low, medium and high emissions ratio stages, establishing a time-sharing carbon emissions measurement model. In this model, the carbon emissions data time series obtained by the model are first input into the discrete second-order difference equation, and the final building carbon emissions value is obtained through model mapping generation, one-time accumulation generation, univariate second-order difference equation modeling, inverse accumulation generation and inverse mapping generation. Then, combined with BP neural network, the prediction error of carbon emissions interval series was estimated and gradually corrected, obtaining more accurate predictions after removing the error. The experimental results show that the model has a small error in predicting the peak carbon emissions of building electricity. It predicts the carbon emissions in different situations, the peak and time to reach the peak, providing a reference for the energy management research of smart buildings. |
|---|---|
| ISSN: | 2731-9237 |