A Data Decomposition and End‐to‐End Optimization‐Based Monthly Carbon Emission Intensity of Electricity Forecasting Method.
Saved in:
| Title: | A Data Decomposition and End‐to‐End Optimization‐Based Monthly Carbon Emission Intensity of Electricity Forecasting Method. |
|---|---|
| Authors: | Yan, Yue1 (AUTHOR), Feng, Haoran2,3 (AUTHOR) 969082563@qq.com, Song, Jinwei1 (AUTHOR), Zhang, Shixu2,3 (AUTHOR), Zhang, Shize1 (AUTHOR), He, Qi1 (AUTHOR), Gao, Yang (AUTHOR) |
| Source: | International Transactions on Electrical Energy Systems. 1/28/2025, Vol. 2025, p1-10. 10p. |
| Subject Terms: | *Carbon emissions, *Electric power consumption, Support vector machines, Differential evolution, Decomposition method |
| Abstract: | Accurate high‐resolution carbon emission intensity of electricity forecasting (CIF) can assist multi‐staker in timely adjusting their electricity consumption strategies to gain benefits. Few studies attempt to perform high‐resolution (monthly and above) CIF due to the limited carbon emission data. High‐resolution electricity data is easily available, and there is a coupling relationship between electricity and carbon emission data, making it possible to perform high‐resolution CIF. Therefore, the paper proposes an end‐to‐end monthly CIF approach using annual carbon emission and monthly electricity consumption data, which can be divided into two stages. In Stage I, a monthly carbon emission data generator based on the Denton decomposition method is proposed. In Stage II, support vector machine (SVM), known for their effectiveness in small‐sample prediction, are employed for monthly CIF. To ensure that the decomposed data effectively improves the predictor's performance, we propose an end‐to‐end optimization strategy. This strategy feeds back the predictor's performance on actual monthly data as optimization target to the generator and uses differential evolution algorithms (DEA) to optimize and adjust the decomposed data. Case studies conducted using actual data from Guangdong Province, China, demonstrate that the proposed method can effectively enhance monthly data, thereby improving prediction accuracy. [ABSTRACT FROM AUTHOR] |
| Copyright of International Transactions on Electrical Energy Systems is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | GreenFILE |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Accurate high‐resolution carbon emission intensity of electricity forecasting (CIF) can assist multi‐staker in timely adjusting their electricity consumption strategies to gain benefits. Few studies attempt to perform high‐resolution (monthly and above) CIF due to the limited carbon emission data. High‐resolution electricity data is easily available, and there is a coupling relationship between electricity and carbon emission data, making it possible to perform high‐resolution CIF. Therefore, the paper proposes an end‐to‐end monthly CIF approach using annual carbon emission and monthly electricity consumption data, which can be divided into two stages. In Stage I, a monthly carbon emission data generator based on the Denton decomposition method is proposed. In Stage II, support vector machine (SVM), known for their effectiveness in small‐sample prediction, are employed for monthly CIF. To ensure that the decomposed data effectively improves the predictor's performance, we propose an end‐to‐end optimization strategy. This strategy feeds back the predictor's performance on actual monthly data as optimization target to the generator and uses differential evolution algorithms (DEA) to optimize and adjust the decomposed data. Case studies conducted using actual data from Guangdong Province, China, demonstrate that the proposed method can effectively enhance monthly data, thereby improving prediction accuracy. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20507038 |
| DOI: | 10.1155/etep/9159507 |
