A Data Decomposition and End-to-End Optimization-Based Monthly Carbon Emission Intensity of Electricity Forecasting Method

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. H...

Full description

Saved in:
Bibliographic Details
Main Authors: Yue Yan, Haoran Feng, Jinwei Song, Shixu Zhang, Shize Zhang, Qi He
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:International Transactions on Electrical Energy Systems
Online Access:http://dx.doi.org/10.1155/etep/9159507
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832540544671154176
author Yue Yan
Haoran Feng
Jinwei Song
Shixu Zhang
Shize Zhang
Qi He
author_facet Yue Yan
Haoran Feng
Jinwei Song
Shixu Zhang
Shize Zhang
Qi He
author_sort Yue Yan
collection DOAJ
description 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.
format Article
id doaj-art-96f5decacd694b0b9bdbe75ea6cff48b
institution Kabale University
issn 2050-7038
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series International Transactions on Electrical Energy Systems
spelling doaj-art-96f5decacd694b0b9bdbe75ea6cff48b2025-02-05T00:00:05ZengWileyInternational Transactions on Electrical Energy Systems2050-70382025-01-01202510.1155/etep/9159507A Data Decomposition and End-to-End Optimization-Based Monthly Carbon Emission Intensity of Electricity Forecasting MethodYue Yan0Haoran Feng1Jinwei Song2Shixu Zhang3Shize Zhang4Qi He5BDC of State Grid Corporation of ChinaSichuan Energy Internet Research InstituteBDC of State Grid Corporation of ChinaSichuan Energy Internet Research InstituteBDC of State Grid Corporation of ChinaBDC of State Grid Corporation of ChinaAccurate 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.http://dx.doi.org/10.1155/etep/9159507
spellingShingle Yue Yan
Haoran Feng
Jinwei Song
Shixu Zhang
Shize Zhang
Qi He
A Data Decomposition and End-to-End Optimization-Based Monthly Carbon Emission Intensity of Electricity Forecasting Method
International Transactions on Electrical Energy Systems
title A Data Decomposition and End-to-End Optimization-Based Monthly Carbon Emission Intensity of Electricity Forecasting Method
title_full A Data Decomposition and End-to-End Optimization-Based Monthly Carbon Emission Intensity of Electricity Forecasting Method
title_fullStr A Data Decomposition and End-to-End Optimization-Based Monthly Carbon Emission Intensity of Electricity Forecasting Method
title_full_unstemmed A Data Decomposition and End-to-End Optimization-Based Monthly Carbon Emission Intensity of Electricity Forecasting Method
title_short A Data Decomposition and End-to-End Optimization-Based Monthly Carbon Emission Intensity of Electricity Forecasting Method
title_sort data decomposition and end to end optimization based monthly carbon emission intensity of electricity forecasting method
url http://dx.doi.org/10.1155/etep/9159507
work_keys_str_mv AT yueyan adatadecompositionandendtoendoptimizationbasedmonthlycarbonemissionintensityofelectricityforecastingmethod
AT haoranfeng adatadecompositionandendtoendoptimizationbasedmonthlycarbonemissionintensityofelectricityforecastingmethod
AT jinweisong adatadecompositionandendtoendoptimizationbasedmonthlycarbonemissionintensityofelectricityforecastingmethod
AT shixuzhang adatadecompositionandendtoendoptimizationbasedmonthlycarbonemissionintensityofelectricityforecastingmethod
AT shizezhang adatadecompositionandendtoendoptimizationbasedmonthlycarbonemissionintensityofelectricityforecastingmethod
AT qihe adatadecompositionandendtoendoptimizationbasedmonthlycarbonemissionintensityofelectricityforecastingmethod
AT yueyan datadecompositionandendtoendoptimizationbasedmonthlycarbonemissionintensityofelectricityforecastingmethod
AT haoranfeng datadecompositionandendtoendoptimizationbasedmonthlycarbonemissionintensityofelectricityforecastingmethod
AT jinweisong datadecompositionandendtoendoptimizationbasedmonthlycarbonemissionintensityofelectricityforecastingmethod
AT shixuzhang datadecompositionandendtoendoptimizationbasedmonthlycarbonemissionintensityofelectricityforecastingmethod
AT shizezhang datadecompositionandendtoendoptimizationbasedmonthlycarbonemissionintensityofelectricityforecastingmethod
AT qihe datadecompositionandendtoendoptimizationbasedmonthlycarbonemissionintensityofelectricityforecastingmethod