Long-term system load forecasting based on data-driven linear clustering method
Abstract In this paper, a data-driven linear clustering (DLC) method is proposed to solve the long-term system load forecasting problem caused by load fluctuation in some developed cities. A large substation load dataset with annual interval is utilized and firstly preprocessed by the proposed linea...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2017-05-01
|
Series: | Journal of Modern Power Systems and Clean Energy |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1007/s40565-017-0288-x |
id |
doaj-6cee257e6ee341c5a940ce54ab32d1e4 |
---|---|
record_format |
Article |
spelling |
doaj-6cee257e6ee341c5a940ce54ab32d1e42021-05-03T01:57:24ZengIEEEJournal of Modern Power Systems and Clean Energy2196-56252196-54202017-05-016230631610.1007/s40565-017-0288-xLong-term system load forecasting based on data-driven linear clustering methodYiyan LI0Dong HAN1Zheng YAN2Key Laboratory of Control of Power Transmission and Conversion, Ministry of Education, Department of Electrical Engineering, Shanghai Jiao Tong UniversityKey Laboratory of Control of Power Transmission and Conversion, Ministry of Education, Department of Electrical Engineering, Shanghai Jiao Tong UniversityKey Laboratory of Control of Power Transmission and Conversion, Ministry of Education, Department of Electrical Engineering, Shanghai Jiao Tong UniversityAbstract In this paper, a data-driven linear clustering (DLC) method is proposed to solve the long-term system load forecasting problem caused by load fluctuation in some developed cities. A large substation load dataset with annual interval is utilized and firstly preprocessed by the proposed linear clustering method to prepare for modelling. Then optimal autoregressive integrated moving average (ARIMA) models are constructed for the sum series of each obtained cluster to forecast their respective future load. Finally, the system load forecasting result is obtained by summing up all the ARIMA forecasts. From error analysis and application results, it is both theoretically and practically proved that the proposed DLC method can reduce random forecasting errors while guaranteeing modelling accuracy, so that a more stable and precise system load forecasting result can be obtained.http://link.springer.com/article/10.1007/s40565-017-0288-xLong-term system load forecastingData-drivenLinear clusteringAutoregressive integrated moving average (ARIMA)Error analysis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yiyan LI Dong HAN Zheng YAN |
spellingShingle |
Yiyan LI Dong HAN Zheng YAN Long-term system load forecasting based on data-driven linear clustering method Journal of Modern Power Systems and Clean Energy Long-term system load forecasting Data-driven Linear clustering Autoregressive integrated moving average (ARIMA) Error analysis |
author_facet |
Yiyan LI Dong HAN Zheng YAN |
author_sort |
Yiyan LI |
title |
Long-term system load forecasting based on data-driven linear clustering method |
title_short |
Long-term system load forecasting based on data-driven linear clustering method |
title_full |
Long-term system load forecasting based on data-driven linear clustering method |
title_fullStr |
Long-term system load forecasting based on data-driven linear clustering method |
title_full_unstemmed |
Long-term system load forecasting based on data-driven linear clustering method |
title_sort |
long-term system load forecasting based on data-driven linear clustering method |
publisher |
IEEE |
series |
Journal of Modern Power Systems and Clean Energy |
issn |
2196-5625 2196-5420 |
publishDate |
2017-05-01 |
description |
Abstract In this paper, a data-driven linear clustering (DLC) method is proposed to solve the long-term system load forecasting problem caused by load fluctuation in some developed cities. A large substation load dataset with annual interval is utilized and firstly preprocessed by the proposed linear clustering method to prepare for modelling. Then optimal autoregressive integrated moving average (ARIMA) models are constructed for the sum series of each obtained cluster to forecast their respective future load. Finally, the system load forecasting result is obtained by summing up all the ARIMA forecasts. From error analysis and application results, it is both theoretically and practically proved that the proposed DLC method can reduce random forecasting errors while guaranteeing modelling accuracy, so that a more stable and precise system load forecasting result can be obtained. |
topic |
Long-term system load forecasting Data-driven Linear clustering Autoregressive integrated moving average (ARIMA) Error analysis |
url |
http://link.springer.com/article/10.1007/s40565-017-0288-x |
work_keys_str_mv |
AT yiyanli longtermsystemloadforecastingbasedondatadrivenlinearclusteringmethod AT donghan longtermsystemloadforecastingbasedondatadrivenlinearclusteringmethod AT zhengyan longtermsystemloadforecastingbasedondatadrivenlinearclusteringmethod |
_version_ |
1721485378904391680 |