The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Sebagai jenis sumber perkhidmatan sains dan teknologi yang penting, data penggunaan tenaga memainkan peranan penting dalam proses penyepaduan rantaian nilai antara pengeluar perkakas rumah dan grid negeri. Ramalan penggunaan elektrik yang tepat adalah penting untuk program tindak balas permintaan dalam perancangan grid pintar. Sebilangan besar algoritma ramalan sedia ada hanya mengeksploitasi data kepunyaan satu domain, iaitu, data beban elektrik sejarah. Walau bagaimanapun, kebergantungan dan korelasi mungkin wujud antara domain yang berbeza, seperti keadaan cuaca serantau dan profil penggunaan tenaga kediaman/industri tempatan. Untuk memanfaatkan sumber merentas domain, rangka kerja ramalan penggunaan tenaga hibrid dibentangkan dalam kertas kerja ini. Rangka kerja ini menggabungkan model ingatan jangka pendek panjang dengan unit penyahkod pengekod (ED-LSTM) untuk melaksanakan peramalan urutan ke jujukan. Percubaan meluas dijalankan dengan beberapa algoritma yang paling biasa digunakan ke atas set data merentas domain bersepadu. Keputusan menunjukkan bahawa rangka kerja ramalan pelbagai langkah yang dicadangkan mengatasi kebanyakan pendekatan sedia ada.
Ye TAO
Qingdao University of Science and Technology
Fang KONG
Qingdao University of Science and Technology
Wenjun JU
Haier Technology Co., Ltd.
Hui LI
Qingdao University of Science and Technology
Ruichun HOU
Ocean University of China
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Ye TAO, Fang KONG, Wenjun JU, Hui LI, Ruichun HOU, "Cross-Domain Energy Consumption Prediction via ED-LSTM Networks" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 8, pp. 1204-1213, August 2021, doi: 10.1587/transinf.2020BDP0006.
Abstract: As an important type of science and technology service resource, energy consumption data play a vital role in the process of value chain integration between home appliance manufacturers and the state grid. Accurate electricity consumption prediction is essential for demand response programs in smart grid planning. The vast majority of existing prediction algorithms only exploit data belonging to a single domain, i.e., historical electricity load data. However, dependencies and correlations may exist among different domains, such as the regional weather condition and local residential/industrial energy consumption profiles. To take advantage of cross-domain resources, a hybrid energy consumption prediction framework is presented in this paper. This framework combines the long short-term memory model with an encoder-decoder unit (ED-LSTM) to perform sequence-to-sequence forecasting. Extensive experiments are conducted with several of the most commonly used algorithms over integrated cross-domain datasets. The results indicate that the proposed multistep forecasting framework outperforms most of the existing approaches.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020BDP0006/_p
Salinan
@ARTICLE{e104-d_8_1204,
author={Ye TAO, Fang KONG, Wenjun JU, Hui LI, Ruichun HOU, },
journal={IEICE TRANSACTIONS on Information},
title={Cross-Domain Energy Consumption Prediction via ED-LSTM Networks},
year={2021},
volume={E104-D},
number={8},
pages={1204-1213},
abstract={As an important type of science and technology service resource, energy consumption data play a vital role in the process of value chain integration between home appliance manufacturers and the state grid. Accurate electricity consumption prediction is essential for demand response programs in smart grid planning. The vast majority of existing prediction algorithms only exploit data belonging to a single domain, i.e., historical electricity load data. However, dependencies and correlations may exist among different domains, such as the regional weather condition and local residential/industrial energy consumption profiles. To take advantage of cross-domain resources, a hybrid energy consumption prediction framework is presented in this paper. This framework combines the long short-term memory model with an encoder-decoder unit (ED-LSTM) to perform sequence-to-sequence forecasting. Extensive experiments are conducted with several of the most commonly used algorithms over integrated cross-domain datasets. The results indicate that the proposed multistep forecasting framework outperforms most of the existing approaches.},
keywords={},
doi={10.1587/transinf.2020BDP0006},
ISSN={1745-1361},
month={August},}
Salinan
TY - JOUR
TI - Cross-Domain Energy Consumption Prediction via ED-LSTM Networks
T2 - IEICE TRANSACTIONS on Information
SP - 1204
EP - 1213
AU - Ye TAO
AU - Fang KONG
AU - Wenjun JU
AU - Hui LI
AU - Ruichun HOU
PY - 2021
DO - 10.1587/transinf.2020BDP0006
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2021
AB - As an important type of science and technology service resource, energy consumption data play a vital role in the process of value chain integration between home appliance manufacturers and the state grid. Accurate electricity consumption prediction is essential for demand response programs in smart grid planning. The vast majority of existing prediction algorithms only exploit data belonging to a single domain, i.e., historical electricity load data. However, dependencies and correlations may exist among different domains, such as the regional weather condition and local residential/industrial energy consumption profiles. To take advantage of cross-domain resources, a hybrid energy consumption prediction framework is presented in this paper. This framework combines the long short-term memory model with an encoder-decoder unit (ED-LSTM) to perform sequence-to-sequence forecasting. Extensive experiments are conducted with several of the most commonly used algorithms over integrated cross-domain datasets. The results indicate that the proposed multistep forecasting framework outperforms most of the existing approaches.
ER -