A Transformer-Based Method of Multienergy Load Forecasting in Integrated Energy System

Multienergy load forecasting technique is the basis for the operation and scheduling of integrated energy system. Different types of loads in an integrated energy system, i.e., electricity load, heat load, cold load, might have complex and strong coupling relationships among them. If the internal re...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on smart grid 2022-07, Vol.13 (4), p.2703-2714
Main Authors: Wang, Chen, Wang, Ying, Ding, Zhetong, Zheng, Tao, Hu, Jiangyi, Zhang, Kaifeng
Format: Article
Language:English
Subjects:
attention mechanism
Buildings
Coders
Correlation
Electrical loads
Encoders-Decoders
Forecasting
Forecasting techniques
Integrated energy system
Integrated energy systems
Load
Load forecasting
Load modeling
Mathematical models
multi-task
multienergy load forecasting
Predictive models
Task analysis
transformer
Transformers
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Multienergy load forecasting technique is the basis for the operation and scheduling of integrated energy system. Different types of loads in an integrated energy system, i.e., electricity load, heat load, cold load, might have complex and strong coupling relationships among them. If the internal relationship of multienergy load can be considered to realize joint prediction, the accuracy of multienergy load forecasting could be improved. This paper proposes a multi-task model, MultiDeT (Multiple-Decoder Transformer), which firstly adopts the one-encoder multi-decoder structure to realize the multi-task architecture and perform joint prediction of multienergy load. Based on the encoder-decoder architecture, the proposed model encodes all the input data by a uniform encoder and performs each forecasting task by multiple decoders. All tasks share the same encoder parameters, but have dedicated decoders for subtask learning. Therefore, the proposed multi-decoder structure can achieve different levels of attention to the output representation of the encoder by multi-head attention. The entire model is jointly trained end-to-end with losses from each task. Finally, the proposed model is tested on the publicly available datasets. Compared with other forecasting models, the results show that the proposed model has more accurate load forecasting results and has higher generalization capability.
ISSN:1949-3053
1949-3061
DOI:10.1109/TSG.2022.3166600