Research on electricity forecast of large industrial consumers based on combination model

Qi Wu; Dong-tao Wang

doi:10.1117/12.3015223

6 February 2024 Research on electricity forecast of large industrial consumers based on combination model

Qi Wu, Dong-tao Wang

Proceedings Volume 12979, Ninth International Conference on Energy Materials and Electrical Engineering (ICEMEE 2023); 1297955 (2024) https://doi.org/10.1117/12.3015223
Event: 9th International Conference on Energy Materials and Electrical Engineering (ICEMEE 2023), 2023, Guilin, China

Abstract

This paper investigates the application of neural network formulas, supported by statistical basic analysis techniques and machine learning, to forecast the monthly electricity consumption of large industrial consumers in a specific province. Firstly, we utilize the SARIMA model, GM (1,1) model, and LSTM neural network model to individually forecast electricity consumption based on data collected from January 2016 to December 2022. Subsequently, we combine these three models using a weighted technique to create a comprehensive forecasting model. Finally, we evaluate the performance of the model by assessing the maximum prediction error and employing the MAPE analysis criteria. The results demonstrate that the combined model outperforms the alternative models, indicating its superior prediction accuracy. Therefore, the combined model can be effectively employed as a forecasting technique for large industrial consumers in the region to predict electricity consumption for the 12-month period of 2023. This approach presents a novel method for predicting electricity consumption among industrial users in this sector.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Qi Wu and Dong-tao Wang "Research on electricity forecast of large industrial consumers based on combination model", Proc. SPIE 12979, Ninth International Conference on Energy Materials and Electrical Engineering (ICEMEE 2023), 1297955 (6 February 2024); https://doi.org/10.1117/12.3015223

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available