Short term heat load forecasting method based on deep belief network

Zhaoxia Wang; Jian Zhao; Feng Ding

doi:10.1117/12.3024377

13 May 2024 Short term heat load forecasting method based on deep belief network

Zhaoxia Wang, Jian Zhao, Feng Ding

Proceedings Volume 13159, Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023); 131594C (2024) https://doi.org/10.1117/12.3024377
Event: Eighth International Conference on Energy System, Electricity and Power (ESEP 2023), 2023, Wuhan, China

Abstract

In order to avoid waste of heat energy, improve energy efficiency and reduce heating costs, this paper proposes a short-term heat load forecasting method based on a Deep Belief Network (DBN). It utilizes the historical heat supply heat data, historical meteorological data, and weather forecast data to predict the user-side heating load in the next 24 hours. First, the correlation coefficient method is used to determine the meteorological data which has a greater impact on the short-term heat load forecast. Second, the 3σ method is used to find and replace the outliers data, and the standardization is processed to form the experimental dataset. Then, using the divided data set, the heat load forecasting model is trained offline and verified, and the parameters are optimized. Finally, the historical heat load data and meteorological data within 72 hours and the weather forecast data within the next 24 hours are used as input to predict the heating load within the next 24 hours online. The experimental results show that the forecasting accuracy of the proposed method is better than the method based on support vector machine and the method based on long and short-term memory network.

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

Citation Download Citation

Zhaoxia Wang, Jian Zhao, and Feng Ding "Short term heat load forecasting method based on deep belief network", Proc. SPIE 13159, Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023), 131594C (13 May 2024); https://doi.org/10.1117/12.3024377

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