Research on short-term power load forecasting of smart grid based on residual DBSCAN-CNN-LSTM model

Jinyang Li; Yuze Hao; Qihao Huang; Yuanpeng Ji; Zi Wang

doi:10.1117/12.3015911

6 February 2024 Research on short-term power load forecasting of smart grid based on residual DBSCAN-CNN-LSTM model

Jinyang Li, Yuze Hao, Qihao Huang, Yuanpeng Ji, Zi Wang

Proceedings Volume 12979, Ninth International Conference on Energy Materials and Electrical Engineering (ICEMEE 2023); 1297970 (2024) https://doi.org/10.1117/12.3015911
Event: 9th International Conference on Energy Materials and Electrical Engineering (ICEMEE 2023), 2023, Guilin, China

Abstract

Under the "double carbon" goal, China's power system will present the characteristics of "double height" and the balance of supply and demand in power system will face new challenges. A more accurate power load forecasting method is urgently needed. Therefore, a method to visualize the load data is presented and the Long Short-Term Memory (LSTM) artificial neural network is used for short-term power load forecasting. Firstly, preprocesses load data using the DBSCAN clustering algo1ithm. Secondly, the graphical time series load data is extracted by Convolutional Neural Network (CNN) and used as the input of LSTM for prediction. Finally, the predicted picture is transformed into time series curve to obtain the final short-term load forecasting results. This method not only enriches the expression of load data, but also highlights the advantages of LSTM method in image analysis and processing. The experimental results show that this method improves the accuracy of short-term load forecasting to a certain extent and meets the needs of practical engineering.

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

Citation Download Citation

Jinyang Li, Yuze Hao, Qihao Huang, Yuanpeng Ji, and Zi Wang "Research on short-term power load forecasting of smart grid based on residual DBSCAN-CNN-LSTM model", Proc. SPIE 12979, Ninth International Conference on Energy Materials and Electrical Engineering (ICEMEE 2023), 1297970 (6 February 2024); https://doi.org/10.1117/12.3015911

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