Short-Term Power Load Forecasting Based on DPSO-LSSVM Model

The accurate prediction of short-term power load is a critical element for maintaining the normal and stable operation of the power system. For short-term power load forecasting, the collected power load data is preprocessed to quantify temperature, weather, and date types. A short-term load forecas...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access Vol. 13; pp. 32211 - 32224
Main Authors: Ji, Shujun, Zhang, Linhao, Wang, Jinteng, Wei, Tao, Li, Jiadong, Ling, Bu, Xu, Jinglong, Wu, Zuoping
Format: Journal Article
Language:English
Published: IEEE 2025
Subjects:
Accuracy
Adaptation models
Data models
dynamic particle swarm optimization algorithm
Heuristic algorithms
Load modeling
LSSVM
Mathematical models
Optimization
power load
Power system dynamics
Prediction algorithms
Predictive models
radial basis kernel function
short-term
ISSN:2169-3536, 2169-3536
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The accurate prediction of short-term power load is a critical element for maintaining the normal and stable operation of the power system. For short-term power load forecasting, the collected power load data is preprocessed to quantify temperature, weather, and date types. A short-term load forecasting model based on least squares support vector machine is constructed, and the optimal parameters of the model are established. The dynamic particle swarm optimization algorithm is utilized to dynamically adjust the parameters to achieve higher accuracy in load forecasting. The findings denoted that the average absolute percentage error of the least squares support vector machine model using linear kernel function is only 3.75%, the average absolute error is only 256.38MW, and the root mean square error is only 311.20MW. The mean absolute percentage error of the proposed model is only 1.91%, significantly lower than other advanced models. The developed model has stronger adaptability and higher prediction accuracy in dealing with the complexity and dynamic changes of power load data, providing effective technical support for the operation optimization and decision-making of the power system.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2025.3540434