Short-term power grid load forecasting based on variable weight combination hybrid model

Tingting Lin, Sen Fan and XinYing Zhang

International Journal of Low-Carbon Technologies, 2024, vol. 19, 683-689

Abstract: The power grid load exhibits non-linearity and volatility, posing challenges to power grid dispatching. To enhance the precision of power grid load forecasting, a variable weight combination forecasting model is suggested to address the issue of inadequate forecasting efficacy of individual algorithms. Considering the impact of various environmental factors on power grid load, a load influence feature dataset is formulated. Initially, support vector machines, genetic algorithm-optimized back propagation (BP) neural networks and radial basis neural networks are employed to forecast individual loads. Subsequently, a variance–covariance weight dynamic distribution method is utilized to merge the prediction results of the three individual algorithms, thereby establishing a short-term power grid load prediction model with variable weight combination. Taking a regional power grid as an example, the simulation results show that the prediction accuracy of the variable weight combination model is higher than that of the single algorithm. Taking the evaluation index MAPE as an example, compared with the three single algorithms, the prediction accuracy is improved by 42.31%, 48.56% and 65.33%. The practice proves that the proposed variable weight combination forecasting model greatly improves the accuracy of power network load forecasting.

Keywords: power network load forecasting; variable weight combination model；LSSVM; WOA-LSTM; XGBoost; deep learning (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1093/ijlct/ctae028 (application/pdf)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:oup:ijlctc:v:19:y:2024:i::p:683-689.

Access Statistics for this article

International Journal of Low-Carbon Technologies is currently edited by Saffa B. Riffat

More articles in International Journal of Low-Carbon Technologies from Oxford University Press
Bibliographic data for series maintained by Oxford University Press ().