Share

IIR document

Load forecasting analysis for the improved collaborative optimization algorithm of ground source heat pump air conditioning. 

Author(s) : LIU Z., CAO M.

Type of article: IJR article

Summary

To address the challenges of model hyperparameter tuning and multi-parameter coupling dynamic modeling in ground source heat pump load forecasting, this paper innovatively proposes a predictive framework that combines hybrid optimization algorithms with deep learning. This model uses an improved quantum genetic algorithm combined with an enhanced adaptive differential evolution algorithm to adjust dynamic parameters, achieving intelligent optimization of key hyperparameters for the BiLSTM model. Additionally, an improved BiLSTM network is constructed, incorporating residual connections and a multi-head attention mechanism to more accurately capture the delayed response characteristics caused by thermal inertia. Compared to existing models, this model outperforms others in load forecasting, providing technical support for the intelligent control and energy efficiency optimization of ground source heat pump air conditioning.

Available documents

Format PDF

Pages: 13

Available

  • Public price

    20 €

  • Member price*

    Free

* Best rate depending on membership category (see the detailed benefits of individual and corporate memberships).

Details

  • Original title: Load forecasting analysis for the improved collaborative optimization algorithm of ground source heat pump air conditioning. 
  • Record ID : 30034941
  • Languages: English
  • Subject: Technology
  • Source: International Journal of Refrigeration - Revue Internationale du Froid - vol. 187
  • Publication date: 2026/07
  • DOI: http://dx.doi.org/https://doi.org/10.1016/j.ijrefrig.2026.106934

Links


See other articles in this issue (35)
See the source

Indexing