Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A novel approach for short-term load forecasting using support vector machines.

Liang Tian1, Afzel Noore

  • 1Lane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV 26506-6109, USA. tian@csee.wvu.edu

International Journal of Neural Systems
|December 14, 2004
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Carbon-Di(indolin-3-one)methene: A BODIPY-Analogue Chromophore Exhibiting Photothermal Conversion.

Organic letters·2026
Same author

Levofloxacin-Induced Cutaneous Adverse Reactions: Characteristics and Rational Use Strategies.

Medical science monitor : international medical journal of experimental and clinical research·2026
Same author

Phosphate-Terminated Nb<sub>2</sub>C MXene as Efficient Catalyst for the Transformation of Glucose Into 5-Hydroxymethylfurfural With 3077 h<sup>-1</sup> Turnover Frequency.

ChemSusChem·2026
Same author

Acid-Triggered, Enzyme-Enabled EPS-Degrading Nanoplatform With Enhanced In Situ Retention for Intravenous Biofilm Therapy.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Investigating the saltiness enhancement in blanch-pretreated celery juice via odor-taste cross-modal integration: insights from EEG, molecular simulations, and flavoromics.

Food chemistry·2026
Same author

Targeting cancer-associated fibroblast-activated HGF/c-MET pathway inhibits extrahepatic cholangiocarcinoma progression and restores gemcitabine therapeutic sensitivity.

Acta pharmaceutica Sinica. B·2026

This study introduces a Support Vector Machine (SVM) for short-term load forecasting. The SVM model demonstrated superior accuracy and generalization compared to traditional neural networks for predicting power demand.

Area of Science:

  • Electrical Engineering
  • Artificial Intelligence
  • Computational Science

Background:

  • Accurate short-term load forecasting is crucial for power system operation and stability.
  • Traditional forecasting methods often struggle with the complex temporal dynamics of power load data.
  • Existing neural network approaches have limitations in generalization and prediction accuracy.

Purpose of the Study:

  • To propose and evaluate a novel Support Vector Machine (SVM) modeling approach for short-term load forecasting.
  • To investigate the impact of incorporating external variables like temperature and humidity into the SVM model.
  • To compare the performance of the SVM approach against established feed-forward and radial basis function neural networks.

Main Methods:

  • Application of the Support Vector Machine (SVM) learning scheme to historical power load data.

Related Experiment Videos

  • Inclusion of relevant input variables such as temperature and humidity to enhance forecasting accuracy.
  • Comparative analysis of the SVM model's performance against feed-forward neural networks and cosine radial basis function neural networks.

    • Main Results:

    • The SVM modeling approach effectively captures the internal temporal properties of power load sequences.
    • Incorporating temperature and humidity as input variables further refines the forecasting accuracy.
    • Numerical results indicate that the SVM approach significantly outperforms both feed-forward and cosine radial basis function neural networks in terms of prediction error.

    Conclusions:

    • The proposed SVM approach offers a robust and accurate method for short-term load forecasting.
    • SVM models exhibit superior generalization capabilities compared to conventional neural network architectures for this task.
    • This research highlights the potential of SVMs in improving the efficiency and reliability of power grid management.