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

Power load forecasting combining deep learning models and improved CLPO algorithm.

Jianguang Song1, Xiang Wei2, Zhipeng Li2

  • 1Electric Power Dispatch Center, State Grid Gansu Electric Power Company, Lanzhou, China.

Plos One
|June 29, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Maximum Power Flow and Line Loadability01:23

Maximum Power Flow and Line Loadability

The maximum power flow for lossy transmission lines is derived using ABCD parameters in phasor form. These parameters create a matrix relationship between the sending-end and receiving-end voltages and currents, allowing the determination of the receiving-end current. This relationship facilitates calculating the complex power delivered to the receiving end, from which real and reactive power components are derived.

You might also read

Related Articles

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

Sort by
Same author

The Association of C-Reactive Protein-Triglyceride Glucose Index with Major Adverse Cardiovascular Events in Patients with Acute Myocardial Infarction.

Journal of inflammation research·2026
Same author

Distribution and Enrichment Regularity of Trace Elements in Meitan Cuiya Tea and Soil.

Toxics·2025
Same author

Developing high-performance Zn<sup>2+</sup>-pre-inserted MnO<sub>2</sub><i>via in situ</i> electrodeposition for aqueous Zn-ion batteries.

Dalton transactions (Cambridge, England : 2003)·2025
Same author

Non-Invasive Monitoring and Differentiation of Aging Mice Treated with Goat Whey Powder by an Electronic Nose Coupled with Chemometric Methods.

Sensors (Basel, Switzerland)·2025
Same author

The Neuroprotective and Anxiolytic Effects of Magnesium Sulfate on Retinal Dopaminergic Neurons in 6-OHDA-Induced Parkinsonian Rats: A Pilot Study.

Brain sciences·2024
Same author

Endothelial Notch Signaling Regulates the Function of the Retinal Pigment Epithelial Barrier via EC Angiocrine Signaling.

Antioxidants (Basel, Switzerland)·2023
Same journal

Modeling and analysis of forward and inverse kinematics for a flexible Stewart platform.

PloS one·2026
Same journal

Barriers and facilitators to healthcare utilization amongst people living with sickle cell disease in the United States: A scoping review.

PloS one·2026
Same journal

Enhancing data completeness in time series: Imputation strategies for missing data using significant periodically correlated components.

PloS one·2026
Same journal

Key targets and mechanisms by which gut microbiota-derived metabolites regulate Alzheimer's disease through the immune - inflammatory pathway: Based on network pharmacology and molecular docking.

PloS one·2026
Same journal

Grid-tied Transformer-less Boost Switched Capacitor Topology (TLBSCT) for PV applications.

PloS one·2026
Same journal

The load-velocity profiles and exercise-specific velocity zones for seven commonly used weightlifting exercises.

PloS one·2026
See all related articles

This study introduces a novel power load forecasting model combining deep learning with parrot optimization for enhanced accuracy and faster convergence. The new model significantly outperforms existing methods, especially under extreme weather and variable load conditions.

Area of Science:

  • Electrical Engineering
  • Artificial Intelligence
  • Data Science

Background:

  • Accurate power load forecasting is crucial for power system stability and energy optimization.
  • Existing forecasting methods struggle with complex nonlinear load data and can converge to suboptimal solutions.

Purpose of the Study:

  • To develop an advanced power load forecasting model that overcomes the limitations of existing methods.
  • To improve prediction accuracy, convergence speed, and adaptability to dynamic grid conditions.

Main Methods:

  • A hybrid deep learning model integrating time-series convolutional networks, Long Short-Term Memory (LSTM), and bidirectional LSTM networks.
  • Incorporation of the parrot optimization algorithm for iterative strategy optimization and joint error correction.

Related Experiment Videos

  • Implementation of continuous learning and lightweight retraining for sustained accuracy and stability.

    • Main Results:

    • The proposed model demonstrates faster convergence (reaching 0.85 accuracy in ~200 rounds vs. ~330 for conventional methods) and higher peak accuracy (~0.95).
    • Achieved a lower mean absolute error (0.181) on the UK-NGED dataset compared to baseline models (0.214-0.257).
    • Significantly reduced root mean square error (0.250 vs. 0.295-0.318) under extreme weather conditions, with statistically significant improvements (p < 0.05).

    Conclusions:

    • The developed model offers superior accuracy and faster convergence for power load forecasting.
    • It exhibits enhanced adaptability to variable load patterns, concept drift, and extreme weather events.
    • Provides reliable decision support for smart grid scheduling and energy optimization.