What does this research mean for the field?

The CNN-LSTM-VMD model achieves the highest prediction accuracy for short-term Amp-load forecasting in medium-voltage electricity networks, outperforming other hybrid models. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To evaluate the effectiveness of hybrid machine learning models for accurate short-term load prediction in medium-voltage electricity networks.

March 4, 2026ElectricityOpen Access

A Comparative Study of Hybridized Machine Learning Models for Short-Term Load Prediction in Medium-Voltage Electricity Networks

View Full Paper

Ask AI

Bookmark

Authors

AMAugustine B. MakokhaMoi University SSSimiyu SitatiMoi University AAAbraham AruseiKenya Seed Company (Kenya)

Discussion

Member takes

Implication

Comparative evaluation of hybrid models improves short-term load prediction in electricity networks, suggesting enhanced methods for accuracy.

Key Points

To evaluate the effectiveness of hybrid machine learning models for accurate short-term load prediction in medium-voltage electricity networks.
Developed four hybrid models including ANFIS-GA, ANFIS-PSO, CNN-LSTM, and CNN-LSTM-VMD.
Used hourly Amp-load and meteorological data from a substation in Kenya (January 2023 - June 2024).
Applied variational mode decomposition (VMD) for input data pre-processing.
Analyzed prediction performance using metrics like MAPE, RMSE, and R2 scores.
ANFIS-PSO and ANFIS-GA models achieved MAPE values of 4.519 and 4.363 respectively.
CNN-LSTM-VMD model exhibited the highest prediction accuracy with a MAPE of 2.625, RMSE of 0.1898, and R2 of 0.9702.
VMD application enhanced prediction accuracy across all models.

Cite This Study

Makokha et al. (2026) studied this question.

synapsesocial.com/papers/69a7cd2ad48f933b5eed950a https://doi.org/10.3390/electricity7010021

View Full Paper

Ask AI

Bookmark

Implication

Comparative evaluation of hybrid models improves short-term load prediction in electricity networks, suggesting enhanced methods for accuracy.

A Comparative Study of Hybridized Machine Learning Models for Short-Term Load Prediction in Medium-Voltage Electricity Networks

Discussion

Member takes

Implication

Key Points

Cite This Study

A Comparative Study of Hybridized Machine Learning Models for Short-Term Load Prediction in Medium-Voltage Electricity Networks

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider