What question did this study set out to answer?

Develop an accurate electricity spot market clearing price prediction framework that integrates fractal analysis into deep learning architectures to capture nonlinear, multi-scale market dynamics.

August 16, 2026Advanced ElectromagneticsOpen Access

Electricity Spot Market Clearing Price Prediction Model: Algorithm Research and Application Based on Time Series Analysis

View Full Paper

Ask AI

Bookmark

Authors

SSong CSC. S. Su GGG. M. Gao

Discussion

Member takes

Overview

Algorithmic modeling study demonstrates superior electricity price prediction accuracy across five pilot markets, suggesting improved scheduling and cost management for smart grids.

Key Points

Develop an accurate electricity spot market clearing price prediction framework that integrates fractal analysis into deep learning architectures to capture nonlinear, multi-scale market dynamics.
Quantified long-range dependence and multi-scale volatility using the Hurst exponent and multifractal detrended fluctuation analysis.
Embedded fractal features directly into the loss function of a Long Short-Term Memory (LSTM) network equipped with a dual-window processing strategy.
Validated performance against standard ARIMA, LSTM, VMD-LSTM, CEEMDAN-BERT-LSTM, and Transformer baselines using actual clearing data from five regional pilot markets.
The proposed fractal-aware LSTM consistently outperformed all baseline methods across both MAPE and RMSE metrics across all five pilot regions.
The dual-window mechanism effectively balanced the statistical data requirements for fractal estimation with the need for rapid real-time price adjustment.

Cite This Study

Song et al. (2026) studied this question.

synapsesocial.com/papers/6a8179dcf2fb91fc834ad550 https://doi.org/10.7716/aem.v15i3.3405

View Full Paper

Ask AI

Bookmark

August 16, 2026Advanced ElectromagneticsOpen Access

Electricity Spot Market Clearing Price Prediction Model: Algorithm Research and Application Based on Time Series Analysis

View Full Paper

Ask AI

Bookmark

Authors

SSong CSC. S. Su GGG. M. Gao

Discussion

Member takes

Overview

Algorithmic modeling study demonstrates superior electricity price prediction accuracy across five pilot markets, suggesting improved scheduling and cost management for smart grids.

Key Points

Develop an accurate electricity spot market clearing price prediction framework that integrates fractal analysis into deep learning architectures to capture nonlinear, multi-scale market dynamics.
Quantified long-range dependence and multi-scale volatility using the Hurst exponent and multifractal detrended fluctuation analysis.
Embedded fractal features directly into the loss function of a Long Short-Term Memory (LSTM) network equipped with a dual-window processing strategy.
Validated performance against standard ARIMA, LSTM, VMD-LSTM, CEEMDAN-BERT-LSTM, and Transformer baselines using actual clearing data from five regional pilot markets.
The proposed fractal-aware LSTM consistently outperformed all baseline methods across both MAPE and RMSE metrics across all five pilot regions.
The dual-window mechanism effectively balanced the statistical data requirements for fractal estimation with the need for rapid real-time price adjustment.

Cite This Study

Song et al. (2026) studied this question.

synapsesocial.com/papers/6a8179dcf2fb91fc834ad550 https://doi.org/10.7716/aem.v15i3.3405

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark