LSTM networks enhance electricity price prediction with adaptive learning

Researchers have developed an adaptive online learning framework using Long Short-Term Memory (LSTM) networks to improve the accuracy of day-ahead electricity price predictions in the California energy market. The model incorporates historical prices, weather data, and energy generation mix, enhanced by a novel custom loss function combining Mean Absolute Error (MAE), Jensen-Shannon Divergence (JSD), and a smoothness penalty. This adaptive approach demonstrated superior performance over static models, reducing Mean Squared Error (MSE), MAE, and Root Mean Square Error (RMSE) by significant margins. AI

IMPACT This research offers a more robust framework for electricity price forecasting, potentially leading to better decision-making in dynamic energy markets.

RANK_REASON Academic paper detailing a new machine learning model and framework. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• California
• Jensen-Shannon divergence
• long short-term memory
• Mae
• Salih Salihoğlu

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →