EMD-LSTM-Markov model leads in building thermal load prediction accuracy

A new paper reviews hybrid forecasting models for short-term building thermal load prediction, comparing various data-driven techniques. The study found that the Empirical Modal Decomposition - long short-term memory - Markov (EMD-LSTM-Markov) model achieved the highest accuracy in predicting day-ahead heating and domestic hot water demands. While this model accurately predicted local power peaks, it underestimated high power swells and spikes. Other evaluated methods, like SVM-SA and RF-ISSA-LSTM, produced smoother demand profiles with less accurate peak predictions. AI

IMPACT This research offers insights into improving the accuracy of AI-driven models for energy demand forecasting in buildings.

RANK_REASON The item is an academic paper detailing a comparative review of forecasting models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Empirical Modal Decomposition
• Improved Sparrow Search Algorithm with the Extreme Learning Machine and Its Application for Prediction
• long short-term memory
• Markov
• random forest
• Scottish households
• Scottish Medical Journal
• simulated annealing
• support vector machine

• paper
• other

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