Authors: Aditya Mishra, Haroon R. Lone, Aayush Mishra

Published on: September 06, 2023

Impact Score: 8.22

Arxiv code: Arxiv:2309.02908

Summary

• What is new: This research introduces a new LSTM model for forecasting building energy consumption that outperforms traditional models like linear regression, decision trees, and random forest in terms of accuracy.
• Why this is important: Effective energy management in buildings requires accurate energy consumption predictions, which has been challenging with existing models.
• What the research proposes: A Long Short-Term Memory (LSTM) model that leverages historical energy data, occupancy patterns, and weather conditions to predict energy consumption more accurately.
• Results: The LSTM model achieved the highest R2 score of 0.97 and the lowest mean absolute error (MAE) of 0.007, demonstrating superior prediction accuracy.

Technical Details

Technological frameworks used: Long Short-Term Memory (LSTM)

Models used: Compared with linear regression, decision trees, random forest

Data used: Historical energy data, occupancy patterns, weather conditions

Potential Impact

Energy management companies, utility providers, and building management systems could significantly benefit or need to adapt.

Want to implement this idea in a business?

We have generated a startup concept here: EnerPredict.