Authors: Fucai Ke, Hao Wang

Published on: March 20, 2024

Impact Score: 8.0

Arxiv code: Arxiv:2403.13246

Summary

• What is new: The use of a self-attention mechanism-based transformer model for home EV charging prediction using smart meter data, distinct from prior reliance on public charging station data.
• Why this is important: The challenge of predicting home EV charging events due to limited data availability, crucial for energy management and the promotion of electric vehicle integration.
• What the research proposes: A novel prediction method that employs a transformer model with a `divide-conquer` strategy to analyze historical smart meter data for future EV charging event prediction.
• Results: The method achieves over 96.81% accuracy in predicting home EV charging events across various time spans, demonstrating its effectiveness solely with smart meter data.

Technical Details

Technological frameworks used: Self-attention mechanism-based transformer

Models used: nan

Data used: Historical smart meter data

Potential Impact

Energy management companies, grid operators, EV charging service providers, and smart home technology developers could benefit or need to adapt.

Want to implement this idea in a business?

We have generated a startup concept here: ChargePredict.