# Divide-Conquer Transformer Learning for Predicting Electric Vehicle Charging Events Using Smart Meter Data

arXiv: https://arxiv.org/abs/2403.13246 · HTML: https://mlsanity.com/paper/2403.13246/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 32 references that are in the map.
- First posted on arXiv 20 Mar 2024.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Pruning Self-attentions into Convolutional Layers in Single Path](https://mlsanity.com/paper/2111.11802/) (2021)
- [Dynamic Focus-aware Positional Queries for Semantic Segmentation](https://mlsanity.com/paper/2204.01244/) (2022)
- [Reducing the Impact of EV Charging Operations on the Distribution Network](https://mlsanity.com/paper/1509.07056/) (2015)
- [Non-Intrusive Load Monitoring for Feeder-Level EV Charging Detection: Sliding Window-based Approaches to Offline and Online Detection](https://mlsanity.com/paper/2312.01887/) (2023)

## Built on by (most cited first, 1 of 1)

- [Synthetic Data Generation for Residential Load Patterns via Recurrent GAN and Ensemble Method](https://mlsanity.com/paper/2410.15379/) (2024)

## Abstract (arXiv)

Predicting electric vehicle (EV) charging events is crucial for load scheduling and energy management, promoting seamless transportation electrification and decarbonization. While prior studies have focused on EV charging demand prediction, primarily for public charging stations using historical charging data, home charging prediction is equally essential. However, existing prediction methods may not be suitable due to the unavailability of or limited access to home charging data. To address this research gap, inspired by the concept of non-intrusive load monitoring (NILM), we develop a home charging prediction method using historical smart meter data. Different from NILM detecting EV charging that has already occurred, our method provides predictive information of future EV charging occurrences, thus enhancing its utility for charging management. Specifically, our method, leverages a self-attention mechanism-based transformer model, employing a ``divide-conquer'' strategy, to process historical meter data to effectively and learn EV charging representation for charging occurrence prediction. Our method enables prediction at one-minute interval hour-ahead. Experimental results demonstrate the effectiveness of our method, achieving consistently high accuracy of over 96.81% across different prediction time spans. Notably, our method achieves high prediction performance solely using smart meter data, making it a practical and suitable solution for grid operators.