Online Electric Vehicle Charging Detection Based on Memory-based Transformer using Smart Meter Data

TL;DR

This paper introduces an unsupervised, memory-based transformer model for real-time detection of EV charging from smart meter data, improving accuracy without prior EV profile knowledge.

Contribution

A novel unsupervised memory-based transformer (M-TR) model that detects EV charging in real-time using streaming smart meter data, without requiring EV profiles or supervised training.

Findings

Outperforms existing unsupervised methods in EV detection accuracy

Operates with a fast execution time of 1.2 seconds per minute of data

Effectively captures both coarse and fine-scale data features

Abstract

The growing popularity of Electric Vehicles (EVs) poses unique challenges for grid operators and infrastructure, which requires effectively managing these vehicles' integration into the grid. Identification of EVs charging is essential to electricity Distribution Network Operators (DNOs) for better planning and managing the distribution grid. One critical aspect is the ability to accurately identify the presence of EV charging in the grid. EV charging identification using smart meter readings obtained from behind-the-meter devices is a challenging task that enables effective managing the integration of EVs into the existing power grid. Different from the existing supervised models that require addressing the imbalance problem caused by EVs and non-EVs data, we propose a novel unsupervised memory-based transformer (M-TR) that can run in real-time (online) to detect EVs charging from a streaming smart meter. It dynamically leverages coarse-scale historical information using an M-TR encoder from an extended global temporal window, in conjunction with an M-TR decoder that concentrates on a limited time frame, local window, aiming to capture the fine-scale characteristics of the smart meter data. The M-TR is based on an anomaly detection technique that does not require any prior knowledge about EVs charging profiles, nor it does only require real power consumption data of non-EV users. In addition, the proposed model leverages the power of transfer learning. The M-TR is compared with different state-of-the-art methods and performs better than other unsupervised learning models. The model can run with an excellent execution time of 1.2 sec. for 1-minute smart recordings.