Location based Probabilistic Load Forecasting of EV Charging Sites: Deep Transfer Learning with Multi-Quantile Temporal Convolutional Network

TL;DR

This paper introduces a deep multi-quantile temporal convolutional network for location-based EV charging load forecasting, demonstrating improved accuracy and transfer learning capabilities across diverse sites with limited data.

Contribution

The study develops a novel deep MQ-TCN model that enhances load forecasting accuracy and enables knowledge transfer among different EV charging sites with limited data.

Findings

MQ-TCN outperforms XGBoost with 28.93% higher PICP score.

Transfer learning achieves 96.88% PICP with only two weeks of data.

Model effectively adapts to diverse locations and user profiles.

Abstract

Electrification of vehicles is a potential way of reducing fossil fuel usage and thus lessening environmental pollution. Electric Vehicles (EVs) of various types for different transport modes (including air, water, and land) are evolving. Moreover, different EV user groups (commuters, commercial or domestic users, drivers) may use different charging infrastructures (public, private, home, and workplace) at various times. Therefore, usage patterns and energy demand are very stochastic. Characterizing and forecasting the charging demand of these diverse EV usage profiles is essential in preventing power outages. Previously developed data-driven load models are limited to specific use cases and locations. None of these models are simultaneously adaptive enough to transfer knowledge of day-ahead forecasting among EV charging sites of diverse locations, trained with limited data, and cost-effective. This article presents a location-based load forecasting of EV charging sites using a deep Multi-Quantile Temporal Convolutional Network (MQ-TCN) to overcome the limitations of earlier models. We conducted our experiments on data from four charging sites, namely Caltech, JPL, Office-1, and NREL, which have diverse EV user types like students, full-time and part-time employees, random visitors, etc. With a Prediction Interval Coverage Probability (PICP) score of 93.62\%, our proposed deep MQ-TCN model exhibited a remarkable 28.93\% improvement over the XGBoost model for a day-ahead load forecasting at the JPL charging site. By transferring knowledge with the inductive Transfer Learning (TL) approach, the MQ-TCN model achieved a 96.88\% PICP score for the load forecasting task at the NREL site using only two weeks of data.