A Unified Variational Imputation Framework for Electric Vehicle Charging Data Using Retrieval-Augmented Language Model

TL;DR

This paper introduces PRAIM, a novel framework that combines large language models and retrieval-augmented memory to improve the imputation of missing electric vehicle charging data, enhancing accuracy and downstream forecasting.

Contribution

It proposes a unified variational imputation framework leveraging language models and retrieval-augmented memory, addressing limitations of existing methods in handling complex, multimodal charging data.

Findings

PRAIM outperforms baseline imputation methods in accuracy.

It better preserves the statistical distribution of original data.

Improves downstream EV demand forecasting performance.

Abstract

The reliability of data-driven applications in electric vehicle (EV) infrastructure, such as charging demand forecasting, hinges on the availability of complete, high-quality charging data. However, real-world EV datasets are often plagued by missing records, and existing imputation methods are ill-equipped for the complex, multimodal context of charging data, often relying on a restrictive one-model-per-station paradigm that ignores valuable inter-station correlations. To address these gaps, we develop a novel PRobabilistic variational imputation framework that leverages the power of large lAnguage models and retrIeval-augmented Memory (PRAIM). PRAIM employs a pre-trained language model to encode heterogeneous data, spanning time-series demand, calendar features, and geospatial context, into a unified, semantically rich representation. This is dynamically fortified by retrieval-augmented memory that retrieves relevant examples from the entire charging network, enabling a single, unified imputation model empowered by variational neural architecture to overcome data sparsity. Extensive experiments on four public datasets demonstrate that PRAIM significantly outperforms established baselines in both imputation accuracy and its ability to preserve the original data's statistical distribution, leading to substantial improvements in downstream forecasting performance.