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

2026-01-20

IEEE Transactions on Smart Grid

AI Summary

Electric vehicle charging data are often challenging to impute effectively due to missing values and multimodal characteristics. Existing approaches typically rely on single-station modeling, neglecting inter-station dependencies. This work proposes PRAIM, a unified variational imputation framework that, for the first time, integrates pretrained language models with a retrieval-augmented memory mechanism to semantically fuse heterogeneous multi-source data—including time series, calendar, and geospatial information—and dynamically enhances representations through cross-station relevant samples. By breaking away from the single-station modeling paradigm, PRAIM significantly outperforms state-of-the-art methods across four public datasets, achieving higher imputation accuracy, better preservation of the original data distribution, and substantially improved performance in downstream charging demand forecasting tasks.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

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.

Problem

• missing data
• electric vehicle charging
• data imputation
• multimodal data
• inter-station correlation

Innovation

• retrieval-augmented language model
• variational imputation
• electric vehicle charging data
• multimodal data fusion
• unified imputation framework