Large Language Model-aided Edge Learning in Distribution System State Estimation

TL;DR

This work tackles distribution system state estimation under missing measurements by proposing a forecast-then-estimate framework that combines LLM-based measurement forecasting with a multi-task learning DSSE model and a CNN-Prox estimator. GPT-2-based forecasting supplies accurate pseudo-measurements for missing data, while multi-task learning with uncertainty weighting improves joint estimation of voltage magnitude and angle. The CNN-Prox estimator, designed to handle incomplete data, achieves superior accuracy on magnitude and competitive performance on angle estimation, particularly when aided by GPT-2 forecasts. The approach, validated on the Simbench dataset, demonstrates that integrating LLM forecasting with topology-aware neural estimators can significantly enhance DSSE robustness and accuracy in realistic, data-degraded environments.

Abstract

Distribution system state estimation (DSSE) plays a crucial role in the real-time monitoring, control, and operation of distribution networks. Besides intensive computational requirements, conventional DSSE methods need high-quality measurements to obtain accurate states, whereas missing values often occur due to sensor failures or communication delays. To address these challenging issues, a forecast-then-estimate framework of edge learning is proposed for DSSE, leveraging large language models (LLMs) to forecast missing measurements and provide pseudo-measurements. Firstly, natural language-based prompts and measurement sequences are integrated by the proposed LLM to learn patterns from historical data and provide accurate forecasting results. Secondly, a convolutional layer-based neural network model is introduced to improve the robustness of state estimation under missing measurement. Thirdly, to alleviate the overfitting of the deep learning-based DSSE, it is reformulated as a multi-task learning framework containing shared and task-specific layers. The uncertainty weighting algorithm is applied to find the optimal weights to balance different tasks. The numerical simulation on the Simbench case is used to demonstrate the effectiveness of the proposed forecast-then-estimate framework.

Figures (10)

• Figure 1: Power flow between buses.
• Figure 2: The forecast-then-estimate framework for real-time DSSE.
• Figure 3: The measurement forecasting framework with LLM
• Figure 4: Multi-task learning framework for DSSE
• Figure 5: The CNN-Prox model structure for DSSE