On-Meter Graph Machine Learning: A Case Study of PV Power Forecasting for Grid Edge Intelligence

arXiv cs.LG / 4/23/2026

📰 NewsDeveloper Stack & InfrastructureIdeas & Deep AnalysisTools & Practical UsageModels & Research

共有:

Key Points

The paper studies using graph neural networks running on edge intelligent meters in a microgrid to forecast photovoltaic (PV) power generation.
It describes the overall technology stack, including ONNX and ONNX Runtime, plus the smart meter’s hardware/software specifications.
Two graph ML models—GCN and GraphSAGE—are trained and deployed, with special focus on creating a customized ONNX operator for GCN.
A case study using real village microgrid datasets compares model performance on both a PC and the smart meter, demonstrating successful on-meter execution.
The work provides a practical blueprint for deploying GNN-based energy forecasting models directly at the grid edge.

Abstract

This paper presents a detailed study of how graph neural networks can be used on edge intelligent meters in a microgrid to forecast photovoltaic power generation. The problem background and the adopted technologies are introduced, including ONNX and ONNX Runtime. The hardware and software specifications of the smart meter are also briefly described. Then, the paper focuses on the training and deployment of two graph machine learning models, GCN and GraphSAGE, with particular emphasis on developing and deploying a customized ONNX operator for GCN. Finally, a case study is conducted using real datasets from a village microgrid. The performance of the two models is compared on both the PC and the smart meter, exhibiting successful deployments and executions on the smart meter.