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

TL;DR

This paper explores the application of graph neural networks on edge smart meters for PV power forecasting in microgrids, demonstrating successful deployment and comparison of models on real datasets.

Contribution

It introduces a practical framework for deploying GCN and GraphSAGE models on smart meters, including a custom ONNX operator for GCN.

Findings

Successful deployment of GCN and GraphSAGE on smart meters

Comparison shows model performance differences in real microgrid scenarios

Demonstrates feasibility of edge intelligence for PV power forecasting

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.