Edge Computing for Microgrid via MATLAB Embedded Coder and Low-Cost Smart Meters

TL;DR

This paper presents an edge computing approach using MATLAB Embedded Coder and low-cost smart meters for real-time solar inverter power forecasting and control in microgrids, reducing communication delays.

Contribution

It introduces deploying machine learning models and control algorithms directly on low-cost edge devices in microgrids, enhancing responsiveness and reducing reliance on cloud servers.

Findings

Successful deployment on ARM-based smart meters.

Reduced communication latency compared to cloud-based systems.

Validated accuracy and feasibility through experimental results.

Abstract

In this paper, an edge computing-based machine-learning study is conducted for solar inverter power forecasting and droop control in a remote microgrid. The machine learning models and control algorithms are directly deployed on an edge-computing device (a smart meter-concentrator) in the microgrid rather than on a cloud server at the far-end control center, reducing the communication time the inverters need to wait. Experimental results on an ARM-based smart meter board demonstrate the feasibility and correctness of the proposed approach by comparing against the results on the desktop PC.