面向网格边缘智能的智能表计上设备训练 PV 功率预测模型
机器学习
2025-07-10 v1 信号处理
摘要
本文对资源受限的智能表计上进行边侧模型训练研究。介绍了网格边缘智能的动机及设备训练的概念。随后描述了进行设备训练的技术准备步骤。 presented for the task of photovoltaic power forecasting, where two representative machine learning models are investigated: a gradient boosting tree model and a recurrent neural network model. To adapt to the resource-limited situation in the smart meter, "mixed"- and "reduced"-precision training schemes are also devised. Experiment results demonstrate the feasibility of economically achieving grid-edge intelligence via the existing advanced metering infrastructures.
引用
@article{arxiv.2507.07016,
title = {On-Device Training of PV Power Forecasting Models in a Smart Meter for Grid Edge Intelligence},
author = {Jian Huang and Yongli Zhu and Linna Xu and Zhe Zheng and Wenpeng Cui and Mingyang Sun},
journal= {arXiv preprint arXiv:2507.07016},
year = {2025}
}
备注
This paper is currently under reviewing by an IEEE publication; it may be subjected to minor changes due to review comments later