# On-Device Training of PV Power Forecasting Models in a Smart Meter for Grid Edge Intelligence

arXiv: https://arxiv.org/abs/2507.07016 · HTML: https://mlsanity.com/paper/2507.07016/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 7 references that are in the map.
- First posted on arXiv 9 Jul 2025.

## Builds on (most cited first, 4 of 4)

- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems](https://mlsanity.com/paper/2307.05999/) (2023)
- [Embedded Machine Learning for Solar PV Power Regulation in a Remote Microgrid](https://mlsanity.com/paper/2412.01054/) (2024)
- [Towards Federated Learning with On-device Training and Communication in 8-bit Floating Point](https://mlsanity.com/paper/2407.02610/) (2024)

## Built on by (most cited first, 1 of 1)

- [When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting](https://mlsanity.com/paper/2609.01126/) (2026)

## Abstract (arXiv)

In this paper, an edge-side model training study is conducted on a resource-limited smart meter. The motivation of grid-edge intelligence and the concept of on-device training are introduced. Then, the technical preparation steps for on-device training are described. A case study on the task of photovoltaic power forecasting is presented, 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.