On-Device Training of PV Power Forecasting Models in a Smart Meter for Grid Edge Intelligence
This work addresses grid-edge intelligence for smart grid applications, but it is incremental as it adapts existing methods to a specific hardware context.
The study tackled on-device training of photovoltaic power forecasting models on resource-limited smart meters, demonstrating feasibility through experiments with gradient boosting trees and recurrent neural networks using mixed- and reduced-precision schemes.
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.