Energy Prediction using Federated Learning
This addresses energy management for households by enabling predictions without compromising privacy, though it is incremental as it applies an existing method to a new domain.
The paper tackled energy consumption and solar production prediction for households using federated learning, demonstrating improved performance over time without sharing private data, as shown in a simulation with four nodes over one year.
In this work, we demonstrate the viability of using federated learning to successfully predict energy consumption as well as solar production for all households within a certain network using low-power and low-space consuming embedded devices. We also demonstrate our prediction performance improving over time without the need for sharing private consumer energy data. We simulate a system with four nodes using data for one year to show this.