Smart grids with distributed clean energy generation, storage and prosumers are the future of energy systems. They need two-way digital communication between multiple customers and suppliers of energy, to produce, buy and sell electricity to the grid at small scales. These arrangements need a system that maintains, checks, and registers information about transactions.

New approaches in federated learning and split learning have the potential to significantly improve ubiquitous intelligence in internet of things (IoT) applications. In split federated learning, the machine learning model is divided into smaller network segments, with each segment trained independently on a server using distributed local client data.