Blockchain-Based Distributed Federated Learning in Smart Grid

The participation of prosumers in demand-response programs is essential for the success of demand-side management in renewable-powered energy grids. Unfortunately, the engagement is still low due to concerns related to the privacy of their energy data used in the prediction processes. In this paper, we propose a blockchain-based distributed federated learning (FL) technique for energy-demand prediction that combines FL with blockchain to provide data privacy and trust features for energy prosumers. The privacy-sensitive energy data are stored locally at edge prosumer nodes without revealing it to third parties, with only the learned local model weights being shared using a blockchain network. The global federated model is not centralized but distributed and replicated over the blockchain overlay, ensuring the model immutability and provenance of parameter updates. We had proposed smart contracts to deal with the integration of local machine-learning prediction models with the blockchain, defining functions for the model parameters' scaling and reduction of blockchain overhead. The centralized, local-edge, and blockchain-integrated models are comparatively evaluated for prediction of energy demand 24 h ahead using a multi-layer perceptron model and the monitored energy data of several prosumers. The results show only a slight decrease in prediction accuracy in the case of blockchain-based distributed FL with reliable data privacy support compared with the centralized learning solution.