Zero-knowledge machine learning models for blockchain peer-to-peer energy trading

Blockchain-based peer-to-peer energy trading enables individuals to directly share renewable energy using Internet of Things technologies. However, it faces significant challenges related to privacy, scalability, and the integration of advanced artificial intelligence. To address these issues, this article proposes zkPET, a secure and intelligent peer-to-peer energy trading framework. zkPET integrates machine learning and blockchain with advanced cryptographic techniques of zero-knowledge machine learning to protect user data while enabling intelligent decision making. In the zkPET framework, the computationally intensive operations of various machine learning models are executed off-chain, and only succinct cryptographic proofs of these computations are uploaded to the blockchain for verification and recording. In addition, a time-series clustering approach is incorporated into federated learning to enhance both inference accuracy and the efficiency of proof generation. Experimental validation using the zero-knowledge proof tool EZKL and a real-world electricity dataset demonstrates the feasibility and effectiveness of zkPET. The results underscore its potential to significantly improve privacy, scalability, and computational efficiency in decentralized energy trading, contributing to the advancement of secure and intelligent energy markets. • We propose a novel privacy-preserving and intelligent solution for peer-to-peer energy trading based on blockchain and zero-knowledge machine learning. • This solution contains three potential models (or structures), i.e., centralized, decentralized, and federated zero-knowledge machine learning from the architectural perspective. • A dynamic time-series clustering algorithm is developed by decomposing the trend and seasonality features. • We conduct a comprehensive performance evaluation of the proposed models on a real-world electricity consumption dataset.