A Blockchain-Empowered Cluster-based Federated Learning Model for Blade Icing Estimation on IoT-enabled Wind Turbine

Abstract

Wind energy is a fast-growing renewable energy but faces the blade icing. Data-driven methods provide talented solutions for blade icing detection but a considerable amount of data need to be collected to a central server, which may lead to the leakage of sensitive business data. To address this limitation, this work proposes BLADE, a Blockchain-empowered imbalanced federated learning (FL) model for blade icing detection. With the help of Blockchain, the conventional FL is improved without worrying the failure of the single centralized server and boosts the privacy-preserving. A validation mechanism is introduced into the Blockchain to enhance the defense of poisoning attacks. In addition, a novel imbalanced learning algorithm is integrated into BLADE to solve the class-imbalance problem in the sensor data. The BLADE is evaluated on the 10 wind turbines from two wind farms. The experimental results verify the effectiveness, superiority, and feasibility of proposed BLADE.