No abstract

This paper proposes an autonomous coil alignment system (ACAS) for electric vehicles (EVs) with dynamic wireless charging (DWC) to mitigate the reduction in received power caused by lateral misalignment between the source and load coils. The key component of the ACAS is a novel sensor coil design, which can detect the load coil's left or right position relative to the source coil by observing the change in voltage phase. This allows the lateral misalignment to be estimated through the wireless power transfer (WPT) system alone, which is a novel tracking method for vehicular applications. Once misalignment is detected, the vehicle's lateral position is self-adjusted by an autonomous steering function. The feasibility of the overall operation of the ACAS was verified through simulation and experiments. In addition, an analysis based on experimental results was conducted, demonstrating that 26% more energy can be transferred during DWC with the ACAS, just by keeping the vehicle's load coil aligned with the source coil.

Federated learning (FL) is a machine learning technique that enables distributed devices to train a learning model collaboratively without sharing their local data. FL-based systems can achieve much stronger privacy preservation since the distributed devices deliver only local model parameters trained with local data to a centralized server. However, there exists a possibility that a centralized server or attackers infer/extract sensitive private information using the structure and parameters of local learning models. We propose employing homomorphic encryption (HE) scheme that can directly perform arithmetic operations on ciphertexts without decryption to protect the model parameters. Using the HE scheme, the proposed privacy-preserving federated learning (PPFL) algorithm enables the centralized server to aggregate encrypted local model parameters without decryption. Furthermore, the proposed algorithm allows each node to use a different HE private key in the same FL-based system using a distributed cryptosystem. The performance analysis and evaluation of the proposed PPFL algorithm are conducted in various cloud computing-based FL service scenarios.

No abstract