IEEE Internet of Things Journal

UTICA, NY – Research by SUNY Polytechnic Institute Assistant Professor of Network and Computer Security Dr. Mahmoud Badr titled, “Privacy-Preserving and Communication-Efficient Energy Prediction Scheme Based on Federated Learning for Smart Grids," was recently published in the IEEE Internet of Things Journal.

Dr. Badr proposes a privacy-preserving and communication-efficient Federated Learning (FL)-based energy predictor for net-metering systems. Based on a dataset of real power consumption/generation readings, the paper first proposes a multi-data-source hybrid Deep Learning (DL)-based predictor to accurately predict future readings. Then, it repurposes an efficient Inner-Product Functional Encryption (IPFE) scheme for implementing secure data aggregation to preserve the customers’ privacy by encrypting their models’ parameters during the FL training.  

To address communication efficiency, the paper uses a Change and Transmit (CAT) approach to update the local models’ parameters, where only the parameters with sufficient changes are updated. The extensive studies demonstrate that the proposed approach accurately predicts future readings while providing privacy protection and high communication efficiency.

To read more, click here.