A Novel Privacy Protection Framework for Power Generation Data based on Generative Adversarial Networks

As more and more data-driven methods are used in smart grid analysis, data have become one of the most valuable assets of power utilities. Traditional method of data trading or exchange without data masking might lead to the violation of privacy for both customers and power utilities. In this paper, we mainly focus on the data privacy protection in power generation data such as wind power generation and PV-solar power generation data. We proposed a novel privacy protection framework based on generative adversarial networks (GANs), which is capable of modeling the uncertainties of original data and generating new realistic data for further usage such as operation, scheduling and planning of power systems. Through this framework, power generation data are not directly exchanged or traded and private information behind those data are well protected.