Privacy Protection Strategy Based on Federated Learning for Smart Park Multi Energy Fusion System

Abstract

In order to realize the promotion of clean energy, the energy Internet which supports the efficient energy utilization has been widely concerned. While, the smart Park energy system to realize the highly coupling of energy, intelligent processing and self-response has become an important part of realizing the energy Internet. In the multi energy integration system of smart Park, the grid needs to collect nearly real-time power consumption data from the user side to analyze the power consumption behavior of the whole park, so as to formulate power dispatching strategy. However, this kind of nearly real-time power consumption data is easy to reveal the status of electric devices, which poses a threat to the user s privacy. This paper proposes a privacy protection strategy based on Federated learning for smart Park multifunctional fusion system. Through federal learning technology, users in the park participate in energy consumption modeling while don t need to send their privacy-sensitive data to the power grid. Therefore, individual privacy can be protected while power grid can obtain the overall power consumption behavior of the park.