PoQ-Consensus Based Private Electricity Consumption Forecasting via Federated Learning

Abstract

With the rapid development of artificial intelligence and computer technology, grid corporations have also begun to move towards comprehensive intelligence and informatization. However, data-based informatization can bring about the risk of privacy exposure of fine-grained information such as electricity consumption data. The modeling of electricity consumption data can help grid corporations to have a more thorough understanding of users’ needs and their habits, providing better services for users. Nevertheless, users’ electricity consumption data is sensitive and private. In order to achieve highly efficient analysis of massive private electricity consumption data without direct access, a blockchain-based federated learning method is proposed for users’ electricity consumption forecasting in this paper. Specifically, a blockchain system is established based on a proof of quality (PoQ) consensus mechanism, and a multilayer hybrid directional long short-term memory (MHD-LSTM) network model is trained for users’ electricity consumption forecasting via the federal learning method. In this way, the model of the MHD-LSTM network is able to avoid suffering from severe security problems and can only share the network parameters without exchanging raw electricity consumption data, which is decentralized, secure and reliable. The experimental result shows that the proposed method has both effectiveness and high-accuracy under the premise of electricity consumption data’s privacy preservation, and can achieve better performance when compared to traditional long short-term memory (LSTM) and bidirectional LSTM (BLSTM).