Federated learning-based privacy-preserving electricity load forecasting scheme in edge computing scenario

In the era of big data, massive amounts of data hold great value. However, much data exists as isolated islands, and the maximum value of the data cannot be fully utilized. Federated learning allows each client to train local data and then share the training model parameters securely, which can address the isolated data island problem and exploit data value while ensuring data privacy and security. Accordingly, in order to securely complete the electric power load forecasting using existing data, this paper constructs a federated learning-based privacy-preserving scheme to support electricity load forecasting in edge computing scenarios. To address the problems of the data-isolated islands and data privacy in electric power systems, this paper proposes a decentralized distributed solution based on the federated learning technique. Our scheme achieves electricity load forecasting for power systems through the federated learning-based framework and uses edge computing architecture to improve real-time data capability and reduce network latency. For the hierarchical scheduling structure in power systems, we divide the system into a cloud-side-device three-layer architecture, which achieves structural coordination and balance, and each layer collects information according to the scheduling control tasks, promoting scheduling effectiveness. Finally, different privacy protection methods are used on the cloud-edge and edge-device sides to significantly enhance data security. Moreover, We have conducted extensive experimental simulations for our proposed scheme. The experimental results show that the relative error of electricity load forecasting is around 1.580%. Meanwhile, our scheme achieves high accuracy and low memory usage. The security analysis proves the feasibility and security of our scheme. We divide the power system into three layers of cloud-edge-device architecture to improve the scheduling efficiency. We utilize differential privacy on the cloud-edge side as well as a secure aggregation privacy protection technique on the edge-device side. In the process of joint training, we have both protected data privacy and improved training efficiency.image