A method for selecting participating nodes in federated learning based on blockchain

Abstract

The present application discloses a method for selecting nodes participating in federated learning based on blockchain. The method for selecting nodes participating in federated learning is used in an Internet of Things system, which includes terminal devices and base stations. The method for selecting nodes participating in federated learning includes: obtaining the number of interactions and distances between each terminal device and the base station and other terminal devices within a preset time, determining the activity density of each terminal device according to the preset cutoff distance, the number of data interactions, and the distance between the terminal device and other terminal devices, selecting the target terminal device according to the size of the activity density, calculating the offset distance from the terminal device to the target terminal device, determining the cluster center point of the terminal device according to the activity density and the offset distance, and transmitting the data of the terminal device in the corresponding clustering model to the base station through the terminal device at the cluster center point. In this way, the transmission time of the Internet of Things system is effectively reduced, and the delay problem caused by the Internet of Things devices is avoided.

Images