Unsupervised Recurrent Federated Learning for Edge Popularity Prediction in Privacy-Preserving Mobile Edge Computing Networks
This addresses the need for accurate popularity prediction in privacy-sensitive industrial IoT edge networks, though it appears incremental as it builds on federated learning with novel adaptations.
The paper tackles the problem of predicting content popularity in mobile edge computing networks for industrial IoT, where data privacy and dynamic patterns are challenges, and proposes an unsupervised recurrent federated learning framework that reduces prediction error by 60.5%-68.7% while preserving privacy.
Nowadays wireless communication is rapidly reshaping entire industry sectors. In particular, mobile edge computing (MEC) as an enabling technology for industrial Internet of things (IIoT) brings powerful computing/storage infrastructure closer to the mobile terminals and, thereby, significant lowers the response latency. To reap the benefit of proactive caching at the network edge, precise knowledge on the popularity pattern among the end devices is essential. However, the complex and dynamic nature of the content popularity over space and time as well as the data-privacy requirements in many IIoT scenarios pose tough challenges to its acquisition. In this article, we propose an unsupervised and privacy-preserving popularity prediction framework for MEC-enabled IIoT. The concepts of local and global popularities are introduced and the time-varying popularity of each user is modelled as a model-free Markov chain. On this basis, a novel unsupervised recurrent federated learning (URFL) algorithm is proposed to predict the distributed popularity while achieve privacy preservation and unsupervised training. Simulations indicate that the proposed framework can enhance the prediction accuracy in terms of a reduced root-mean-squared error by up to $60.5\%-68.7\%$. Additionally, manual labeling and violation of users' data privacy are both avoided.