Federated Dynamic Spectrum Access

Abstract

Due to the growing volume of data traffic produced by the surge of Internet of Things (IoT) devices, the demand for radio spectrum resources is approaching their limitation defined by Federal Communications Commission (FCC). To this end, Dynamic Spectrum Access (DSA) is considered as a promising technology to handle this spectrum scarcity. However, standard DSA techniques often rely on analytical modeling wireless networks, making its application intractable in under-measured network environments. Therefore, utilizing neural networks to approximate the network dynamics is an alternative approach. In this article, we introduce a Federated Learning (FL) based framework for the task of DSA, where FL is a distributive machine learning framework that can reserve the privacy of network terminals under heterogeneous data distributions. We discuss the opportunities, challenges, and opening problems of this framework. To evaluate its feasibility, we implement a Multi-Agent Reinforcement Learning (MARL)-based FL as a realization associated with its initial evaluation results.

Distributed Learning for 6G–IoT Networks: A Comprehensive Survey

“…However, each IoT device can generate or collect very small amounts of data that are not enough for training any highly efficient AI model. Federated ML can overcome this limitation in smart IoT systems which handle huge training data at multiple edge devices [58][59]. The key benefits of FL are explained below.…”

“…The proposed model is chosen SINR as a metric of channel quality prediction that features entirely the elements of secondary users' network, i.e., additive white Gaussian noise, the allocation of transmission power to each UE, and the CCI among concurrent communication pairs. Furthermore, the proposed model selects data rate by performing actions to obtain rewards for mitigating the interference-based on dynamic spectrum access strategy and client selection [59].…”