Deep Reinforcement Learning Based Resource Allocation For Narrowband Cognitive Radio-IoT Systems

Abstract

Narrowband Internet-of-Things (NB-IoT) is a low-power wide area (LPWA) technology developed by the Third-generation Partnership Project (3GPP) with objective to enable a wide range of IoT devices, low cost device and low power in the 5G era. As the number of IoT devices continue to increase, the demand for the spectrum allocation grows proportionately. The NB-IoT spectrum allocation is limited from 180 KHz to 200 KHz and is not sufficient to accomodate the exponential surge in the size of the NB-IoT devices.Thus, the need to efficiently allocate the available spectrum to the NB-IoT devices. Furthermore, in an attempt to enhance the coverage in NB-IoT network, recent relevant studies (3GPP release 13) have introduced the concept of repeated transmission. Since repeated transmissions ensure coverage enhancement but cause spectrum wastage, the traditional resource allocation is not appropriate for NB-IoT network. Motivated by this research gap we propose a NB-Cognitive Radio-IoT (NB-CR-IoT) technique which integrates Cognitive Radio (CR) techniques into the operation of the conventional NB-IoT. The resulting architecture seeks to foster an efficient opportunistic spectrum access in distributed heterogeneous networks.We further formulate the resource allocation problem as a deep Q-learning solved by reducing the number of repeated transmissions and allocating more IoT devices in NB-IoT network. The results in this contribution indicate that DQN outperforms the traditional Q-learning algorithm.