Abstract
Since the birth of narrowband Internet of Things (NB-IoT), the Internet of Things (IoT) industry has made a considerable progress in the application for smart cities, smart manufacturing, and healthcare. Therefore, the number of UEs is increasing exponentially, which brings considerable pressure to the efficient resource allocation for the bandwidth and power constrained NB-IoT networks. In view of the conventional algorithms that cannot dynamically adjust resource allocation, resulting in a low resource utilization and prone to resource fragmentation, this paper proposes a double deep Q-network (DDQN)-based NB-IoT dynamic resource allocation algorithm. It first builds an NB-IoT environment model based on the real environment. Then, the DDQN algorithm interacts with the NB-IoT environment model to learn and optimize resource allocation strategies until it converges to the optimum. Finally, the simulation results show that the DDQN-based NB-IoT dynamic resource allocation algorithm is better than the traditional algorithm in the resource utilization, average transmission rate, and UE average queuing time.
Highlights
With the advancement of science and technology, the IoT is being used more and more widely in various industries [1]
We consider the waiting delay of the user equipment (UE) and the NB-IoT scheduling problem for 3GPP NBIoT cellular networks. e objective is to maximize resource utilization and reduce resource fragmentation while ensuring UE has a short waiting time delay. erefore, we propose a dynamic resource scheduling algorithm based on deep reinforcement learning to optimize the resource utilization of NB-IoT
The state includes UE data size, Narrowband physical uplink shared channel (NPUSCH) format, transmission quality, number of repetitions, and the number of NRU. e corresponding action taken by the agent is to allocate the corresponding resources required by the UE in the frequency domain resources. erefore, the action of the agent is composed of 12 actions, corresponding to the divided 12 frequency domain positions
Summary
With the advancement of science and technology, the IoT is being used more and more widely in various industries [1]. E NB-IoT system focuses on lowcomplexity and low-throughput radio access technology. Under the coverage of the same base station, NB-IoT can support up to 50–100 times the number of access devices compared to the existing wireless technology. It is expected to be Security and Communication Networks reduced to US$2-3 by 2020, and a single antenna is used for transmission It can reduce the complexity of chip processing, thereby reducing costs. In view of the low resource utilization of traditional resource allocation algorithms, fragmentation is prone to occur, and the average waiting delay is high, and this article proposes a DDQN-based dynamic resource allocation algorithm.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
