No abstract

The Internet of Things (IoT) application scenarios is becoming extensive due to the quick evolution of smart devices with fifth-generation (5G) network slicing technologies and hence IoT becoming significantly important beyond fifth-generation (B5G) networks. However, communication with IoT devices is more sensitive in disasters because the network depends on the main power supply and devices are fragile. In this paper, we consider Unmanned Aerial Vehicles (UAV) as a flying base station (BS) for the emergency communication system with 5G mMTC Network Slicing to improve the quality of service. The UAV-assisted mMTC creates a base station selection method with the aim of maximizing the system energy efficiency. Then, the system model is reduced into the stochastic optimization based problem using Markov Decision Process (MDP) theory. We propose a Dueling-Deep-Q-Networks (DDQN) based approach based on Reinforcement Learning (RL) technique for maximization of energy efficiency to solve the resource allocation problem. We compare the proposed model with DQN and Q-Learning models and found that the proposed DDQN based model performs better for resource allocation in terms of low transmission power and maximum energy efficiency.

No abstract

The Internet of Things (IoT) application scenarios is becoming extensive due to the quick evolution of smart devices with fifth-generation (5G) network slicing technologies and hence IoT becoming significantly important beyond fifth-generation (B5G) networks. However, communication with IoT devices is more sensitive in disasters because the network depends on the main power supply and devices are fragile. In this paper, we consider Unmanned Aerial Vehicles (UAV) as a flying base station (BS) for the emergency communication system with 5G mMTC Network Slicing to improve the quality of service. The UAV-assisted mMTC creates a base station selection method with the aim of maximizing the system energy efficiency. Then, the system model is reduced into the stochastic optimization based problem using Markov Decision Process (MDP) theory. We propose a Dueling-Deep-Q-Networks (DDQN) based approach based on Reinforcement Learning (RL) technique for maximization of energy efficiency to solve the resource allocation problem. We compare the proposed model with DQN and Q-Learning models and found that the proposed DDQN based model performs better for resource allocation in terms of low transmission power and maximum energy efficiency.