A New Deep-Q-Learning-Based Transmission Scheduling Mechanism for the Cognitive Internet of Things

Cognitive networks (CNs) are one of the key enablers for the Internet of Things (IoT), where CNs will play an important role in the future Internet in several application scenarios, such as healthcare, agriculture, environment monitoring, and smart metering. However, the current low packet transmission efficiency of IoT faces a problem of the crowded spectrum for the rapidly increasing popularities of various wireless applications. Hence, the IoT that uses the advantages of cognitive technology, namely the cognitive radio-based IoT (CIoT), is a promising solution for IoT applications. A major challenge in CIoT is the packet transmission efficiency using CNs. Therefore, a new Q-learning-based transmission scheduling mechanism using deep learning for the CIoT is proposed to solve the problem of how to achieve the appropriate strategy to transmit packets of different buffers through multiple channels to maximize the system throughput. A Markov decision process-based model is formulated to describe the state transformation of the system. A relay is used to transmit packets to the sink for the other nodes. To maximize the system utility in different system states, the reinforcement learning method, i.e., the Q learning algorithm, is introduced to help the relay to find the optimal strategy. In addition, the stacked auto-encoders deep learning model is used to establish the mapping between the state and the action to accelerate the solution of the problem. Finally, the experimental results demonstrate that the new action selection method can converge after a certain number of iterations. Compared with other algorithms, the proposed method can better transmit packets with less power consumption and packet loss.