The radio spectrum is one of the world’s most highly regulated and limited natural resources. The number of wireless devices has increased dramatically in recent years, resulting in a scarcity of available radio spectrum due to static spectrum allocation. However, many studies on static allocation show that the licensed spectrum bands are underutilized. Cognitive radio has been considered as a viable solution to the issues of spectrum scarcity and underutilization. Spectrum sensing is an important part in cognitive radio for detecting spectrum holes. To detect the availability or unavailability of primary user signals, many spectrum sensing techniques such as matched filter detection, cyclostationary feature detection, and energy detection have been developed. Energy detection has gained significant attention from researchers because of its ease of implementation, fast sensing time, and low computational complexity. Conventional detectors’ performance degrades rapidly at low SNR due to their sensitivity to the uncertainty of noise. To mitigate noise uncertainty, Shannon, Tsallis, Kapur, and Renyi entropy-based detection has been used in this study, and their performances are compared to choose the best performer. According to the comparison results, the Renyi entropy outperforms other entropy methods. In this study, two-stage spectrum sensing is proposed using energy detection as the coarse stage and Renyi entropy-based detection as the fine stage to improve the performance of single-stage detection techniques. Furthermore, the performance comparison among conventional energy detection, entropy-based detection, and the proposed two-stage techniques over AWGN channel are performed. The parameters such as probability of detection, false alarm probability, miss-detection probability, and receiver operating characteristics curve are used to evaluate the performance of spectrum sensing techniques. It has been shown that the proposed two-stage sensing technique outperforms single-stage energy detection and Renyi entropy-based detection by 11 dB and 1 dB, respectively.

This paper aims to solve the optimization problems in far-field wireless power transfer systems using deep reinforcement learning techniques. The Radio-Frequency (RF) wireless transmitter is mounted on a mobile robot, which patrols near the harvested energy-enabled Internet of Things (IoT) devices. The wireless transmitter intends to continuously cruise on the designated path in order to fairly charge all the stationary IoT devices in the shortest time. The Deep Q-Network (DQN) algorithm is applied to determine the optimal path for the robot to cruise on. When the number of IoT devices increases, the traditional DQN cannot converge to a closed-loop path or achieve the maximum reward. In order to solve these problems, an area division Deep Q-Network (AD-DQN) is invented. The algorithm can intelligently divide the complete charging field into several areas. In each area, the DQN algorithm is utilized to calculate the optimal path. After that, the segmented paths are combined to create a closed-loop path for the robot to cruise on, which can enable the robot to continuously charge all the IoT devices in the shortest time. The numerical results prove the superiority of the AD-DQN in optimizing the proposed wireless power transfer system.