This article focuses on the issue of cooperative spectrum sensing (CSS) in a mobile energy-harvesting cognitive radio network (EH-CRN), where secondary transmitters (STs) are powered by the radio-frequency (RF) signal emitted from primary transmissions. Only the STs with sufficient energy participate in CSS, and send their local sensing decisions to a fusion center (FC), which makes a final decision on the state of the spectrum by a general k-out-of-M(k) fusion rule. The target of this article is to develop an optimal CSS strategy in terms of final decision threshold k that maximizes the expected achievable throughput of the EH-CRN, subject to a collision constraint and an energy causality constraint. We first show that the EH-CRN can be divided into an energy-deficit state and a spectrum-deficit state depending on the final decision threshold. The final decision threshold has a negative correlation with the number of STs participating in CSS in the energy-deficit state, and has no impact on that in the spectrum-deficit state. We then derive the collision probability and the expected achievable throughput of the EH-CRN, both of which are indicated to be determined by the active probability of a ST, the state of the spectrum, and the spectrum access opportunity. By tackling the tradeoff between the active probability and spectrum access opportunity introduced by the final decision threshold, we derive the optimal final decision threshold that maximizes the expected achievable throughput of the EH-CRN while protecting primary transmissions to a predefined extent. Extensive numerical simulations are conducted to illustrate the performance versus the final decision threshold. One of the main findings indicates that the optimal range of final decision threshold in the energy-deficit state could be acquired by the number of reporting received at the FC.

Ambient backscatter (AB) communications and radio frequency (RF)-powered cognitive radio networks (CRNs) address the concerns of energy and spectrum scarcities from different perspectives, and the integration of them has potential benefits for throughput. Motivated by this fact, we study the RF-powered AB-assisted hybrid underlay CRN (ABHU-CRN), and optimize the long-term secondary throughput. Based on the channel states, secondary users choose to perform different actions, and two action spaces are accordingly designed. Due to dynamic and unpredictable environment states, we jointly control the time scheduling and energy management of secondary users, and propose two algorithms, i.e., adjusted-deep deterministic policy gradient (A-DDPG) and combination of A-DDPG and convex optimization (C-ADCO), for the long-term secondary throughput. A-DDPG, a deep reinforcement learning algorithm with continuous spaces, is extended from DDPG to adapt to the design of two action spaces. C-ADCO utilizes the convex optimization that can find the optimal solution to assist A-DDPG to accelerate the convergence. In simulations, the ABHU-CRN under A-DDPG and C-ADCO achieves higher throughput than the optimal throughput of AB-assisted overlay CRN and AB-assisted underlay CRN, which indicates the advantage of the hybrid transmission mode in the ABHU-CRN.

Wireless power transfer (WPT) and edge computing have been validated as effective ways to solve the energy-limited problem and computation-capacity-limited problem of wireless devices (WDs), respectively. This paper studies the wireless-powered multi-access edge computing (WP-MEC) network, where WDs conduct either local computing or task offloading for their individable computation tasks. We aim to minimize total computation delay (TCD) when each WD has a computation task to execute, referred to as the total computation delay minimization (TCDM) problem, by jointly optimizing the offloading-decision, WPT duration, and transmission durations of offloading WDs. The TCDM problem is a mixed integer programming (MIP) problem that is challenging to efficiently obtain the optimal or near-optimal solution. To tackle this challenge, we decompose the TCDM problem into the sub-problem of optimizing the WPT duration and transmission durations, and the top-problem of optimizing the offloading decision. For the nonconvex sub-problem, we design a worst-WD-adjusting (WDA) algorithm to efficiently obtain its optimal solution. For the top-problem, under the time-varying channel conditions, traditional optimization methods are hard to determine the optimal or near-optimal offloading decision within the channel coherence duration. To fast obtain the near-optimal offloading decision, we propose a deep neural networks (DNN)-based deep reinforcement learning (DRL) model, which takes the sub-problem solving as one component for utility evaluation. Finally, numerical results demonstrate that the proposed online DRL-based offloading algorithm achieves the near-minimal TCD with low computational complexity, and is suitable for the fast-fading WP-MEC network.

This paper investigates the long-term average age of information (AoI)-minimal problem in an unmanned aerial vehicle (UAV)-assisted wireless-powered communication network (WPCN), which consists of a static hybrid access point (HAP), a mobile UAV, and many static sensor nodes (SNs) randomly distributed on multiple islands. The UAV first is fully charged by the HAP, and then flies to each island to charge SNs and receive data from them. Before running out the energy in battery, the UAV flies back to the HAP to offload the received data and be fully charged again. Due to the finite battery capacity of the UAV, it is impossible for the UAV to traverse all the islands to collect all the data from SNs for once flight. We are thus inspired to divide islands into multiple clusters so that the UAV could traverse all the islands in each cluster. The key factors affecting the long-term average AoI contain the hovering duration, the flying duration, and the amount of data from each island reflected by the number of SNs on each island. Therefore, we formulate the long-term average AoI-minimal problem by jointly optimizing the transmit power of SNs, clustering of islands, and UAV's flight trajectory, subject to the battery capacity of the UAV. Since the optimization problem is NP-hard, there are no standard methods to solve it optimally in general. To tackle this problem, we decouple it into two subproblems: the power allocation subproblem for SNs, and the joint clustering of islands and UAV's flight trajectory design subproblem, which is much more perplexed and complicated owing to the tight coupling between them. To solve the first subproblem, we propose a hybrid TDMA and NOMA (HTN) protocol that takes advantage of the two protocols. To solve the second subproblem, we propose a clustering-based dynamic adjustment of the shortest path (C-DASP) algorithm, which is composed of three sub-algorithms, i.e, a proposed merging-aided K-means clustering (MaKMC) algorithm, the particle swarm optimization (PSO) algorithm employed to find the shortest path in each cluster, and a proposed dynamic adjustment (DA) algorithm taking into account the number of SNs on each island. Simulations verify the effectiveness and superiority of the proposed HTN protocol and C-DASP algorithm.

As a vital metric of information timeliness, Age of Information (AoI) is important for real-time applications in Internet of Things (IoT), such as health monitoring. To satisfy these requirements, we study a wireless-powered IoT (WPIoT), where a static hybrid access point (HAP) coordinates wireless energy transfer to mobile IoT nodes, and mobile IoT nodes transmit data to the HAP or static IoT nodes. We minimize the AoI of mobile IoT nodes by optimizing the selection of the HAP or static IoT node for transmission, the channel selection, the duration of data transmission, and the transmit power, and prove the AoI minimization problem as nondeterministic polynomial hard. To tackle it, we propose a deep deterministic policy gradient (DDPG)-based distributed multinode resource allocation (DDMRA) algorithm, which combines the advantages of the distributed algorithms and centralized algorithms, and combines the selection of discrete actions in the deep Q-network algorithm into the DDPG algorithm. In the DDMRA algorithm, mobile IoT nodes save the energy consumption of transmitting state information to the HAP. Numerical results validate the superior performance of the DDMRA algorithm compared with the baseline algorithms.

This paper investigates a wireless powered mobile edge computing (WP-MEC) network with multiple hybrid access points (HAPs) in a dynamic environment, where wireless devices (WDs) harvest energy from radio frequency (RF) signals of HAPs, and then compute their computation data locally (i.e., local computing mode) or offload it to the chosen HAPs (i.e., edge computing mode). In order to pursue a green computing design, we formulate an optimization problem that minimizes the long-term energy provision of the WP-MEC network subject to the energy, computing delay and computation data demand constraints. The transmit power of HAPs, the duration of the wireless power transfer (WPT) phase, the offloading decisions of WDs, the time allocation for offloading and the CPU frequency for local computing are jointly optimized adapting to the time-varying generated computation data and wireless channels of WDs. To efficiently address the formulated non-convex mixed integer programming (MIP) problem in a distributed manner, we propose a T wo-stage M ulti- A gent deep reinforcement learning-based D istributed computation O ffloading (TMADO) framework, which consists of a high-level agent and multiple low-level agents. The high-level agent residing in all HAPs optimizes the transmit power of HAPs and the duration of the WPT phase, while each low-level agent residing in each WD optimizes its offloading decision, time allocation for offloading and CPU frequency for local computing. Simulation results show the superiority of the proposed TMADO framework in terms of the energy provision minimization.