A 5G network is the key driving factor in the development of vehicle-to-vehicle (V2V) communication technology, and V2V communication in 5G has recently attracted great interest. In the V2V communication network, users can choose different transmission modes and power levels for communication, to guarantee their quality-of-service (QoS), high capacity of vehicle-to-infrastructure (V2I) links and ultra-reliability of V2V links. Aiming at V2V communication mode selection and power adaptation in 5G communication networks, a reinforcement learning (RL) framework based on slow fading parameters and statistical information is proposed. In this paper, our objective is to maximize the total capacity of V2I links while guaranteeing the strict transmission delay and reliability constraints of V2V links. Considering the fast channel variations and the continuous-valued state in a high mobility vehicular environment, we use a multi-agent double deep Q-learning (DDQN) algorithm. Each V2V link is considered as an agent, learning the optimal policy with the updated Q-network by interacting with the environment. Experiments verify the convergence of our algorithm. The simulation results show that the proposed scheme can significantly optimize the total capacity of the V2I links and ensure the latency and reliability requirements of the V2V links.

Cognitive radio (CR) is a critical technique to solve the conflict between the explosive growth of traffic and severe spectrum scarcity. Reasonable radio resource allocation with CR can effectively achieve spectrum sharing and co-channel interference (CCI) mitigation. In this paper, we propose a joint channel selection and power adaptation scheme for the underlay cognitive radio network (CRN), maximizing the data rate of all secondary users (SUs) while guaranteeing the quality of service (QoS) of primary users (PUs). To exploit the underlying topology of CRNs, we model the communication network as dynamic graphs, and the random walk is used to imitate the users’ movements. Considering the lack of accurate channel state information (CSI), we use the user distance distribution contained in the graph to estimate CSI. Moreover, the graph convolutional network (GCN) is employed to extract the crucial interference features. Further, an end-to-end learning model is designed to implement the following resource allocation task to avoid the split with mismatched features and tasks. Finally, the deep reinforcement learning (DRL) framework is adopted for model learning, to explore the optimal resource allocation strategy. The simulation results verify the feasibility and convergence of the proposed scheme, and prove that its performance is significantly improved.

With digitization and globalization in the era of 5G and beyond, research on high-throughput satellites (HTS) to increase communication capacity and improve flexibility is becoming essential. To achieve efficient resource utilization and dynamic traffic demand matching, the multi-dimensional resource management (MDRM) problem of the HTS communication system has been studied in this paper. Since the MDRM problem is a non-convex mixed integer problem, we decompose it into two tractable sub-problems. First, the beam-domain resource configuration problem is formed to enable on-demand coverage. Next, the user-domain resource allocation problem is modeled to enable on-demand communication. Considering the two-domain optimization problem, a two-stage framework is developed based on the combination of self-supervised learning and deep reinforcement learning. Specifically, in the first stage, a maximum co-channel interference based self-supervised learning method is proposed to perform traffic demand matching through demand awareness. In the second stage, a soft frequency reuse based proximal policy optimization approach is presented to further increase the system capacity through interference coordination. The simulation results demonstrate that our proposed two-stage algorithm outperforms the benchmark schemes in terms of spectrum efficiency and demand satisfaction.

The large-scale expansion of low Earth orbit (LEO) satellite constellations has ushered in a new era of space communications. However, the limitations of orbital and spectrum resources pose significant obstacles. With the aid of cognitive radio technology, spectrum sharing between LEO and geostationary Earth orbit (GEO) satellite communication systems provides a feasible solution to alleviate spectrum scarcity. Aiming at the scenario where LEO satellites pass through GEO satellite coverage areas, we seek to explore flexible and efficient spectrum sharing schemes to achieve co-linear interference avoidance. In this paper, we formulate a joint optimization problem for beam management and resource allocation, emphasizing the necessity of improving system throughput while ensuring quality of service for GEO satellite users. To address this issue, we first construct a space information model to describe the signal connections between satellites and users, as well as the overlapping coverage relationships among satellites. Then, we develop an adaptive approach that integrates both model-based and model-free deep reinforcement learning (DRL) methods. Guided by the space information graph, the model-based DRL employs a hybrid attention mechanism to mitigate beam-level interference through beam hopping and pointing optimization. Meanwhile, the model-free DRL optimizes channel allocation and power control to achieve user-level spectrum sharing, aiming to maximize resource utilization through continuous interaction. Simulation results demonstrate that the proposed algorithm significantly enhances the overall system throughput, showing its potential for effective interference coordination in the coexistence of LEO and GEO satellite communication systems.

The rapid development of low Earth orbit (LEO) satellite constellations has enabled global broadband coverage and low-latency communication, but also brings new challenges to connection continuity and network stability. Due to the ultra-dense deployment and high orbital velocity of LEO satellites, users frequently experience mandatory handovers and are prone to triggering “ping-pong” effects in overlapping coverage areas. To address these issues, we propose a hierarchical reinforcement learning (HRL)-based inter-satellite handover framework that decouples decision-making into two subproblems: when to initiate a handover at the temporal level and which satellite to handover to at the spatial level. To achieve long-term planning, the temporal agent utilizes the proximal policy optimization (PPO) algorithm to determine the handover timing by predicting future satellite load and interference levels. For short-term adaptability, the spatial agent employs the deep Q-network (DQN) to select the target satellite based on a utility function incorporating satellite load, signal quality, and service duration. We implement the proposed method in a Starlink constellation environment. Simulation results show that the proposed HRL-based scheme outperforms traditional and non-hierarchical RL methods in terms of user handover frequency and handover success rate. Furthermore, we validate that the proposed approach significantly improves transmission rate and load balancing, demonstrating its effectiveness in highly dynamic LEO satellite environments.

In IoT-enabled smart home scenarios, heterogeneous communication devices such as Bluetooth (BT) and Wi-Fi are widely used in applications such as home automation, remote monitoring, and intelligent device interconnection. However, in such a multi-device coexistence environment, efficiently allocating limited time-frequency resources to mitigate communication interference and enhance system performance has become a critical challenge. To address these issues, this article proposes a comprehensive solution that integrates master selection, resource allocation, and task scheduling to optimize resource utilization and service quality in smart home IoT systems. For device management, we propose a hierarchical entropy weight method (HEWM), considering factors such as device parameters, sensing capabilities, communication performance, and device interoperability. This method ensures efficient and stable selection of the primary device, optimizing network topology and communication efficiency. For resource allocation, we introduce a proximal policy optimization (PPO) algorithm that dynamically adjusts time-frequency resource allocation based on the varying device usage, network load, and communication condition. This adaptive strategy reduces interference between devices and improves system throughput. For task scheduling, we develop a task urgency-based queueing (TUQ) mechanism that prioritizes tasks based on urgency. A task preemption mechanism ensures that high-urgency tasks are processed with minimal delay, enhancing scheduling efficiency and service responsiveness. Simulation results show that the proposed approach significantly outperforms traditional methods in smart home IoT scenarios, achieving higher primary device scores, a 3%–22% improvement in system throughput, and a 5%–36% reduction in task delay.