Artificial Intelligence Internet of Things (AIoT) is an emerging technology within the Internet of Things (IoT), bringing an increasing demand for intelligent task offloading. Multi-node cooperative Vehicular Fog Computing (VFC) offers efficient and low-latency data processing to meet this requirement. However, due to the limited resource of fog nodes and latency-sensitive and computing-intensive task requirements, how to efficiently improve Quality of Service (QoS) and reduce energy consumption is an important issue in VFC. In this paper, we propose QECLO, a novel QoS-aware task offloading method. Unlike most previous studies, our goal is to improve QoS while minimizing energy consumption thus avoiding the overallocation of resource and high energy consumption caused by the one-sided pursuit of high QoS for few high-priority tasks. We solve the computation resource allocation subproblem by convex optimization and then optimize the communication resource and power allocation by an improved heuristic algorithm based on Decision Tree (DT). Moreover, we evaluate proposed approach through traffic scenario simulations. The experimental results show that our proposed approach outperforms existing methods in terms of energy consumption and latency.

In Internet of Vehicles (IoV), vehicles communicate with Roadside Units (RSU) to ensure driving safety. The variability in complex road trajectories intensifies the angle changes between vehicles and RSU, impacting the stability of IoV Millimeter Wave (mmWave) communications. The paper proposes an Integrated Sensing and Communication (ISAC) RCG-Net beam tracking solution for IoV on complex road trajectories, integrating Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU). The RCG-Net beam tracking solution leverages the powerful feature learning capability of deep neural networks, predicting and tracking angles using spatial features of echo signals and historical information features. This enhances beam tracking precision and resolves communication instability issues in IoV on complex road trajectories. Simulation results demonstrate that the proposed solution achieves high angle tracking accuracy and communication performance on intricate road trajectories, outperforming beam tracking solutions based on communication feedback and state evolution model.

Future 6G wireless networks will integrate communication and sensing functions, sharing resources across time, frequency, and space domains to achieve Integrated Sensing and Communication (ISAC). The millimeter-wave (mmWave) spectrum is poised to offer ISAC systems high communication rates and precise sensing capabilities, while the integration of RIS can enhance the stability of communication links. This advancement is significant for the Internet of Things (IoT), where device interconnectivity and accurate environmental sensing are crucial for intelligent operations and decision-making. This paper introduces a passive relay RIS-assisted mmWave ISAC system for Multiple Input Single Output (MU-MISO) communication and multi-target sensing in IoT, aiming for efficient information exchange and high-precision sensing. Simulation results show that the proposed algorithms achieve high spectral efficiency (SE) and low bit error rates (BER), further propelling IoT technology towards more advanced levels of intelligence.

For future 6G wireless networks, communication and sensing will be collaboratively integrated into one system, sharing the same resource configuration in the time, frequency, and space domains to achieve "Integrated Sensing and Communication" (ISAC). The mmWave technology will provide high communication capacity and ultra-precision sensing ability. This paper introduces a WMMSE-based hybrid beamforming methodology, where a flexible trade-off between communication and sensing performance is achieved. Moreover, the alternating direction method of multipliers (ADMM) framework will be used to optimize the ISAC digital beamformer for each subcarrier and the analog beamformer for the entire bandwidth. The simulation outcomes confirm the efficiency of the proposed approach.

In the rapidly evolving landscape of wireless communication technology, Integrated Communication and Sensing (ISAC) has emerged as a focal point of research owing to its efficient utilization of hardware resources. Unmanned Aerial Vehicles (UAVs), serving as an auxiliary tool in this domain, extend the applicability of ISAC significantly due to their high mobility, cost-effectiveness, and portability. This study delves into an innovative UAV-assisted ISAC dynamic patrolling model. In this paradigm, UAVs equipped with ISAC capabilities function not only as mobile aerial base stations providing communication services but also as radar and computational units for transmitting sensory information. To cater to the requisites of communication and sensing tasks, while mitigating the impact of UAV mobility, a Mix-ISAC frame structure is proposed, ensuring continuous communication services. Furthermore, this research introduces a method for jointly optimizing UAV trajectory and power allocation, aimed at augmenting the energy efficiency of UAVs. Considering the dynamic nature of user and UAV positioning, a Deep Reinforcement Learning(DRL)-based dynamic trajectory optimization and power allocation (DTPA)algorithm is proposed. To address the inefficiency of traditional non-uniform sampling strategies in training actor networks in continuous action spaces, a multi-tiered prioritized sampling strategy is incorporated, ensuring the effectiveness of the training process. Numerical experiments validate the convergence of the proposed algorithm and, through comparative analysis, demonstrate its superior performance.