Mobile Edge Computing (MEC) effectively alleviates the pressure on limited in-vehicle computing resources and energy supply caused by computation-intensive vehicular applications. However, the uneven spatial distribution of users leads to load imbalance among adjacent MEC servers, significantly increase the latency and energy consumption costs for vehicles. Therefore, achieving optimal configuration of available computing resources in MEC servers to accomplish the goal of low-latency and low-energy task offloading has become a critical issue to address. To tackle this problem, this study proposes a Multi-RSU Load Balancing (MRLB) strategy based on multi-hop network technology. This strategy dynamically allocates computing tasks to neighboring RSU server clusters with available computing resources through task segmentation and computation offloading mechanisms. Meanwhile, adaptive resource allocation strategies are implemented based on task quantity and task scale characteristics. Specifically, this study designs a multi-RSU collaborative offloading algorithm based on Deep Deterministic Policy Gradient (DDPG) to solve the optimal offloading decision. Additionally, by integrating the Lagrange multiplier method and Sequential Quadratic Programming (SQP) algorithm, the joint optimization of imbalanced task segmentation decisions and optimal CPU frequency allocation decisions for RSU servers is achieved. Experimental results demonstrate that the proposed method can achieve efficient multi-RSU resource allocation and ensure coordinated optimization of both system latency and energy consumption costs across diverse device conditions and varying network scenarios, particularly in load-imbalanced situations.

In the vehicular networks (VN) assisted by the integration of sensing and communication (ISAC), rapid processing of data from sensors is a necessary condition to ensure safe driving and enhance user experience. Utilizing the computational resources of the roadside unit (RSU) can effectively reduce the task processing delay. However, in some areas of the road, uneven distribution of task-vehicles can lead to severe load imbalance in neighbouring RSUs, and these tasks often have different delay requirements. The tasks in the high-load area can be offloaded to the low-load area to balance the load. We use the idle-vehicles in the low-load RSU area that are close to the task-vehicles as relays to hop and offload the tasks to the low-load RSUs. On the other hand, in order to satisfy the delay requirements of the heterogeneous tasks, this paper proposes the priority ordering of the heterogeneous tasks, the more delay-sensitive tasks require more resources to meet their delay requirements, i.e., the higher the priority. In order to both satisfy the delay requirements of heterogeneous tasks and maintain a small average system delay, we establish the optimization problem of minimizing the weighted average system delay and solve it by using the Relay Hopping and Differentiated Task Prioritization (RHATP) algorithm. Simulation results show that under the condition of guaranteeing the delay requirement of high-priority tasks, the strategy can achieve lower system delay and effectively reduce the processing delay in high-load areas. And it still maintains stable performance in different scenarios.

With the rapid development of Artificial Intelligence (AI) and Internet of Vehicles (IoV), the types of vehicular applications are becoming more diverse. And Vehicular Edge Computing (VEC) can provide the computing resource and caching resource for the diverse applications with the lower latency compared with the cloud. However, due to the limited resource of VEC and the long haul transmission from the cloud, the multi-type caching of the diverse applications from multi-users bring the huge challenges. In this paper, we propose a joint optimization problem of multi-type caching placement and multi-user computation offloading in the three-layer end-edge-cloud architecture to minimize the overall system latency. As the resolution of the NP-Hard problem, a Caching and Offloading Framework for Multi-user Multi-type Requests (COF-MMR) based on Deep Deterministic Policy Gradient (DDPG) algorithm is explored. Simulation results show that our proposed COFMMR framework has achieved an up to 20% improvement in reducing the overall system latency compared to the baseline scheme.

Taxi demand prediction plays a significant role in assisting the pre-allocation of taxi resources to avoid mismatches between demand and service, particularly in the era of the sharing economy and autonomous driving. However, most studies have only tried to figure out the complex spatial-temporal pattern of taxi demand from historical taxi demand series, neglecting the intrinsic influences of regional functions, and failing to effectively capture the dynamic long-term periodicity. In this paper, we make two important observations: (1) taxi demand pattern varies significantly between different functional regions; and (2) taxi demand follows a dynamic daily and weekly pattern. To address these two issues, we adopt Points of Interest (POIs) to identify regional functions, and propose a novel BERT-based Deep Spatial-Temporal Network (BDSTN) to model the complex spatial-temporal relations from heterogeneous local and global features. In BDSTN, a Spatiotemporal Pattern Matching module is introduced to capture the complex spatiotemporal pattern of taxi demand while considering its dynamic temporal periodicity, and a Functional Similarity Embedding module is adopted to learn the functional similarity among all regions via POIs. To the best of our knowledge, this is the first work to use BERT-based architecture to learn taxi demand patterns, and is also the first to take functional similarity represented by POIs into consideration. Our experimental results on real-world traffic datasets in New York City demonstrate that the effectiveness of the proposed method outperforms the state-of-the-art methods, and that the efficiency of our proposed model is higher than other deep learning methods.

The Internet of Vehicles (IoV) has always attracted attention as the emerging communication network with the most development potential in the 5G era. However, the performance of IoV under 5G ultra-dense networks is an open issue, especially in practice the outage probability and ergodic capacity of the relay cooperative IoV network under aggregate interference are still unclear. Therefore, an opportunistic Decoding and Forwarding (DF) relay cooperative transmission algorithm was proposed in this paper when the destination node of IoV has aggregated interference. In addition, based on mathematical theoretical knowledge such as numerical analysis, the closed expressions of the outage probability and ergodic capacity of the IoV system under aggregated interference was derived. Finally, simulation experiments verify the effectiveness of the proposed scheme and the correctness of the theoretical analysis, which improves the transmission rate of the system.

Channel state information-based activity recognition has gathered immense attention over recent years. Many existing works achieved desirable performance in various applications, including healthcare, security, and Internet of Things, with different machine learning algorithms. However, they usually fail to consider the availability of enough samples to be trained. Besides, many applications only focus on the scenario where only single subject presents. To address these challenges, in this paper, we propose a three-phase system Wi-multi that targets at recognizing multiple human activities in a wireless environment. Different system phases are applied according to the size of available collected samples. Specifically, distance-based classification using dynamic time warping is applied when there are few samples in the profile. Then, support vector machine is employed when representative features can be extracted from training samples. Lastly, recurrent neural networks is exploited when a large number of samples are available. Extensive experiments results show that Wi-multi achieves an accuracy of 96.1% on average. It is also able to achieve a desirable tradeoff between accuracy and efficiency in different phases.