The integration of mobile edge computing (MEC) and air-ground integrated network is viewed as a crucial technology for Internet of Remote Things (IoRT) devices. It provides widespread service coverage and allows the tasks of IoRT devices to be executed by the uncrewed aerial vehicles (UAVs) and the high altitude platforms (HAPs). In this article, we investigate a joint partial task offloading, resource allocation, and UAV trajectory design problem to minimize the total task offloading delay of all IoRT devices in the air-ground integrated MEC network. Given that the problem is nonconvex and hard to solve by the traditional methods, we convert it into a Markov decision process (MDP) and leverage the deep reinforcement learning method to address it. Considering the complexity of the MDP grows with the number of the IoRT devices and the UAVs increasing, the primal problem is decomposed into two subproblems: 1) the UAV trajectory design and IoRT device power control subproblem, and 2) the partial task offloading and resource allocation subproblem. To address these two subproblems, we apply the basic concepts of the multiagent deep deterministic policy gradient (MADDPG) and the independent proximal policy optimization (IPPO) methods, respectively. Additionally, we introduce the enhanced prioritized experience replay and noise value to improve both the convergence performance and rate. This leads to the development of the MADDPG-improved prioritized experience replay (MADDPG-IPER) algorithm and noise value-IPPO (NV-IPPO) algorithm. Based on the solution of these two subproblems, a joint partial task offloading, resource allocation, and UAV trajectory design (JPTORAUTD) algorithm is proposed. Simulation results present that the proposed JPTORAUTD algorithm outperforms other benchmark algorithms in terms of reducing the total task offloading delay.

Vehicle Edge Computing (VEC) leverages compact cloud computing at the mobile network edge to meet the processing and latency needs of vehicles. By bringing computation closer to the vehicles, VEC reduces data transmission, minimizes latency, and boosts performance for compute-intensive applications. However, during peak hours of urban road traffic, the scarce computational resources available at edge servers could pose challenges in fulfilling the processing needs of vehicles. Introducing Unmanned Aerial Vehicles (UAVs) as supplementary edge computing nodes could significantly mitigate the aforementioned issue. In this paper, we propose a flexible edge computing framework in which a fleet of UAVs function as mobile computational service providers, offering computation offloading services to multiple vehicles. We design and optimize a computation offloading model for the UAV-enabled vehicle edge computing environment. The proposed model tackles the task offloading challenge, aiming to optimize UAV revenue and task processing efficiency while considering the constraints of UAVs’ restricted computational power and energy resources. Towards this end, our model jointly considers two key factors: task partitioning and computational resource allocation. To tackle the challenges posed by the aforementioned non-convex optimization problem, we construct a Markov Decision Process (MDP) model for the multi-UAV-enabled mobile edge computing system and introduce an innovative Multi-Agent Deep Reinforcement Learning (MADRL) framework addressing the decision-making challenge represented by MDP model. Comprehensive simulation outcomes illustrate that our devised task offloading technique outperforms other optimization methods.

Semantic communication (SC) has emerged as a promising paradigm for upcoming intelligent applications, enabling mobile devices to collaboratively execute intelligent tasks with edge servers through computation offloading. However, few studies have addressed the problem of collaborative inference in SC networks. Traditional collaborative inference mechanisms may suffer performance decline in SC systems and are vulnerable to eavesdroppers. To address these issues, first, we present an encryptor that encrypts semantic information to avoid privacy leakage and a decryptor for restoration. Besides, we propose a novel SC-empowered edge computing framework enabling mobile devices to deploy a partial semantic encoder and offload the rest to edge servers. Based on this framework, we formulate the collaborative inference optimization problem, jointly optimizing delay, energy consumption, and privacy leakage. DNNPart is devised based on deep deterministic policy gradient to address the problem, which consists of a semantic attention mechanism that enables it to focus on important state variables, a hybrid action representation method that makes it adapt to mixed discrete and continuous action spaces, a dynamic model splitting algorithm that locates the optimal partition layer and adaptively splits the semantic coders. Integrated with these components, DNNPart iteratively optimizes the offloading strategy to find the optimal offloading strategy. Extensive simulations were conducted to verify the effectiveness of the proposed method by comparing it with baseline mechanisms.

The integration of vehicle edge computing (VEC) and air-ground integrated network is considered as a key technology to achieve autonomous driving. It exploits the ubiquitous service coverage and enables tasks to be offloaded to various components, such as high-altitude platform (HAP), unmanned aerial vehicle (UAV), and roadside unit (RSU). In this article, we address the challenge of minimizing the overall task offloading delay in the air-ground integrated VEC network through a joint multicomputation equipment selection and multidimensional resource allocation (JCESRA) problem. Considering the nonconvexity inherent in the problem, we employ the fundamental idea of the block coordinate descent (BCD) method to tackle it. Initially, we exclude the HAP and decompose the primal problem into three subproblems: 1) low-altitude computation equipment selection; 2) joint bandwidth and computation resource allocation; and 3) UAV trajectory design. The first subproblem, which involves integer programming, is solved by using the many-to-one matching method. Meanwhile, we utilize the CVX and successive convex approximation (SCA) method to solve the last two subproblems, respectively. Considering the matching externality, we utilize the coalition game method to deal with it. Based on the solutions of the three subproblems, the JCESRA algorithm without considering the HAP has been proposed. Subsequently, we consider the HAP into the problem. Because the task offloading decision and computation resource allocation of the HAP problem can be viewed as a knapsack problem, we utilize the dynamic programming method to solve it. Because some tasks are offloaded to the HAP, there are some redundant computation resources in UAVs and RSU. We reallocate the computation resources of UAVs and RSU to further reduce the task offloading delay. At last, we present the complete JCESRA algorithm. The simulation results unequivocally indicate that the proposed JCESRA algorithm outperforms other algorithms by significantly reducing the task offloading delay.

The 6G network is expected to accommodate a wide array of connected devices, supporting diverse services from any location at any time. In this article, we introduce an aerial mobile edge computing (MEC) framework composed of high-altitude platforms (HAPs) and low-altitude unmanned aerial vehicles (UAVs), to cater to computing offloading for Internet of Things (IoT) devices, particularly in rural/remote areas or disaster zones. The framework accommodates various types of tasks, each computed by the corresponding Docker container. The objective is to achieve optimal workload fairness for UAVs while simultaneously minimizing the weighted processing costs among IoT devices in terms of task computation latency and energy consumption over the long term. This is achieved by jointly optimizing the flight trajectories and Docker image caching decisions of the UAVs with limited storage capacities, alongside ensuring service fairness for IoT devices. We tailor a multiagent deep deterministic policy gradient (MADDPG)-based approach to solve the long-term joint optimization problem, normalizing continuous actions and sampling discrete actions by generalizing the Gumbel-Softmax reparameterization trick. Experimental results indicate that our approach significantly outperforms benchmark schemes in terms of processing delay, energy consumption, and fairness.

Mobile-edge computing (MEC) has been regarded as a promising paradigm to reduce service latency for data processing in the Internet of Things (IoT) by provisioning computing resources at the network edges. In this work, we jointly optimize the task partitioning and computational power allocation for computation offloading in a dynamic environment with multiple IoT devices and multiple edge servers. We formulate the problem as a Markov decision process with constrained hybrid action space, which cannot be well handled by existing deep reinforcement learning (DRL) algorithms. Therefore, we develop a novel DRL called Dirichlet deep deterministic policy gradient (D3PG), which is built on deep deterministic policy gradient (DDPG) to solve the problem. The developed model can learn to solve multiobjective optimization, including maximizing the number of tasks processed before deadlines and minimizing the energy cost and service latency. More importantly, D3PG can effectively deal with a constrained distribution-continuous hybrid action spaces, where the distribution variables are for the task partitioning and offloading, while the continuous variables are for computational frequency control. Moreover, the D3PG can address many similar issues in MEC and general reinforcement learning problems. Extensive simulation results show that the proposed D3PG outperforms the state-of-the-art methods.

A smart city improves operational efficiency and comfort of living by harnessing techniques such as the Internet of Things (IoT) to collect and process data for decision-making. To better support smart cities, data collected by IoT should be stored and processed appropriately. However, IoT devices are often task-specialized and resource-constrained, and thus, they heavily rely on online resources in terms of computing and storage to accomplish various tasks. Moreover, these cloud-based solutions often centralize the resources and are far away from the end IoTs and cannot respond to users in time due to network congestion when massive numbers of tasks offload through the core network. Therefore, by decentralizing resources spatially close to IoT devices, mobile edge computing (MEC) can reduce latency and improve service quality for a smart city, where service requests can be fulfilled in proximity. As the service demands exhibit spatial-temporal features, deploying MEC servers at optimal locations and allocating MEC resources play an essential role in efficiently meeting service requirements in a smart city. In this regard, it is essential to learn the distribution of resource demands in time and space. In this work, we first propose a spatio-temporal Bayesian hierarchical learning approach to learn and predict the distribution of MEC resource demand over space and time to facilitate MEC deployment and resource management. Second, the proposed model is trained and tested on real-world data, and the results demonstrate that the proposed method can achieve very high accuracy. Third, we demonstrate an application of the proposed method by simulating task offloading. Finally, the simulated results show that resources allocated based upon our models’ predictions are exploited more efficiently than the resources are equally divided into all servers in unobserved areas.

With emergence of Internet of Things (IoT), wireless traffic has grown dramatically, posing severe strain on core network and backhaul bandwidth. Proactive caching in mobile edge computing systems can not only efficiently mitigate the traffic congestion and relieve burden of backhaul but also can reduce the service latency for end devices. However, proactive caching heavily relies on the prediction accuracy of content popularity, which is typically unknown and change over time. In this paper, we propose an online proactive caching scheme based on bidirectional deep recurrent neural network (BRNN) model to predict time-series content requests and update edge caching accordingly. Specifically, on the first layer, a 1-D convolution neural network (CNN) is devised to reduce the computational costs. Then, BRNN is employed to predict time-varying requests from users. Afterward, a fully connected neural network (FCNN) is harnessed to learn and sample predicts from the BRNN. Finally, we conduct experiments based on real datasets, which demonstrate that the proposed approach can achieve considerably high prediction accuracy and significantly improve content hit rate of end devices.

Road damage detection is of importance to road maintenance, which typically requires huge amount of manual efforts. In this work, we leverage deep learning models to analyze the road images to detect road damages efficiently. Specifically, we train and test different deep learning methods to identify efficient models with high accuracy. Although two-stage detector, applied object classification and bounding-box regression on proposed regions, can achieve high accuracy in object detection, it runs slow due to its high computational cost. Instead, we adopt one-stage detectors, classification and bounding-box regression at a single stage, because they are faster than two-stage detectors. In this work, we have trained and tested several one-stage models and found a fast model called RetinaNet can detect road damages with relatively high accuracy. A user guide of the source code and predicted examples of trained model have been provided as a markdown document and jupyter notebook, respectively.