关键词： mobile edge computing   MEC   vehicular networks   intelligent transportation systems   vehicle-to-everything  

摘要： In recent years, the need for computation-intensive applications in mobile networks requiring more storage, powerful processors, and real-time responses has risen substantially. Vehicular networks play an important role in this ecosystem, as they must support multiple services, such as traffic monitoring or sharing of data involving different aspects of the vehicular traffic. Moreover, new resource-hungry applications have been envisaged, such as autonomous driving or in-cruise entertainment, hence making the demand for computation and storage resources one of the most important challenges in vehicular networks. In this context, Mobile Edge Computing (MEC) has become the key technology to handle these problems by providing cloud-like capabilities at the edge of mobile networks to support delay-sensitive and computation-intensive tasks. In the meantime, researchers have envisaged use of onboard vehicle resources to extend the computing capabilities of MEC systems. This paper presents a comprehensive review of the most recent works related to MEC-assisted vehicular networks, as well as vehicle-assisted MEC systems. We illustrate the MEC system architecture and discuss its deployment in vehicular environments, as well as the key technologies to realize this integration. After that, we review the recent literature by identifying three different areas, i.e.: (i) MEC providing additional resources to vehicles (e.g., for task offloading);(ii) MEC enabling innovative vehicular applications (e.g., platooning), and (iii) vehicular networks providing additional resources to MEC systems. Finally, we discuss open challenges and future research directions, addressing the possible interplays between MEC systems and vehicular networks.

关键词： Internet of vehicle   Mobile edge computing   Modified sparrow search algorithm   Multi-hop task offloading  

摘要： Mobile edge computing (MEC) is an emerging technology that can be integrated with the Internet of vehicles (IoV) to enhance vehicle services with low latency and optimize task offloading efficiency. MEC technology enhances the battery life of mobile devices by bringing storage and computational services closer to the edge of the network. However, challenges arise in areas with limited MEC server coverage. To address these challenges, this paper proposes a multi-hop task offloading model in MEC-IoV utilizing the modified sparrow search algorithm (MSSAMTO-IoV). The MSSAMTO-IoV model consists of two phases: candidate vehicle selection and task offloading. In the candidate vehicle selection mechanism, the model takes into account the k-hop wireless communication range. It identifies and selects candidate vehicles from neighboring vehicles for task offloading. The task offloading problem is then formulated as an optimization problem, aiming to minimize the delay. To solve this problem, MSSA is utilized, with modifications introduced to enhance the initial population quality and diversity of the standard SSA using the logistic map. Furthermore, an inertia weight is introduced to improve search speed, convergence rate, and exploration capabilities. The mean termination criterion is employed to avoid unnecessary iterations and minimize run-time. Additionally, a mutation strategy is employed to prevent falling into local optima. The simulation results demonstrate that MSSAMTO-IoV achieves faster convergence and outperforms BAT and SSA by approximately 2 times and 3 times, respectively. Moreover, MSSAMTO-IoV effectively reduces latency across different task sizes. For a 500 KB task, it reduces latency by approximately 5, 9, and 13% compared to basic SSA, BAT, and greedy algorithms, respectively.

关键词： Resource management   Data models   Energy consumption   Computational modeling   Task analysis   Wireless communication   Training   Multi-access edge computing   Machine learning   Mobile edge learning   dynamic task allocation   distributed machine learning   mobile edge computing  

摘要： This paper extends the paradigm of "mobile edge learning (MEL)" by designing an energy-aware optimal task allocation scheme for training a machine learning (ML) model in a semi-asynchronous manner across multiple learners connected via the resource-constrained wireless edge network. The tasks are allocated such that the local dataset size selected at each learner ensures completion within a given global delay constraint and a local maximum energy consumption limit. Hence, the designed method is heterogeneity aware (HA) because it offers a trade-off between resource consumption and MEL performance by directly relating the time and energy consumption to the heterogeneous communication/computational capabilities of learners. Because the resulting optimization is an NP-hard quadratically-constrained integer linear program (QCILP), a two-step suggest-and-improve (SAI) solution is proposed. The proposed HA semi-asynchronous (HA-Asyn) approach is compared against the HA synchronous (HA-Sync) scheme and the heterogeneity unaware (HU) synchronous/asynchronous (HU-Sync/Asyn) equal batch allocation schemes. Results from a system of 20 learners tested for various completion time and energy consumption constraints show that the proposed HA-Asyn method works better than the HU-Sync/Asyn approaches and can even provide gains of up-to 25% compared to the HA-Sync scheme.

关键词： Sensors   Autonomous aerial vehicles   Task analysis   Radar   Training   Servers   Optimization   Digital twins   Multi-access edge computing   Optimization methods   Digital twin   mobile edge computing   dual function radar and communication   proximal policy optimization  

摘要： In this paper, we study a digital twin (DT)-empowered integrated sensing, communication, and computation network. Specifically, the users perform radar sensing and computation offloading on the same spectrum, while unmanned aerial vehicles (UAVs) are deployed to provide edge computing service. We first formulate a multi-objective optimization problem to minimize the beampattern performance of multi-input multi-output (MIMO) radars and the computation offloading energy consumption simultaneously. Then, we explore the prediction capability of DT to provide intelligent offloading decision, where the DT estimation deviation is considered. To track this challenge, we reformulate the original problem as a multi-agent Markov decision process and design a multi-agent proximal policy optimization (MAPPO) framework to achieve a flexible learning policy. Furthermore, the Beta-policy and attention mechanism are used to improve the training performance. Numerical results show that the proposed method is able to balance the performance tradeoff between sensing and computation functions, while reducing the energy consumption compared with the existing studies.

关键词： Servers   Task analysis   Resource management   Optimization   Stability analysis   Channel allocation   Delays   Lyapunov optimization   mobile edge computing   deep reinforcement learning (DRL)   queueing networks  

摘要： Mobile Edge Computing (MEC) is a key technology towards delay-sensitive and computation-intensive applications in future cellular networks. In this paper, we consider a multi-user, multi-server system where the cellular base station is assisted by a UAV, both of which provide additional MEC services to the terrestrial users. Via dual connectivity (DC), each user can simultaneously offload tasks to the macro base station and the UAV-mounted MEC server for parallel computing, while also processing some tasks locally. We aim to propose an online resource management framework that minimizes the average power consumption of the whole system, considering long-term constraints on queue stability and computational delay of the queueing system. Due to the coexistence of two servers, the problem is highly complex and formulated as a multi-stage mixed integer non-linear programming (MINLP) problem. To solve the MINLP with reduced computational complexity, we first adopt Lyapunov optimization to transform the original multi-stage problem into deterministic problems that are manageable in each time slot. Afterward, the transformed problem is solved using an integrated learning-optimization approach, where model-free Deep Reinforcement Learning (DRL) is combined with model-based optimization. Via extensive simulation and theoretical analyses, we show that the proposed framework is guaranteed to converge and can produce nearly the same performance as the optimal solution obtained via an exhaustive search.

关键词： deep reinforcement learning   wireless power transfer   mobile edge computing   time division multiple access  

摘要： Many nodes in Internet of Things (IoT) rely on batteries for power. Additionally, the demand for executing compute-intensive and latency-sensitive tasks is increasing for IoT nodes. In some practical scenarios, the computation tasks of WDs have the non-separable characteristic, that is, binary offloading strategies should be used. In this paper, we focus on the design of an efficient binary offloading algorithm that minimizes system energy consumption (EC) for TDMA-based wireless-powered multiaccess edge computing networks, where WDs either compute tasks locally or offload them to hybrid access points (H-APs). We formulate the EC minimization problem which is a non-convex problem and decompose it into a master problem optimizing binary offloading decision and a subproblem optimizing WPT duration and task offloading transmission durations. For the master problem, a DRL based method is applied to obtain the near optimal offloading decision. For the subproblem, we firstly consider the scenario where the nodes do not have completion time constraints and obtain the optimal analytical solution. Then we consider the scenario with the constraints. By jointly using the Golden Section Method and bisection method, the optimal solution can be obtained due to the convexity of the constraint function. Simulation results show that the proposed offloading algorithm based on DRL can achieve the near-minimal EC.

关键词： Mobile edge computing   Computation offloading   Offloading strategy   Directed acyclic graph  

摘要： The Internet of Things (IoT) and mobile edge computing (MEC) technologies advance, more workloads are being transferred to edge servers for processing. The offloading strategy is a crucial aspect of this development, considering all relevant factors and requiring a rapid development approach. This research aims to develop and propose an innovative solution for fine-grained task offloading scheduling in the context of the evolving technologies of the Internet of Things (IoT) and mobile edge computing (MEC). The research addresses the challenges posed by task dependencies within user-generated applications processed across distributed edge servers. This study presents a solution for fine-grained task offloading scheduling by representing user-generated applications as a directed acyclic graph (DAG). We propose a multi-population cooperative elite algorithm (MCE-PSO) based on particle swarm optimization to address the challenge of offloading tasks with dependencies in MEC, reducing application execution time and energy consumption. The proposed method uses a Penalty-based algorithm to minimize energy usage. The results of our experiments show that MCE-PSO outperforms benchmark algorithms, reducing overhead by up to 82.6%, 36.6%, and 16.3%. This demonstrates the efficiency and reliability of our system.

关键词： Mobile edge computing   multi-objective reinforcement learning   task offloading   trajectory control   unmanned aerial vehicle  

摘要： This article studies the trajectory control and task offloading (TCTO) problem in an unmanned aerial vehicle (UAV)-assisted mobile edge computing system, where a UAV flies along a planned trajectory to collect computation tasks from smart devices (SDs). We consider a scenario that SDs are not directly connected by the base station (BS) and the UAV has two roles to play: MEC server or wireless relay. The UAV makes task offloading decisions online, in which the collected tasks can be executed locally on the UAV or offloaded to the BS for remote processing. The TCTO problem involves multi-objective optimization as its objectives are to minimize the task delay and the UAV's energy consumption, and maximize the number of tasks collected by the UAV, simultaneously. This problem is challenging because the three objectives conflict with each other. The existing reinforcement learning (RL) algorithms, either single-objective RLs or single-policy multi-objective RLs, cannot well address the problem since they cannot output multiple policies for various preferences (i.e., weights) across objectives in a single run. An evolutionary multi-objective RL (EMORL) algorithm is applied to address the TCTO problem. We improve the multi-task multi-objective proximal policy optimization of the original EMORL by retaining all new learning tasks in the offspring population, which can preserve promissing learning tasks. The simulation results demonstrate that the proposed algorithm can obtain more excellent non-dominated policies by striking a balance between the three objectives regarding policy quality, compared with two evolutionary algorithms, two multi-policy RL algorithms, and the original EMORL.

关键词： Vehicular networks   mobile edge computing   task offloading   resource allocation   joint optimization  

摘要： In this article, we study the task offloading problem on mobile edge in vehicular networks. Specifically, we take computational resource constraints into consideration, and aim to simultaneously reduce latency and energy consumption. For this purpose, we establish an offloading model that consists of local edge computing resources, edge server resources of both macro and subsidiary base stations, as well as cloud computing server resources. Each task can be offloaded through one of five strategies, and is evaluated via a loss function determined by its latency and energy consumption. Based on this model, our goal is to solve a mixed-integer non-linear optimization problem (MINLP) whose objective function is the weighted sum of the task-specific loss functions. To address this optimization problem, we split it into two sub-problems, referred to as resource allocation and offloading strategy. We develop a method based on Block Coordinate Descent technique combining convex optimization and Gray Wolf algorithm (BCD-CONGW) that alternatively solves the two sub-problems, until convergence. The former sub-problem is convex and can be solved in polynomial time, whereas the latter is non-convex and hence NP-hard. For the latter, we relax discrete variables and employ Gray Wolf algorithm with elite strategy to approximate its optimal point. By numerical evaluations, we show that our method outperforms existent methods in terms of latency and energy consumption.

关键词： Task analysis   Cloud computing   Resource management   Energy consumption   Wireless communication   Logic gates   Collaboration   Collaborative task offloading   mobile edge computing   distributed wireless backhaul  

摘要： Collaborative cloud-edge-end computing is a promising solution to support computation-intensive and latency-sensitive tasks by utilizing rich computing resources of cloud datacenters and low access delay of mobile edge computing (MEC) servers. Compared with traditional cloud computing and MEC, the cloud-edge environment has a stronger heterogeneity of servers and networks, resulting in significant differences between servers in the computation speed and access delay. However, few studies on cloud-edge-end task offloading focused on the characteristic of 5G heterogeneous networks in the cloud-edge environment. In this paper, we study the task offloading problem for collaborative cloud-edge-end computing in MEC-enabled small cell networks with low-cost distributed wireless backhaul. We aim to minimize the energy consumption of all user devices (UDs) via jointly optimizing the offloading decision, UDs' transmission power, and the allocation of spectrum and computation resources. To solve the non-convex problem, we decouple the original problem into three subproblems, and design an efficient method with solving these three subproblems iteratively to obtain a high-quality solution. The simulation results indicate that our proposed method can lead to significant reduction in the energy consumption of all UDs compared with other conventional methods.