关键词： Autonomous aerial vehicles   Optimization   Trajectory   Servers   Energy consumption   Wireless communication   Quality of experience   Minimization   Vectors   Resource management   Mobile edge computing   computation offloading   UAV trajectory  

摘要： As a promising network architecture, Mobile Edge Computing (MEC), has been proven that can effectively reduce the end-to-end latency and the energy consumption. The Unmanned Aerial Vehicle (UAV) assisted MEC network, where the UAV can provide the computation offloading services for the mobile users, can further alleviate the huge deployment cost of static edge servers. However, it remains unsolved how multiple cooperative flying UAVs serve the ground users, especially considering that these UAVs may share the same wireless channel and can communicate with the users while flying. In this paper, we first propose the Age of Task (AoT) metric to measure the quality of experience, and then formulate the joint optimization problem to minimize the worst AoT among all the users. Based on the block coordinate descent (BCD) method, this problem is transformed into three non-convex programming sub-problems (i.e., the UAV-user association sub-problem, the UAV trajectory planning sub-problem and the transmit power optimization sub-problem). Specifically, the successive convex approximation (SCA) technique is exploited iteratively to deal with the non-convexity in the UAV trajectory and transmit power optimization. Numerical results show that the proposed scheme outperforms the benchmark offloading schemes in terms of AoT.

关键词： Resource management   Computer architecture   Optimization   Computational modeling   Quality of experience   Dynamic scheduling   Real-time systems   Adaptive systems   Quality of service   Knowledge engineering   Adaptive computation offloading   resource allocation   knowledge-defined networking   mobile edge computing   quality of experience  

摘要： In large-scale dynamic network environments, optimizing the computation offloading and resource allocation strategy is key to improving resource utilization and meeting the diverse demands of User Equipment (UE). However, traditional strategies for providing personalized computing services face several challenges: dynamic changes in the environment and UE demands, along with the inefficiency and high costs of real-time data collection;the unpredictability of resource status leads to an inability to ensure long-term UE satisfaction. To address these challenges, we propose a Knowledge-Defined Networking (KDN)-based Adaptive Edge Resource Allocation Optimization (KARO) architecture, facilitating real-time data collection and analysis of environmental conditions. Additionally, we implement an environmental resource change perception module in the KARO to assess current and future resource utilization trends. Based on the real-time state and resource urgency, we develop a deep reinforcement learning-based Adaptive Long-term Computation Offloading and Resource Allocation (AL-CORA) strategy optimization algorithm. This algorithm adapts to the environmental resource urgency, autonomously balancing UE satisfaction and task execution cost. Experimental results indicate that AL-CORA effectively improves long-term UE satisfaction and task execution success rates, under the limited computation resource constraints.

关键词： Federated learning   vehicular edge computing   vehicular edge computing   intelligent transportation   intelligent transportation   variational autoencoders   variational autoencoders   federated vehicular networks   federated vehicular networks   Internet of vehicles   Internet of vehicles   mobile edge computing   mobile edge computing   double dueling deep Q-network   double dueling deep Q-network   popularity-based caching   popularity-based caching  

摘要： This paper proposes an innovative framework for enhancing vehicular edge computing (VEC) efficiency by addressing challenges in traditional intelligent transportation systems and Internet of vehicles. Our aim is to improve content prediction accuracy, reduce offload latency, and ensure data privacy by utilizing advanced techniques such as federated learning (FL) and deep reinforcement learning. We propose an in-car popularity-based caching (PBC) asynchronous system, based on FL, for edge computing. Unlike traditional synchronous FL, asynchronous FL allows the global model to be updated without waiting for all cars to complete learning process and upload their individual models, which helps to reduce training time. Integrating VEC with roadside infrastructure system allows real-time data processing by enabling low latency and high-quality services for applications like traffic management and autonomous driving. Through collaborative caching schemes and personalized content delivery, the proposed model optimizes system performance while adapting to dynamic vehicular environments. By prefetching potentially popular content ahead of time and caching it in edge nodes or roadside units, depending on the position and movement direction of the vehicle, the PBC system reduces the delay in content queries. Comprehensive experimental evaluations demonstrate that the PBC technique outperforms existing benchmark caching schemes in reducing the latency.

关键词： Mobile edge computing   Task priority   Computation offloading   Task migration   Dynamic programming  

摘要： Mobile edge computing (MEC) solves the problem of limited resources by offloading computation-intensive tasks to edge servers. However, as important factors affecting offloading decisions, task priority and migration strategy are often overlooked. This paper considers a MEC system with multiple servers and multi-priority tasks, aiming to minimize the completion delay of low-priority tasks by constructing a task offloading and migration model. Each server has two priority queues, one for high-priority tasks and another for low-priority tasks, both priority tasks arrive randomly. The migration behavior of low-priority tasks among multiple edge servers is modeled using PRP M/G/1 queuing model. Furthermore, the task offloading and migration problem is formulated as a sequential decision-making problem, and an algorithm based on dynamic programming is designed to find the optimal offloading and migration strategy. Through simulation experimental analysis, the algorithm proposed in this paper has better performance in reducing task completion delay and migration times compared with RSAS, MTCC and PSO.

关键词： Processor scheduling   Collaboration   Servers   Delays   Optimization   Cloud computing   Bandwidth   Internet of Things   Energy consumption   Artificial intelligence   Mobile edge computing   multi-layer collaboration   deep learning   resource scheduling   performance evaluation  

摘要： In the application of the Internet of Things (IoT), existing cloud edge collaboration technologies face the problem of poor coordination of heterogeneous resources. In this article, we propose CFEMC, which is a novel Cloud-Fog-Edge Multi-layer Collaboration resource scheduling framework for IoT. First, we design a collaborative resource scheduling framework based on semi-distributed artificial intelligence. It can achieve collaborative optimization of cloud/edge computing resource allocation under the constraints of high reliability and low latency. Second, we present a workflow applications scheduling strategy based on the proposed collaborative resource scheduling framework. This can solve the problem of unstable computing performance and transmission bandwidth during the scheduling process. Finally, the extensive and real data supported simulation results show that CFEMC has advantages in terms of energy consumption, delay and throughput compared with other benchmark strategies. Against CEC Hu et al. 2023 and PSO Zeng et al. 2022, the average throughput increases by 16.37% and 24.21%, and the total queuing delay decreases by 54.23% and 58.12%, respectively.

关键词： Autonomous aerial vehicles   Delays   Predictive models   Optimization   Servers   Training   Heuristic algorithms   Data models   Computational modeling   Resource management   Digital twin   mobile edge computing   deep reinforcement learning   generative and predictive models  

摘要： The emerging digital twin (DT) technology involves creating a digital clone of the physical world through techniques such as computer simulation and machine learning. This facilitates the management and decision-making of the physical world. In this correspondence, we propose a DT-assisted deep reinforcement learning (DRL) method to optimize the decision of computation offloading in an autonomous aerial vehicles (AAV)-based communication system. Our focus is on minimizing task processing delay by jointly optimizing task offloading and the AAV's flight path. This problem can be effectively addressed using the DRL method. However, it necessitates frequent interactions with the environment, which may lead to increased resource consumption and risks associated with some "bad" actions. To mitigate these challenges, our proposed DT comprises a predictive model to anticipate the reward and next stage of the physical environment. Additionally, a generative model is introduced to enhance sample efficiency, with these two models realized by a fully connected neural network and a variational auto-encoder, respectively. Subsequently, we generate a hybrid experience replay buffer to facilitate DRL training, resulting in faster convergence, improved performance, and fewer environmental interactions. Numerical results demonstrate that our proposed method achieves superior delay performance and training efficiency compared to state-of-the-art methods.

关键词： Servers   Dynamic scheduling   Processor scheduling   Internet of Things   Optimal scheduling   Adaptive scheduling   Resource management   Consumer electronics   Job shop scheduling   Energy consumption   Mobile edge computing   deep reinforcement learning   consumer electronics   task scheduling   GPPO algorithm  

摘要： The rapid advancement of IoT, AI, and edge computing has led to a significant increase in consumer devices and computation tasks, with new electronics incorporating these technologies to enhance services like VR/AR and autonomous driving, requiring real-time processing for safety and efficiency. However, recent research has focused on optimizing IoT task scheduling and resource allocation through various methods, yet overlooks the dynamic nature of IoT environments, fails to adapt to changing device counts and movements, and often ignores task completion rate in favor of minimizing latency and energy cost. In this context, an adaptive task scheduling and resource allocation strategy is proposed for Edge IoT systems, based on the designed Graph-based Proximal Policy Optimization (GPPO) algorithm. Firstly, the GPPO algorithm enhances PPO for adaptive task scheduling in the fluctuating MEC scenarios, adjusting for the varying number of nearby edge servers. Secondly, it accounts for consumer mobility by opting for local task execution if the consumer risks moving outside the edge server's range, ensuring result reception. Thirdly, it prioritizes task completion rate to increase the number of tasks finished within their acceptable duration. Experimental results demonstrated that the proposed method outperforms traditional methods.

关键词： Containers   Servers   Handover   Virtual machines   Predictive models   Accuracy   Ensemble learning   Delays   Deep learning   Consumer electronics   Proactive service migration   ensemble learning   mobile edge computing   container migration  

摘要： Mobile edge computing is considered as a key technology for consumer Internet of Vehicles networks, which provides low-latency, high-reliability network services for end-users. Service migration need to address where to migrate and how to implement service migration procedure based on user mobility. The existing reactive migrating solutions lead to overlong service migration time and end to end latency. The proactive service migration method obtains the target server in advance through mobility prediction, and the service migration procedure starts before communication handover. Based on the above observation, a Mobility Aware Proactive edge Service Migration framework (MAPSM) is proposed in this paper. MAPSM includes the key aspects: 1) predicting the next location of an end user based on ensemble learning method combining recurrent neural networks and geographical embedding Markov chain predictors;2) using the mobility prediction result to determine the target edge server of service migration, a proactive migration-handover coordinated method is proposed by performing container pre-migration, memory state migration and communication handover. The time planning scheme in the procedure is also designed. Experimental results demonstrate that MAPSM can greatly improve migration performance, effectively reduce end-to-end latency and significantly reduce service migration time. MAPSM outperforms other baseline service migration approaches.

关键词： Federated learning   mobile edge computing   differential privacy   Federated learning   mobile edge computing   differential privacy  

摘要： Mobile Edge Computing (MEC) has been successfully applied to smart homes, mobile devices, and other electronic products, offering reduced communication latency and alleviating pressure on cloud services. The integration of Federated Learning (FL) and MEC provides customized services for enhancing user experiences. However, there are still gaps in combining these technologies: FL is susceptible to membership inference attacks, risking user privacy;MEC faces limitations in energy and computational resources, restricting FL performance. In order to address these issues, we propose a novel approach, named DynamicNet, which incorporates Privacy Budget Regulation (PBR) and Dynamic Aggregation Weights (DAW). PBR addresses privacy leaks in edge devices by assessing local model privacy, dynamically adjusting privacy budget for subsequent use, ensuring desired level of privacy protection while minimizing noise impact on global model. DAW tackles MEC-related performance limitations by generating synthetic data, computing optimal weights for edge devices using this synthetic data, and aggregating parameters accordingly. Experimental results on two mainstream datasets demonstrate: 1) PBR preserves participant data privacy while enhancing global model convergence speed and accuracy;2) DAW adapts well to heterogeneous federated environments, ensuring high global model accuracy even when some edge device datasets are of inferior quality.

关键词： Aerial computing   Mobile edge computing   Unmanned aerial vehicle   High-altitude platform   Offloading decision   Resource allocation  

摘要： Aerial computing can facilitate the successful execution of tasks, ensuring low latency for Internet of things (IoT) devices. It gains greater significance and practicality by offering both edge and cloud computing services for IoT applications. However, in aerial computing, resources such as computing power, energy, and bandwidth are limited and constrained. Consequently, certain tasks must be offloaded to different platforms for sustained operation. Hence, the offloading decision (OD) and resource allocation (RA) are closely interconnected. Currently, numerous research efforts are underway to address efficient offloading and resource management. However, a comprehensive review of OD and RA in aerial computing platforms is yet to be explored. This study presents a thorough survey of OD and RA in aerial computing platforms, extensively reviewing and comparatively discussing various algorithms and approaches. The discussion delves deep into key design issues and also explores unresolved challenges, providing possible future directions. Our work can help researchers in studying and designing efficient methods for task offloading and resource management across different application scenarios.