关键词： Federated learning   Computational modeling   Privacy   Data models   Training   Differential privacy   Multi-access edge computing   mobile edge computing   consumer electronics   deep reinforcement learning   local differential privacy  

摘要： Consumer electronic devices often involve processing and analyzing a large amount of user personal data. Nevertheless, owing to apprehensions regarding privacy and security, users are hesitant to transmit this sensitive data to centralized cloud servers for training. The combination of mobile edge computing and federated learning (FL) enables local devices to access computational power and storage resources, allowing them to engage in distributed learning and model training while safeguarding user privacy. However, these resources are not unlimited. Furthermore, as artificial intelligence technology progresses, inference attacks have become a major threat to privacy in traditional federated learning. To address these challenges, we propose an innovative federated deep learning algorithm, called Fed-PEMC. This algorithm combines local differential privacy and model compression techniques. By leveraging deep reinforcement learning for model compression, Fed-PEMC reduces model size while maintaining model accuracy, improving communication efficiency. We also introduce customized label sampling to accelerate model training. Before uploading the model, we implement local differential privacy protection on the compressed model, reducing privacy budget and addressing privacy leakage caused by inference attacks. Theoretical analysis and experimental results validate that Fed-PEMC adheres to (epsilon, delta) -differential privacy and exhibits a communication cost linked to the model size. Experimental results show that compared to baseline algorithms, Fed-PEMC excels in ensuring privacy, maintaining model accuracy, and optimizing communication efficiency, and Fed-PEMC outperforms the baseline solution DP-Fed by 2.27 and 2.02 percentage points in testing accuracy on the Mnist and Cifar10 datasets, respectively.

关键词： mobile edge computing   computing offloading   serial and parallel priority   improved graphgravitational search algorithm   genetic algorithm  

摘要： Mobile edge computing (MEC) distributes computing and storage resources to the edge of the network closer to the user and significantly reduces user task completion latency and system energy consumption. This paper investigates the problem of computation offloading in a three-tier mobile edge computing network composed of multiple users, multiple edge servers, and a cloud server. In this network, each user's task can be divided into multiple subtasks with serial and parallel priority relationships existing among these subtasks. An optimization model is established with the objective of minimizing the total user delay and processor cost under constraints such as the available resources of users and servers and the interrelationships among the subtasks. An improved gravitational search algorithm (IGSA) is proposed to solve this optimization model. In contrast with the other gravitational search algorithm, the convergence factor is introduced in the calculation of the resultant force and the crossover operation in a genetic algorithm is performed when generating the new particles during each iteration. The simulation results show that the proposed IGSA greatly improves the system performance compared with the existing algorithms.

关键词： Consumer electronics   Performance evaluation   mobile edge computing   auction   task offloading  

摘要： This work presents a novel offloading approach to mobile edge computing (MEC). MEC aims to bring computation, storage, and network control closer to the edges of the network, such as base stations and access points, to support resource-limited mobile devices like smartphones and wearable devices. Conventional MEC solutions assume a priori knowledge on the number of processing cycles required by a computational task, which is often impractical. To address this challenge, we propose an online energy-efficient auction (OEA) algorithm for MEC systems consisting of multiple servers and mobile devices. The OEA algorithm takes into account computing tasks with both certain and uncertain processing cycle numbers, and considers both energy consumption and energy harvesting. OEA adopts a combinatorial optimization framework, translated into a series of one-shot procurement auctions optimized using the Vickrey-Clarke-Groves mechanism. The performance of the OEA algorithm is validated through theoretical analysis and simulation studies, demonstrating that it outperforms benchmark strategies.

关键词： Heterogeneous task replication   mobile edge computing   convex relaxation   interior point method   distributed ADMM-based framework  

摘要： Mobile edge computing (MEC) is expected to support real-time services at wireless networks, where task replication is applied to guarantee job completion within a strict deadline through replicating multiple copies to different edge servers. Most of previous works focused on guaranteeing the reliability of individual task in MEC-based networks with the assumption of homogeneous task execution distribution. Further, these algorithms cannot suit dynamic network scales, due to overhigh communication or retraining overhead. Therefore, this article formulates the problem of heterogeneous task replication in a finer level by modeling outage probability of individual replication, where the decisions of all tasks are jointly optimized within the constraints of both mobile users and MEC servers for minimizing job outage probability. To adapt to varying network scales, we develop centralized and distributed algorithms, respectively. The centralized algorithm is developed based on Interior Point Method, which obtains the optimal solution of relaxed model and then approximates to the solution of original problem. Further, the distributed algorithm decomposes the HTR into multiple subproblems and parallelly compute each local solution based on Distributed ADMM. Finally, we build a simulation model and conduct comprehensive results, which demonstrates that the proposed algorithms can achieve high-accuracy solution with fast convergence.

关键词： Mobile edge computing   Task scheduling   Energy harvesting   Renewable energy   Energy storage unit   Sample average approximation  

摘要： Aiming to provide low-cost MEC services for mobile devices in areas without/lacking infrastructure, we propose a renewable-energy-driven energy-harvesting-based task scheduling and energy management framework. First, for mobile devices, the constructed energy consumption minimization problem is solved by an alternating-optimization-based algorithm. Then, we design an energy management algorithm based on sampling average approximation to derive the optimal charging/discharging strategies, number of energy storage units, and renewable energy utilization. The simulation results show that the proposed framework can significantly reduce the cost of MEC servers and prolong the working hours of mobile devices. (c) 2023 The Author(s). Published by Elsevier B.V. on behalf of The Korean Institute of Communications and Information Sciences. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).

关键词： Mobile edge computing   unmanned aerial vehicle   resource allocation   task offloading   federated reinforcement learning   digital twin  

摘要： Federated learning (FL) is proposed as a different approach for distributed learning on the edges while maintaining privacy. Existing FL methods, are mainly focused on learning deep classifying and clustering models, with little consideration offered to the federated reinforcement learning (FRL) task on the edge, a difficult task in which several trained agents track local state and take local actions to train a global learning model without disclosing their local dataset. Several neural network models based on FRL have been presented recently to determine the best method for computation offloading (CO) and resource allocation (RA), particularly in Unmanned Aerial Vehicle (UAV) assisted Mobile Edge Computing (MEC). However, because of the complexity and variety of computational tasks involved in 6G and beyond networks, the FRL algorithms are challenging to apply directly to complicated UAV-assisted MEC scenarios. In this study, we present a generalized FRL approach based on a meta learning technique that incorporates RL models explained by numerous smart devices into a generic model. This research uses a normalized characteristic matrix to divide a complex network into small-scale units and provides a normalized network model for complex network situations based on the FRL meta critic method to determine the CO and RA strategy in a Digital Twin (DT)-enabled UAV-assisted MEC system. Numerical results show that the proposed scheme achieves higher and more reliable overall rewards. Proposed method achieves a 73.15% reduction in reward variance and a 14.23% increase in average rewards over 570 continuous operations.

关键词： Mobile edge computing   Edge intelligence   Service placement   Deep deterministic policy gradient  

摘要： Mobile edge computing is an energy-efficient paradigm which has great support for resource-limited user devices performing compute-intensive programs and applications. However, limited edge resources, mobility of user equipment, growth of service requirements, and dynamic nature of service types make it a challenging task to configure computing and storage resources for executing various services on edge servers. Therefore, an adaptive joint service placement framework in the edge system with various devices of user and mobile edge servers is proposed in this paper. The proposed framework takes into account the mobility of user devices, the dynamic changes in various types of services, the cost of service placement and service usage, and optimizes the service placement scheme from the perspective of different target groups. Simultaneously, we design a deep deterministic policy gradient based service placement tuning approach in which centralized critic networks and actor networks are jointly used to improve the service placement performance. The relative evaluation results validate the effectiveness of the proposed framework and approach in improving the performance of the edge system.

关键词： Mobile edge computing   computation offloading   blockchain   deep reinforcement learning  

摘要： With the widespread popularity of the Internet of Things and various intelligent medical devices, the amount of medical data is rising sharply, and thus medical data processing has become increasingly challenging. Mobile edge computing technology allows computing power to be allocated at the edge closer to users, which enables efficient data offloading for healthcare systems. However, existing studies on medical data offloading seldom guarantee effective data privacy and security. Moreover, the research equipping data offloading architectures with Blockchain neglect the delay and energy consumption costs incurred in using Blockchain technology for medical data offloading. Therefore, in this paper, we propose a data offloading scheme for healthcare based on Blockchain technology, which achieves optimal medical resource allocation and simultaneously minimizes the cost of offloading tasks. Specifically, we design a smart contract to ensure secure data offloading. And, we formulate the cost problem as a Markov Decision Process, solved by a policy search-based deep reinforcement learning (Asynchronous Advantage Actor-Critic) scheme, where we jointly consider offloading decisions, allocation of computing resources and radio transmission bandwidth, and Blockchain data security audits. The security of our smart-contract-based mechanism is theoretically and empirically proved, while extensive experimental results also show that our solution can obtain superior performance gains with lower cost than other baselines.

关键词： vehicle-to-everything   mobile edge computing   offloading   transmit power   deep reinforcement learning  

摘要： Offloading computation-intensive tasks to mobile edge computing (MEC) servers, such as road-side units (RSUs) and a base station (BS), can enhance the computation capacities of the vehicle-to-everything (V2X) communication system. In this work, we study an MEC-assisted multi-vehicle V2X communication system in which multi-antenna RSUs with liner receivers and a multi-antenna BS with a zero-forcing (ZF) receiver work as MEC servers jointly to offload the tasks of the vehicles. To control the energy consumption and ensure the delay requirement of the V2X communication system, an energy consumption minimization problem under a delay constraint is formulated. The multi-agent deep reinforcement learning (MADRL) algorithm is proposed to solve the non-convex energy optimization problem, which can train vehicles to select the beneficial server association, transmit power and offloading ratio intelligently according to the reward function related to the delay and energy consumption. The improved K-nearest neighbors (KNN) algorithm is proposed to assign vehicles to the specific RSU, which can reduce the action space dimensions and the complexity of the MADRL algorithm. Numerical simulation results show that the proposed scheme can decrease energy consumption while satisfying the delay constraint. When the RSUs adopt the indirect transmission mode and are equipped with matched-filter (MF) receivers, the proposed joint optimization scheme can decrease the energy consumption by 56.90% and 65.52% compared to the maximum transmit power and full offloading schemes, respectively. When the RSUs are equipped with ZF receivers, the proposed scheme can decrease the energy consumption by 36.8% compared to the MF receivers.

关键词： Mobile edge computing   Unmanned aerial vehicles   UAV-enabled MEC   Energy efficient   Resource allocation   Trajectory control   Latency   Privacy  

摘要： The huge prospects of the internet of things (IoT) have led to an ever-growing demand for computing power by IoT users to enable various applications. Multi-access edge computing (MEC) research and development has rapidly gained attention during the last decade. The ability to deploy edge servers at different points across a content delivery network that can offer communication and computing services close to mobile user devices is one of the main factors driving the evolution of MEC. Furthermore, MEC has been considered a potentially transformational approach for fifth -generation (5 G) and beyond 5 G (B5G) networks, as well as a potential improvement to conventional cloud computing. Unmanned aerial vehicles (UAVs) can be used as effective aerial platforms to offer reliable and ubiquitous connections in wireless communication networks due to their distinctive qualities, such as high cruising altitude, on -demand deployment, and three-dimensional (3D) maneuverability. The number of research studies published in this area has dramatically increased due to the growing interest in UAV-enabled MEC. Although UAV-enabled MEC systems have been well studied, the existing models are becoming increasingly heterogeneous and scattered without harmony. This paper provides a comprehensive analysis of the literature on UAV-enabled MEC systems with a special focus on the system modeling, and optimization techniques for five identified domains, such as energy efficiency, resource allocation, trajectory control, latency, and security. For each domain, we have highlighted the recent advances, critical findings, and the advantages and disadvantages. Additionally, the identified proposed techniques were analyzed and discussed, with emphasize on the constraints and performance metrics. We also discuss a general system model for each highlighted domain. Moreover, the lessons are also derived from the study on system optimization and system modeling techniques identified in this paper. The