关键词： Mobile edge computing   server placement   heuristic algorithm   performance optimization  

摘要： The rapid development of the Internet of Things and 5G networks have generated a large amount of data. By offloading computing tasks from mobile devices to edge servers with sufficient computing resources, network congestion and data transmission delays can be effectively reduced. The placement of edge server is the core of task offloading and is a multi-objective optimization problem with multiple resource constraints. Efficient placement approach can effectively meet the needs of mobile users to access services with low latency and high bandwidth. To this end, an optimization model of edge server placement has been established in this paper through minimizing both communication delay and load difference as the optimization goal. Then, an Edge Server placement based on meta-Heuristic alGorithM (ESH-GM) has been proposed to achieve multi-objective optimization. Firstly, the K-means algorithm is combined with the ant colony algorithm, and the pheromone feedback mechanism is introduced into the placement of edge servers by emulating the mechanism of ant colony sharing pheromone in the foraging process, and the ant colony algorithm is improved by setting the taboo table to improve the convergence speed of the algorithm. Then, the improved heuristic algorithm is used to solve the optimal placement of edge servers. Experimental results using Shanghai Telecom's real datasets show that the proposed ESH-GM achieves an optimal balance between low latency and load balancing, while guaranteeing quality of service, which outperforms several existing representative approaches.

关键词： Computational modeling   Training   Data models   Servers   Adaptation models   Data privacy   Collaborative work   Client selection   federated learning   mobile edge computing   reinforcement learning  

摘要： With data increasingly collected by end devices and the number of devices is growing rapidly in which data source mainly located outside the cloud today. To guarantee data privacy and remain data on client devices, federated learning (FL) has been proposed. In FL, end devices train a local model with their data and send the model parameters rather than raw data to server for aggregating a new global model. However, due to the limited wireless bandwidth and energy of mobile devices, it is not practical for FL to perform model updating and aggregation on all participating devices in parallel. And it is difficulty for FL server to select apposite clients to take part in model training which is important to save energy and reduce latency. In this paper, we establish a novel mobile edge computing (MEC) system for FL and propose an experience-driven control algorithm that adaptively chooses client devices to participate in each round of FL. Adaptive client selection mechanism in MEC can be modeled as a Markov Decision Process in which we do not need any prior knowledge of the environment. We then propose a client selection scheme based on reinforcement learning that learns to select a subset of devices in each communication round to minimize energy consumption and training delay that encourages the increase number of client devices to participate in model updating. The experimental results show that the unit of energy required in FL can be reduced by up to 50% and training delay required can be reduced by up to 20.70% compared to the other static algorithms. Finally, we demonstrate the scalability of MEC system with different tasks and the influence of different non independent and identically distributed (non-IID) settings.

关键词： Performance evaluation   Network topology   Image edge detection   Urban areas   Cognition   Graph neural networks   Topology   Hotspot analysis   mobile edge computing   human-centric IoT   graph attention networks  

摘要： Mobile edge computing works well with the rapid growth of human-centric IoT applications by providing timely and in-situ data caching and processing. Edge oriented urban hotspot prediction is to predict the high traffic regions in case to provide basis for further deployment and replenishment of edge servers. Most of the existing hotspot analysis work is not well suited for human-centric IoT application scenarios especially for large-scale urban city areas. Instead, in this paper we propose edge-oriented hotspot prediction scheme based on information Interactive Graph Attention Networks (I-GAN) for urban city within the human-centric IoT and MEC application scenarios. I-GAN makes reasoning on the user service needs by learning the interactive relations of multifaceted human-centric factors: including online human behavior and offline crowd flow through graph attention networks. On the other hand, I-GAN makes representation of urban-scale edge service capability by graph embeddings through inductive learning with distributed multi-layer graph convolutions. Based on it, I-GAN makes matching between them and then predicts the edge-oriented hotspots with time variance. The performance evaluations are based on realistic dataset of a southern city of China provided by China Unicom. I-GAN is compared with the other related hotspot analysis schemes. The results show that I-GAN is with much better prediction accuracy with multiple time dimensions.

关键词： compute first networking   CFN   mobile edge computing   cloud computing   5G  

摘要： Edge computing has become an important innovative business model in the 5G era, especially its low latency feature, which is considered to be not available in traditional solutions. Therefore, edge computing can provide more service capabilities and has a wider range of application scenarios. However, the collaboration of computing power between edge computing and cloud computing in the central position has become a new technical problem. That is, it is necessary to achieve cloud-to-network collaboration, cloud-to-edge collaboration, or even edge-to-edge collaboration among edge computing, cloud computing, and network to achieve the optimisation of resource utilisation. On the basis of studying the compute distribution and scheduling requirements of edge computing, this paper introduces a compute network scheme based on the deep fusion of cloud, edge and network, called compute first networking (CFN). Firstly, we introduce the basic concept and related work of CFN. Then, we mainly discuss the framework and key technology of CFN. After that, we present some applications with respect to CFN. Finally, we discuss the challenges and opportunities in the area of compute first networking.

关键词： mobile edge computing   user cooperation   wireless power transfer   energy consumption   resource management  

摘要： Mobile edge computing(MEC) meets the high-bandwidth and ultra-low-latency requirements of mobile networks and improves communication reliability by reducing the networks’ load. In this study, we study a wireless powered MEC system, which includes an access point(AP) and two mobile devices. The endurance of mobile devices can be effectively enhanced using the wireless power transfer technology and user cooperation. However, during user cooperation, a closer user assists a farther user with forwarding tasks by sharing the same bandwidth, which causes interference. To overcome the interference issue, the closer user can instead assist other users in forwarding tasks by using a different bandwidth. We aim to minimize the power of the AP by joint power and bandwidth optimization while satisfying the delay and users’ computational tasks. Simulation results show that the proposed user collaboration method can overcome user interference,reduce energy consumption, and improve user performance compared with the baseline policies.

关键词： Mobile edge computing   multi-task multi-server   non-orthogonal multiple access   processing capability   resource allocation   task offloading  

摘要： By offloading computationally intensive tasks of smart end devices to edge servers deployed at the edge of the network, mobile edge computing (MEC) has become a promising technology to provide computing services for Internet of Things (IoT) devices. In order to further improve the access capability of MEC and increase the spectrum utilization efficiency, in this article, Non-Orthogonal Multiple Access (NOMA) technology is introduced into MEC systems and we study the computing offloading problem of multi-user, multi-task and multi-server through joint optimization of task offloading and resource allocation, we intend to maximize the system's processing capability as an optimization goal. To solve the proposed mixed integer nonlinear programming (MINLP) problem, the objective optimization problem is firstly decoupled into two sub-problems of resource allocation and task allocation. Secondly the resource allocation problem is further decomposed into computation resource optimization and communication resource allocation. For the communication resource allocation, it first fixed power allocation, then the sub-channel allocation problem is regarded as a many-to-one matching problem between sub-channels and users. In addition, we propose a low-complexity sub-optimal matching algorithm for sub-channel allocation to maximize the offloading efficiency. Based on our proposed sub-channel allocation scheme, the transmission power allocation is regarded as a convex optimization problem, which is tackled by Lagrangian multiplier method. Finally, under the condition of resource allocation, the tasks of all end devices (EDs) are allocated. Experimental numerical results show that the proposed scheme can effectively decrease latency and energy consumption of networks, improve system processing capability, and further improve MEC system performance.

关键词： Mobile edge computing   Deep learning   Auction   Delay and energy sensitive tasks  

摘要： Mobile edge computing has emerged as a promising paradigm to complement the computing and energy resources of mobile devices. In this computing paradigm, mobile devices offload their computing tasks to nearby edge servers, which can potentially reduce their energy consumption and task completion delay. In exchange for processing the computing tasks, edge servers expect to receive a payment that covers their operating costs and allows them to make a profit. Unfortunately, existing works either ignore the payments to the edge servers, or ignore the task processing delay and energy consumption of the mobile devices. To bridge this gap, we propose an auction to allocate edge servers to mobile devices that is executed by a pair of deep neural networks. Our proposed auction maximizes the profit of the edge servers, and satisfies the task processing delay and energy consumption constraints of the mobile devices. The proposed deep neural networks also guarantee that the mobile devices are unable to unfairly affect the results of the auctions. Our extensive simulations show that our proposed auction mechanism increases the profit of the edge servers by at least 50% compared to randomized auctions, and satisfies the task processing delay and energy consumption constraints of mobile devices.

关键词： quality of service   mobile computing   greedy algorithms   genetic algorithms   resource allocation   cloud computing   metropolitan area networks   QoS-aware edge server placement method   wireless metropolitan area networks   mobile edge computing   load balancing problem   edge servers   greedy algorithm  

摘要： Mobile edge computing (MEC) is concerned with moving complex tasks from data sources to nearby computing resources, which can reduce computing latency and remote cloud workload. Although there has been significant research in the field of MEC, research on edge server placement in wireless metropolitan area networks (WMANs) is overlooked, and the load balancing problem of edge servers is seldom discussed. From a practical perspective, how to place edge servers efficiently in WMANs while considering load balancing between edge servers is studied. A greedy algorithm is proposed that can balance the workload of edge servers more effectively. However, the performance of the greedy algorithm as the number of servers placed increases is not ideal. Therefore, the authors combine the greedy algorithm with a genetic algorithm (GA) to minimise the number of edge servers while ensuring load balancing between edge servers and quality of service (QoS) requirements for mobile users. Finally, they conduct simulation experiments and compare the proposed algorithms with other algorithms. The improved GA proposed is superior to the greedy algorithm in terms of load balancing and the number of servers. The experimental results demonstrate that the algorithm has excellent performance.

关键词： Mobile edge computing  

摘要： In mobile edge computing (MEC), one of the important challenges is how much resources of which mobile edge server (MES) should be allocated to which user equipment (UE). The existing resource allocation schemes only consider CPU as the requested resource and assume utility for MESs as either a random variable or dependent on the requested CPU only. This paper presents a novel comprehensive utility function for resource allocation in MEC. The utility function considers the heterogeneous nature of applications that a UE offloads to MES. The proposed utility function considers all important parameters, including CPU, RAM, hard disk space, required time, and distance, to calculate a more realistic utility value for MESs. Moreover, we improve upon some general algorithms, used for resource allocation in MEC and cloud computing, by considering our proposed utility function. We name the improved versions of these resource allocation schemes as comprehensive resource allocation schemes. The UE requests are modeled to represent the amount of resources requested by the UE as well as the time for which the UE has requested these resources. The utility function depends upon the UE requests and the distance between UEs and MES, and serves as a realistic means of comparison between different types of UE requests. Choosing (or selecting) an optimal MES with the optimal amount of resources to be allocated to each UE request is a challenging task. We show that MES resource allocation is sub-optimal if CPU is the only resource considered. By taking into account the other resources, i.e., RAM, disk space, request time, and distance in the utility function, we demonstrate improvement in the resource allocation algorithms in terms of service rate, utility, and MES energy *** Codes 46Fxx © 2020, CC BY.

关键词： Mobile edge computing  

摘要： Mobile-edge computing (MEC) offloads computational tasks from wireless devices to network edge, and enables real-time information transmission and computing. Most existing work concerns a small-scale synchronous MEC system. In this paper, we focus on a large-scale asynchronous MEC system with random task arrivals, distinct workloads, and diverse deadlines. We formulate the offloading policy design as a restless multi-armed bandit (RMAB) to maximize the total discounted reward over the time horizon. However, the formulated RMAB is related to a PSPACE-hard sequential decision-making problem, which is intractable. To address this issue, by exploiting the Whittle index (WI) theory, we rigorously establish the WI indexability and derive a scalable closed-form solution. Consequently, in our WI policy, each user only needs to calculate its WI and report it to the BS, and the users with the highest indices are selected for task offloading. Furthermore, when the task completion ratio becomes the focus, the shorter slack time less remaining workload (STLW) priority rule is introduced into the WI policy for performance improvement. When the knowledge of user offloading energy consumption is not available prior to the offloading, we develop Bayesian learning-enabled WI policies, including maximum likelihood estimation, Bayesian learning with conjugate prior, and prior-swapping techniques. Simulation results show that the proposed policies significantly outperform the other existing policies. © 2020, CC BY-NC-ND.