关键词： Mobile edge computing  

摘要： The body health plays an important metric in people's everyday life, and it directly determines whether people have the ability to preferably contribute to the society. In fact, the physical training is a universal sport to enhance the body health. Therefore, the evaluation and analysis of physical training become particularly significant. With the rapid development and emerging of new techniques and networking paradigms, the traditional offline physical training evaluation and analysis cannot be performed well. Instead, this paper uses Mobile Edge Computing (MEC) and Software-Defined Networking (SDN) to implement the evaluation and analysis of physical training, shortened for MSPT, where MEC is the new computing technique and SDN is the new networking paradigm. The proposed MSPT includes two parts. At first, the physical training data from different mobile devices are migrated into the edge server for computing according to the current condition, in which the game theory is used to complete the task scheduling. Then, SDN is responsible for the global scheduling in the centralized control manner, in which the multigranularity scheduling strategy is used to handle the traffic between the SDN controller and edge computing server. The experiments are driven by OMNet, including three aspects of evaluation, i.e., task offloading of MEC, traffic scheduling of SDN, and performance analysis of physical training, and the results show that the proposed MSPT has better performance than the corresponding baselines.

关键词： Mobile edge computing   Task offloading   Energy and deadline-aware   Deep reinforcement learning (DRL)   Actor-critic framework   K-nearest neighbor (K-NN)  

摘要： With the development of the wireless network, increasing mobile applications are emerging and receiving great popularity. These applications cover a wide area, such as traffic monitoring, smart homes, real-time vision processing, objective tracking, and so on, and typically require computation-intensive resources to achieve a high quality of experience. Although the performance of mobile devices (MDs) has been continuously enhanced, running all the applications on a single MD still causes high energy consumption and latency. Fortunately, mobile edge computing (MEC) allows MDs to offload their computation-intensive tasks to proximal eNodeBs (eNBs) to augment computational capabilities. However, the current task offloading schemes mainly concentrate on average-based performance metrics, failing to meet the deadline constraint of the tasks. Based on the deep reinforcement learning (DRL) approach, this paper proposes an Energy-aware Task Offloading with Deadline constraint (DRL-E2D) algorithm for a multi-eNB MEC environment, which is to maximize the reward under the deadline constraint of the tasks. In terms of the actor-critic framework, we integrate the action representation into DRL-E2D to handle the large discrete action space problem, i.e., using the low-complexity k-nearest neighbor as an approximate approach to extract optimal discrete actions from the continuous action space. The extensive experimental results show that DRL-E2D achieves better performance than the comparison algorithms on all parameter settings, indicating that DRL-E2D is robust to the state changes in the MEC environment.

关键词： Offloading   Mobile edge computing   Machine learning   Neural networks   Hidden markov model   Regression  

摘要： The fast growth of under developing internet-based technologies has been leading to propose promising methods to handle the heterogeneous massive volume of data produced by pervasive smart equipments such as handy mobile devices. Thanks to the mentioned technologies, these mobile devices can run critical business/entertainment applications such as Augmented Reality, Virtual Reality, vehicular networks, and media streaming. However, due to such devices' inherent limitations, some emerging computation environments such as Mobile Edge Computing have been introduced to achieve some essential requirements such as low latency, low energy consumption, and low cost. In the literature, offloading is a technique to transfer the burden of the mobile devices' work incurred by running applications' requests to these computation environments. On the other hand, exploring the computation environment to find the most efficient place to execute such requests is challenging work to achieve. In addition, different researches have been proposed to cope with the management problems of the offloading criterion. In this paper, an autonomous computation offloading framework is proposed to address some challenges related to time-intensive and resource-intensive applications. However, to the best of the authors' knowledge, the proposed autonomous framework has not been explored as a control model for self management in the computation offloading criterion. Besides, to cope with the large dimension of the offloading decision-making problem, different simulations including Deep Neural Networks, multiple linear regression, hybrid model, and Hidden Markov Model as the planning module of the mentioned autonomous methodology have been conducted. Simulation results show that the proposed hybrid model can appropriately fit the problem with near-optimal accuracy regarding the offloading decision-making, the latency, and the energy consumption predictions in the proposed self-management framework.

关键词： Mobile edge computing  

摘要： In recent years, mobile clients’ computing ability and storage capacity have greatly improved, efficiently dealing with some applications locally. Federated learning is a promising distributed machine learning solution that uses local computing and local data to train the Artificial Intelligence (AI) model. Combining local computing and federated learning can train a powerful AI model under the premise of ensuring local data privacy while making full use of mobile clients’ resources. However, the heterogeneity of local data, that is, Non-independent and identical distribution (Non-IID) and imbalance of local data size, may bring a bottleneck hindering the application of federated learning in mobile edge computing (MEC) system. Inspired by this, we propose a cluster-based clients selection method that can generate a federated virtual dataset that satisfies the global distribution to offset the impact of data heterogeneity and proved that the proposed scheme could converge to an approximate optimal solution. Based on the clustering method, we propose an auction-based clients selection scheme within each cluster that fully considers the system’s energy heterogeneity and gives the Nash equilibrium solution of the proposed scheme for balance the energy consumption and improving the convergence rate. The simulation results show that our proposed selection methods and auction-based federated learning can achieve better performance with the Convolutional Neural Network model (CNN) under different data distributions. Copyright © 2021, The Authors. All rights reserved.

关键词： Computation offloading   Mobile edge computing   Context‐   aware  

摘要： Along with the rise of mobile devices, the resource demands of respective applications grow. However, mobile devices have limited computation and storage resources. Computation offloading is a prominent solution to overcome the limitations. However, current approaches fail to address the complexity caused by quickly and constantly changing context conditions in mobile edge computing. In this paper, the contexts are gathered and processed using Monitor-Analysis-Plan-Execution (MAPE) loop for making offloading decisions. The results show that the proposed context-aware approach outperforms local computing and offloading without considering context approaches in terms of delay, energy consumption, network usage, and execution cost.

关键词： Mobile edge computing   Vehicular networks   Task offloading   Performance optimization  

摘要： Taking the mobile edge computing paradigm as an effective supplement to the vehicular networks can enable vehicles to obtain network resources and computing capability nearby, and meet the current large-scale increase in vehicular service requirements. However, the congestion of wireless networks and insufficient computing resources of edge servers caused by the strong mobility of vehicles and the offloading of a large number of tasks make it difficult to provide users with good quality of service. In existing work, the influence of network access point selection on task execution latency was often not considered. In this paper, a pre-allocation algorithm for vehicle tasks is proposed to solve the problem of service interruption caused by vehicle movement and the limited edge coverage. Then, a system model is utilized to comprehensively consider the vehicle movement characteristics, access point resource utilization, and edge server workloads, so as to characterize the overall latency of vehicle task offloading execution. Furthermore, an adaptive task offloading strategy for automatic and efficient network selection, task offloading decisions in vehicular edge computing is implemented. Experimental results show that the proposed method significantly improves the overall task execution performance and reduces the time overhead of task offloading.

关键词： Mobile edge computing  

摘要： In this paper, we study a mobile edge computing (MEC) system in which the mobile device is assisted by a base station (BS) and a cooperative node. The mobile device has sequential tasks to complete, whereas the cooperative node assists the mobile device on both task offloading and task computation. In specific, two cases are investigated, which are 1) the cooperative node has no tasks to complete itself, and 2) the cooperative node has tasks to complete itself. Our target is to minimize the total energy consumption of the mobile device and the cooperative node through optimizing the transmit duration in task offloading, CPU frequency in task computing along with the task index to offload in the sequential tasks. In the first case, we decompose the mixed-integer non-convex problem into two levels. In the lower level problem, thanks to the convexity, Karush-Kuhn-Tucker (KKT) conditions are utilized to simplify the problem, which is then solved with bisection search. In the upper level problem, to find solution of the task index to offload, rather than utilizing traversal method, we develop a monotonic condition to simplify the searching process. In the second case, in order to guarantee the successful computation of the mobile device and cooperative node, the uploading transmission is classified into three schemes. Within each scheme, the non-convex problem is decomposed. In the lower level problem, semi-closed solution is found by Lagrangian dual method. In the upper level problem, traversal method is applied to find the optimal offloading index. Copyright © 2021, The Authors. All rights reserved.

关键词： Mobile edge computing   SDN   Edge caching   Service migration   Deep Q learning  

摘要： In recent years, with the rapid growth in the demand for online streaming services, video streaming platforms are becoming more and more popular, and users' demand for low latency and high-quality services is increasing. Therefore, in order to be able to allocate caching resources reasonably to serve as many user requests as possible, and reduce latency and energy consumption, the edge cooperative caching method based on delay and energy consumption balance in SDN based mobile edge computing is proposed. In the proposed caching method, firstly, the multilayer perceptron neural network is used to predict the video content requested by the mobile user. Secondly, an objective function to minimize delay and energy consumption is established, and an edge cache optimization model is constructed. Finally, the branch-and-bound algorithm is used to obtain the optimal edge cache strategy. Meanwhile, to provide users with seamless service migration to ensure service continuity and high-quality services, the dynamic service migration method based on deep Q learning is proposed. In the proposed service migration method, firstly, the service migration problem is expressed as a Markov decision process. Secondly, the service migration process is analyzed and a service migration reward function is constructed. Finally, deep Q learning is used to obtain the optimal service migration strategy. In the experiment, the proposed edge caching algorithm can effectively improve the cache hit rate, reduce the backhaul traffic load, and control the average access delay and energy cost. Moreover, the proposed service migration algorithm can effectively reduce the number of service migrations and transmission cost, improve the success rate of service migration, and reduce the average traffic consumed by migration.

关键词： Blockchain   Servers   Computational modeling   Games   Stochastic processes   Mobile computing   Edge computing   Blockchain   deep learning   game theory   incomplete information   Markov decision process   mining   mobile edge computing   partially-observable Markov decision process   reinforcement learning   resource management  

摘要： We consider a public blockchain realized in the mobile edge computing (MEC) network, where the blockchain miners compete against each other to solve the proof-of-work puzzle and win a mining reward. Due to limited computing capabilities of their mobile terminals, miners offload computations to the MEC servers. The MEC servers are maintained by the service provider (SP) that sells its computing resources to the miners. The SP aims at maximizing its long-term profit subject to miners' budget constraints. The miners decide on their hash rates, i.e., computing powers, simultaneously and independently, to maximize their payoffs without revealing their decisions to other miners. As such, the interactions between the SP and miners are modeled as a stochastic Stackelberg game under private information, where the SP assigns the price per unit hash rate, and miners select their actions, i.e., hash rate decisions, without observing actions of other miners. We develop a hierarchical learning framework for this game based on fully- and partially-observable Markov decision models of the decision processes of the SP and miners. We show that the proposed learning algorithms converge to stable states in which miners' actions are the best responses to the optimal price assigned by the SP.

关键词： Big Data   Privacy   Recommender systems   Social networking (online)   Context modeling   Prediction algorithms   Differential privacy   Recommender system   differential privacy   online learning   federated Learning   big data   distributed and scalable model   cloud computing   mobile edge computing  

摘要： Nowadays, the booming demand of big data analytics and the constraints of computational ability and network bandwidth have made it difficult for a stand-alone agent/service provider to provide suitable information for every user from the large volume online data within the limited time. To handle this challenge, a recommender system (RS) can call in a group of agents to collaborate to learn users' preference and taste, which is known as a distributed recommender system (DRS). DRSs can improve the accuracy of a traditional RS by requesting agents to share information with each other. However, it is challenging for DRSs to make personalized recommendations for each user due to the large amount of candidates. In addition, information sharing among agents raises a privacy concern. Thus, we propose a privacy-preserving DRS in this paper, and then model each service provider as a distributed online learner with context-awareness. Service providers collaborate to make personalized recommendations by learning users' preferences according to the user context and users' history behaviors. We adopt the federated learning framework to help train a high quality privacy- preserving centralized model over a large number of distributed agents which is probably unreliable with relatively slow network connections. To handle big data scenario, we build an item-cluster tree to deal with online and increasing datasets from top to the bottom. We further consider the structure of social network and present an efficient algorithm to avoid more performance loss adaptively. Theoretical proofs show that our proposed algorithm can achieve sublinear regret and differential privacy protection simultaneously for service providers and users. Numerical results confirm that our novel framework can handle increasing big datasets and strike a trade-off between privacy-preserving level and the prediction accuracy.