关键词： Resource management   Collaboration   Task analysis   Servers   Mobile handsets   Wireless communication   Delays   Mobile edge computing   computing offloading   resource allocation   power and subcarrier allocation   deep Q-network  

摘要： Mobile edge computing (MEC) is an emergent architecture, which brings computation and storage resources to the edge of mobile network and provides rich services and applications near the end users. The joint problem of task offloading and resource allocation in the multi-user collaborative mobile edge computing network (C-MEC) based on Orthogonal Frequency-Division Multiple Access (OFDMA) is a challenging issue. In this paper, we investigate the offloading decision, collaboration decision, computing resource allocation and communication resource allocation problem in C-MEC. The delay-sensitive tasks of users can be computed locally, offloaded to collaborative devices or MEC servers. The goal is to minimize the total energy consumption of all mobile users under the delay constraint. The problem is formulated as a mixed-integer nonlinear programming (MINLP), which involves the joint optimization of task offloading decision, collaboration decision, subcarrier and power allocation, and computing resource allocation. A two-level alternation method framework is proposed to solve the formulated MINLP problem. In the upper level, a heuristic algorithm is used to handle the collaboration decision and offloading decisions under the initial setting;and in the lower level, the allocation of power, subcarrier, and computing resources is updated through deep reinforcement learning based on the current offloading decision. Simulation results show that the proposed algorithm achieves excellent performance in energy efficient and task completion rate (CR) for different network parameter settings.

关键词： Mobile edge computing   Vertical offloading   Horizontal offloading  

摘要： Mobile Edge Computing architecture is one of the most promising architectures that can satisfy different quality of Services required by various applications. In this paper, we model mobile edge computing architecture with queue-length thresholds at user equipments and edges to determine whether the task is offloaded or not in federated cloud and edge computing systems. We propose two models as vertical default & vertical (VDV) model and vertical default & horizontal shortest (VDHS) model. The former only does vertical offloading, meaning that the edge can offload tasks to the cloud, while the latter does vertical offloading and horizontal offloading, meaning that the edge can offload tasks to other edges. However, it is very difficult to directly derive the performance metrics in our models, so we approximate them. Based on these approximations, we determine the optimal queue-length thresholds of UEs and edges. Experiment results show that analytical and simulation results match very well. Also VDHS can reduce the mean task sojourn time by 30% at most and increase delay satisfaction ratio by 11% at most compared with VDV.

关键词： Servers   Codes   Privacy   Data privacy   Cryptography   Computational modeling   Spatial diversity   Coded computing   joint beamforming   mobile edge computing   privacy   spatial diversity  

摘要： We consider a mobile edge computing scenario where a number of devices want to perform a linear inference Wx on some local data x given a network-side matrix W. The computation is performed at the network edge over a number of edge servers. We propose a coding scheme that provides information-theoretic privacy against z colluding (honest-but-curious) edge servers, while minimizing the overall latency-comprising upload, computation, download, and decoding latency-in the presence of straggling servers. The proposed scheme exploits Shamir's secret sharing to yield data privacy and straggler mitigation, combined with replication to provide spatial diversity for the download. We also propose two variants of the scheme that further reduce latency. For a considered scenario with 9 edge servers, the proposed scheme reduces the latency by 8% compared to the nonprivate scheme recently introduced by Zhang and Simeone, while providing privacy against an honest-but-curious edge server.

关键词： Training   Servers   Computational modeling   Data models   Transfer learning   Multi-access edge computing   Training data   Client selection   federated transfer learning   intrusion detection   mobile edge computing   reinforcement learning  

摘要： In this letter, we propose an efficient federated transfer learning (FTL) framework with client selection for intrusion detection (ID) in mobile edge computing (MEC). Specifically, we leverage federated learning (FL) to preserve privacy by training model locally, and utilize transfer learning (TL) to improve training efficiency by knowledge transfer. For FL, unreliable and low-quality clients should not be selected to participate in the training. Therefore, we integrate FTL with a reinforcement learning (RL)-based client selection scheme to achieve the highest ID accuracy within a budget limit on the number of participating clients. Experimental results show that the FTL significantly improves ID accuracy and communication efficiency as compared with the FL. Furthermore, the FTL framework with RL-based client selection can achieve the highest accuracy within budget, which improves performance while saving cost.

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

摘要： Mobile edge computing (MEC) is a promising solution to enable resource-limited mobile devices to offload computation-intensive tasks to nearby edge servers. In this paper, dynamic computation offloading in a non-orthogonal multiple access (NOMA) based multi-user network is investigated by considering stochastic task arrivals and wireless channels. Specifically, a cooperative multi-agent deep reinforcement learning (CMADRL) based framework is proposed to learn decentralized offloading policies to allocate task offloading and local execution powers at each user, which minimizes long-term average network computation cost in terms of power consumption and buffering delay. By leveraging a centralized training and distributed execution strategy, the proposed framework can not only learn efficient decentralized policies, but also relieves users' computational pressure and works well in coordinating the interference of NOMA-based networks. To reduce the training complexity, it is further improved to train one parameter shared policy network that can be exploited by all users with slightly sacrificed performance. Numerical simulations demonstrate that the proposed CMADRL based framework can learn efficient dynamic offloading policies at each user, which significantly outperforms the conventional independent Q-learning based framework as well as some greedy strategies with lower network computation cost.

关键词： dynamic service placement   delay optimization   cost efficiency   mobile edge computing  

摘要： Mobile edge computing is an emerging paradigm that supplies computation, storage, and networking resources between end devices and traditional cloud data centers. With increased investment of resources, users demand a higher quality-of-service (QoS). However, it is nontrivial to maintain service performance under the erratic activities of end-users. In this paper, we focus on the service placement problem under the continuous provisioning scenario in mobile edge computing for multiple mobile users. We propose a novel dynamic placement framework based on deep reinforcement learning (DSP-DRL) to optimize the total delay without overwhelming the constraints on physical resources and operational costs. In the learning framework, we propose a new migration conflicting resolution mechanism to avoid the invalid state in the decision module. We first formulate the service placement under the migration confliction into a mixed-integer linear programming (MILP) problem. Then, we propose a new migration conflict resolution mechanism to avoid the invalid state and approximate the policy in the decision modular according to the introduced migration feasibility factor. Extensive evaluations demonstrate that the proposed dynamic service placement framework outperforms baselines in terms of efficiency and overall latency.

关键词： Media Access Protocol   Merging   Protocols   Vehicle dynamics   Time division multiple access   Safety   Roads   collision prediction   slot assignment   medium access control   mobile edge computing   VANETs  

摘要： Vehicular ad hoc networks (VANETs) have been widely recognized as a promising solution to improve traffic safety and efficiency for the ability to provide situation awareness even though the potential dangers and traffic anomalies are out of the visual range. In VANETs, time-division multiple access (TDMA) based overlay protocols can prevent transmission collisions and play an important role in providing an efficient communication channel. However, due to high vehicle mobility and time-varying traffic flow, the existing TDMA-based slot allocation approaches cannot fully utilize the channel resources, resulting in high transmission delay and packet collision. To overcome these shortcomings, we propose a collision prediction and avoidance MAC (CPA-MAC) protocol that utilizes the capability of mobile edge computing (MEC) and machine learning in this paper. Specifically, we propose a new slot assignment method that aims to guarantee the high channel utilization and low delay of safety message under dynamic traffic conditions. Furthermore, we propose a new same-direction collisions prediction algorithm that combines the V2R communication and LSTM-based trajectory prediction algorithm. Finally, we conduct extensive experiments to demonstrate the effectiveness of the proposed protocol.

关键词： Mobile edge computing  

摘要： Optimal user association and resource utilization entails a challenging problem of high latency in mobile edge computing (MEC)-driven Internet of Things (IoT) applications. Increased power consumption is another aspect that requires attention, specifically for the systems that involve huge number of users (IoT nodes) and computing devices (cloudlets/MEC nodes/fog nodes). Though MEC/fog networks are designed for low latency and low transmit power connections, yet the substantial increase in IoT devices signify the need to redesign it for future demands. In this article, we formulate an optimization problem related to quality of service-driven node selection and utility maximization subject to power and workload constraints for applications that require very low latency. Outer approximation algorithm is a proven technique in the field of optimization theory and is scalable with number of nodes. A distributed self-converging algorithm based on the outer approximation algorithm is presented in this work, which proved to be efficient for the problem formulated. Extensive simulations are done to validate the numerical results. This work concludes by comparing results of outer approximation method with matching theory to validate its effectiveness.

关键词： Servers   Delays   Computational modeling   Cloud computing   Costs   Energy consumption   Collaboration   Mobile edge computing   cloud computing   QoS   computation offloading   DNN partition  

摘要： With the rapid development of the Internet of Things (IoT) and communication technology, Deep Neural Network (DNN) applications like computer vision, can now be widely used in IoT devices. However, due to the insufficient memory, low computing capacity, and low battery capacity of IoT devices, it is difficult to support the high-efficiency DNN inference and meet users' requirements for Quality of Service (QoS). Worse still, offloading failures may occur during the massive DNN data transmission due to the intermittent wireless connectivity between IoT devices and the cloud. In order to fill this gap, we consider the partitioning and offloading of the DNN model, and design a novel optimization method for parallel offloading of large-scale DNN models in a local-edge-cloud collaborative environment with limited resources. Combined with the coupling coordination degree and node balance degree, an improved Double Dueling Prioritized deep Q-Network (DDPQN) algorithm is proposed to obtain the DNN offloading strategy. Compared with existing algorithms, the DDPQN algorithm can obtain an efficient DNN offloading strategy with low delay, low energy consumption, and low cost under the premise of ensuring "delay-energy-cost" coordination and reasonable allocation of computing resources in a local-edge-cloud collaborative environment.

关键词： Servers   Vehicle dynamics   Privacy   Optimization   Training   Reinforcement learning   Wireless networks   Edge caching   mobile edge computing   privacy preservation   distributed reinforcement learning   federated learning  

摘要： Mobile edge computing (MEC) is a prominent computing paradigm which expands the application fields of wireless communication. Due to the limitation of the capacities of user equipments and MEC servers, edge caching (EC) optimization is crucial to the effective utilization of the caching resources in MEC-enabled wireless networks. However, the dynamics and complexities of content popularities over space and time as well as the privacy preservation of users pose significant challenges to EC optimization. In this paper, a privacy-preserving distributed deep deterministic policy gradient (P2D3PG) algorithm is proposed to maximize the cache hit rates of devices in the MEC networks. Specifically, we consider the fact that content popularities are dynamic, complicated and unobservable, and formulate the maximization of cache hit rates on devices as distributed problems under the constraints of privacy preservation. In particular, we convert the distributed optimizations into distributed model-free Markov decision process problems and then introduce a privacy-preserving federated learning method for popularity prediction. Subsequently, a P2D3PG algorithm is developed based on distributed reinforcement learning to solve the distributed problems. Simulation results demonstrate the superiority of the proposed approach in improving EC hit rate over the baseline methods while preserving user privacy.