关键词： Task analysis   Mobile handsets   Delays   Heuristic algorithms   Mobile computing   Edge computing   Distributed algorithms   Mobile edge computing   computation offloading   resource allocation   deep reinforcement learning   deep Q-learning  

摘要： In mobile edge computing systems, an edge node may have a high load when a large number of mobile devices offload their tasks to it. Those offloaded tasks may experience large processing delay or even be dropped when their deadlines expire. Due to the uncertain load dynamics at the edge nodes, it is challenging for each device to determine its offloading decision (i.e., whether to offload or not, and which edge node it should offload its task to) in a decentralized manner. In this work, we consider non-divisible and delay-sensitive tasks as well as edge load dynamics, and formulate a task offloading problem to minimize the expected long-term cost. We propose a model-free deep reinforcement learning-based distributed algorithm, where each device can determine its offloading decision without knowing the task models and offloading decision of other devices. To improve the estimation of the long-term cost in the algorithm, we incorporate the long short-term memory (LSTM), dueling deep Q-network (DQN), and double-DQN techniques. Simulation results show that our proposed algorithm can better exploit the processing capacities of the edge nodes and significantly reduce the ratio of dropped tasks and average delay when compared with several existing algorithms.

关键词： Internet of thing(IoT)   mobile edge computing   network function virtualization(NFV)   deep Q-learning(DQL)  

摘要： With the rapid development of Internet of thing(IoT) technology, it has become a challenge to deal with the increasing number and diverse requirements of IoT services. By combining burgeoning network function virtualization(NFV) technology with cloud computing and mobile edge computing(MEC), an NFV-enabled cloud-and-edge-collaborative IoT(CECIoT) architecture can efficiently provide flexible service for IoT traffic in the form of a service function chain(SFC) by jointly utilizing edge and cloud resources. In this promising architecture, a difficult issue is how to balance the consumption of resource and energy in SFC mapping. To overcome this challenge, an intelligent energy-and-resource-balanced SFC mapping scheme is designed in this paper. It takes the comprehensive deployment consumption as the optimization goal, and applies a deep Q-learning(DQL)-based SFC mapping(DQLBM) algorithm as well as an energy-based topology adjustment(EBTA) strategy to make efficient use of the limited network resources, while satisfying the delay requirement of users. Simulation results show that the proposed scheme can decrease service delay, as well as energy and resource consumption.

关键词： C-V2X   Mobile edge computing   Internet of vehicles   Server placement   Converged network  

摘要： To accommodate the high mobility and large-scale interconnection requirements of the Internet of Vehicles (IoVs) and to realize low-latency and high-reliability communication in IoVs, Cellular Vehicle-to-Everything (C-V2X) intelligent converged networks based on Mobile Edge Computing (MEC) is proposed. Various types of C-V2X applications impose diverse requirements on the network in terms of communication, computation, and storage, thus the MEC platform needs to be flexibly deployed in C-V2X. We can divide the MEC platform into Roadside-edge and Area-edge layers according to the service scope and business functions, and strategically select Road Side Units (RSUs) and Macro Base Stations (MBSs) with the optimal location in the Roadside-edge and Area-edge layer to place different types of Edge Servers (ESs). In the scenario of MEC and C-V2X convergence, we consider the trade-off between the response latency of computation requests and the placement cost, and modelled the hierarchical placement and configuration of ESs based on queuing theory. To reduce the complexity of the problem and improve the efficiency of the solution, heuristic algorithms are proposed to realize the joint hierarchical placement and configuration of ESs in C-V2X from the aspects of delay-aware, suitability evaluation, and spatial clustering. Finally, the real C-V2X scenarios are simulated based on the Poisson Line Process (PLP) and Poisson Point Process (PPP), and sufficient experimental results verify the effectiveness and superiority of the proposed algorithms.

关键词： DNN model partitioning   mobile edge computing   mobile vision application   optimization   quality of user experience  

摘要： Through the advancement of wireless network technology, real-time mobile vision applications such as object detection and image analysis in mobile devices are being used in various fields. Such applications leverage mobile edge computing (MEC) to utilize high-accuracy deep learning models, but show low QoE due to network overhead. To tackle this, deep model partitioning has emerged that splits processing for inference between a mobile device and MEC server. Existing works proposed deep learning model partitioning algorithms to improve one or two metrics among end-to-end latency, energy consumption, and frame per second (fps) to enhance the QoE of mobile vision applications. In this paper, we propose an algorithm to jointly control (i) the model partitioing point, (ii) the number of frames to be processed among the input frames, and (iii) the GPU clock frequency of the mobile device to improve the performance of the above three metrics. With trace-driven simulation, we verify that our RT-DMP can save 90.2% of energy consumption than mobile processing algorithm, and improve processed fps by 91.8% compared to MEC algorithm. © 2022, Korean Institute of Communications and Information Sciences. All rights reserved.

关键词： blockchain   mobile edge computing   deep reinforcement learning   consensus mechanism  

摘要： To cope with the low latency requirements and security issues of the emerging applications such as Internet of Vehicles(Io V)and Industrial Internet of Things(IIo T),the blockchain-enabled Mobile Edge Computing(MEC)system has received extensive ***,blockchain is a computing and communication intensive technology due to the complex consensus *** facilitate the implementation of blockchain in the MEC system,this paper adopts the committee-based Practical Byzantine Fault Tolerance(PBFT)consensus algorithm and focuses on the committee selection *** and IIo T devices generate the transactions which are records of the application *** Stations(BSs)with MEC servers,which serve the transactions according to the wireless channel quality and the available computing resources,are blockchain nodes and candidates for committee *** income of transaction service fees,the penalty of service delay,the decentralization of the blockchain and the communication complexity of the consensus process constitute the performance *** committee selection problem is modeled as a Markov decision process,and the Proximal Policy Optimization(PPO)algorithm is adopted in the *** results show that the proposed PPO-based committee selection algorithm can adapt to the system design requirements with different emphases and outperforms other comparison methods.

关键词： Mobile edge computing   wireless power transfer   Lyapunov optimization   dynamic throughput maximum (DTM)  

摘要： Wireless powered mobile edge computing (WP-MEC) has been widely studied as a promising technology to liberate wireless terminals from the computation-intensive and energy-consuming tasks. This article considers a WP-MEC system consisting of multiple base stations (BSs) and mobile devices (MDs), where the MDs offload tasks to the BSs for computational resources and the BSs charge the MDs using wireless power transfer (WPT). In practice, each BS and MD are equipped with a task buffer with limited size and a battery with limited capacity. First, we develop a time slotted WP-MEC system with task and energy queuing dynamics to study long-term system performance under time-varying fading channels and stochastic task and energy arrivals. Second, we propose a dynamic throughput maximum (DTM) algorithm based on perturbed Lyapunov optimization to maximize the system throughput under task and energy queue stability constraints, by optimizing the allocation of communication, computation, and energy resources. For the DTM algorithm, we characterize a throughput-backlog trade-off of [O(1/V) , O(V)] to indicate that the system throughput goes up as the queue backlog increases, where V is a control parameter between the system throughput and the queue backlog. However, we find that, as V goes large, the system throughput can be pushed arbitrarily close to the optimum at the cost of linearly increasing queue backlog (i.e., O(V)). To reduce the cost, we further develop an improved dynamic throughput maximum (IDTM) algorithm, and verify that the IDTM algorithm can achieve a trade-off of [ O(1/V) , O((log(V))(2)) ] between the system throughput and the queue backlog. The simulation results demonstrate that IDTM retains close system throughput to DTM with only O((log(V))(2)) queue backlog.

关键词： Cloud   Cloudlet   Fog   Optimization   Mobile edge computing   Radio resource management   Unmanned aerial vehicles  

摘要： Unmanned aerial vehicles (UAVs) have huge potential in empowering new applications in different areas ranging from military to medical applications and traffic control to the entertainment information industry. There has been overwhelming interest in improving UAVs and multi-UAVs frameworks to collaborate and complete all missions efficiently. UAVs can be connected to IoT devices at any time and fulfill their requirements. Because of the constrained onboard resources, there is a need for radio resource management (RRM) in UAV correspondent situations. Optimization plays a significant role in the efficient utilization of these resources and provides services to the network's edge. This survey presents a comprehensive overview of RRM optimization techniques, including cloud, fog, mobile edge computing (MEC), and cloudlet for UAVs. Further, the mathematical modeling of objectives and constraints discussed in the literature is also presented here. A summary of the challenges while using these computing paradigms is explored. Future research directions on the UAV-assisted network are introduced. In short, this survey provides key guidelines of how various radio resources in different environments are analyzed and optimized using different algorithms and strategies.

关键词： mobile edge computing   joint resource allocation   reinforcement learning  

摘要： A distributed reinforcement learning(RL)based resource management framework is proposed for a mobile edge computing(MEC)system with both latency-sensitive and latency-insensitive *** investigate joint optimization of both computing and radio resources to achieve efficient on-demand matches of multi-dimensional resources and diverse requirements of users.A multi-objective integer programming problem is formulated by two subproblems,i.e.,access point(AP)selection and subcarrier allocation,which can be solved jointly by our proposed distributed RL-based approach with a heuristic iteration *** proposed algorithm allows for the reduction in complexity since each user needs to consider only its own selection of AP without knowing full global *** results show that our algorithm can achieve near-optimal performance while reducing computational complexity *** with other algorithms that only optimize either of the two sub-problems,the proposed algorithm can serve more users with much less power consumption and content delivery latency.

关键词： Mobile edge computing   power control   invex   joint heterogeneous resource allocation  

摘要： Energy saving for mobile devices is considered to be one of prospective benefits of mobile edge computing (MEC) networks, where computation-intensive tasks can be offloaded from the mobile devices to their associated MEC servers for execution. Extra energy consumption for data migration should therefore be less than the energy consumption for local execution. However, in multi-cell MEC-assisted networks, due to both the presence of co-channel interference and the latency requirement of each offloading task, power control is tightly coupled with computation offloading, which becomes an obstacle to achieve the aim of energy' saving. In this paper, we develop an analytic model to decouple power control and computation resource allocation from each other, in which the transmission power can he considered as a solution to a set of linear equations with a coefficient matrix depending on the computation resource budget. Based on this analytic foundation, we show that with a fixed offloading decision, the joint power control and computation resource allocation problem is invex, which ensures that every KKT (Karush-Kuhn-Tucker) stationary point of the problem must be a global minimizer. Moreover, we deduce a criterion for energy-efficient offloading decision making from the partial derivative of the total energy consumption of mobile devices with respect to the computation resource budget. Finally, we propose a heuristic algorithms to jointly optimizing power and computation resource allocation, and offloading decision. The numerical results demonstrate the optimality and efficiency of our proposed algorithm.

关键词： Edge computing   Path planning   Quality of service   Planning   Task analysis   Reinforcement learning   Prediction algorithms   Unmanned Aerial Vehicle   Mobile Edge Computing   Path Planning   Reinforcement Learning  

摘要： Unmanned Aerial vehicles (UAVs) are widely used as network processors in mobile networks, but more recently, UAVs have been used in Mobile Edge Computing as mobile servers. However, there are significant challenges to use UAVs in complex environments with obstacles and cooperation between UAVs. We introduce a new multi-UAV Mobile Edge Computing platform, which aims to provide better Quality-of-Service and path planning based on reinforcement learning to address these issues. The contributions of our work include: 1) optimizing the quality of service for mobile edge computing and path planning in the same reinforcement learning framework;2) using a sigmoid-like function to depict the terminal users' demand to ensure a higher quality of service;3) applying synthetic considerations of the terminal users' demand, risk and geometric distance in reinforcement learning reward matrix to ensure the quality of service, risk avoidance, and the cost-savings. Simulations have shown the effectiveness and feasibility of our platform, which can help advance related researches. The source code can be found at https://***/bczhangbczhang.