关键词： Mobile edge computing   incentive mechanism   truthful   auction mechanism  

摘要： Mobile edge computing (MEC) shows prominent application prospects in the Industrial Internet of Things (IIoT) by allowing resource-restricted IIoTmobile devices (MDs) to offload their tasks to geographical proximity edge clouds. An efficient incentive mechanism should be designed jointly addressing resource allocation and pricing to incentivizeMDs (i.e., buyers) and edge clouds (i.e., sellers) to participate in offloading service trading. This article aims to solve the socialwelfaremaximization problemof a personalizedMEC computation offloading service marketwhere each edge cloud can allocate different computing and wireless resources to eachMD according to theMDs' delay and energy consumption constraints, and eachMD submits bids to edge clouds differently based on the resource allocation of the edge clouds. We propose a truthful combinatorial auction (TCA) mechanismwhich involves three phases of resource allocation, buyer-seller matching, and payment determination. It should be highlighted that our proposed buyer-seller matching algorithmcombines optimal matching and heuristicmatching, so it greatly improves the auction effect while ensuring computational efficiency. Considerable theoretical analysis and experimental results prove that the performance of the proposed TCAmechanismis significantly superior to that of other auctionmechanismswhile holding the desirable properties.

关键词： Service function chaining   Mobile edge computing   Actor-critic   Zero -forcing beamforming   Proximal center dual decomposition  

摘要： As two promising paradigms in emerging 6G wireless systems, service function chaining (SFC) and mobile edge computing (MEC) have attracted insensitive attentions from both industry and academia, and would bring more close-proximity services to 6G users with communication, computing and caching (3C) resources, yet also faced with challenges arising in time-varying channel conditions and resource dynamics. In this work, boosted by recent advents in artificial intelligence and reinforcement learning, we investigate the on-line SFC deployment in the edge of 6G wireless systems via the actor- critic learning framework. First, one long-run cost-efficient SFC deployment problem is investigated, and the coordinated multiple points (CoMP)-based zero-forcing beamforming is utilized to cancel the interference across SFCs. Then, by exploiting the Markov decision processes (MDP) property of long-run SFC deployment, one natural gradient-based actor-critic framework is proposed to characterize edge network dynamics, and meanwhile facilitates the training of neural networks to the global optimum. Next, to lower the size of action space, we follow the principle that a subproblem is embedded into each state-action pair's critic to solve the reward function, and then utilize both the lp (0 < p < 1) norm-based successive convex approximation (SCA) and proximal center-based dual decomposition to approach the global optimum and accelerate the convergence. Finally, numerical results are used to validate proposed actor-critic approach, showing that the communication resource management deserves special attentions in the SFC deployment in the edge of 6G wireless systems.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Protocols   Task analysis   Resource management   Energy exchange   Energy harvesting   Uplink   Servers   Wireless power transfer   mobile edge computing   reconfigurable intelligent surface   simultaneous transmission and reflection   resource allocation  

摘要： In this paper, a novel concept called simultaneously transmitting and reflecting RIS (STAR-RIS) is introduced into the wireless-powered mobile edge computing (MEC) systems to improve the efficiency of energy transfer and task offloading. Compared with traditional reflecting-only RIS, STAR-RIS extends the half-space coverage to full-space coverage by simultaneously transmitting and reflecting incident signals, and also provides new degrees-of-freedom (DoFs) for manipulating signal propagation. We aim to maximize the total computation rate of all users, where the energy transfer time, transmit power and CPU frequencies of users, and the configuration design of STAR-RIS are jointly optimized. Considering the characteristics of STAR-RIS, three operating protocols, namely energy splitting (ES), mode switching (MS), and time splitting (TS) are studied, respectively. For the ES protocol, based on the penalty method, successive convex approximation (SCA), and the linear search method, an iterative algorithm is proposed to solve the formulated non-convex problem. Then, the proposed algorithm for ES protocol is extended to solve the MS and TS problems. Simulation results illustrate that the STAR-RIS outperforms traditional reflecting/transmitting-only RIS. More importantly, the TS protocol can achieve the largest computation rate among the three operating protocols of STAR-RIS.

关键词： reinforcement learning   interning of things   mobile edge computing   computation offloading   linear regression  

摘要： Various edge collaboration schemes that rely on reinforcement learning (RL) have been proposed to improve the quality of experience (QoE). Deep RL (DRL) maximizes cumulative rewards through large-scale exploration and exploitation. However, the existing DRL schemes do not consider the temporal states using a fully connected layer. Moreover, they learn the offloading policy regardless of the importance of experience. They also do not learn enough because of their limited experiences in distributed environments. To solve these problems, we proposed a distributed DRL-based computation offloading scheme for improving the QoE in edge computing environments. The proposed scheme selects the offloading target by modeling the task service time and load balance. We implemented three methods to improve the learning performance. Firstly, the DRL scheme used the least absolute shrinkage and selection operator (LASSO) regression and attention layer to consider the temporal states. Secondly, we learned the optimal policy based on the importance of experience using the TD error and loss of the critic network. Finally, we adaptively shared the experience between agents, based on the strategy gradient, to solve the data sparsity problem. The simulation results showed that the proposed scheme achieved lower variation and higher rewards than the existing schemes.

关键词： Task analysis   Delays   Artificial intelligence   Computational modeling   Energy consumption   Servers   Inference algorithms   Mobile augmented reality   edge intelligence   mobile edge computing   resource allocation  

摘要： The high computational complexity and energy consumption of artificial intelligence (AI) algorithms hinder their application in augmented reality (AR) systems. However, mobile edge computing (MEC) makes it possible to solve this problem. This paper considers the scene of completing video-based AI inference tasks in the MEC system. We formulate a mixed-integer nonlinear programming problem (MINLP) to reduce inference delays, energy consumption and to improve recognition accuracy. We give a simplified expression of the inference complexity model and accuracy model through derivation and experimentation. The problem is then solved iteratively by using alternating optimization. Specifically, by assuming that the offloading decision is given, the problem is decoupled into two sub-problems, i.e., the resource allocation problem for the devices set that completes the inference tasks locally, and that for the devices set that offloads tasks. For the problem of offloading decision optimization, we propose a Channel-Aware heuristic algorithm. To further reduce the complexity, we propose an alternating direction method of multipliers (ADMM) based distributed algorithm. The ADMM-based algorithm has a low computational complexity that grows linearly with the number of devices. Numerical experiments show the effectiveness of proposed algorithms. The trade-off relationship between delay, energy consumption, and accuracy is also analyzed.

关键词： Absolute performance bound   asymptotic performance bound   device-edge-cloud fusion   energy-constrained task scheduling   heuristic algorithm   mobile edge computing  

摘要： Mobile edge computing with device-edge-cloud fusion provides a new type of heterogeneous computing environment. We consider task scheduling with device-edge-cloud fusion (without energy concern) and energy-constrained task scheduling with device-edge-cloud fusion as combinatorial optimization problems. The main contributions of the paper are summarized as follows. We design three heuristic algorithms for task scheduling with device-edge-cloud fusion and prove an asymptotic performance bound. We design one heuristic algorithm for energy-constrained task scheduling with device-edge-cloud fusion, which solves the two subproblems of task scheduling and power allocation in an interleaved way. We derive lower bounds for the optimal solutions for both task scheduling with device-edge-cloud fusion and energy-constrained task scheduling with device-edge-cloud fusion, so that the performance of our heuristic algorithms can be compared with that of an optimal algorithm. We experimentally evaluate the performance of our heuristic algorithms and find that the performance of our heuristic algorithms are very close to that of optimal algorithms. To the best of our knowledge, this is the first paper which studies task scheduling with device-edge-cloud fusion and energy-constrained task scheduling with device-edge-cloud fusion as combinatorial optimization problems and conducts analytical performance evaluation.

关键词： Mobile edge computing   relay   intelligent reflecting surface   non-orthogonal multiple access   orthogonal frequency division multiplexing  

摘要： In this paper, the design of task offloading and computing strategy in a mobile edge computing (MEC) system deployed over a reconfigurable intelligent surface (RIS)-aided orthogonal frequency division multiplexing based non-orthogonal multiple access (OFDM-NOMA) relay network is studied, where both a relay node and an MEC server located at an access point help a user terminal accomplish task computing. Our objective is to minimize energy consumption for communication and computation at the user terminal and the relay subject to a given task executing delay constraint. To this end, a novel protocol is first proposed to enable the user terminal and the relay to fully utilize the high passive beamforming gain provided by RIS and the high spectral efficiency offered by OFDM and NOMA techniques for task offloading. Then, under the newly proposed protocol, a resource allocation optimization problem is formulated, where RIS reflection coefficients, task offloading and computing time allocation, subcarrier and power allocation, task partition, and CPU frequency of the MEC server are jointly optimized. Because the numerous optimization variables are coupled with each other and integer programming is involved for subcarrier allocation optimization, the formulated problem is a mixed integer programming and highly non-convex problem that is hard to tackle. To address this problem, an efficient algorithm is devised to achieve its solution by employing alternating optimization, layer optimization, big-M formulation and successive convex approximation techniques. Simulation results validate that substantial energy savings can be achieved by employing RIS and OFDM-NOMA techniques in wireless relaying-based MEC systems.

关键词： Mobile edge computing  

摘要： Mobile edge computing (MEC) mainly offers strong computing capabilities and functions to finish the delay-sensitive task in time with the help of 5G wireless networks. Task scheduling is a technique for managing the increasing number of mobile edge users, decreasing task execution time, and improving the system's load-balancing capabilities. To achieve these goals, a distributed task scheduling system is developed in this research to satisfy multi-objectives such as cost, total execution time, overhead, and energy consumption for large-scale MEC tasks. First, a Hybrid Fuzzy Archimedes (HFA) algorithm is proposed to select the MEC node, which finishes the tasks with minimal cost and a higher security level. In the second step, the Hybrid LGBM and XGBoost architecture is formed to minimize the energy consumption and latency of each node for distributed task scheduling. The HFA algorithm modifies the search behavior of the Archimedes optimization algorithm using the fuzzy tendency factor and a normalized objective function. The HFA algorithm mainly selects the rule with an improved security value and lower cost for delay-sensitive applications. The main aim of the hybrid LGBM-XGBoost architecture is to minimize energy consumption and latency by taking the makespan and energy values. The efficiency of the proposed methodology is evaluated in terms of resource utilization, average completion time, completion rate, and Computation Workload Completion Rate. The proposed model offers a 20% improvement in average completion time and a 30% improvement in the energy consumption ratio. When 64 users are present in the system, the proposed model offers a CPU usage of 22% whereas MOCOSC, ADMM, and ANNIDS approaches offer CPU utilization of 62%, 78%, and 82%, respectively.

关键词： Mobile edge computing  

摘要： Personalized Federated Learning (PFL) is a new Federated Learning (FL) paradigm, particularly tackling the heterogeneity issues brought by various mobile user equipments (UEs) in mobile edge computing (MEC) networks. However, due to the ever-increasing number of UEs and the complicated administrative work it brings, it is desirable to switch the PFL algorithm from its conventional two-layer framework to a multiple-layer one. In this paper, we propose hierarchical PFL (HPFL), an algorithm for deploying PFL over massive MEC networks. The UEs in HPFL are divided into multiple clusters, and the UEs in each cluster forward their local updates to the edge server (ES) synchronously for edge model aggregation, while the ESs forward their edge models to the cloud server semi-asynchronously for global model aggregation. The above training manner leads to a tradeoff between the training loss in each round and the round latency. HPFL combines the objectives of training loss minimization and round latency minimization while jointly determining the optimal bandwidth allocation as well as the ES scheduling policy in the hierarchical learning framework. Extensive experiments verify that HPFL not only guarantees convergence in hierarchical aggregation frameworks but also has advantages in round training loss maximization and round latency minimization. Copyright © 2023, The Authors. All rights reserved.

关键词： Mobile edge computing   UAVs hybrid networks   Multi-objective cooperative computation   offloading   Integrated optimization framework  

摘要： With the continuous expansion of the application field of the Internet of Things (IoT), mobile edge computing (MEC) is regarded as a promising technique to reduce the time-delay and energy-consumption of application. However, the conventional MEC infrastructure is lack of flexibility, and failed to meet the different requires of mobile device. UAVs have the distinct features of high scalability and mobility for communications, which can act as the complement of conventional MEC infrastructure. This paper investigates the issues of multi -objective cooperative computation offloading for MEC in UAVs hybrid Networks. The proposed UAVs hybrid MEC system enables edge-cloud and UAVs cooperation to address the flexible limitations of conventional MEC infrastructure and the efficient computation offloading of computation task. To support good-quality services in a cost-effective manner, we model the computation offloading problem as a multi-objective optimization process, and propose an intelligent computation offloading algorithms based on integrated optimization framework, including mixed integer transformation solving framework, improved multi-adaptive MOEA/D-DE(MOEA/D-MSDE) and Grey Relational Projection (GRP). Evaluation results show that the proposed algorithms outperform in solving multi-objective cooperative computation offloading problem in terms of service time-delay, energy-consumption and server-cost.