关键词： Mobile edge computing   vehicular application   analytical modelling   bursty arrivals   performance analysis  

摘要： The quantitative performance analysis plays a critical role in assessing the capability of vehicular edge computing (VEC) systems to meet the requirements of vehicular applications. However, developing accurate analytical models for VEC systems is extremely challenging due to the unique features of intelligent vehicular applications. Specifically, recent work revealed that the tasks generated by intelligent vehicular applications exhibit a high degree of burstiness, rendering the existing models that were designed based on the assumption of the non-bursty Poisson process unsuitable for VEC systems. To fill this gap, we developed an original analytical model to investigate the performance of VEC systems with bursty task arrivals. To facilitate vehicle cooperation, a new priority-based resource allocation scheme is exploited to schedule the tasks of vehicular applications, which are modelled by a Markov Modulated Poisson Process (MMPP). Next, a multi-state Markov chain is established to investigate the impact of load sharing strategy on the performance of VEC systems. Then, the end-to-end transmission latency is derived based on the proposed model. Comprehensive experiments are conducted to validate the accuracy of this analytical model under various system configurations. Furthermore, the developed model is used as a cost-effective tool to investigate the performance bottleneck of VEC systems.

关键词： edge AI   mobile edge computing   deep learning   citrus orchards  

摘要： Deep Learning models have presented promising results when applied to Agriculture 4.0. Among other applications, these models can be used in disease detection and fruit counting. Deep Learning models usually have many layers in the architecture and millions of parameters. This aspect hinders the use of Deep Learning on mobile devices as they require a large amount of processing power for inference. In addition, the lack of high-quality Internet connectivity in the field impedes the usage of cloud computing, pushing the processing towards edge devices. This work describes the proposal of an edge AI application to detect and map diseases in citrus orchards. The proposed system has low computational demand, enabling the use of low-footprint models for both detection and classification tasks. We initially compared AI algorithms to detect fruits on trees. Specifically, we analyzed and compared YOLO and Faster R-CNN. Then, we studied lean AI models to perform the classification task. In this context, we tested and compared the performance of MobileNetV2, EfficientNetV2-B0, and NASNet-Mobile. In the detection task, YOLO and Faster R-CNN had similar AI performance metrics, but YOLO was significantly faster. In the image classification task, MobileNetMobileV2 and EfficientNetV2-B0 obtained an accuracy of 100%, while NASNet-Mobile had a 98% performance. As for the timing performance, MobileNetV2 and EfficientNetV2-B0 were the best candidates, while NASNet-Mobile was significantly worse. Furthermore, MobileNetV2 had a 10% better performance than EfficientNetV2-B0. Finally, we provide a method to evaluate the results from these algorithms towards describing the disease spread using statistical parametric models and a genetic algorithm to perform the parameters' regression. With these results, we validated the proposed pipeline, enabling the usage of adequate AI models to develop a mobile edge AI solution.

关键词： Video transcoding analysis   Dataset   Edge transcoding   Mobile edge computing  

摘要： The developments in smartphones, high data rates, and substantial video data traffic have increased the burden on cellular networks. Consequently, this burden significantly affects the Quality of Experience of the cellular users leading to an increased network delay for the diverse video content requests. To accommodate the requests from different users with varying requirements, one of the promising solutions is to cache videos in the near vicinity of users and transcode them online. The online transcoding is performed at the edge level of the cellular network to minimize the network delay and use the bandwidth efficiently. However, the feasibility of online transcoding is significantly affected by various factors, such as the codecs, configurations of virtual machines, the cost incurred, and estimated time to complete the transcoding task, among other parameters. Although online transcoding is discussed in the literature adequately, few studies discuss the feasibility of online transcoding while considering all the aforementioned critical parameters. This study examined the effects of a diverse range of critical parameters on the feasibility of online transcoding. We performed extensive simulations on the local machine environment to study various possible factors affecting online transcoding in detail. We then transcoded the same videos on Amazon Elastic Cloud Computing (EC2) Virtual Machines (VMs) to further study realistic cloud settings with fine-tuned configurations. Our experiments show the superior performance of some codecs and the effects of machine configurations on transcoding tasks duration. We aim to provide a benchmark for practitioners and researchers considering online transcoding in real-time multimedia applications.

关键词： Priority-based task scheduling   Resource allocation   Mobile edge computing   Cloud computing   Smart hospitals   Healthcare monitoring system  

摘要： New and innovative wearable IoT devices for health monitoring systems (HMS) have been invented one after another. However, most of these devices are resource-constrained with restricted energy and computation power. The HMS data need to be processed via mobile edge computing (MEC) to improve the response time to fulfill the latency-sensitive and computation-intensive applications and to reduce bandwidth consumption. This paper presents an efficient task scheduling and resource allocation mechanism in MEC to meet these demands in contemplating emergency conditions under HMS. We propose a priority-based task-scheduling and resource-allocation (PTS-RA) mechanism that can assign different priorities to different tasks by considering the tasks' emergency levels computed with respect to the data aggregated from a patient's smart wearable devices. The mechanism can optimally determine whether a task should be processed locally at the hospital workstations (HW) or in the cloud. This is aimed to reduce the total task processing time and the bandwidth cost as much as possible. The proposed approach is to ensure that tasks related to the emergency are given higher priorities and to run first. After the tasks' computations, results are sent to the doctor to response promptly with quick decisions. The proposed PTS-RA was benchmarked against state-of-the-art algorithms concerning average latency, task scheduling efficiency, task execution time, network usage, CPU utilization, and energy consumption. The bench marking results are promising as PTS-RA is capable to manage the emergency conditions and is meeting the latency-sensitive tasks' requirements with reduced bandwidth cost.& COPY;2023 The Authors. Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Mobile edge computing   Mobile cloud computing   Cloud-edge collaboration   Task offloading   Lyapunov optimization  

摘要： Due to the limitation of computing resources and storage resources, mobile edge computing cannot cope with the massive data generated by the Industrial Internet of Things (IIoT). However, traditional mobile cloud computing has rich computing resources. Therefore, through the construction of cloud computing and edge computing collaborative system, high bandwidth and low latency network services for the Internet of things can be provided. Based on Lyapunov optimization theory, the resource allocation and power consumption in cloud-edge collaborative system are investigated in this paper. Firstly, a cloud-edge collaboration architecture is proposed, then by establishing the dynamic queue model of cloud computing server and edge computing server, and combining with the system power function to form a drift plus penalty function framework, the problem is reduced to a constrained optimization problem. Finally, the offloading algorithm based on congestion is given. The simulation results show that the proposed optimization scheme can effectively reduce the overall power consumption and congestion of cloud-edge collaborative system.

关键词： IoT   collaborative inference   deep neural networks   distributed computing   DNN splitting   task offloading   mobile edge computing  

摘要： Motivated by the pervasiveness of artificial intelligence (AI) and the Internet of Things (IoT) in the current "smart everything" scenario, this article provides a comprehensive overview of the most recent research at the intersection of both domains, focusing on the design and development of specific mechanisms for enabling a collaborative inference across edge devices towards the in situ execution of highly complex state-of-the-art deep neural networks (DNNs), despite the resource-constrained nature of such infrastructures. In particular, the review discusses the most salient approaches conceived along those lines, elaborating on the specificities of the partitioning schemes and the parallelism paradigms explored, providing an organized and schematic discussion of the underlying workflows and associated communication patterns, as well as the architectural aspects of the DNNs that have driven the design of such techniques, while also highlighting both the primary challenges encountered at the design and operational levels and the specific adjustments or enhancements explored in response to them.

关键词： Collaborative inference   computation partition   mobile edge computing   multi-agent reinforcement learning  

摘要： Collaborative inference in mobile edge computing (MEC) enables mobile devices to offload the computation tasks for the computation-intensive perception services, and the inference policy determines the inference latency and energy consumption. The optimal inference policy depends on the inference performance model of deep learning, the data generation model and the network model that are rarely known by mobile devices in time. In this paper, we propose a multi-agent reinforcement learning (RL) based energy-efficient MEC collaborative inference scheme, which enables each mobile device to choose both the partition point of deep learning and the collaborative edge of each mobile device based on the image quantity, the channel conditions and the previous inference performance. A learning experience exchange mechanism exploits the Q-values of the neighboring mobile devices to accelerate the inference policy optimization with less energy consumption. We also provide a deep multi-agent RL based inference scheme to accelerate learning for large-scale MEC networks, in which an actor network yields the collaborative inference policy probability distribution and a critic network guides the weight update of the actor network to enhance sample efficiency. We provide the inference performance bound and analyze the computational complexity. Both simulation and experimental results show that our proposed schemes reduce the inference latency and save the MEC energy consumption.

关键词： Array signal processing   Task analysis   Internet of Things   Optimization   Servers   Resource management   Cloud computing   Intelligent reflecting surface (IRS)   mobile edge computing   dynamic beamforming   resource allocation   binary offloading   computation rate  

摘要： In this paper, we develop a unified dynamic intelligent reflecting surface (IRS) beamforming framework to boost the sum computation rate of an IRS-aided mobile edge computing (MEC) system, where each device follows a binary offloading policy. Specifically, the task of each device has to be either executed locally or offloaded to MEC servers as a whole with the aid of given number of IRS beamforming vectors available. By flexibly controlling the number of times for IRS reconfiguring phase-shifts, the system can achieve a balance between the performance and associated signalling overhead. We aim to maximize the sum computation rate by jointly optimizing the computational mode selection for each device, offloading time allocation, and IRS beamforming vectors across time. Since the resulting optimization problem is non-convex and NP-hard, there are generally no standard methods to solve it optimally. To tackle this problem, we first propose a penalty-based successive convex approximation algorithm, where all the associated variables in the inner-layer iterations are optimized simultaneously and the obtained solution is guaranteed to be locally optimal. Then, we further derive the offloading activation condition for each device by deeply exploiting the intrinsic structure of the original optimization problem. According to the offloading activation condition, a low-complexity algorithm based on the successive refinement method is proposed to obtain high-quality suboptimal solutions, which are more appealing for practical systems with a large number of devices and IRS elements. Moreover, the optimal condition for the proposed low-complexity algorithm is revealed. The effectiveness of the proposed algorithms is demonstrated through numerical examples. In addition, the results illustrate the practical significance of the IRS in MEC systems for achieving coverage extension and supporting multiple energy-limited devices for task offloading, and also unveil the fundamental perf

关键词： Computation offloading   Dynamic game   5G networks   Mobile edge computing   Non-cooperative game  

摘要： Mobile Edge Computing (MEC) has become a promising technology for 5G networks. Computation offloading is an essential issue of MEC, which enables mobile User Equipment (UE) to enjoy rich wireless resources and huge computing power anywhere. This paper considers the Quality-of-Experience (QoE) of UEs in 5G MEC systems and presents a dynamic non-cooperative game (QCOG-DG) algorithm and a static non-cooperative game (QCOG-SG) algorithm for computation offloading of MEC applications. We establish an MEC computation offloading model by considering the QoE requirements of UEs, and discuss the communication overheads, computation cost, and energy consumption models to minimize the energy consumption and time delay of each UE. Considering that there are multiple UEs who want to offload their computation tasks to a resource-constrained MEC server, and each UE is selfish and competitive, we formulate the problem of computation offloading decision as a non-cooperative game model. We prove the existence of a Nash Equilibrium (NE) solution for the proposed game model. In addition, we propose an algorithm that jointly optimizes energy consumption and time delay under QoE preferences to achieve optimal offloading benefits for each UE. Moreover, we respectively propose a dynamic non-cooperative game (QCOG-DG) algorithm and a static non-cooperative game (QCOG-SG) algorithm to efficiently find the NE solution. Extensive simulation experiments are conducted to verify the effectiveness of the proposed MEC computation offloading model and the QCOG-DG and QCOG-SG algorithms. Simulation results show that the proposed QCOG-DG algorithm can efficiently find the NE solutions in the MEC scenarios with UEs of different sizes. (c) 2022 Elsevier Inc. All rights reserved.

关键词： Mobile edge computing   Internet of things   Service collaboration   Multimedia contents  

摘要： In recent years, cloud computing can provide efficient data storage and processing infrastructure for Internet of things (IoT). However, the complete centralization of cloud computing brings inevitable limitations, such as the inability to support real-time service response. Mobile edge computing can solve the problems caused by traditional cloud computing. By placing computing and storage resources at the edge of the mobile network near the user, mobile edge computing extends the ability of cloud computing at the edge of the network. The advantage of mobile edge computing is that it reduces the amount of data sent to the cloud. Therefore, data processing is more flexible and convenient. Mobile edge computing can realize lower latency and higher data processing ratio, which will play an important role in the future application of IoT. Firstly, a system model for the application scenario is established, which is a real-time and context aware service resource collaboration model. Then a service collaboration method based on mobile edge computing is designed, which mainly includes service function description, service collaboration process and algorithm design. Finally, the simulation experiments are carried out. Compared with the other two existing methods, our method can effectively reduce service execution time and improve the success ratio of service requests. So the method presented in this paper is more effective and reliable. We provide a solution for service collaboration method based on mobile edge computing in IoT, which can make better use of various service resources.