关键词： Mobile edge computing   Tasks offloading   Data quality   Optimal stopping theory   Sequential decision making  

摘要： An important use case of the Mobile Edge Computing (MEC) paradigm is task and data offloading. Computational offloading is beneficial for a wide variety of mobile applications on different platforms including autonomous vehicles and smartphones. With the envision deployment of MEC servers along the roads and while mobile nodes are moving and having certain tasks (or data) to be offloaded to edge servers, choosing an appropriate time and an ideally suited MEC server to guarantee the Quality of Service (QoS) is challenging. We tackle the data quality-aware offloading sequential decision making problem by adopting the principles of Optimal Stopping Theory (OST) to minimize the expected processing time. A variety of OST stochastic models and their applications to the offloading decision making problem are investigated and assessed. A performance evaluation is provided using simulation approach and real world data sets together with the assessment of baseline deterministic and stochastic offloading models. The results show that the proposed OST models can significantly minimize the expected processing time for analytics task execution and can be implemented in the mobile nodes efficiently. (C) 2020 Elsevier B.V. All rights reserved.

关键词： mobile edge computing   wireless energy transfer   wireless powered mobile edge computing  

摘要： To improve the computational power and limited battery capacity of mobile devices (MDs), wireless powered mobile edge computing (MEC) systems are gaining much importance. In this paper, we consider a wireless powered MEC system composed of one MD and a hybrid access point (HAP) attached to MEC. Our objective is to achieve a joint time allocation and offloading policy simultaneously. We propose a cost function that considers both the energy consumption and the time delay of an MD. The proposed algorithm, joint time allocation and offload policy (JTAOP), is used to train a neural network for reducing the complexity of our algorithm that depends on the resolution of time and the number of components in a task. The numerical results are compared with three benchmark schemes, namely, total local computation, total offloading and partial offloading. Simulations show that the proposed algorithm performs better in producing the minimum cost and energy consumption as compared to the considered benchmark schemes.

关键词： Mobile edge computing   Green cloud   Virtual list   Congestion control   Queue management   Cloudlet  

摘要： The mobile users have acquired the benefits of cloud computing with the help of Mobile Edge Computing (MEC) technology in order to satisfy the increasing data demands. The efficiency of the system is highly limited by the bandwidth limitations and limitations associated with the mobile devices despite the rapid development of MEC as well as the cloud computing technology. Our aim is to provide an optimal method to optimize the energy consumption in the mobile edge computing. In this regard, the research paper proposed a Green Cloud based Queue Management system for 5G networks that helps in addressing the issues related to latency and energy consumption. While serving the users, the proposed methodology results in less amount of energy being wasted and hence the reduced latency. By means of alleviating the congestion and implementing the virtual list, this issue can be resolved greatly. Simulation is done with the help of NS2 green cloud simulator and the results are obtained by comparing the proposed model to conventional cloud model and cloudlet based on throughput, latency, energy consumption and normalized overhead as these are the evaluation measures. The results show that there has been considerable enhancement in the energy consumption. As the throughput increases, the quality of the service also increases.

关键词： Servers   Edge computing   Connected vehicles   Wireless sensor networks   State estimation   Sensors   Nonlinear systems   Mobile edge computing   unreliable communications   wireless communications   nonlinear systems   state estimation  

摘要： In this letter, we investigate the state estimation problem in Mobile Edge Computing with unreliable communications. A finite-time convergent estimator is proposed, aiming to restore the unmeasurable states within a finite time length. We apply the proposed estimator in two practical scenarios to evaluate its performance. The numerical results show that the proposed estimator is able to quickly make accurate estimations once the interrupted connection resumes. The results also suggest that the effect of short-term data loss is easier to remedy than that of long-term data loss, which shed light on relay deployment and future investigations in this field.

关键词： Mobile edge computing   Computation offloading   Ultra-dense network   Edge server deployment   Average completion time  

摘要： With the emergence of compute-intensive applications and rapid growth of mobile users and Internet of Things(IoT) devices, edge computing was proposed to provide cloudlike services in close proximity to meet the requirements of low-latency, security, and lower energy consumption. Ultra-dense network (UDN) is a promising technique to meet the requirements of explosive data traffic in 5G mobile communications to improve regional spectrum efficiency and network coverage. This paper proposed an optimal deployment and allocation strategy for deploying edge servers(ESs) in UDN to minimize the cost of service providers and to guarantee the completion time of services. Based on queuing theory and vector quantization(VQ) technique, the strategy can optimize both the number and locations of edge servers, and mobile users allocation for the given UDN environments. The experimental results show that the strategy is superior to existing algorithms in both qualitative and quantitative aspects, and can minimize the cost of deployment and guarantee the mobile user's requirements for the completion time of the offloading task. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Processor scheduling   Cloud computing   Servers   Bandwidth   Complexity theory   Edge computing   Computational modeling   Mobile edge computing   service placement   workload scheduling   complexity analysis   algorithm design  

摘要： Mobile edge computing provides the opportunity for wireless users to exploit the power of cloud computing without a large communication delay. To serve data-intensive applications (e.g., video analytics, machine learning tasks) from the edge, we need, in addition to computation resources, storage resources for storing server code and data as well as network bandwidth for receiving user-provided data. Moreover, due to time-varying demands, the code and data placement needs to be adjusted over time, which raises concerns of system stability and operation cost. In this paper, we address these issues by proposing a two-time-scale framework that jointly optimizes service (code and data) placement and request scheduling, while considering storage, communication, computation, and budget constraints. First, by analyzing the hardness of various cases, we completely characterize the complexity of our problem. Next, we develop a polynomial-time service placement algorithm by formulating our problem as a set function optimization, which attains a constant-factor approximation under certain conditions. Furthermore, we develop a polynomial-time request scheduling algorithm by computing the maximum flow in a carefully constructed auxiliary graph, which satisfies hard resource constraints and is provably optimal in the special case where requests have homogeneous resource demands. Extensive synthetic and trace-driven simulations show that the proposed algorithms achieve 90% of the optimal performance.

关键词： Computation offloading   Task caching   Energy-efficient   Mobile edge computing   Q learning   Deep Q Network  

摘要： Computation offloading at mobile edge computing (MEC) servers can mitigate the resource limitation and reduce the communication latency for mobile devices. Thereby, in this study, we proposed an offloading model for a multi-user MEC system with multi-task. In addition, a new caching concept is introduced for the computation tasks, where the application program and related code for the completed tasks are cached at the edge server. Furthermore, an efficient model of task offloading and caching integration is formulated as a nonlinear problem whose goal is to reduce the total overhead of time and energy. However, solving these types of problems is computationally prohibitive, especially for large-scale of mobile users. Thus, an equivalent form of reinforcement learning is created where the state spaces are defined based on all possible solutions and the actions are defined on the basis of movement between the different states. Afterwards, two effective Q-learning and Deep-Q-Network-based algorithms are proposed to derive the near-optimal solution for this problem. Finally, experimental evaluations verify that our proposed model can substantially minimize the mobile devices' overhead by deploying computation offloading and task caching strategy reasonably.

关键词： Mobile Edge Computing   Fog Computing   Classical virtualization   Network function Virtualization (NFV)  

摘要： With the advent of Internet of Things (IoT) connecting billions of mobile and stationary devices to serve real-time applications, cloud computing paradigms face some significant challenges such as high latency and jitter, non-supportive location-awareness and mobility, and non-adaptive communication types. To address these challenges, edge computing paradigms, namely Fog Computing (FC), Mobile Edge Computing (MEC) and Cloudlet, have emerged to shift the digital services from centralized cloud computing to computing at edges. In this article, we analyze cloud and edge computing paradigms from features and pillars perspectives to identify the key motivators of the transitions from one type of virtualized computing paradigm to another one. We then focus on computing and network virtualization techniques as the essence of all these paradigms, and delineate why virtualization features, resource richness and application requirements are the primary factors for the selection of virtualization types in IoT frameworks. Based on these features, we compare the state-of-the-art research studies in the IoT domain. We finally investigate the deployment of virtualized computing and networking resources from performance perspective in an edge-cloud environment, followed by mapping of the existing work to the provided taxonomy for this research domain. The lessons from the reviewed are that the selection of virtualization technique, placement and migration of virtualized resources rely on the requirements of IoT services (i.e., latency, scalability, mobility, multi-tenancy, privacy, and security). As a result, there is a need for prioritizing the requirements, integrating different virtualization techniques, and exploiting a hierarchical edge-cloud architecture. (c) 2020 Elsevier Inc. All rights reserved.

关键词： Greedy strategy   Lyapunov optimization   Mobile edge computing   Mobility characteristic   Task offloading strategy  

摘要： Task offloading strategy optimization in mobile edge computing (MEC) has always been a hot issue. However, the mobility of a user equipment (UE) seriously affects the UE's cost and performance. This paper proposes three mobility types depending on whether the mobility characteristic of a UE is known, and formulates an energy minimization problem and a latency minimization problem to optimize the cost and performance, respectively. We first develop greedy strategy based task offloading algorithms for UEs according to their mobility characteristics. However, accurately obtaining the mobility characteristics of the UEs over a long time in practice is a huge challenge, especially in a highly random environment like the MEC. To address the issue, we use a Lyapunov optimization method to develop the algorithms that do not require any prior knowledge of the mobility characteristics to minimize the long-term energy and latency of UEs. Experimental results show that the greedy strategy based algorithms can optimize the cost and performance of UEs by using their mobility characteristics, and perform better than the Lyapunov optimization based algorithms in a short-term. However, the Lyapunov optimization based algorithms perform better than the greedy strategy based algorithms over a long-term. (c) 2020 Elsevier Inc. All rights reserved.

关键词： Mobile edge computing  

摘要： With the growing demand for latency-critical and computation-intensive Internet of Things (IoT) services, the IoT-oriented network architecture, mobile edge computing (MEC), has emerged as a promising technique to reinforce the computation capability of the resource-constrained IoT devices. To exploit the cloud-like functions at the network edge, service caching has been implemented to reuse the computation task input/output data, thus effectively reducing the delay incurred by data retransmissions and repeated execution of the same task. In a multiuser cache-assisted MEC system, users’ preferences for different types of services, possibly dependent on their locations, play an important role in joint design of communication, computation and service caching. In this paper, we consider multiple representative locations, where users at the same location share the same preference profile for a given set of services. Specifically, by exploiting the location-aware users’ preference profiles, we propose joint optimization of the binary cache placement, the edge computation resource and the bandwidth allocation to minimize the expected sum-energy consumption, subject to the bandwidth and the computation limitations as well as the service latency constraints. To effectively solve the mixed-integer non-convex problem, we propose a deep learning (DL)-based offline cache placement scheme using a novel stochastic quantization based discrete-action generation method. The proposed hybrid learning framework advocates both benefits from the model-free DL approach and the model-based optimization. The simulations verify that the proposed DL-based scheme saves roughly 33% and 6.69% of energy consumption compared with the greedy caching and the popular caching, respectively, while achieving up to 99.01% of the optimal performance. Copyright © 2021, The Authors. All rights reserved.