关键词： Mobile edge computing   Deep Q Network Algorithm   Latency Optimized   Computation Offloading   5G  

摘要： The future Internet of Things (IoT) era is anticipated to support computation-intensive and time-critical applications using edge computing for mobile (MEC), which is regarded as promising technique. However, the transmitting uplink performance will be highly impacted by the hostile wireless channel, the low bandwidth, and the low transmission power of IoT devices. Using edge computing for mobile (MEC) to offload tasks becomes a crucial technology to reduce service latency for computation-intensive applications and reduce the computational workloads of mobile devices. Under the restrictions of computation latency and cloud computing capacity, our goal is to reduce the overall energy consumption of all users, including transmission energy and local computation energy. In this article, the Deep Q Network Algorithm (DQNA) to deal with the data rates with respect to the user base in different time slots of 5G NOMA network. The DQNA is optimized by considering more number of cell structures like 2, 4, 6 and 8. Therefore, the DQNA provides the optimal distribution of power among all 3 users in the 5G network, which gives the increased data rates. The existing various power distribution algorithms like frequent pattern (FP), weighted least squares mean error weighted least squares mean error (WLSME), and Random Power and Maximal Power allocation are used to justify the proposed DQNA technique. The proposed technique which gives 81.6% more the data rates when increased the cell structure to 8. Thus 25% more in comparison to other algorithms like FP, WLSME Random Power and Maximal Power allocation.

关键词： Mobile edge computing  

摘要： In view of the problem of long migration time and low availability of VM (virtual machine) migration in MD (mobile devices) in the MEC (mobile edge computing) environment, this paper designs a MD2N (Mobile Device to Network) model. This model no longer uploads requests to the cloud center, but centers on the edge server, scheduling and selecting migration services through the communication between the servers. And, a virtual machine migration strategy based on Markov decision and greedy algorithm is proposed. Model the edge server based on its geographic location, imitating the traditional cellular network method, and then the improved greedy algorithm is used to dynamically select the best edge device to migrate VM. Simulation and comparison experiments show that the proposed scheme has small migration fluctuations, stable migration status, short migration time, low average time delay, and high virtual machine migration availability after migration. © 2023 Xiaoxue Ma et al.

关键词： Mobile edge computing   neural network splitting   container orchestration   artificial intelligence   QoS optimization  

摘要： In recent years, deep learning models have become ubiquitous in industry and academia alike. Deep neural networks can solve some of the most complex pattern-recognition problems today, but come with the price of massive compute and memory requirements. This makes the problem of deploying such large-scale neural networks challenging in resource-constrained mobile edge computing platforms, specifically in mission-critical domains like surveillance and healthcare. To solve this, a promising solution is to split resource-hungry neural networks into lightweight disjoint smaller components for pipelined distributed processing. At present, there are two main approaches to do this: semantic and layer-wise splitting. The former partitions a neural network into parallel disjoint models that produce a part of the result, whereas the latter partitions into sequential models that produce intermediate results. However, there is no intelligent algorithm that decides which splitting strategy to use and places such modular splits to edge nodes for optimal performance. To combat this, this work proposes a novel AI-driven online policy, SplitPlace, that uses Multi-Armed-Bandits to intelligently decide between layer and semantic splitting strategies based on the input task's service deadline demands. SplitPlace places such neural network split fragments on mobile edge devices using decision-aware reinforcement learning for efficient and scalable computing. Moreover, SplitPlace fine-tunes its placement engine to adapt to volatile environments. Our experiments on physical mobile-edge environments with real-world workloads show that SplitPlace can significantly improve the state-of-the-art in terms of average response time, deadline violation rate, inference accuracy, and total reward by up to 46, 69, 3 and 12 percent respectively.

关键词： Mobile edge computing   distributed computing   NOMA   millimeter wave communication   energy efficiency  

摘要： In this paper, we investigate the cooperation of idle computation resources of nearby mobile devices in mobile edge computing (MEC) systems, in which each mobile device jointly offloads computation tasks to a MEC node and a nearby mobile device by employing non-orthogonal multiple access (NOMA) in a millimeter-wave (mmWave) heterogeneous network. In this setup, the nearby device acts as a helper by performing local computation and offloading data simultaneously to the MEC system. We formulate an optimization problem for joint taSk assignmenT, poweR allOcation and Node Grouping (STRONG) aiming to minimize the energy consumption of devices (i.e., user and helper devices). To tackle this problem, we present a two-step solution. First, we adopt a low complexity search-based algorithm for both helper and MEC server selection. Next, considering the non-convex nature of the energy minimization problem, we develop algorithms that provide sub-optimal solutions for power allocation to the helper and MEC server, as well as the offloading task ratios between them. Numerical results are provided to validate the effectiveness of our proposed algorithms. The results not only validate the efficiency of our approach but also demonstrate the superiority of our cooperative NOMA-based MEC scenario compared to methods without cooperation and other cooperation-based scenarios.

关键词： Mobile edge computing   service caching   digital twin   deep reinforcement learning   task dependency  

摘要： The combination of Mobile Edge Computing (MEC) and Digital Twin (DT) is anticipated to enhance the quality of mobile application services in the 6G era. However, current research often overlooks service caching and task dependency, which may deteriorate system performance. Moreover, Edge Servers (ESs) have limited computing resources and caching capacities, which require collaboration to meet user demands. To address these challenges, we propose a DT-empowered MEC architecture that supports Mobile Users (MUs) offloading dependency-aware tasks, while considering service caching and edge collaboration. The objective is to jointly optimize computation offloading and resource allocation to minimize the system's energy consumption. Hence, this problem can be formulated as a Mixed Integer Non-linear Programming (MINLP) problem and addressed by utilizing the Asynchronous Advantage Actor-Critic (A3C)-based method. Extensive simulation results demonstrate that our approach outperforms other benchmark algorithms under various scenarios, significantly reducing energy consumption.

关键词： C-RAN   deep reinforcement learning   DRL   mobile edge computing   Q-learning   resource allocation   task offloading  

摘要： Mobile applications often demand computationally heavy resources to attain high quality, on the other hand, running all programs on a single mobile device still consumes a lot of energy and generates a lot of delay. By breaking a single operation into distinct components, partial computational offloading may be intelligently investigated in mobile edge computing (MEC) to minimise energy consumption and service latency of mobile device. Some of the components run on the mobile device itself, while the rest are sent to a mobile edge server. Current task offloading systems, primarily focus on average-based performance indicators, failing to satisfy the deadline constraints. This paper offers a deep reinforcement learning (DRL) empowered energy efficient task offloading method, to optimise the reward under task deadline constraints. Simulation results show that the proposed technique can efficiently transfer traffic from cloud-radio access networks to next-generation node B, while also saving energy by turning off underutilised baseband processing units.

关键词： Mobile edge computing   edge server side   game   multi server multi task offloading   deadline-aware  

摘要： In this paper, a novel task offloading architecture called Flex-MEC is proposed, which achieves efficient task allocation and scheduling (TAS) between MEC servers. By adding metadata before task data, we redesign the offloading process in Flex-MEC, the TAS planning can be conducted without finishing the task data receiving. Once planning is done the task data can be directly forwarded to the allocated server and executed. This reduces latency compared to the traditional way of transmitting, planning, forwarding and executing sequentially. For TAS planning, a multi-server multi-task allocation and scheduling (MMAS) problem is formulated to maximize the MEC system profit. The MMAS problem is proven as an NP-complete problem, thus is challenging to solve. Then, a distributed scheme and a centralized scheme are proposed to solve the MMAS problem with low complexity. In the distributed scheme, the MMAS problem is converted into a non-cooperative game and the existence of Nash Equilibrium (NE) is proven and a low complexity response update algorithm is proposed to converge to NE. And the centralized scheme is based on a greedy idea and runs on a MEC controller in a centralized way. Verified by experiments, these two schemes can achieve better performance than compared schemes.

关键词： Mobile edge computing  

摘要： Background: With the rapid development of artificial intelligence, the traditional cloud computing model has serious bandwidth and energy consumption problems when storing and pro-cessing massive amounts of raw data. To address this problem, recent patents have investigated methods for intelligent task offloading and allocation in mobile edge computing. Objective: A Directed Acyclic Graph (DAG) task unloading model is established to reduce the problem of task delay and energy consumption in edge networks. At the same time, Modified Tuna Swarm Optimization (MTSO) is used to improve execution efficiency. Methods: Firstly, this paper integrates (i) inter-task dependencies;(ii) heterogeneity of computing re-sources in the edge network;and (iii) interference of wireless channels in the edge network. A DAG task offloading model is developed to reduce latency and energy consumption. The end users are guided to offload their tasks/sub-tasks to the most appropriate servers in the edge network, thus minimizing the end-to-end latency of all tasks in the edge network. Secondly, the MTSO algorithm is used to coordinate the dependencies and priorities of subtasks to improve execution efficiency. Results: The experimental results show that when the number of users including subtasks is 10, the final edge server utilization rate is as high as 92%. A more fine-grained segmentation scheme can reduce the average delay of tasks and improve the utilization rate of edge servers. Conclusion: The approach proposed in this paper reduces the end-to-end latency and improves resource utilization in complex applications under the premise of ensuring task dependency. It will relieve the pressure on the cloud and has certain engineering application value. © 2023 Bentham Science Publishers.

关键词： energy consumption   fifth -generation   latency   mobile edge computing   Multimedia tasks   network selection   service placement   surveillance   video conferencing   traffic monitoring)   latency -critical (automated vehicles   robotic  

摘要： In the current era of technology, the utilization of tablets and smart phones plays a major role in every situation. As the numbers of mobile users increase, the quality of service (QoS) and quality of experience (QoE) are facing the greater challenges. Thus, this can significantly reduce the latency and optimize the power consumed by the tasks executed locally. Most of the previous works are focused only on quality optimization in the dynamic service layouts. However, they ignored the significant impact of accurate access network selection and perfect service placement. This article performs the detailed survey of various MEC approaches with service provision and adoption. The survey also provides the analysis of various approaches for optimizing the QoS parameters and MEC resources. In this regarding, the survey classifies the approaches based on service placement, network selection, QoS, and QoE parameters, and resources such as latency, energy, bandwidth, memory, storage, and processing.

关键词： Mobile edge computing   ultra-dense network   contextual bandit learning   Lyapunov optimization  

摘要： Integrating mobile edge computing (MEC) in ultra-dense network (UDN) is a key enabler to meet the service demand by allowing smart devices to perform uninterrupted task offloading via densely deployed MEC servers. In most cases, the smart devices randomly move around the whole network. Consequently, the popular "MEC-centralized decision" offloading approach could be inapplicable, as joint decision-making among multiple MEC servers becomes difficult due to time synchronization and information exchange overhead. In this paper, we take a user-centric approach to minimize a long-term delay for a given task duration under a price budget constraint. To address this problem, we develop a novel contextual sleeping bandit learning (CSBL) algorithm, which integrates contextual information and sleeping characteristic to accelerate the learning convergence and leverage Lyapunov optimization to deal with the price budget constraint. Furthermore, we extend to a multiple offloading scenario where multiple MEC servers can be selected in each offloading round and propose a CSBL-multiple (CSBL-M) algorithm to address the exponential increase of the offloading selections. For both CSBL and CSBL-M, we derive the upper bounds of learning regret and provide rigorous proofs that they asymptotically approach the Oracle algorithm within bounded deviations for finite task duration. Simulation results illustrate that our proposed algorithms significantly outperform existing algorithms in both single offloading and multiple offloading scenario.