关键词： Mobile edge computing  

摘要： Edge Intelligence (EI) has been instrumental in delivering real-time, localized services by leveraging the computational capabilities of edge networks. The integration of Large Language Models (LLMs) empowers EI to evolve into the next stage: Edge General Intelligence (EGI), enabling more adaptive and versatile applications that require advanced understanding and reasoning capabilities. However, systematic exploration in this area remains insufficient. This survey delineates the distinctions between EGI and traditional EI, categorizing LLM-empowered EGI into three conceptual systems: centralized, hybrid, and decentralized. For each system, we detail the framework designs and review existing implementations. Furthermore, we evaluate the performance and throughput of various Small Language Models (SLMs) that are more suitable for deployment on edge devices. This survey provides researchers with a comprehensive vision of EGI, offering insights into its vast potential and establishing a foundation for future advancements in this rapidly evolving field. Copyright © 2024, The Authors. All rights reserved.

关键词： Mobile edge computing  

摘要： Recent advances in Deep Neural Networks (DNNs) have demonstrated outstanding performance across various domains. However, their large size is a challenge for deployment on resource-constrained devices such as mobile, edge, and IoT platforms. To overcome this, a distributed inference setup can be used where a small-sized DNN (initial few layers) can be deployed on mobile, a bigger version on the edge, and the full-fledged on the cloud. A sample that has low complexity (easy) could be then inferred on mobile, that has moderate complexity (medium) on edge, and higher complexity (hard) on the cloud. As the complexity of each sample is not known beforehand, the following question arises in distributed inference: how to decide complexity so that it is processed by enough layers of DNNs. We develop a novel approach named DIMEE that utilizes Early Exit (EE) strategies developed to minimize inference latency in DNNs. DIMEE aims to improve the accuracy, taking into account the offloading cost from mobile to edge/cloud. Experimental validation on GLUE datasets, encompassing various NLP tasks, shows that our method significantly reduces the inference cost (> 43%) while maintaining a minimal drop in accuracy ( © 2024, CC BY.

关键词： Virtual reality   Adaptive transmission   Edge cache   Buffer management   5G   Mobile edge computing  

摘要： Virtual Reality(VR)is a key industry for the development of the digital economy in the *** VR has advantages in terms of mobility,lightweight and cost-effectiveness,which has gradually become the mainstream implementation of *** this paper,a mobile VR video adaptive transmission mechanism based on intelligent caching and hierarchical buffering strategy in Mobile Edge Computing(MEC)-equipped 5G networks is proposed,aiming at the low latency requirements of mobile VR services and flexible buffer management for VR video adaptive *** support VR content proactive caching and intelligent buffer management,users’behavioral similarity and head movement trajectory are jointly used for viewpoint *** tile-based content is proactively cached in the MEC nodes based on the popularity of the VR ***,a hierarchical buffer-based adaptive update algorithm is presented,which jointly considers bandwidth,buffer,and predicted viewpoint status to update the tile chunk in client ***,according to the decomposition of the problem,the buffer update problem is modeled as an optimization problem,and the corresponding solution algorithms are ***,the simulation results show that the adaptive caching algorithm based on 5G intelligent edge and hierarchical buffer strategy can improve the user experience in the case of bandwidth fluctuations,and the proposed viewpoint prediction method can significantly improve the accuracy of viewpoint prediction by 15%.

关键词： Mobile edge computing   Workflow scheduling   Security   Remora optimization algorithm   Feedback artificial tree  

摘要： The rapid advancement of mobile communication technology and devices has greatly improved our way of life. It also presents a new possibility that data sources can be used to accomplish computing tasks at nearby locations. Mobile Edge Computing (MEC) is a computing model that provides computer resources specifically designed to handle mobile tasks. Nevertheless, there are certain obstacles that must be carefully tackled, specifically regarding the security and quality of services in the workflow scheduling over MEC. This research proposes a new method called Feedback Artificial Remora Optimization (FARO)-based workflow scheduling method to address the issues of scheduling processes with improved security in MEC. In this context, the fitness functions that are taken into account include multi-objective, such as CPU utilization, memory utilization, encryption cost, and execution time. These functions are used to enhance the scheduling of workflow tasks based on security considerations. The FARO algorithm is a combination of the Feedback Artificial Tree (FAT) and the Remora Optimization Algorithm (ROA). The experimental findings have demonstrated that the developed approach surpassed current methods by a large margin in terms of CPU use, memory consumption, encryption cost, and execution time, with values of 0.012, 0.010, 0.017, and 0.036, respectively.

关键词： Federated learning   Meta-learning   Mobile edge computing   Resource allocation   Task offloading  

摘要： MEC and IoT are rapidly expanding technologies that offer numerous oppor-tunities to enhance efficiency and application performance. However, the huge volume of data generated by IoT devices, coupled with computational and latency constraints, poses data processing challenges. To address this within the MEC architecture, deploying computing servers at the network edge near IoT devices is a promising approach. This reduces latency and traffic load on the core network while improving the user experience. However, offloading com-putations task from IoT devices to MEC servers and efficiently allocating computing resources is a complex problem. IoT tasks may have specific requirements in terms of latency, bandwidth and energy efficiency, while computing resources and capacities maybe limited or shared between several users. We propose an approach called FedMeta2Ag, which we evaluate using the MNIST database. With 20 epochs, the training accuracy reached 91.5%, while the test accuracy achieved 92.0%. Performance consistently improved during the initial 20 iterations and gradually stabilized thereafter. Additionally, we compared the performance of our proposed model with existing methods, finding that our approach outperforms existing models in predicting performance more accurately. Thus, this approach effectively meets the demanding performance requirements of wireless communication systems. © 2024, Institute of Advanced Engineering and Science. All rights reserved.

关键词： Servers   Task analysis   Resource management   Cost accounting   Approximation algorithms   Computational modeling   Multitasking   Mobile edge computing   truthfulness   resource allocation   multi-minded   algorithm design  

摘要： In the context of mobile edge computing (MEC), it can be quite challenging to provide and allocate multiple resources from heterogeneous MEC servers for remote execution of tasks of mobile devices (MDs). However, obtaining more resources for tasks can save time and effort, and MDs are willing to pay higher prices for more resources. Motivated by these challenges, this study addresses the problem of heterogeneous resource allocation with multi-minded (HRAM) in MEC. Unlike other studies that have focused on MDs with single-minded demands, this study considers the multi-attribute demands of MDs. It considers cases where an MD declares multiple demands, each with a different bid attached to it. This multi-minded approach gives MDs more flexibility and control over the resources they receive, leading to increased satisfaction and better outcomes. However, MDs are self-interested and can misreport their preferences, which results in a low utilization rate of heterogeneous resources. Therefore, we have formulated this problem in an auction-based setting, and our objective is to allocate heterogeneous resources of heterogeneous MEC servers to maximize social welfare, which is the sum of MDs' valuations. We demonstrate that the HRAM problem is NP-hard, proposing a randomized mechanism consisting of a second-price auction and a fixed-price auction. This study claims that the proposed randomized mechanism is universally truthful and that the MDs have no desire to misreport their demands. Additionally, we analyze the randomized mechanism's time complexity and approximation ratio and present the experimental results to support our claim. We demonstrate that the randomized mechanism performs excellently in different environments, benefiting MDs and edge cloud providers.

关键词： Resource management   Optimization   Task analysis   NOMA   Vehicle dynamics   Servers   Energy consumption   Mobile edge computing   non-orthogonal multiple access   resource allocation   Lyapunov optimization   vehicular networks  

摘要： Mobile Edge Computing (MEC) has envisioned to be a promising technology to provide more efficient services for computation-intensive but delay-sensitive onboard mobile services. In this paper, the Non-Orthogonal Multiple Access (NOMA) technology is applied in a vehicular edge computing network, in which vehicular users (VUs) can offload partial computation tasks to MEC servers over wireless channels for remote execution. In this network, an optimization problem for the long-term energy consumption of the system is presented and aims to minimize it by jointly optimizing the Successive Interference Cancellation (SIC) ordering of NOMA, the VUs' transmit power for computation offloading, and computation resource allocation of the MEC server. To deal with the intractable long-term optimization problem, we first transform it into an equivalent instantaneous form based on the Lyapunov optimization theory. Since the transformed problem is still highly non-convex, we further decompose it into the interactive resource allocation and SIC ordering sub-problems. For the resource allocation sub-problem, we exploit its convexity through the transformation and reparameterization, and derive the optimal solution in accordance with the Karush-Kuhn-Tucker (KKT) conditions and the gradient descent algorithm. After that, we propose a low-complexity algorithm by leveraging the Tabu search to obtain the sub-optimal SIC ordering. Simulation results validate the effectiveness of the proposed algorithm and the superiority of NOMA compared to Frequency Division Multiple Access (FDMA).

关键词： Mobile edge computing   Task scheduling   Reinforcement deep learning   DAG task   Internet of Things   Data analysis  

摘要： As the deployment of Internet of Things (IoT) devices becomes more widespread, the demand for data analysis services is also increasing in both range and volume. Despite the increasing demand for services due to the rise of IoT devices, efficiently processing latency-sensitive data analysis tasks (DATs) remains a significant challenge, especially in areas where communication infrastructure is limited or unavailable. Unmanned aerial vehicles (UAVs) can enhance communication coverage and quality by leveraging their flexible deployment characteristics, particularly in areas where network coverage is limited for IoT devices. UAVs can provide edge computing services while simultaneously offering network coverage, making them a valuable asset for improving communication in such areas. In this paper, we propose an Mobile Edge Computing (MEC) system that utilizes multiple UAVs equipped with edge servers to offer latency-sensitive analytical services to IoT devices on the ground. However, traditional task scheduling algorithms are challenging to adapt to dynamic and complex edge network environments, particularly for scheduling tasks with dependencies. To address this challenge, we employ deep reinforcement learning (DRL) to develop Directed Acyclic Graph (DAG) task scheduling algorithms and UAV deployment optimization algorithms. Our algorithm enables us to obtain optimal scheduling and deployment adjustment strategies in dynamic and changing environments. Simulation experiments demonstrate that in a MEC system comprising of multiple UAVs, our algorithm can swiftly converge to the optimal value, resulting in a significant reduction in DAT response time and cluster energy consumption compared to baseline algorithms.

关键词： Sensitive information   Privacy protection   Computation offloading   Mobile edge computing   Deep reinforcement learning  

摘要： With the development of fifth -generation mobile communication technology and artificial intelligence, resource -intensive applications on mobile terminal devices process tasks by offloading them to servers. However, the presence of untrustworthy edge servers poses a threat to user terminal (UT) privacy. Therefore, this paper proposes an efficient computation offloading architecture based on personalized privacy protection to address the privacy leakage problem during computation offloading. In this architecture, we design a personalized privacy -sensitive level calculation method to achieve hierarchical protection of personal information. This method calculates based on users' demands for four indicators: integrity, confidentiality, availability, and real-time performance of tasks at different times and locations. An improved deep deterministic policy gradient (DDPG) method is proposed to resolve the optimization solution. The method solves the overestimation problem in the original DDPG algorithm and utilizes an optimal behavior selection mechanism with privacypreserving constraints. Simulation experiments show that the proposed scheme increases the weighted sum of latency and energy consumption by an average of 29.32%, while effectively protecting user privacy.

关键词： Millimeter wave communication   Optical fiber networks   Optical fiber communication   Costs   Optical fibers   Backhaul networks   Reliability   Mobile edge computing   edge network deployment   millimeter-wave communication   fronthaul network   cost efficiency  

摘要： Mobile edge computing (MEC) and millimeter-wave (mmWave) communication are promising techniques for future cellular networks. MEC enables latency-critical tasks offloading at the network edge, while mmWave provides an abundant spectrum for gigabit-per-second data transmission. Dense deployment of remote radio units (RRUs) is necessary due to high mmWave signal path loss, and hence limiting the deployment cost becomes a prime network design factor. Our work considers that RRUs are deployed to provide mmWave access and to offload computation requests to edge servers (ESs) via fronthaul links. We propose an edge network (EN) deployment problem by jointly optimizing the mmWave access and fronthaul networks. Converged fiber and in-band mmWave techniques are utilized for flexible fronthaul links deployment and cost reduction. The deployed EN is expected to fulfill coverage, reliability and latency requirements of ultra-reliable low-latency (uRLLC) services. We formulate the optimization problem as an integer linear program (ILP) and propose a multi-objective evolutionary algorithm to solve the problem. The numerical results demonstrate that our proposed algorithm can achieve close-to-optimal solutions compared with the ILP formulation. We also comparatively evaluate the deployment costs under different EN settings and show that our algorithm provides up to 20.3% cost savings compared to non-converged solutions.