关键词： Mobile edge computing   digital twin   task offloading   service caching   multi-agent reinforcement learning   graph attention network  

摘要： Mobile edge computing (MEC) enables various services to be cached in close proximity to the user equipments (UEs), thereby reducing the service delay of many emerging applications. However, the limitation of storage, computation, and radio resources, the dynamics of the decentralized MEC environment, and the complex spatial relationships of service request types and wireless network states between edge nodes make it difficult to realize efficient edge computing services. To address these challenges, this paper integrates the digital twin (DT) technology with a multi-cell MEC network to study an intelligent cooperative task offloading and service caching scheme, aiming at maximizing a quality of services (QoE)-based system utility. Specifically, we first construct a digital twin edge network (DITEN) to reflect the physical MEC system in real-time and provide data for training. With the help of DT technology, it is easy to access data resources in the DITEN to improve the simulation ability and reduce the communication cost. Then, we propose a graph attention-based multi-agent reinforcement learning (GatMARL) algorithm to learn the optimal task offloading and service caching strategies in the DITEN. The GatMARL employs a graph attention-based value decomposition network to capture the potential spatial relationships between edge nodes to learn better attentive cooperation policy. Simulation results demonstrate that the proposed GatMARL algorithm exhibits an effective performance improvement compared with state-of-the-art benchmarks.

关键词： Ant Colony Optimization   Autonomous vehicles   Dynamic Source Dynamic Destination   Meta-heuristic   Mobile Edge Computing   Optimization   Shortest path estimation   Swarm intelligence  

摘要： In the present literature, various algorithms are available for computing the shortest path between two objects. The maximum number of these algorithms compute the shortest path either between two static objects or one static object and one dynamic object. This article presents an insight to integrated Mobile Edge Computing (MEC) based smart devices for tracking mobile rogue objects based on dynamic source and dynamic destination optimal cost estimation. This device considers any two mobile objects to estimate the shortest path between them. The proposed Ant Colony Optimization (ACO) based algorithm considers the property of dead-end removal and nth path exploration with efficient self-loop removal strategy. To review the performance of the proposed algorithm, experimentations are carried out and compared with several well-established shortest cost estimation techniques available in the literature - Floyd Warshall, Bellman Ford, Dijkstra, A* algorithms and the only dynamic shortest path algorithm. The detailed algorithmic comparisons clearly indicate the superiority of the proposed one over the existing dynamic and present state-of-the-art shortest path estimation methodologies.

关键词： Mobile edge computing  

摘要： Large language models (LLMs), which have shown remarkable capabilities, are revolutionizing AI development and potentially shaping our future. However, given their multimodality, the status quo cloud-based deployment faces some critical challenges: 1) long response time;2) high bandwidth costs;and 3) the violation of data privacy. 6G mobile edge computing (MEC) systems may resolve these pressing issues. In this article, we explore the potential of deploying LLMs at the 6G edge. We start by introducing killer applications powered by multimodal LLMs, including robotics and healthcare, to highlight the need for deploying LLMs in the vicinity of end users. Then, we identify the critical challenges for LLM deployment at the edge and envision the 6G MEC architecture for LLMs. Furthermore, we delve into two design aspects, i.e., edge training and edge inference for LLMs. In both aspects, considering the inherent resource limitations at the edge, we discuss various cutting-edge techniques, including split learning/inference, parameter-efficient fine-tuning, quantization, and parameter-sharing inference, to facilitate the efficient deployment of LLMs. This article serves as a position paper for thoroughly identifying the motivation, challenges, and pathway for enabling LLMs at the 6G edge. Copyright © 2023, The Authors. All rights reserved.

关键词： adaptive proximate computing   mobile edge computing   mobile resource augmentation architecture   neuro-fuzzy hybrid framework   task offloading   web service-based IoT framework  

摘要： Mobile devices play a vital role in people's day-to-day activities and are essential for communication, accessing Internet resources, entertainment, and so forth. In most cases, the performance of mobile applications is restricted due to the inadequate resources of mobile specifications such as controlled battery power, predetermined storage, and limited processing competence. Thus to improve the processing efficiency of resource-constrained mobile devices, this research proposes a model developed on offloading technique based on the recent literature observations which transfer the resource-consuming tasks from mobile devices to proximate computing entities. This generic architecture aiming for resource augmentation is formulated with five fundamental components including a mobile device, offloading engine, resource augmentation engine, scheduler, and synchronizer. The offloading engine identifies the resource-intensive tasks that need to be executed on external entities using soft computing techniques such as neural network training algorithms, fuzzy logic, and neuro-fuzzy logic processing. The augmentation engine chooses feasible edge computing entities such as Arduino, Raspberry PI controller, and fog devices. The scheduler prioritizes the resource-consuming tasks for offloading based on their importance. The synchronizer coordinates all the central components by updating the execution status of tasks at regular intervals of time. Further extension of this research work, based on the proposed architecture three resource augmentation frameworks are developed namely (a) an adaptive proximate computing framework (b) a web service-based IoT framework, and (c) a neuro-fuzzy hybrid framework. Moreover, these frameworks are realized through the development of resource-efficient intelligent edge computing IoT mobile apps namely (a) an inventory monitoring app (b) a lecture recording app, and (c) an intelligent transport app. The performance of these three resource augme

关键词： Mobile edge computing   Radio frequency energy harvesting   Non-orthogonal multiple access   Multiple users   IIoT   Optimization  

摘要： In this day and age, the Industrial Internet of Things (IIoT) has been considered to revolutionize industrial manufacturing by capturing and accessing massive data sources with incredible speed and efficiency than before. Combined with it, Mobile Edge Computing (MEC) is a comprehensive Digital Transformation tendency to solve the problems Cloud computing faces. However, the fundamental challenges of energy and latency make deploying IIoT MEC networks difficult. Accordingly, this paper considers the efficient design of time allocation for successful computation probability (SCP) maximization for multiple energy-constrained mobile devices (MD) and multiple antennas access point (AP) in uplink radio frequency energy harvesting (RF EH) non-orthogonal multiple access (NOMA) IIoT network. Specifically, multiple MDs need to receive the energy and compute support of a MEC server placed in a multiple antenna wireless AP to complete the task immediately. Accordingly, a four-phase communication protocol is proposed to ensure system performance. The system follows the cluster head (CH) scheme based on the channel state information (CSI) to harvest RF energy from the AP. To ensure the highest system performance, we propose two algorithms for determining the optimal EH time for two CHs: SCPM-GSS and SCPM-GA. In addition, we derive the closed-form expressions for the SCP of the system and each CH. Monte Carlo simulations are used to verify the results of the analysis. The numerical results demonstrate the effects of crucial system parameters of our proposed NOMA scheme with those of conventional orthogonal multiple access (OMA) schemes. Furthermore, the proposed optimization algorithms allow the system to avoid outages like the random parameters setting approach and improve the SCP by 3 to 30% compared to the fixed parameters set when the transmit power is low and medium.

关键词： Mobile edge computing   Object detection   Deep reinforcement learning   Task offloading  

摘要： With the development of communication technology and mobile edge computing (MEC), self-driving has received more and more research interests. However, most object detection tasks for self-driving vehicles are still performed at vehicle terminals, which often requires a trade-off between detection accuracy and speed. To achieve efficient object detection without sacrificing accuracy, we propose an end-edge collaboration object detection approach based on Deep Reinforcement Learning (DRL) with a task prioritization mechanism. We use a time utility function to measure the efficiency of object detection task and aim to provide an online approach to maximize the average sum of the time utilities in all slots. Since this is an NP-hard mixed-integer nonlinear programming (MINLP) problem, we propose an online approach for task offloading and resource allocation based on Deep Reinforcement learning and Piecewise Linearization (DRPL). A deep neural network (DNN) is implemented as a flexible solution for learning offloading strategies based on road traffic conditions and wireless network environment, which can significantly reduce computational complexity. In addition, to accelerate DRPL network convergence, DNN outputs are grouped by in-vehicle cameras to form offloading strategies via permutation. Numerical results show that the DRPL scheme is at least 10% more effective and superior in terms of time utility compared to several representative offloading schemes for various vehicle local computing resource scenarios.

关键词： adversarial deep learning   dynamic threshold   game-theoretical   IoT   mobile edge computing  

摘要： As mobile communications, the Internet, databases, distributed computing, and other technologies continue to develop, the Internet of Things (IoT) has emerged as prevalent technique. However, attacks on security and sensitive data in IoT occur frequently, and these attacks often evade intrusion detection systems strategically by mutating their traffic. To prevent security threats and sensitive data leakage, we propose a game approach based on adversarial deep learning to optimize a dynamic security threshold strategy. We introduce a mobile edge computing framework and utilize a game model to describe the adversarial interaction between the two participants. To solve the complexity of the game problem to gain dynamically randomized adversarial attacks, we present a column generation (CG) framework, which uses a feedforward neural network to quantify data flowing through IoT devices. Considering the limited resources of IoT devices, we calculate an optimal response to cyberattacks via a particle swarm optimization algorithm, aiming to reduce the false alarm rate. The adversarial dynamic threshold (ADT)-based column generation (CG-ADT) algorithm generates the set of detection threshold and the probability. Finally, we present the results of experiments conducted to demonstrate the effectiveness and robustness of the proposed dynamic threshold scheme for sensitive data security protection in IoT and its suitability for implementation in production systems.

关键词： Mobile edge computing  

摘要： Mobile edge computing (MEC) has been regarded as a promising approach to deal with explosive computation requirements by enabling cloud computing capabilities at the edge of networks. Existing models of MEC impose some strong assumptions on the known processing cycles and unintermittent communications. However, practical MEC systems are constrained by various uncertainties and intermittent communications, rendering these assumptions impractical. In view of this, we investigate how to schedule task offloading in MEC systems with uncertainties. First, we derive a closed-form expression of the average offloading success probability in a device-to-device (D2D) assisted MEC system with uncertain computation processing cycles and intermittent communications. Then, we formulate a task offloading maximization problem (TOMP), and prove that the problem is NP-hard. For problem solving, if the problem instance exhibits a symmetric structure, we propose a task scheduling algorithm based on dynamic programming (TSDP). By solving this problem instance, we derive a bound to benchmark sub-optimal algorithm. For general scenarios, by reformulating the problem, we propose a repeated matching algorithm (RMA). Finally, in performance evaluations, we validate the accuracy of the closed-form expression of the average offloading success probability by Monte Carlo simulations, as well as the effectiveness of the proposed algorithms. Copyright © 2023, The Authors. All rights reserved.

关键词： Mobile edge computing  

摘要： Extended reality-enabled Internet of Things (XRI) provides the new user experience and the sense of immersion by adding virtual elements to the real world through Internet of Things (IoT) devices and emerging 6G technologies. However, the computational-intensive XRI tasks are challenging for the energy-constrained small-size XRI devices to cope with, and moreover certain data requires centralized computing that needs to be shared among users. To this end, we propose a cache-assisted space-air-ground integrated network mobile edge computing (SAGIN-MEC) system for XRI applications, consisting of two types of edge servers mounted on an unmanned aerial vehicle (UAV) and low Earth orbit (LEO) equipped with cache and the multiple ground XRI devices. For system efficiency, the four different offloading procedures of the XRI data are considered according to the type of information, i.e., shared data and private data, as well as the offloading decision and the caching status. Specifically, the private data can be offloaded to either UAV or LEO, while the offloading decision of the shared data to the LEO can be determined by the caching status. With the aim of maximizing the energy efficiency of the overall system, we jointly optimize UAV trajectory, resource allocation and offloading decisions under latency constraints and UAV’s operational limitations by using the alternating optimization (AO)-based method along with Dinkelbach algorithm and successive convex optimization (SCA). Via numerical results, the proposed algorithm is verified to have the superior performance compared to conventional partial optimizations or without cache. Copyright © 2023, The Authors. All rights reserved.

关键词： Mobile edge computing   Device-free sensing   Blockchain   SDR   Fireworks algorithm  

摘要： Recent studies have shown that wireless signals can not only be used as communication medium for data transmission, but also can be employed for device-free sensing (DFS). However, the sensed raw big data processing needs large amount of processing resources. Moreover, the sensed data are usually privacy-sensitive, where blockchain can be employed to guarantee the privacy related issues, and however, blockchain tasks are usually also computation-intensive. To provide the processing capabilities for sensed big data processing and blockchain task executing in DFS, mobile edge computing (MEC) and cloud computing are essential enabling technologies. In this paper, we consider a multiuser mobile offloading network consisting a edge node (or fog node) and a remote cloud server. The tasks could be processed locally, or offloaded to the edge nodes, or further migrated to the cloud relayed by the edge node. We formulate the offloading problem as the joint optimization of task offloading decision making of all the users, the computation resource allocation among the edge-executing applications, and radio resource assignment among all the remote-processing applications, aiming to minimize the maximum weighted cost of all the users. It is demonstrated that the problem is NP-hard. To tackle this challenge, we decoupled the problem into subproblems, where offloading decisions are obtained using semi-definite relaxation (SDR), and next, a swarm intelligence algorithm, i.e., fireworks algorithm, is adopted in radio resource allocation. Simulation results exhibit that as a result of the collaboration of the collaborate of edge and cloud, the proposed joint algorithm could achieves nearly optimal performance in the aspects of energy consumption and delay compared with other benchmark algorithms.