关键词： Mobile edge computing  

摘要： Multi-Access Edge Computing (MEC) emerged as a viable computing allocation method that facilitates offloading tasks to edge servers for efficient processing. The integration of MEC with 5G, referred to as 5G-MEC, provides real-time processing and data-driven decision-making in close proximity to the user. The 5G-MEC has gained significant recognition in task offloading as an essential tool for applications that require low delay. Nevertheless, few studies consider the dropped task ratio metric. Disregarding this metric might possibly undermine system efficiency. In this paper, the dropped task ratio and delay has been minimized in a realistic 5G-MEC task offloading scenario implemented in NS3. We utilize Mixed Integer Linear Programming (MILP) and Genetic Algorithm (GA) to optimize delay and dropped task ratio. We examined the effect of the number of tasks and users on the dropped task ratio and delay. Compared to two traditional offloading schemes, First Come First Serve (FCFS) and Shortest Task First (STF), our proposed method effectively works in 5G-MEC task offloading scenario. For MILP, the dropped task ratio and delay has been minimized by 20% and 2ms compared to GA. © 2024, CC BY-NC-ND.

关键词： Mobile edge computing  

摘要： Federated Learning is a promising approach for learning from user data while preserving data privacy. However, the high requirements of the model training process make it difficult for clients with limited memory or bandwidth to participate. To tackle this problem, Split Federated Learning is utilized, where clients upload their intermediate model training outcomes to a cloud server for collaborative server-client model training. This methodology facilitates resource-constrained clients' participation in model training but also increases the training time and communication overhead. To overcome these limitations, we propose a novel algorithm, called Hierarchical Split Federated Learning (HierSFL), that amalgamates models at the edge and cloud phases, presenting qualitative directives for determining the best aggregation time-frames to reduce computation and communication expenses. By implementing local differential privacy at the client and edge server levels, we enhance privacy during local model parameter updates. Our experiments using CIFAR-10 and MNIST datasets show that HierSFL outperforms standard FL approaches with better training accuracy, training time, and communication-computing trade-offs. HierSFL offers a promising solution to mobile edge computing's challenges, ultimately leading to faster content delivery and improved mobile service quality. Copyright © 2024, The Authors. All rights reserved.

关键词： Mobile edge computing  

摘要： Mobile edge computing offers a myriad of opportunities to innovate and introduce novel applications, thereby enhancing user experiences considerably. A critical issue extensively investigated in this domain is efficient deployment of Service Function Chains (SFCs) across the physical network, spanning from the edge to the cloud. This problem is known to be NPhard. As a result of its practical importance, there is significant interest in the development of high-quality sub-optimal solutions. In this paper, we consider this problem and propose a novel near-optimal heuristic that is extremely efficient and scalable. We compare our solution to the state-of-the-art heuristics and to the theoretical optimum. In our large scale evaluations, we use realistic topologies which are previously reported in the literature. We demonstrate that the execution time offered by our solution grows slowly as the number of Virtual Network Function (VNF) forwarding graph embedding requests grows, and it handles one million requests in slightly more than 20 seconds for 100 nodes and 150 edges physical topology. © 2024, CC BY-NC-ND.

关键词： Edge server allocation   Mobile edge computing   Workload balance   Fitness dependent optimizer   Access delay  

摘要： Due to the speedy development of mobile communication devices, the traditional cloudlet computing networks struggle to manipulate the huge collected data from these devices. Mobile computing has been developed to overcome the access delay (AD) and the workload balance (WB) in the traditional cloudlet networks by transferring the computing process from the remote servers in the cloudlet to the edge servers (ESs) allocated closer to the mobile users. The searching for the optimal place to allocate the ESs in mobile edge computing is the main challenge and it considers an NP-hard problem. In this work, we propose a new objective function with threefold objectives, the AD between base stations and ESs, the WB among various controlled ESs, and the energy consumption (EC) of ESs. Therefore, we formulate the edge server allocation problem as a multi-objective optimization problem that requires an efficient optimizer algorithm for solving it. To minimize the proposed objective function, we present an effective fitness-dependent optimizer (EFDO) algorithm and test it on Shanghai Telecom's BS dataset. To investigate the efficiency of the proposed EFDO algorithm, we compare it against seven algorithms taken from literature (e.g., K-means, Random, TopFirst, PSO, CSA, Jaya, and JS). The numerical results verified the superiority of the proposed algorithm in terms fitness function reached up to 14.84%, 18.56%, 17.28%, and 13.48% when compared with PSO, CSA, Jaya, and JS, respectively with various number of base stations and edge servers. Although k-means has been achieved the least average AD among compared algorithms which considered only the distance between the BS and ES, the proposed algorithm has achieved the superior results in WB ranged from 12 to 72% when compared against other algorithms. In addition, it has gained the least average EC among the compared algorithms.

关键词： Lentinula Edodes logs   Contamination detection   Mobile edge computing   Cloud computing   Small object detection  

摘要： A small object Lentinus Edodes logs contamination detection method (SRW-YOLO) based on improved YOLOv7 in edge-cloud computing environment was proposed to address the problem of the difficulty in the detection of small object contaminated areas of Lentinula Edodes logs. First, the SPD (space-to-depth)-Conv was used to reconstruct the MP module to enhance the learning of effective features of Lentinula Edodes logs images and prevent the loss of small object contamination information, and improve the detection reliability of resource-limited edge devices. Meanwhile, RepVGG was introduced into the ELAN structure to improve the efficiency and accuracy of inference on the contaminated regions of Lentinula Edodes logs through structural reparameterization. This enables models to run more efficiently in mobile edge computing environments while reducing the burden on cloud computing servers. Finally, the boundary regression loss function was replaced with the WIoU (Wise-IoU) loss function, which focuses more on ordinary-quality anchor boxes and makes the model output results more accurate. In this study, the measures of Precision, Recall, and mAP@0.5 reached 97.63%, 96.43%, and 98.62%, respectively, which are 4.62%, 3.63%, and 2.31% higher compared to those for YOLOv7. Meanwhile, the SRW-YOLO model detects better compared with the current advanced one-stage object detection model, providing an efficient, accurate and practical small object detection solution in mobile edge computing environments and cloud computing scenarios.

关键词： Mobile edge computing   Artificial intelligence   Knowledge graph   Natural language processing  

摘要： As the demand for edge services intensifies, text, being the most common type of data, has seen a significant expansion in data volume and an escalation in processing complexity. Furthermore, mobile edge computing (MEC) service systems often faces challenges such as limited computational capabilities and difficulties in data integration, requiring the development and implementation of more efficient and lightweight methodologies for text data processing. To swiftly extract and analysis vital information from MEC text data, an automatic generation scheme of multi-document text summarization based on knowledge graph is proposed in this paper, named KGCPN. For the text data from MEC devices and applications, the natural language processing technology is used to execute the data pre-processing steps, which transforms the MEC text data into a computationally tractable and semantically comprehensible format. Then, the knowledge graph of multi-document text is constructed by integrating the relationship paths and entity descriptions. The nodes and edges of the knowledge graph serve to symbolize the semantic relationships within the text, and the Graph Convolution Neural network (GCN) is used to understand the text and learn the semantic representation. Finally, a pointer-generator network model accepts the encoding information from GCN and automatically generate a general text summarization. The experimental results indicate that our scheme can effectively facilitate the smart pre-processing and integration of MEC data.

关键词： Mobile edge computing   Deep learning   Application division   Energy conserving computation   Partial offloading   Energy efficient offloading  

摘要： In mobile edge computing networks, total or partial computational offloading of delay sensitive and compute intensive applications to the nearby edge servers is a promising solution to reduce transmission delay and energy consumption of mobile nodes (MNs). However, in computational offloading of an application to edge server, considerations of energy consumption and time delay are not sufficient for the decision of minimum cost of application. In this article, a novel battery dependent cost selection strategy for computational offloading of an application capable for sequential execution of dependent sub tasks is proposed. The strategy considers current battery level of MN in the cost function for optimal selection of offloading policy based on the amount of data, computational resources, and radio resources of the server. Our comprehensive cost function takes into account all the said parameters, calculates all the costs for possible offloading policies, and chooses the policy with minimum cost from a huge dataset. The cost selection is energy efficient for low battery level and prioritizes faster execution for full battery level of MNs. A deep neural network is trained on the generated dataset to minimize the overhead of computations. Simulation results reveal that our proposed strategy outperforms the benchmark strategies in terms of deep neural network accuracy for different sizes of dataset, energy consumption, time delay, and cost for different sizes of applications.

关键词： Internet of Things   Autonomous aerial vehicles   Costs   Servers   Task analysis   Resource management   Optimization   Deep learning   intelligent reflecting surface   mobile edge computing   unmanned aerial vehicles  

摘要： With the blossom of Internet of Things (IoT) technology, the big data volumes raised by the large number of IoT devices have posed great burden on the communication and computing network. Considering the advantages of reflecting intelligent surface (RIS), mobile edge computing (MEC), and unmanned aerial vehicle (UAV), this article proposes a flying-RIS-assisted MEC system to assist offloading services to alleviate the ground computation burden in IoT. The UAV equipped with RIS is dispatched to fly over a specific area to assist in offloading the ground's computing mission to MEC server situated nearby access point (AP) in IoT. The cost of the IoT device is introduced as the weighted sum of the device's energy consumption and the time consumed to accomplish all computation tasks. To prolong the lifetime and guarantee the communication quality of the IoT devices, this article minimizes the sum cost of all IoT devices by collaboratively planning UAV's trajectory, scheduling the IoT devices' association with flying-RIS, and optimizing the phase shift value of each reflecting components. To address the posed nonconvex optimization challenge, a deep deterministic policy gradient (DDPG)-based algorithm is brought forward. Besides, the state and action normalization mechanism is used to ease up on the training difficulty. Finally, the numerical simulation results prove the superiority of the proposed algorithm compared with other benchmark schemes.

关键词： Mobile edge computing  

摘要： In the context of the rapid development of power IoT, the application of edge computing technology has become the key to improving the level of grid intelligence and enhancing the data processing capability. This paper initially designs the edge computing system for electric power IoT based on the edge computing model. Key-edge computing technologies are combined to process and analyze power IoT data in real-time. Simulation experiments have formed and verified an intelligent security monitoring system for electric power IoT using the LightGBM algorithm. The training convergence speed and effectiveness of this paper's scheme are better than Stroj's scheme, and this paper's scheme can increase the security of power IoT data through key generation and filter de-duplication. This paper's nodes have an average synchronization time of 9.25 ms. The 128MB data node has an upload time of 57143ms. The data sharing time is about 292~7489 ms faster than the comparison scheme, and in the data search phase, the time overhead of this paper's scheme is less than the comparison scheme. In summary, this paper's constructed security monitoring system can offer robust technical support for the advancement of intelligent, efficient, and omnipotent power in the Internet of Things. © 2024 Danni Liu, Shengda Wang, Cong Chen, Yan Zhang and Wei Zhao, published by Sciendo.

关键词： deep reinforcement learning   task caching   computational offloading   mobile edge computing  

摘要： Mobile edge computing extends the capabilities of the cloud to the edge to meet the latency performance required by new types of applications. Task caching reduces network energy consumption by caching task applications and associated databases in advance on edge devices. However, determining an effective caching strategy is crucial since users generate numerous repetitive tasks, but edge devices and storage resources are limited. We aimed to address the problem of highly coupled decision variables in dynamic task caching and computational offloading for multiuser multitasking in mobile edge computing systems. This paper presents a joint computation and caching framework with the aim of minimizing delays and energy expenditure for mobile users and transforming the problem into a form of reinforcement learning. Based on this, an improved deep reinforcement learning algorithm, P-DDPG, is proposed to achieve efficient computation offloading and task caching decisions for mobile users. The algorithm integrates a deep and deterministic policy grading and a prioritized empirical replay mechanism to reduce system costs. The simulations show that the designed algorithm performs better in terms of task latencies and lower computing power consumption.