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  

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： 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   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： mobile edge computing   location privacy   differential privacy   location perturbation   safe reinforcement learning  

摘要： Mobile edge computing (MEC) integration with 5G/6G technologies is an essential direction in mobile communications and computing. However, it is crucial to be aware of the potential privacy implications of task offloading in MEC scenarios, specifically the leakage of user location information. To address this issue, this paper proposes a location-privacy-preserved task offloading (LPTO) scheme based on safe reinforcement learning to balance computational cost and privacy protection. This scheme uses the differential privacy technique to perturb the user's actual location to achieve location privacy protection. We model the privacy-preserving location perturbation problem as a Markov decision process (MDP), and we develop a safe deep Q-network (DQN)-based LPTO (SDLPTO) scheme to select the offloading policy and location perturbation policy dynamically. This approach effectively mitigates the selection of high-risk state-action pairs by conducting a risk assessment for each state-action pair. Simulation results show that the proposed SDLPTO scheme has a lower computational cost and location privacy leakage than the benchmarks. These results highlight the significance of our approach in protecting user location privacy while achieving improved performance in MEC environments.

关键词： Computational offloading   deep reinforcement learning   mobile edge computing   resource allocation   trajectory optimization   unmanned aerial vehicles  

摘要： With the promising techniques and mobile applications of the Internet of Things (IoT) in the fifth-generation (5G) wireless networks, the mobile edge computing (MEC) paradigm has been widely utilized to support the massive data processing and meet the computation demand of mobile devices. However, the service coverage is limited by the static servers. Therefore, the unmanned aerial vehicles (UAVs) with high mobility are deployed as aerial base stations (BS) to assist ground users to offload the task and process the data on edge. In this article, we introduce a decentralized user allocation and dynamic service scheme to assign the UAV deployment for a multi-UAV MEC system, which incorporates the deep reinforcement learning (DRL) technology into a two-layer training framework. The continuous action, including the UAV trajectory and bit allocation of offloading, is first optimized in the lower layer, while the upper one concentrates on the discrete action space for the user allocation. In particular, we develop a constraint reward function that considers the communication quality in the lower layer to accomplish efficient communication. The well-trained neural network is embedded in the upper layer to provide rapid feedback for the upper environment. Experimental results demonstrate that the proposed approach achieves superior performance than the baseline methods in terms of the user energy consumption.

关键词： Augmented reality   deep reinforcement learning   mobile edge computing   task offloading  

摘要： With the popularity of mobile devices and the continuous advancement of mobile network technology, running online augmented reality (AR) on lightweight mobile devices is much more desirable than on heavy and expensive head-mounted devices that are difficult to satisfy users. Mobile edge computing can assist in supporting AR applications running on mobile devices, which copes with compute-intensive and delay-sensitive requirements. However, subject to the limited and heterogeneous edge resources, offloading tasks to edge devices is not easy, especially if the application requires multi-party interaction. It is challenging to develop a credible task placement scheme that satisfies user experience with flexible use of edge resources. This article focus on the task offloading placement problem for AR overlay rendering in multi-party mobile augmented reality system. We first present our observations about performance bottlenecks of edge devices and explain the necessity of splitting the AR overlay rendering pipeline. We then formulate a joint optimization problem of task placement decisions, aiming to maximize the user experience of quality and minimize the service cost. We develop a novel decision approach based on deep reinforcement learning (DRL) to address this complex problem. Finally, we verify the effectiveness and superiority of the proposed method through extensive evaluation experiments.

关键词： Internet of medical things   Mobile edge computing   Wireless body area network   Task offloading   Federated reinforcement learning  

摘要： The exponential proliferation of wearable medical apparatus and healthcare information within the framework of the Internet of Medical Things (IoMT) introduces supplementary complexities pertaining to the elevated Quality of Service (QoS) of intelligent healthcare in the forthcoming 6G era. Healthcare services and applications need ultra-reliable data transfer and processing with ultra-low latency and energy usage. Wireless Body Area Network (WBAN) and Mobile Edge Computing (MEC) technologies enabled IoMT to handle large amounts of data sensing, transmission, and processing while maintaining good QoS. Traditional frame aggregation (FA) systems in WBAN, on the other hand, create an excessive number of control frames during data transmission, resulting in significant latency and energy consumption, as well as a lack of flexibility. A Federated Reinforcement Learning (FRL) based TO Approach is recommended in this research. In the beginning, different types of service-related information were separated into queues with equal QoS needs. The duration of the FA was then automatically determined by the aggregation vertex based on energy consumption, latency, and throughput using FRL. Finally, based on the existing status, the amount of tasks offloaded was determined. The simulation results demonstrate that, as compared to the baseline schemes, the suggested FRLTO efficiently reduces energy consumption and latency while enhancing throughput and total WBAN utilization. Numerical results show that the proposed scheme improves the throughput by 37.06% and reduced the energy consumption by around 69.84% and time delay by about 6.23%, as compared to the state-of-the-art existing baseline schemes.