关键词： Mobile edge computing   Internet of Vehicle   Stackelberg game   Federal learning   Incentive mechanism  

摘要： With the development of Intelligent Transportation Systems (ITS), data on the Internet of Vehicles (IoV) is increasing day by day. To alleviate computing pressure in IoV, Vehicle Edge Computing (VEC) is being widely used as a new computing paradigm. Moreover, to address the serious problem of privacy leakage in VEC, Federated Learning (FL) is increasingly considered for analyzing big data in VEC. However, in actual VEC, problems such as data heterogeneity and poor training often occur. To address this set of problems, we introduce a two-stage Stackelberg game structure for FL training, choosing the Cloud Server (CS) as the leader and the Roadside Unit (RSU) as the follower. Then, we define the utility functions of CS and RSU and obtain the optimal reward rate and local accuracy for each iteration. To address the problem of inefficiency during learning process, we separate high-dimensional data features into global features and personalized features based on feature separation, and use them to capture historical information. Next, vehicle federated learning with historical information based on dynamic Stackelberg game (VFLHI-DSG) was proposed. Finally, we conducted a comprehensive comparative experiment, results show that VFLHI-DSG has excellent performance in different scenarios.

关键词： Ultra dense network   Mobile edge computing   Dynamic task allocation   Internet of things   NONORTHOGONAL MULTIPLE-ACCESS   ULTRA-DENSE NETWORKS   CHALLENGES  

摘要： This study investigates the challenges of task scheduling and resource allocation in an ultra-dense edge cloud (UDEC) network incorporating micro (macro) base stations and different equipment users (UE) under 5G technology. By utilizing multiple access interference (MAI), we enable multiple access capabilities to the UEs under the Non-Orthogonal Multiple Access (NOMA) protocol. To accommodate the dynamic nature of user tasks, we propose a two-level scheduling framework. At the upper level, the non-convex, non-linear power allocation problem for mobile users is formulated and solved using the Inertia Weight Particle Swarm Optimization (IWPSO) algorithm to minimize the transmission energy consumption. Simultaneously, at the lower level, the joint task offloading and resource allocation problem is formulated as MINP and solved with the binary Particle Swarm Optimization (PSO) algorithm to find an optimal schedule that maximizes the response rate and the overall welfare of the system while minimizing the energy consumption. In this study, various sensitivity analyses are conducted for different parameters, including the number of mobile users, channel power, and request profile parameters, including workload and request size. Comparative analyses with other methods from recent literature consistently reveal the comparable performance of the proposed framework and confirm its effectiveness in addressing the challenges of dynamic task scheduling.

关键词： Mobile edge computing   Computing migration   Physical layer security(PLS)   Interval many-objective optimization   Evolutionary algorithm  

摘要： In this paper, we study secure computing migration scenarios in uncertain environments with the presence of multiple malicious eavesdroppers (MEs). Specifically, when edge servers (ESs) execute tasks delivered by smart devices (SDs), SDs may move beyond the coverage of ESs, and computing migration (CM) of unfinished tasks is required to ensure service continuity. There is a risk of privacy leakage during task migration, and MEs use colluding eavesdropping to eavesdrop on the migrated tasks, and we consider eavesdropping on the associated tasks through data sharing among MEs to improve the eavesdropping efficiency. For eavesdropping in MEs, we achieve eavesdropping strikes using cooperative interference by jammers, which benefit by providing jamming services. In addition, uncertain computational scenarios directly affect the efficiency of task execution, and we consider the uncertainty factor in the malicious eavesdropping environment. To this end, this paper proposes the secure computational migration of associative privacy in uncertain environments (SCMAPUE) model, which transforms uncertainties into interval parameters, and optimizes the five objectives of migration delay, maximum completion time, energy consumption, load balancing and migration reliability to achieve efficient task execution and reliable migration. Aiming at the model characteristics, this paper designs an interval many-objective evolutionary algorithm for reliable migration (IMaOEA-RM), which employs a condition-based interval confidence strategy and a multi-access secure migration selection strategy to improve the convergence of the algorithm, and utilizes a dual-migration crossover strategy in order to adjust the jammer partners and improve the population diversity. Simulation results show that our proposed IMaOEA-RM algorithm can provide a more reliable and efficient migration scheme than existing algorithms.

关键词： Mobile edge computing   Knowledge sharing algorithm   Harmony search algorithm   Task scheduling   Multi-UAV deployment   RESOURCE-ALLOCATION   MAXIMIZATION   SWARM  

摘要： In the realm of multi-UAV-assisted mobile edge computing (MEC), the joint optimization of UAV deployment and task scheduling has emerged as a potent approach for mitigating energy consumption while ensuring highquality services for mobile users. Nevertheless, the intricate interdependence between UAV deployment and task scheduling presents formidable challenges when implementing this scheme. In response, we introduce a novel methodology called the Dual-Stage Hybrid Strategy with Genetic-Simulated Annealing and Knowledge Sharing (DSHSGSK). DSHSGSK employs an alternating optimization strategy known as HS-GSK, supplemented by an elimination operator, to simultaneously optimize UAV deployment and task scheduling. In pursuit of heightened efficiency in UAV deployment and a more effective task scheduling strategy, we propose an innovative location encoding scheme for UAVs. To harness the local search capabilities of the Harmony search (HS) algorithm and the global search capabilities of the Gaining Sharing Knowledge based Algorithm (GSK), we introduce a coordination parameter (CP) to modulate the frequency of alternation between these two optimization techniques. Experimental results validate the superiority of our proposed method over other state-of-theart algorithms for jointly optimizing multi-UAV deployment and task scheduling. Notably, our approach excels in terms of energy consumption, underscoring its exceptional performance.

关键词： Mobile edge computing   Task offloading   Long short-term memory   Deep reinforcement learning   Recurrent neural networks   Energy efficiency   Latency   RESOURCE-ALLOCATION   AWARE  

摘要： Edge computing is a novel and potential computing model which moves storage and computing capabilities to the network edge, substantially decreasing service latency and network traffic. The existing Internet of Things (IoT) network offloading algorithm faces limitations such as a fixed number of applications, high edge-to-edge delay, and reliance on a single Mobile Edge Computing (MEC) server, posing security and privacy concerns. Moreover, resource-constrained mobile devices need more effective data integration and compression strategies. Addressing these challenges, this study suggests an approach based on deep reinforcement learning (DRL), specifically the SAV (State Action Value) Oriented QL (Q-Learning) based Task Offloading method, to optimise task offloading and resource allocation in edge-cloud computing. The model aims to empower Mobile Devices (MDs) to develop optimal offloading decisions for long-term Quality Perception, utilising a neural network to establish the relationship between MD state and action value. The paper introduces a Recurrent Extended Memory Network (REMN) to capture dynamic workload behaviour at Edge nodes (ENs). It incorporates Quality Mapping, Quality Estimation, and a Quality-Aware DRL Task Offloading Algorithm to improve the accuracy and efficiency of the offloading procedure in MEC systems. This systematic approach improves overall system performance and enables MDs to leverage ENs for neural network training, reducing computational burdens. As a result, it can accomplish a more significant number of tasks, reducing latency from 0.74 ms to 7.168 ms and decreasing energy consumption from 270 J to 1820.39 J for tasks ranging from 10 to 50, respectively.

关键词： Near field communication   Mobile edge computing   Multi-agent reinforcement learning   Resource optimization   CHANNEL PARAMETER-ESTIMATION   OPTIMAL RESOURCE-ALLOCATION   OPTIMIZATION   RADIO   FUNDAMENTALS   MINIMIZATION  

摘要： In the next-generation communication system, near-field communication (NFC) is a key enabler of contactless transactions, including mobile payments, ticketing, and access control. With the growing demand for contact- less solutions, NFC technology will play a pivotal role in enabling secure and convenient payment experiences across various sectors. In contrast, Internet of Things (IoT) devices such as phones' Point of Sale (PoS) constitute limited battery life and finite computational resources that act as a bottleneck to doing the authentication in a minimal amount of time. Because of this, it garnered considerable attention in both academic and industrial realms. To overcome this, in this work we consider the Multiple Mobile Edge Computing (MEC) as an effective solution that provides extensive computation to PoS connected to it. To address the above, this work considers the PoS-enabled multi-MEC network to guarantee NFC communication reliably and effectively. For this, we formulate the joint optimization problem to maximize the probability of successful authentication while minimizing the queueing delay by jointly optimizing the computation and communication resources by utilizing a multi-agent reinforcement learning optimization approach. Through extensive simulations based on real-world scenarios, the effectiveness of the proposed approach was demonstrated. The results demonstrate that adjusting the complexity and learning rates of the model, coupled with strategic allocation of edge resources, significantly increased authentication success rates. Furthermore, the optimal allocation strategy was found to be crucial in reducing latency and improving authentication success by approximately 9.75%, surpassing other approaches. This study highlights the importance of resource management in optimizing MEC systems, paving the way for advancements in establishing secure, efficient, and dependable systems within the Internet of Things framework.

关键词： Training   Memory Management   Computational Modeling   Accuracy   Servers   Data Models   Federated Learning   Checkpointing   Adaptation Models   Optimization   Cross Device Federated Learning FL   Memory Wall   Heterogeneity Aware   Federated Learning   Memory Bottleneck   Heterogeneous Federated Learning   Data Distribution   Accuracy Of Model   Mobile Devices   Management Center   Multiple Devices   Progressive Training   Local Training   Edge Server   Mobile Edge Computing   Training Round   Training Capacity   Split Point   Side Of The Device   Training Data   Training Time   Computational Resources   Training Loss   Mobile Edge Computing Server   Training Efficiency   Memory Reduction   Central Server   Federated Learning Model   Communication Overhead   DNN Model   Collaborative Model   Memory Usage   Resource Contention  

摘要： Federated Learning (FL) enables multiple devices to collaboratively train a shared model while preserving data privacy. Ever-increasing model complexity coupled with limited memory resources on the participating devices severely bottlenecks the deployment of FL in real-world scenarios. Thus, a framework that can effectively break the memory wall while jointly taking into account the hardware and statistical heterogeneity in FL is urgently required. In this article, we propose SmartSplit a framework that effectively reduces the memory footprint on the device side while guaranteeing the training progress and model accuracy for heterogeneous FL through model splitting. Towards this end, SmartSplit employs a hierarchical structure to adaptively guide the overall training process. In each training round, the central manager, hosted on the server, dynamically selects the participating devices and sets the cutting layer by jointly considering the memory budget, training capacity, and data distribution of each device. The MEC manager, deployed within the edge server, proceeds to split the local model and perform training of the server-side portion. Meanwhile, it fine-tunes the splitting points based on the time-evolving statistical importance. The on-device manager, embedded inside each mobile device, continuously monitors the local training status while employing cost-aware checkpointing to match the runtime dynamic memory budget. Extensive experiments on representative datasets are conducted on both commercial off-the-shelf mobile device testbeds. The experimental results show that SmartSplit excels in FL training on highly memory-constrained mobile SoCs, offering up to a 94% peak latency reduction and 100-fold memory savings. It enhances accuracy performance by 1.49%-57.18% and adaptively adjusts to dynamic memory budgets through cost-aware recomputation

关键词： Hardware impairments   Rate splitting multiple access   Mobile edge computing   Successful computation probability   MULTIPLE-ACCESS   DELAY MINIMIZATION   ENERGY EFFICIENCY   NOMA   COMPUTATION   ALLOCATION   SYSTEMS   IMPACT   LIMITS  

摘要： In this paper, we investigate a cognitive radio (CR) inspired rate splitting multiple access (RSMA) aided mobile edge computing (MEC) network, where hardware impairments (HIs) in all transceivers are considered. Given that allowing the secondary user (SU) to share the resource with the primary user (PU) for data offloading does not degrade the PU's offloading performance, we derive closed-form expressions for the rate-splitting parameter and power allocation coefficient at the SU to maximize its offloading rate. Using the derived parameters, we then derive the successful computation probability (SCP), which is defined as the probability that both the PU and SU can successfully compute their task bits within a given latency budget, into the closed form. To further enhance the performance of the CR inspired RSMA-MEC network with HIs, a SCP maximization-based problem is formulated to jointly optimize the task offloading ratio and task offloading time of both the SU and PU. Leveraging the convex theory, we obtain the optimal solutions in the closed form. Simulation results confirm the following two insights. First, the presence of HIs leads to a decreasing on the SCP and the SCP approaches to a constant which is less than 1 with the increase of the transmit power. Second, with the optimal task offloading ratio and time, the CR inspired RSMA-MEC achieves the highest SCP compared to the existing schemes.

关键词： Mobile edge computing   Task caching   Convolutional neural networks   Multi-criteria task ranking   RESOURCE-ALLOCATION   DELAY ANALYSIS   FOG   NETWORKS   CLOUD   OPTIMIZATION   CHALLENGES   SYSTEMS  

摘要： Given the problems with a centralized cloud and the emergence of ultra-low latency applications, and the needs of the Internet of Things (IoT), it has been found that novel methods are needed to support centralized cloud technology. Mobile edge computing is one of the solutions to mitigate these challenges. In this paper, we study task caching at Device to Device (D2D)-assisted network edge. In the proposed scheme, we predict the possibility of re-requesting tasks in the future using convolutional neural networks (CNN). Based on this predicted possibility, the number of last requests, and the number of cached versions of this task type in the neighbors, in addition to the characteristics of a task itself, including the required cache volume and processing resources, we rank the tasks using the proposed Multi-Criteria Task Ranking using Predicted requests (MCTRP) scheme and select the best replacement option in the cache of each Mobile User Equipment (MUE). The proposed scheme has proved to be of considerable benefit in terms of reducing delay and energy consumption and improving the utility of MUEs.

关键词： Mobile edge computing   Satellite network   Multi-objective joint optimization   Task offloading   Multi-agent DRL   EDGE   CHALLENGES  

摘要： The Internet of Things (IoT) integrates a large number of heterogeneous terminals and systems, possessing ubiquitous sensing and computing capabilities. Satellite networks are the crucial supplement to terrestrial networks, particularly in remote areas where network infrastructures are sparingly distributed or unavailable. Combining edge computing with satellite networks provides on-orbit computing capabilities for IoT applications, reducing service delay and enhancing service quality. Due to the resource constraints of satellites, achieving collaborative services through task offloading among multiple satellites becomes essential. Both the privacy leakage risk arising from frequent data interactions and the load imbalance resulting from offloading preferences cannot be overlooked. The key challenge of task offloading is to safeguard the privacy of offloaded data and ensure the system's load balance while minimizing the delay and energy consumption. In this paper, the task offloading problem is formulated as a Partially Observable Markov Decision Process (POMDP), and a task offloading algorithm based on multi-objective joint optimization using multi-agent deep reinforcement learning in a distributed architecture is proposed. The simulation results validate the efficacy of our model and algorithm, demonstrating that our proposed algorithm achieves better performance in minimizing comprehensive offloading costs.