关键词： Blockchains   Data models   Training   Computational modeling   Servers   Smart contracts   Artificial intelligence   Resource management   Cloud computing   Internet of Things   Federated learning   two-level cooperation   incentive mechanism   jointcloud   mobile edge computing  

摘要： With advances in the edge computing (EC) and federated learning (FL) technologies in jointcloud, the edge FL service market has emerged recently and it requires trading edge resources between model requesters and data owners to complete FL tasks, which needs to incentivize sufficient data owners to participate in model training tasks. However, the limitations of resource trading and incentive design for edge FL service market have not been well addressed. In this paper, we propose a two-level blockchain-aided resource trading mechanism for encouraging appropriate edge servers to compete for dynamic FL tasks from the market while incentivizing data owners to participate in the FL tasks. At the upper level, we apply the deep learning-based reverse auction to model the dynamics of the task server selection process, with the aim of maximizing the total social welfare of the edge FL service market, where the edge server, as a seller, considers not only the data contribution of edge devices but also the cost of using blockchain when bidding. At the lower level, the edge servers offer rewards in exchange for the data owners' participation, while the parameter aggregation is completed through the blockchain in a decentralized manner, which improves the FL's robustness. Then, we utilize the Stackelberg game to model the dynamic process that the data owners compete for the servers' revenue. We conduct extensive simulation experiments and the experimental results show that the proposed mechanism is able to get maximized social welfare and provide effective insights and strategies for the resource trading in the edge FL market to complete the federated training.

关键词： computation offloading   resource allocation   MADDPG   integrated space-air-marine network   mobile edge computing  

摘要： This paper investigates the problem of computation offloading and resource allocation in an integrated space-air-sea network based on unmanned aerial vehicle (UAV) and low Earth orbit (LEO) satellites supporting Maritime Internet of Things (M-IoT) devices. Considering the complex, dynamic environment comprising M-IoT devices, UAVs and LEO satellites, traditional optimization methods encounter significant limitations due to non-convexity and the combinatorial explosion in possible solutions. A multi-agent deep deterministic policy gradient (MADDPG)-based optimization algorithm is proposed to address these challenges. This algorithm is designed to minimize the total system costs, balancing energy consumption and latency through partial task offloading within a cloud-edge-device collaborative mobile edge computing (MEC) system. A comprehensive system model is proposed, with the problem formulated as a partially observable Markov decision process (POMDP) that integrates association control, power control, computing resource allocation, and task distribution. Each M-IoT device and UAV acts as an intelligent agent, collaboratively learning the optimal offloading strategies through a centralized training and decentralized execution framework inherent in the MADDPG. The numerical simulations validate the effectiveness of the proposed MADDPG-based approach, which demonstrates rapid convergence and significantly outperforms baseline methods, and indicate that the proposed MADDPG-based algorithm reduces the total system cost by 15-60% specifically.

关键词： blockchain technology   clouded leopard optimization   conditional self-attention generative adversarial network   fair proof-of-reputation   Internet of Vehicles   mobile edge computing  

摘要： The Internet of Vehicles (IoV) heralds a paradigm shift in vehicular communication by enhancing traffic efficiency, safety, and overall driving experiences through interconnectivity. However, real-world IoV systems often face significant challenges. High computational demands for processing real-time data in autonomous vehicles lead to rapid energy depletion, whereas vulnerabilities in communication networks can expose systems to cyberattacks. Although mobile edge computing (MEC) alleviates some of the issues by relocating computational resources closer to vehicles, it introduces critical hurdles. Frequent handovers due to high vehicle mobility result in service discontinuity and dynamic environments with dense vehicular networks complicate resource management and scalability. To tackle this, a blockchain-based multiobjective secure task offloading strategy utilizing an optimized conditional self-attention generative adversarial network (CSAGAN) enhanced by clouded leopard optimization (CLOA) is proposed (BMOSTO-CSAGAN-MEC-IoV). The self-attention mechanism of CSAGAN and the exploration-exploitation balance of CLOA prevent premature convergence by maintaining diverse search space, leading to optimized task scheduling. The model leverages fair proof of reputation (FPoR) for secure, decentralized task offloading ensuring data integrity and reliability. The proposed method attains 24.8% lower energy consumption, 26.2% lower latency, and 22.5% lower cost compared to existing methods when evaluated using IoV-synthetic dataset. These results demonstrate the model's effectiveness in enhancing IoV-MEC system performance.

关键词： Cloud computing   Computation offloading   Convex optimization   Energy efficiency   Mobile edge computing   Reinforcement learning  

摘要： Energy efficiency is one of the most critical aspects of modern computing paradigms due to minimizing carbon footprint and lowering operational costs. To achieve efficiency, the typical approach is to address the source of energy consumption and apply the appropriate strategies for energy savings. In this paper, based on an offloading framework for edge and cloud computing, we propose a comprehensive methodology that leverages predictive analysis and convex optimization techniques to achieve efficiency in power utilization. This methodology aimed to reduce the power consumption of edge/cloud computing clusters while maintaining an acceptable quality of service. The core idea was to enhance the historical data in the first place by using the prediction. This predictive historical data revealed the trend of computational resource allocation. Subsequently, the convex optimization technique coupled with the Deep Q-Network model was employed to formulate and schedule the distribution of the offloaded tasks. By engaging this combination, the offloading framework could produce a near-optimal and adaptive energy decision, which helps achieve energy efficiency. The experimental results showed that the proposed methodology could obtain significant energy savings while maintaining a suitable level of performance compared to other state-of-the-art approaches.

关键词： Mobile edge computing   uncrewed aerial vehicle   3D trajectory design   task offloading   multi-agent deep reinforcement learning  

摘要： Mobile Edge Computing (MEC) reduces the computational burden on terminal devices by shortening the distance between these devices and computing nodes. Integrating Uncrewed Aerial Vehicles (UAVs) with enhanced MEC networks can leverage the high mobility of UAVs to flexibly adjust network topology, further expanding the applicability of MEC. However, in highly dynamic and complex real-world environments, it is crucial to balance task offloading effectiveness with algorithm performance. This paper investigates a multi-UAV communication network equipped with edge computing nodes to assist terminal users in task computation. Our goal is to reduce the task processing delay for users through the joint optimization of discrete computation modes, continuous 3D trajectories, and resource assignment. To address the challenges posed by the mixed action space, we propose a Multi-UAV Edge Computing Resource Scheduling (MUECRS) algorithm, which comprises two key components: 1) trajectory optimization, and 2) computation mode and resource management. Experimental results show that our method effectively plans 3D UAV trajectories and enables rapid user coverage. Compared to state-of-the-art baselines, our approach achieves at least 16.5% reduction in task delay, demonstrating superior adaptability and robustness.

关键词： Mobile edge computing   Deep reinforcement learning   Graph convolutional networks   Service migration   Energy efficiency  

摘要： In mobile edge computing, service migration promises intelligent task placement as well as maintaining seamless functionality in bandwidth-intensive, latency-sensitive applications. Despite the promise of service migration offered by deep reinforcement learning (DRL), existing techniques lack topology awareness and dynamic adaptability. This research proposes a novel graph convolutional network (GCN)-based DRL framework enhanced with multi-parameter feedback (energy, delay, bandwidth) for intelligent service migration in MEC. Unlike prior DRL methods, our GCN-based framework models server topologies as spatial relationships and adapts feedback weights dynamically in response to changing system conditions. Experimental evaluation using EdgeSimPy and EdgeAISim shows that our proposed method reduces power consumption by 27% compared to traditional DRL (DQN) and by 44% compared to heuristic approaches (Worst-Fit). Moreover, the framework consistently outperforms existing state-of-the-art DRL algorithms in terms of energy efficiency, latency reduction, and resource optimization. Our key contributions include: (1) A topology-aware GCN-DRL architecture;(2) Dynamic multi-parameter feedback-driven reward formulation that improve energy efficiency by 15% under high network stress;and (3) Comprehensive benchmarking against six algorithm classes in varied MEC scenarios.

关键词： mobile edge computing   computation offloading   resource allocation   deep reinforcement learning  

摘要： This paper presents a novel framework for optimizing multimodal large language model (MLLM) inference through task offloading and resource allocation in UAV-assisted satellite edge computing (SEC) networks. MLLMs leverage transformer architectures to integrate heterogeneous data modalities for IoT applications, particularly real-time monitoring in remote areas. However, cloud computing dependency introduces latency, bandwidth, and privacy challenges, while IoT device limitations require efficient distributed computing solutions. SEC, utilizing low-earth orbit (LEO) satellites and unmanned aerial vehicles (UAVs), extends mobile edge computing to provide ubiquitous computational resources for remote IoTDs. We formulate the joint optimization of MLLM task offloading and resource allocation as a mixed-integer nonlinear programming (MINLP) problem, minimizing latency and energy consumption while optimizing offloading decisions, power allocation, and UAV trajectories. To address the dynamic SEC environment characterized by satellite mobility, we propose an action-decoupled soft actor-critic (AD-SAC) algorithm with discrete-continuous hybrid action spaces. The simulation results demonstrate that our approach significantly outperforms conventional deep reinforcement learning methods in convergence and system cost reduction compared to baseline algorithms.

关键词： Unmanned aerial vehicles   Non-orthogonal multiple access   Wireless power transfer   Mobile edge computing   Physical layer security   Friendly jammer  

摘要： This article investigates the efficacy of the secure computation offloading within an Internet of Things (IoT) network that employs wireless power transfer (WPT) -enabled unmanned aerial vehicle (UAV)-assisted mobile-edge computing (MEC) incorporating non-orthogonal multiple access (NOMA) over Nakagami-m fading channels. The proposed system is designed with the capability of offering proximate computational resources and substantial wireless power to clusters of resource-constrained edge devices (EDs). To proactively ensure secure communications, a friendly jammer (FJ) is strategically deployed to mitigate the adverse security threats posed by a multi-antenna passive eavesdropper. Accordingly, the assessment of the system's secure computation offloading performance is facilitated through the derivation of a closed-form formulation termed secrecy successful computation probability (SSCP). This formulation explicitly considers the implications of imperfect channel state information (iCSI) and imperfect successive interference cancellation (iSIC), thereby ensuring realistic model applications. By aiming at maximizing SSCP and prioritizing an optimization algorithm that offers simplicity in implementation, computational efficiency, and minimal parameter-tuning requirements, an approach grounded on Ananya algorithm is formulated. Eventually, extensive numerical simulations have robustly validated the accuracy and viability of the system model, considering a wide range of critical parameters. Comparative findings demonstrate Ananya algorithm's superiority on substantial aspects of rapid convergence towards optimal solutions and total computational duration compared to genetic algorithm (GA) and particle swarm intelligent (PSO).

关键词： mobile edge computing   Internet of Things   task offloading   ultra-dense network   power optimization  

摘要： The rapid growth of ultra-dense mobile edge computing (UDEC) in 5G IoT networks has intensified energy inefficiencies and latency bottlenecks exacerbated by dynamic channel conditions and imperfect CSI in real-world deployments. This paper introduces POTMEC, a power optimization framework that combines a channel-aware adaptive power allocator using real-time SNR measurements, a MATLAB-trained RL model for joint offloading decisions and a decaying step-size algorithm guaranteeing convergence. Computational offloading is a productive technique to overcome mobile battery life issues by processing a few parts of the mobile application on the cloud. It investigated how multi-access edge computing can reduce latency and energy usage. The experiments demonstrate that the proposed model reduces transmission energy consumption by 27.5% compared to baseline methods while maintaining the latency below 15 ms in ultra-dense scenarios. The simulation results confirm a 92% accuracy in near-optimal offloading decisions under dynamic channel conditions. This work advances sustainable edge computing by enabling energy-efficient IoT deployments in 5G ultra-dense networks without compromising QoS.

关键词： Computation offloading   Game theory   Fog computing   Mobile cloud computing   Mobile edge computing   5G/6G networks  

摘要： Due to the distance of users from remote cloud data centers, cloud computing (CC) may not be a good solution for latency-sensitive applications. Fog computing (FC) and Mobile Edge Computing (MEC) are two complementary paradigms for CC that can reduce energy consumption and delay. In FC, if the cloud resources are not enough to process the task, it is offloaded to the remote cloud. On the other hand, the main advantage of MEC is to reduce latency and availability of data and services for end users. If the edge resources are insufficient to process the work, it may be offloaded to remote cloud servers or fog. One of the suitable tools for modeling edge/fog/cloud discharge is Game Theory (GT). Game theory tries to predict the behaviors and decision results of agents who have the right to choose in interaction with each other by using scenario design and analysis. Here, the goal is to achieve a stable allocation of network resources to meet user requirements. Game-theoretic modeling can lead to agents located at the edge of the network acting more reliably. In this paper, we present an extensive systematic review of GT-based task offloading in different computational paradigms such as MEC, FC, and MCC. In addition to classical game theory, we pay special attention to evolutionary game theory. Generally, these methods are more scalable than classical methods. Instead of considering the user as a player, they consider network characteristics such as the number of CPU cycles. This article applies game theory from different perspectives such as the type of offloading, performance criteria, algorithm type, system components, evaluation tools, and computing environment.