关键词： Task offloading   Resource allocation   UAV-enabled systems   Deep reinforcement learning   Mobile edge computing  

摘要： The rapid and continuous growth of the Internet of Things has led to a rising demand for processing and storage solutions that can overcome the limitations of user devices. While cloud computing provides scalability, it often introduces considerable delay. To address this challenge, a computing paradigm that brings resources closer to user devices is preferable. Unmanned Aerial Vehicles (UAVs) have emerged as an effective solution to enhance communication quality and coverage in wireless systems, particularly in specific conditions. This paper presents a UAV-enabled Mobile Edge Computing (MEC) system, where UAVs equipped with computational capabilities provide task offloading services to users. In this system, users process part of their computing tasks locally, while offloading the remaining tasks to UAVs for processing. The primary goal of the proposed algorithm is to minimize processing delays, taking into account the environmental and energy constraints of the UAVs, such as movement boundaries, link blockages, transmission delays, and battery consumption for computation and flight. To achieve this, we propose a Deep Reinforcement Learning algorithm based on the Rainbow Deep Q-Network. This algorithm explores the dynamic and stochastic environment of MEC to deploy an appropriate computation offloading policy. The extensive experiments conducted in this study demonstrate the superior performance of the proposed method. The results show fast convergence to an optimal value and an average improvement of 12.63 percent in delay compared to state-of-the-art methods.

关键词： Servers   Mobile handsets   Costs   Computational modeling   Pricing   Training   Performance evaluation   Optimization   Collaboration   Adaptation models   Federated edge learning (FEL)   incentive mechanism   bargaining model   mobile edge computing  

摘要： Devices and servers in Federated Edge Learning (FEL) are self-interested and resource-constrained, making it critical to design incentives to improve model performance. However, dynamic network conditions raise energy consumption, while data heterogeneity undermines device cooperation. Current research overlooks the interplay between system efficiency and device clustering, resulting in suboptimal updates. To address these challenges, we develop BENCH, a bilateral pricing mechanism consisting of three core rules aimed at incentivizing participation from both devices and servers. Specifically, we first design a reward allocation rule, based on the Rubinstein bargaining model, which dynamically allocates rewards. Theoretically, we derive a closed-form solution for this rule, demonstrating BENCH achieves Nash equilibrium. Secondly, we design a device partitioning rule that leverages modularity to group similar devices, facilitating personalized edge aggregation to accelerate local data adaptation. Thirdly, we design an edge matching rule that employs the Kuhn-Munkres algorithm to balance the load at edge servers, thus minimizing the congestion. Together, these three rules enable hierarchical optimization of pricing and associations, effectively mitigating the impact of dynamic costs and device heterogeneity. Extensive experiments demonstrate BENCH's effectiveness in increasing device participation by 28.81% and improving model performance by 2.66% compared to state-of-the-art baselines.

关键词： OFDM   Optimization   Antennas   Channel estimation   Energy consumption   Central Processing Unit   Time-domain analysis   Sun   Servers   Mobile edge computing   reconfigurable intelligent surface   resource allocation   resource allocation  

摘要： This letter proposes a novel resource allocation algorithm to enable a reconfigurable intelligent surface (RIS) to support delay-bounded mobile edge computing (MEC) in orthogonal frequency division multiplexing (OFDM) settings, adhering to per-subcarrier power constraint. The energy requirement of the smart devices (SDs) is minimized through the joint optimization of task offloading parameters, RIS configuration, and the receive beamforming of the base station (BS). A key contribution is that we find the semi-closed-form receive beamformers as a function of the RIS phases. Hence, the joint optimization is decoupled between convex offloading scheduling and non-convex RIS configuration by alternating optimization (AO). Another contribution is that we convexify the per-subcarrier power constraint by exploiting successive convex approximation (SCA), and acquiring a Karush-Kuhn-Tucker (KKT) point solution for the RIS configuration. Numerical results show the superiority of the new approach compared with baseline schemes in energy saving, and reveal that the optimal RIS location hinges on the channel quality differences among the RIS, BS, and SDs.

关键词： Mobile edge computing   UAV communication   Secrecy rate maximization   Transmit beamforming   Trajectory design  

摘要： This paper is concerned with the optimization problem for dual unmanned aerial vehicle (UAV) mobile edge computing systems. One UAV acts as a computation server and the other is a jammer in the system, while the terminal device (TD) on the ground uploads its computation task to the UAV server with the presence of an eavesdropper. The design objective is to maximize the average secrecy rate of TD. Furthermore, the trajectories of UAVs, transmit beamformers, and computation bits are jointly optimized. As the formulated problem is non-convex, it is decomposed into two sub-problems. Then, we employ the successive convex approximation and alternative optimization method to solve the problem iteratively. Moreover, the zero-forcing (ZF) beamforming scheme is utilized for further simplification of calculation. Simulation results demonstrate that our algorithm is effective, and the proposed ZF scheme achieves close-to-optimal performance.

关键词： Blockchain   Hybrid intrusion   Intrusion detection   Machine learning   Mobile edge computing  

摘要： The growing use of mobile edge computing (MEC) has had a positive impact on user experience and reduced latency. However, this closeness also makes MEC environments vulnerable to a number of security risks. This research article presents an edge-based hybrid intrusion detection system for MEC and the Internet of Things (IoT). The system uses techniques like behavioral analysis, anomaly detection, and signature-based detection, ensuring real-time response and reduced bandwidth usage. The system also addresses challenges in data acquisition and cleaning due to potential threats from malicious users and noise. The model uses smoothing filters, unsupervised learning, and deep learning techniques to detect anomalies and threats, reducing bandwidth. According to the findings, securing MEC environments against changing cyber threats can be accomplished using an edge-based hybrid intrusion detection system. © Little Lion Scientific.

关键词： Mobile edge computing   Task offloading   Meta-reinforcement learning   Unmanned aerial vehicle  

摘要： Existing task offloading models struggle to rapidly adapt to dynamic environmental changes in emergency scenarios, such as natural disasters or unforeseen events. To address this challenge, a meta-reinforcement learning-based task offloading method (MRLTO) for unmanned aerial vehicle (UAV)-enabled mobile edge computing (MEC) is proposed. First, an objective function for optimizing task offloading is formulated based on communication, local computing, and UAV computing models. Subsequently, the task offloading problem is reformulated as a Markov decision process (MDP). By incorporating a meta-learning framework, our approach consolidates the learning experiences of various mobile devices across diverse environments, allowing the offloading model to rapidly adapt to dynamic environmental changes. Furthermore, a dueling deep Q-network (D3QN) is employed to decouple state values and action advantage values, thereby improving task offloading decision mapping and dynamically generating more efficient offloading decisions. Finally, an experimental scenario is set up to compare MRLTO with RNOF, AGGO, and DTTO. The results show that MRLTO reduces the average latency by 8.14%, lowers the average energy consumption by 6.89%, and decreases the task drop rate by 12.89%.

关键词： mathematical methods   artificial intelligence   mobile edge computing  

摘要： The integration of mathematical methods with artificial intelligence (AI) and mobile edge computing (MEC) has emerged as a promising research direction to address the growing complexity of intelligent distributed systems. To chart the landscape of this interdisciplinary field, we first examine recent surveys that primarily focus on architectural designs, learning paradigms, and system-level deployments in edge AI. However, these studies largely overlook the theoretical foundations essential for ensuring reliability, interpretability, and efficiency. This paper fills this gap by conducting a comprehensive survey of mathematical methods and analyzing their applications in AI-enabled MEC systems. We focus on addressing three key challenges: heterogeneous data integration, real-time optimization, and computational scalability. We summarize state-of-the-art schemes to address these challenges and identify several open issues and promising future research directions.

关键词： Delays   Resource management   Energy consumption   Optimization   Autonomous aerial vehicles   Quality of experience   Processor scheduling   Heuristic algorithms   Base stations   Convergence   Dependent task scheduling   mobile edge computing   multi-objective evolutionary algorithms based on decomposition   resource allocation   service caching   uncrewed aerial vehicles  

摘要： This paper studies the joint optimization of multi-objective dependent task scheduling, resource allocation, and service caching in an aerial-ground integrated mobile edge computing system that includes multiple uncrewed aerial vehicles (UAVs). These UAVs, in coordination with a high-altitude platform, work together to process numerous dependent tasks collected by the UAVs. The optimization problem involves two conflicting objectives that need to be minimized simultaneously: the average execution delay of all dependent tasks and the average energy consumption of all UAVs. The conflict between the two objectives makes the problem quite challenging. Recently, some multi-objective approaches, such as multi-objective evolutionary algorithms (MOEAs), have been introduced to address dependent task scheduling. However, these approaches often suffer from premature convergence and tend to fall into local optima. To address these issues, we propose a modified MOEA based on decomposition that incorporates two performance-improving strategies. The first one is a probability-based neighborhood search strategy that selects two individuals to update neighborhood individuals based on the neighborhoods and external population, thereby improving population updating efficiency. The second one is a dynamic voltage and frequency scaling-based energy reduction strategy that further enhances the quality of solutions by adjusting the computing frequencies. Experimental results verify that the proposed algorithm obtains a number of outstanding nondominated solutions and achieves a better balance between objectives compared with several algorithms.

关键词： Premium services emerge   Hyper-service network   Network evolution   Preferred connection   Mobile edge computing  

摘要： Recently, massive services from multiple domains are available on the network with the rapid development of Mobile Edge Computing (MEC) technology. These various services construct a service network through services' collaboration, which can provide users with rich resources at anytime and anywhere. However, in MEC, due to the proliferation of services, as well as the dynamics of Quality of Service (QoS), it becomes more and more difficult for users to discover the premium services effectively, which seriously impacts users' satisfaction and the utilization of resources. Therefore, how to proactively perceive the emergence of premium services in the service networks has become an challenge. To tackle this issue, we propose a method for perception of the premium services based on the evolution of hyper-service network (named as PPSHSN). First, based on the hypergraph theory, we construct a hyper-service network with the optimal connection method. Then, we develop the evolution mechanism of the hyper-service network and optimize the hyper-service network with the hyperdegree premium value evolution algorithm, thus to conduct the evolution of the service networks. Next, we devise the evaluation indexes based on the topological characteristics of hypergraphs, which are updated according to the evolution of the hyper-service network. Finally, we complete perception of premium services based on the evolution results of the hyper-service network. The effectiveness and feasibility of our proposed method are verified through extensive simulation experiments.

关键词： Autonomous aerial vehicles   Collaboration   Artificial neural networks   Internet of Things   Computational modeling   Servers   Heuristic algorithms   Cloud computing   Real-time systems   Energy consumption   Deep neural network   generative artificial intelligence (AI)   mobile edge computing   multiagent reinforcement learning (MARL)   path planning   task assignment   uncrewed aerial vehicle (UAV) network  

摘要： uncrewed aerial vehicles (UAVs) offer high mobility and flexible deployment capabilities, making them ideal for Internet of Things (IoT) applications. However, the substantial amount of data generated by various applications within the existing low-altitude network requires processing through deep neural networks (DNN) on UAVs, which is challenging due to their limited computational resources. To address this issue, we propose a two-stage optimization method for flight path planning and task allocation based on a mother-child UAV swarm system. In the first stage, we employ a greedy algorithm to solve the path planning problem by considering the task size of the target area to be inspected and the shortest flight path as constraints. The goal is to minimize both the flight path of the UAV and the overall cost of the system. In the second stage, we introduce a novel DNN task assignment algorithm that combines multiagent deep deterministic policy gradient (MADDPG) and generative diffusion models (GDMs), named GDM-MADDPG. This algorithm takes advantage of the reverse denoising process of GDM to replace the actor network in MADDPG. It enables UAVs to generate specific DNN task assignment actions based on agents' observations in a dynamic environment, thereby improving the efficiency of task assignment and overall system performance. The simulation results demonstrate that our algorithm outperforms the benchmarks in terms of path planning, Age of Information (AoI), task completion rate, and system utility, demonstrating its effectiveness.