关键词： Autonomous aerial vehicles   Inspection   Energy consumption   Resource management   Energy efficiency   Base stations   Real-time systems   Trajectory optimization   Topology   Multi-access edge computing   Cellular-connected uavs   patrol inspection   task assignment   energy consumption   mobile edge computing  

摘要： This paper considers a patrol inspection scenario where multiple autonomous aerial vehicles (AAVs) are adopted to traverse multiple predetermined cruise points for data collection. The AAVs are connected to cellular networks and they would offload the collected data to the ground base stations (GBSs) for data processing within the constrained duration. This paper proposes a balanced task assignment strategy among patrol AAVs and an energy-efficient trajectory design method. Through jointly optimizing the cruise point assignment, communication scheduling, computational allocation, and AAV trajectory, a novel solution can be obtained to balance the multiple AAVs' task completion time and minimize the total energy consumption. Firstly, we propose a novel clustering method that considers geometry topology, communication rate, and offload volume;it can determine each AAV's cruise points and balance the AAVs' patrol task. Secondly, a hybrid Time-Energy traveling salesman problem is formulated to analyze the cruise point traversal sequence, and the energy-efficient AAV trajectory can be designed by adopting the successive convex approximation (SCA) technique and block coordinate descent (BCD) scheme. The numerical results demonstrate that the proposed balanced task assignment strategy can efficiently balance the multiple AAVs' tasks. Moreover, the min-max task completion time and total energy consumption performance of the proposed solution outperform that of the current conventional approach.

关键词： Internet of Things   Spread spectrum communication   Routing   Heuristic algorithms   Delays   Optimization   Lyapunov optimization   mobile edge computing   relay   task offloading   deep reinforcement learning   deep reinforcement learning  

摘要： To bridge the gap of conventional single-hop task offloading schemes in infrastructure-free scenarios, multi-hop task offloading schemes for IoT devices in Mobile Edge Computing (MEC) are desired to jointly optimize task offloading decisions and routing paths. In this paper, we investigate a hierarchical multi-hop edge computing framework and propose a joint Task Offloading and Relay Selection (TORS) scheme. It considers real-time computation at each relay node and employs directional searches to facilitate the task execution and results reporting at the fastest speed. However, finding the optimal TORS solution is a formidable challenge due to the time-varying network environments, the strong interdependence of decision sets across different time slots, and the high computational complexity. To address these challenges, we first leverage Lyapunov optimization to transform the stochastic TORS problem into a deterministic per-slot block problem, avoiding the need for extensive system prior knowledge. Subsequently, we propose a Soft Actor-Critic (SAC)-based algorithm, SAC-TORS, to find a satisfactory TORS solution with minimal computational complexity in a distributed manner. Accordingly, each IoT device can independently make self-determined and directional decisions with observable network information. Through extensive experiments, we demonstrate that the SAC-TORS outperforms state-of-the-art solutions, achieving performance improvements of up to 66%.

关键词： Mobile edge computing   Graph reinforcement learning   Graph neural network   Edge node   File caching strategy   Federated Learning  

摘要： The exponential growth of data and user density in mobile networks has led to increased latency in delivering content, particularly in mobile edge computing (MEC). Edge caching strategies, which store frequently accessed data closer to users, are crucial to minimize latency. However, traditional caching methods struggle to adapt to the dynamic environment of MEC, where user mobility and data popularity are highly variable. This paper addresses the problem of optimizing caching strategies to reduce content transmission delay in MEC while preserving user privacy. We propose a federated graph reinforcement learning (CFGRL) approach that integrates graph neural networks with federated learning and deep reinforcement learning (DRL). This model predicts popular content and updates caching strategies dynamically, improving latency without sharing user data. Simulations on real-world datasets show that CFGRL achieves a 32% reduction in content transmission delay and an 11.9% increase in cache hit ratio compared to existing methods like CFDRL and Thompson sampling. The CFGRL model demonstrates superior scalability and efficiency, making it well-suited for real-time applications in highly dynamic mobile environments. These results suggest that the proposed approach can significantly enhance the performance of MEC systems, making it a vital solution for modern mobile networks.

关键词： Play-to-earn   mobile edge computing   deep reinforcement learning   resource allocation   Play-to-earn   mobile edge computing   deep reinforcement learning   resource allocation  

摘要： Play-to-earn (P2E) games have been gaining popularity as they enable players to earn in-game tokens which can be translated to real-world profits. With the advancements in augmented reality (AR) technologies, AR play-to-earn games become compute-intensive. In-game graphical scenes need to be offloaded from mobile devices to an edge server for computation. In this work, we consider an optimization problem where the Mobile edge computing Service Provider (MSP)'s objective is to reduce downlink transmission latency of in-game graphics, the latency of uplink data transmission, and the worst-case (greatest) battery charge expenditure of user equipments (UEs), while maximizing the worst-case (lowest) UE resolution-influenced in-game earning potential through optimizing the downlink UE-Mobile edge computing Base Station (UE-MBS) assignment, downlink, and the uplink transmission power selection. The downlink and uplink transmissions are executed asynchronously. We propose a Multi-Asynchronous-Agent, Loss-Sharing (MALS) reinforcement learning model to tackle the asynchronous and asymmetric problem. We then compare the MALS model with other baseline models and show its superiority over other methods. Finally, we conduct multi-variable optimization weighting analyses and show the viability of using our proposed MALS algorithm to tackle joint optimization problems.

关键词： Mobile edge computing   Task offloading   Dynamic offloading decision   Heuristic transmission mechanism   Deep reinforcement learning  

摘要： Considering that the increasingly complex two-dimensional characteristics of real-world application scenarios such as diverse user needs and random user mobility bring great challenges to the applicability and effectiveness of traditional mobile edge computing (MEC) system models with linear deployment structure of edge servers, how to design a system model that can achieve efficient service offloading strategies while keeping a sound computation load balance across the edge servers is the key problem to be solved. To address the challenges faced by foregoing traditional MEC systems and the problem outlined above, this study proposes a double deep Qnetwork (DDQN) based dynamic offloading decision-making approach for MEC with regular hexagonal deployment structure of servers. First, we present an MEC system model in which edge servers are deployed in a regular hexagonal structure to cover a large region and balance the computation load across the edge servers as much as possible. The superiority of the proposed regular hexagonal structure-based server deployment in uniformly partitioning two-dimensional space is theoretically demonstrated by comparing it with three other possible server deployment structures. The proposed deployment's performance in terms of load balance and transmission efficiency for the overall system is also analyzed. Then, we formulate the dynamic offloading problem considered in the MEC system with sequential subtask linking relationships as an optimization problem aimed at minimizing the total task service latency of the system, and propose a novel DDQN-based dynamic offloading decision-making algorithm to optimize offloading decisions in the system. Finally, we conduct extensive experiments on the proposed system model and the proposed algorithm to demonstrate their effectiveness, and experimental results demonstrate that the proposals of this study are far superior to other similar studies and have good scalability and acceptable responsiven

关键词： Optimization   Computational modeling   Resource management   Autonomous aerial vehicles   Servers   Energy consumption   Cloud computing   Vehicle platoon   mobile edge computing   unmanned aerial vehicle   task offloading   resource allocation   Lyapunov optimization  

摘要： Vehicle platooning is a key application in the realm of smart connected vehicles and autonomous driving technologies, holding significant potential to enhance road utilization and save energy consumption. Simultaneously, within intelligent transportation systems, the limited computing resources of vehicle users themselves fail to meet the computational demands of various new applications. Therefore, addressing the ever-increasing computational demands of vehicles is an urgent problem that needs resolution. Unmanned Aerial Vehicle (UAV) equipped with edge computing servers leverage their advantages of flexible deployment and high maneuverability to promptly alleviate issues such as high latency and narrow bandwidth associated with processing remote data in cloud computing. This paper focuses on the scenario of UAV-assisted vehicle platooning, conducting research on task offloading and resource allocation mechanisms within UAV-assisted vehicle platooning systems. We construct a joint optimization problem for decision-making on task offloading, transmission power allocation, and CPU computing frequency allocation in UAV-assisted vehicle platooning systems. The objective is to minimize system energy consumption while ensuring the stability of the task computation queue. Since the formulated joint optimization problem is a mixed-integer nonlinear programming problem, we decompose it into two sub-problems and simultaneously transform them into Markov decision processes. Subsequently, we proposed a continuous optimization algorithm based on Block Coordinate Descent (BCD) and deep deterministic policy gradient(DDPG). Simulation results validate the effectiveness of this method, demonstrating comparatively low energy consumption under different network environments and parameter settings.

关键词： Reliability   Servers   Internet of Things   Costs   5G mobile communication   Resource management   Delays   Optimization   Queueing analysis   Performance evaluation   Finite block length   MMTC   mean field game   mobile edge computing   task replication  

摘要： The increasing demand for connectivity in 5G networks has led to a focus on massive machine-type communication (mMTC) in mobile edge computing (MEC) for IoTs. However, the proliferation of IoT devices has resulted in densely deployed networks and led to a high volume of task offloading to the same edge servers simultaneously. As a consequence, mMTC applications may experience service congestion, negatively impacting service reliability. To enhance the service reliability of latency-sensitive applications, task replication with resource allocation is proposed in MEC, in which a task can be sent simultaneously to multiple computing nodes. Task replication can reduce task latency and improve service reliability at the cost of consuming more computation resources. However, unconstrained task replication may result in too many uploading links, leading to severe costs in network operation. To handle the above challenge, we propose a constrained stochastic optimization problem by task replication with wireless resource block (RB) allocation and edge server queue management. To ensure queue stability while minimizing cost, we design one strategy based on the Lyapunov optimization framework. Accordingly, we further model RB allocation as a mean-field game (MFG) due to the intensive coupling of the RB pool for massive users. Tractable partial differential equations are used to analyze MFG equilibrium, and we derive the optimal edge server queue management based on a given task replication strategy and RB allocation scheme. Our theoretical analysis demonstrates that our algorithm closely approaches the optimal overall costs within a small gap, and simulation results show that our strategy generates a significantly lower cumulative cost than other alternative strategies.

关键词： Smart grid anomaly detection   Blockchain machine learning   Mobile edge computing   Multi Agent System (MAS)   Gradient Neural Network  

摘要： Based on Advanced Metering Infrastructures (AMIs), which enable bidirectional communication between the utility provider and the customer to improve reliability and customer satisfaction, smart grids are deemed completely indispensable in the next generation of electricity networks. Using blockchain machine learning in mobile edge computing for multi-agent systems (MAS), this research proposes a unique approach for smart grid anomaly detection. Here, a blockchain encoder adversarial multi-agent gradient neural network is used to identify anomalies in the smart grid network. Edge Computing reduces traffic and delays communication by shifting processing, data, and services from centralised clouds to Edge Servers (ESs). In terms of prediction accuracy, quality of service, scalability, and anomaly detection rate, experimental investigation is conducted for a variety of smart grid anomaly analysis datasets. The suggested method achieved 89 % scalability, 95 % prediction accuracy, 92 % QoS, and 85 % anomaly detection rate.

关键词： Secure channel   Mobile Edge Computing   Security   Scyther   Authentication  

摘要： The rapid expansion of Mobile Edge Computing (MEC) and the Internet of Things (IoT) has revolutionized technology by enabling real-time data processing at the network edge, which is essential for applications such as autonomous vehicles and smart cities. With the advent of 6G networks, which promise ultra-fast speeds, vast connectivity, and low-latency communication, MEC-IoT systems are becoming more powerful but also face significant security challenges. Existing authentication mechanisms (AMs) are often vulnerable to attacks like impersonation and insider threats. This paper introduces a novel lightweight AM, called RAM-MEN that employs cryptography and physically unclonable functions (PUFs) to secure IoT-enabled MEC environments in the 6G era. It protects against insider threats and fake MEC access points while ensuring efficiency and scalability. Additionally, the proposed RAM-MEN establishes a secure communication channel (session key) between IoT devices and the MEC server, enabling secure offloading of computationally intensive tasks. The security of the session is rigorously evaluated using formal methods, including Scyther and the random or real model, alongside informal approaches. Comparative performance evaluations show that the proposed RAM- MEN reduces communication costs by 21.54% to 45.53% and computational costs by 17.09% to 83.72%, while providing enhanced security features.

关键词： Servers   Training   Computational modeling   Adaptation models   Federated learning   Data models   Costs   Communication optimization   federated learning   mobile edge computing   personalization  

摘要： Personalized Federated Learning (pFL) can improve the accuracy of local models and provide enhanced edge intelligence without exposing the raw data in Mobile Edge Computing (MEC). However, in the MEC environment with constrained communication resources, transmitting the entire model between the server and the clients in traditional pFL methods imposes substantial communication overhead, which can lead to inaccurate personalization and degraded performance of mobile clients. In response, we propose a Communication-Efficient pFL architecture to enhance the performance of personalized models while minimizing communication overhead in MEC. First, a Knowledge-Aware Parameter Coaching method (KAPC) is presented to produce a more accurate personalized model by utilizing the layer-wise parameters of other clients with adaptive aggregation weights. Then, convergence analysis of the proposed KAPC is developed in both the convex and non-convex settings. Second, a Bidirectional Layer Selection algorithm (BLS) based on self-relationship and generalization error is proposed to select the most informative layers for transmission, which reduces communication costs. Extensive experiments are conducted, and the results demonstrate that the proposed KAPC achieves superior accuracy compared to the state-of-the-art baselines, while the proposed BLS substantially improves resource utilization without sacrificing performance.