关键词： Connected car   Mobile edge computing   Deep reinforcement learning  

摘要： With the rapid development of intelligent transportation systems,vehicular networks(VANETs)have become an essential part of the intelligent transportation *** to the high dynamics of efficient vehicular network nodes and the low latency requirement of data interaction,the traditional cloud computing model makes it difficult to meet the real-time and performance criteria,and the storage optimization strategy based on edge computing can effectively improve the data access efficiency and system *** paper aims to explore how to optimize the data caching mechanism of intelligent telematics using edge computing to reduce network latency,improve data availability,and enhance overall system performance.

关键词： 5G networks   Mobile edge computing   Non-orthogonal multiple access   Deep learning   Bird swarm optimization   Resource allocation   Multi-objective optimization   Energy efficiency   Latency reduction  

摘要： The increase in mobile communication has escalated network load, necessitating more intelligent resource management in 5G and forthcoming networks. This research introduces a novel methodology to enhance network performance by integrating bird swarm optimization (BSO) with deep learning (DL). We investigate a configuration in which several users inside a single cell solicit services from proximate edge servers and remote cloud servers, employing Non-Orthogonal Multiple Access (NOMA) to optimize radio spectrum utilization. BSO, influenced by avian flocking patterns, aggregates users and distributes workloads among servers to reduce energy consumption, service latency, and operational expenses. Simultaneously, DL examines historical network data to forecast traffic and user requirements, enabling BSO to make immediate, educated decisions. We utilize queuing theory to model this system, addressing a complicated optimization problem that concurrently reduces energy, latency, and costs. In contrast to conventional solutions, our technology dynamically adjusts to fluctuating network conditions, providing an effective remedy for the requirements of 5G. Simulations demonstrate that the integrated BSO-DL approach diminishes energy usage, delays, and expenses by around 54 %, substantiating its efficacy in improving broadband performance. This research facilitates the development of more efficient and sustainable 5G networks, addressing the increasing demands of contemporary mobile communication through a scalable and intelligent approach.

关键词： Smart healthcare network   Mobile edge computing   Resource allocation   Computation offloading   Deep reinforcement learning  

摘要： Significant breakthroughs in the Internet of Things(IoT)and 5G technologies have driven several smart healthcare activities,leading to a flood of computationally intensive applications in smart healthcare *** Edge Computing(MEC)is considered as an efficient solution to provide powerful computing capabilities to latency or energy sensitive *** low-latency and high-reliability requirements of healthcare application services can be met through optimal offloading and resource allocation for the computational tasks of the *** this study,we established a system model consisting of two types of nodes by considering nondivisible and trade-off computational tasks between latency and energy *** minimize processing cost of the system tasks,a Mixed-Integer Nonlinear Programming(MINLP)task offloading problem is ***,this problem is decomposed into task offloading decisions and resource allocation *** resource allocation problem is solved using traditional optimization algorithms,and the offloading decision problem is solved using a deep reinforcement learning *** propose an Online Offloading based on the Deep Reinforcement Learning(OO-DRL)algorithm with parallel deep neural networks and a weightsensitive experience replay *** results show that,compared with several existing methods,our proposed algorithm can perform real-time task offloading in a smart healthcare network in dynamically varying environments and reduce the system task processing cost.

关键词： Internet of vehicles   Multi-intelligence deep reinforcement learning   Mobile edge computing   Queuing theory   Non-orthogonal multiple access   Task offloading  

摘要： With the rapid advancement of autonomous driving technology, the volume of data generated by vehicle sensors is growing exponentially. Due to spatial limitations within vehicles, high-performance computing equipment cannot be accommodated, resulting in limited vehicle resources being unable to meet the real-time and low-energy consumption demands of vehicular network data processing. To address this challenge, Vehicular Edge Computing (VEC) has emerged as a new development trend in intelligent transportation. VEC effectively relieves the pressure of data transmission and processing by integrating edge computing into the in-vehicle network. Based on this, an efficient offloading strategy for VEC system under resource-constrained conditions is proposed. Firstly, a vehicular edge computing system framework incorporating Non-Orthogonal Multiple Access (NOMA) and queuing theory is constructed, involving multiple servers and multi-priority tasks. The transmission model and computation model from vehicles to edge nodes are derived. This framework significantly reduces inter-vehicle signal interference using the characteristics of NOMA, and optimizes the average delay and energy consumption performance during multi-task processing. Secondly, considering the resource constraints in practical operations, this paper establishes a stochastic game with delay, energy consumption, and cost as the optimization objectives. Given the superiority of Multi-Agent Deep Reinforcement Learning (MADRL) in complex environments, a MADRL-based task offloading algorithm, named Multi-Agent Distributed Deep Action Semantic Deterministic Policy Gradient (MADSASPG), is proposed for vehicular task computation offloading. Finally, to further enhance the action prediction accuracy and performance of the algorithm, the Actor network of the algorithm is improved into an Action Semantic Network (ASN). Through information sharing among Agents, the cooperation between Agents is strengthened. The experiment

关键词： Visual analytics   Accuracy   Resource management   Analytical models   Computational modeling   Image edge detection   Feature extraction   Bandwidth   Numerical models   Servers   Video analytics   mobile edge computing   knob configuration   and resource allocation  

摘要： Characterized by its ease of low-latency response, edge computing is capable of supporting real-time video analytics applications, constituting an edge video analytics paradigm, where the joint knob configuration and network scheduling design has drawn ever-escalating research attention. However, the potential of edge video analytics has not been fully exploited, owing to the limitations of the state-of-the-art as follows. i) The eminent impact of video content on accuracy performance has been ignored. ii) The variables that can be tuned are not fully considered in scheduling. iii) The heuristic algorithm-based solutions are far from the optimal. To fill in this gap, in this paper, we conceive a content-aware joint knob configuration and resource allocation scheme for edge video analytics. Concretely, fed with the features extracted from the video content, a deep neural network (DNN)-based predictor is proposed to predict the configuration-accuracy performance in a real-time manner. With an aid of the predictive results, we formulate an accuracy-maximization problem as an integer programming problem, by optimizing the variables, including resolution, frame rate, video analytic model, network bandwidth, and computational resource subject to the latency constraints. To solve this problem in an efficient manner, we devise a novel low-complexity dynamic programming method. Simulation results verify the efficiency of our content-aware joint knob configuration and resource allocation scheme. Quantitatively, a 3.3% gap is attained towards the upper bound in terms of the accuracy in an object detection scenario, relying on the scheme proposed.

关键词： Servers   Data retrieval   Uncertainty   Costs   Optimization   Data centers   Multi-access edge computing   Fluctuations   Data models   Cloud computing   Mobile edge computing   edge data caching   data popularity   optimization approach  

摘要： In the mobile edge computing environment, caching data in edge storage systems can significantly reduce data retrieval latency for users while saving the costs incurred by cloud-edge data transmissions for app vendors. Existing edge data caching (EDC) methods prioritize popular data and aim to minimize users' data retrieval latency and system storage costs jointly. However, these EDC methods often rely on the assumption that data popularity always follows certain distributions. As a result, they cannot properly adapt to the fluctuations in data popularity due to user mobility or unexpected increases in user demands. Meanwhile, unlike cloud data centers, complex and fragile edge servers are more likely to experience physical failures or network outages, presenting new challenges for EDC strategies. Specifically, when an edge server fails or experiences an outage, cached data may become temporarily unavailable, leading to increased latency as requests are redirected to alternative servers or the cloud. In this paper, to enable uncertainty-aware edge data caching (uEDC), we first model the problem as a robust optimization problem and propose an optimal algorithm named uEDC-B to find the optimal uEDC solution. To address the high computational complexity of uEDC-B, we introduce an approximate algorithm named uEDC-L based on linear decision rules. Theoretical analysis and extensive experiments on a real-world dataset demonstrate that the proposed methods outperform two state-of-the-art approaches in handling the uncertainties in data popularity and edge server failure with a significant performance improvement of 59.27% in data retrieval latency and 55.07% in data caching cost.

关键词： Mobile Edge Computing   Server selection   Reinforcement learning   Non-stationary systems   Serverauswahl   Reinforcement Learning   Nicht-station & auml   re Systeme  

摘要： Mobile Edge Computing (MEC) is an architecture that brings computational capabilities to the edge of mobile networks. It enables low-latency and efficient task execution by allowing the Mobile Units (MU) to offload computation tasks to nearby computing servers. However, server selection in MEC remains an open and complex challenge due to the non-stationary nature of the system dynamics, where channel conditions, server loads, and resource availability change over time. Traditional reinforcement learning approaches, while effective for adaptive decision-making, often assume stationary system dynamics. In this perspective, we discuss the role of learning and forgetting mechanisms in MEC server selection, emphasizing the need for adaptive mechanisms that can retain and exploit relevant experience while discarding outdated information. Mobile Edge Computing (MEC) ist eine Architektur, die Rechenkapazit & auml;ten an den Rand mobiler Netzwerke bringt. Sie erm & ouml;glicht eine latenzarme und effiziente Ausf & uuml;hrung von Aufgaben, indem sie mobilen Einheiten (MUs) erlaubt, Rechenaufgaben an nahegelegene Server auszulagern. Die Auswahl des geeigneten Servers im MEC stellt jedoch nach wie vor eine offene und komplexe Herausforderung dar, da die Systemdynamik nicht station & auml;r ist - Kanalbedingungen, Serverauslastung und Ressourcenverf & uuml;gbarkeit & auml;ndern sich im Zeitverlauf. Traditionelle Ans & auml;tze des Reinforcement Learning sind zwar wirksam f & uuml;r adaptive Entscheidungsfindung, gehen jedoch h & auml;ufig von station & auml;ren Systemdynamiken aus. In dieser Perspektive er & ouml;rtern wir die Rolle von Lern- und Vergessensmechanismen bei der Serverauswahl im MEC und betonen die Notwendigkeit adaptiver Mechanismen, die relevante Erfahrungen bewahren und nutzen k & ouml;nnen, w & auml;hrend veraltete Informationen verworfen werden.

关键词： Computational modeling   Heuristic algorithms   Delays   Collaboration   Long short term memory   Vehicle dynamics   Predictive models   Prediction algorithms   Decision making   Resource management   Mobile edge computing   task offloading   deep reinforcement learning   internet of vehicles  

摘要： Roadside units (RSUs) with strong sensing abilities enhance the viability of the RSU-to-Everything (R2X) paradigm, offering crucial infrastructure support for Mobile Edge Computing (MEC) that enables real-time data processing and reduced delay. Since RSUs collect a large volume of data but have limited computing capability, data analysis tasks are usually offloaded to other network nodes, such as the cloud, other RSUs, or even vehicles. The multi-hop distributed collaborative task offloading scheme is expected to achieve high resource utilization efficiency and low task delay in this scenario, despite increasing energy consumption in data transmission. However, the highly dynamic nature of the R2X network topology makes it challenging for a node to independently select the next hop and collaboratively allocate tasks to neighbors in a multi-hop transmission path. Specifically, offloading decisions made by an individual node are influenced not only by its immediate neighbors but also by other nodes along the multi-hop path, referred to in this paper as the effect value. Additionally, the heterogeneity in computing resources and link delays among network nodes further increases the difficulty. To address these challenges, we first apply a Long Short-Term Memory (LSTM) model to predict and update the neighbors for each node while considering effect values, allowing them to independently adapt to environmental changes. Then, we design a two-layer Deep Reinforcement Learning (DRL) algorithm for network nodes to make decisions. The first-layer DRL algorithm is implemented by RSUs to determine task offloading modes. When an RSU decides to offload tasks to multiple vehicles for collaborative computing, the second-layer DRL algorithm is used by a vehicle to select its next hop vehicle and allocate tasks. Simulation results show that our proposed approach effectively adapts to topology changes in complex and highly dynamic network environments. Compared with existing methods,

关键词： Architecture   Deep Reinforcement Learning   Computation offloading   Task offloading   Metrics   Multi-Access Edge Computing   Mobile Edge Computing   Unmanned Aerial Vehicles   Drones   Internet of Things   Wireless sensor networks  

摘要： Unmanned Aerial Vehicle (UAV)-assisted Internet of Things (IoT) applications vary widely including data monitoring, data collection and analysis, intelligent navigation and object tracking, surveillance and emergency response, vehicular and intelligent transport, and agricultural, marine, and photogrammetry. Mobile Edge Computing (MEC)-based UAV-assisted IoT networks enable resource-constrained mobile or IoT devices to offload computationally demanding tasks to UAVs or edge nodes with more computing power in order to improve battery consumption, performance, or Quality of Service. UAV-assisted IoT applications generally require a lot of precision for efficient UAV control involving UAV movement and position optimization and Deep Reinforcement Learning (DRL) has recently been identified as one of the most prominent techniques for facilitating this and optimizing of the terrestrial network performance, thus improving the operation of these applications. This paper aims to answer twelve important research questions relating to the research on DRL for Mobile Edge Computing (MEC)-based UAV-assisted sensor and IoT applications from 47 systematically selected articles. The questions cover a variety of topics including the UAV-assisted MEC IoT applications studied, variants of deployed DRL, the purpose of DRL, Markov Decision Processes (MDPs) components, unique network architectural features, environments and integrated technologies, role of UAVs, optimization constraints, joint optimization frameworks, energy-management techniques, metrics examined, benchmark algorithms and performance results as well as identified probable future considerations based on the review. Lastly, the challenges and future directions of DRL application in UAV-assisted MEC systems are discussed. This paper aims to provide both communication generalists and optimization specialists with a comprehensive understanding of the research landscape in this field.

关键词： Mobile edge computing   Heterogeneous cellular networks   Stackelberg game   Computation offloading   Resource pricing  

摘要： The explosive growth of mobile users (MUs) has led to a substantial increase in computing tasks being offloaded to MEC, bringing tremendous pressure to the sustainable development of MEC. To address this problem, the integration of multi-base station (BS) with MEC has attracted widespread attention. In this paper, we propose the joint optimization problem of resource allocation, computation offloading, and resource pricing for multi-BS cooperative MEC in heterogeneous multicell networks. We model the interactions between MEC server, macro base station (MBS), femto base station (FBS), and MUs as a four-stage Stackelberg game, and derive the equilibrium resource pricing and allocation strategies. In the first three stages, we focus on devising optimal resource allocation and pricing strategies to maximize the utility of all stakeholders. In the fourth stage, MUs make an offloading decision to maximize their utility based on the different pricing strategies. The optimization problems in each stage are simplified and proved by derivation using backward induction method. Our approach offers a novel strategy by effectively integrating multiple BSs, enabling a more flexible and efficient resource distribution. The simulation results demonstrate that the proposed multi-BS model can improve the utilities of MBS and MUs by 53% and 50% respectively by introducing FBS.