检索结果-内蒙古大学图书馆

Deep reinforcement learning with dual-Q and Kolmogorov-Arnold Networks for computation offloading in Industrial IoT

COMPUTER NETWORKS 2025年 257卷

作者： Wu, Jinru Du, Ruizhong Wang, Ziyuan Hebei Univ Sch Cyber Secur & Comp Baoding 071000 Hebei Peoples R China Hebei Univ Key Lab High Trusted Informat Syst Hebei Prov Baoding 071000 Hebei Peoples R China

In the industrial internet of things, the rapid development of smart mobile devices and 5G network technology has driven the application of mobile edge computing, reducing the delay in task computation offloading to some extent. However, the increasing complexity of the IIoT environment presents challenges for communication management and offloading performance. To achieve efficient computation offloading communication, we designed a cloud-edge-device IIoT system model, utilizing Voronoi diagrams to partition the service areas of edge servers, thereby adapting to the complex IIoT environment and improving communication efficiency. Additionally, considering that different offloading strategies may result in varying levels of offloading security risks, we developed a principal component analysis-based offloading security evaluation model (PCA-OSEM) to analyze potential security risks during the offloading process and identify key factors. Finally, to optimize offloading strategies to reduce offloading delay and security risks, we proposed a dual-Q with Kolmogorov- Arnold networks in deep reinforcement learning computation offloading (D2KCO). This method enhances the neural network's approximation capability and training stability. Experimental results show that the proposed PCA-OSEM is effective, and the D2KCO method can reduce offloading delay by 13% and 23.52% compared to the D3PG and DDPG algorithms, respectively, while also reducing security risks.

关键词： Industrial internet of things Mobile edge computing computation offloading Security Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

computation offloading in Heterogeneous Vehicular Edge Networks: On-Line and Off-Policy Bandit Solutions

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2022年第12期21卷 4233-4248页

作者： Bozorgchenani, Arash Maghsudi, Setareh Tarchi, Daniele Hossain, Ekram Univ Bologna Dept Elect Elect & Informat Engn I-40126 Bologna Italy Univ Lancaster Dept Comp & Commun Lancaster LA1 4YW England Univ Tiibingen Dept Comp Sci D-72074 Tubingen Germany Fraunhofer Heinrich Hertz Inst D-10587 Berlin Germany Univ Manitoba Dept Elect & Comp Engn Winnipeg MB R3T 2N2 Canada

With the rapid advancement of intelligent transportation systems (ITS) and vehicular communications, vehicular edge computing (VEC) is emerging as a promising technology to support low-latency ITS applications and services. In this paper, we consider the computation offloading problem from mobile vehicles/users in a heterogeneous VEC scenario, and focus on the network- and base station selection problems, where different networks have different traffic loads. In a fast-varying vehicular environment, computation offloading experience of users is strongly affected by the latency due to the congestion at the edge computing servers co-located with the base stations. However, as a result of the non-stationary property of such an environment and also information shortage, predicting this congestion is an involved task. To address this challenge, we propose an on-line learning algorithm and an off-policy learning algorithm based on multi-armed bandit theory. To dynamically select the least congested network in a piece-wise stationary environment, these algorithms predict the latency that the offloaded tasks experience using the offloading history. In addition, to minimize the task loss due to the mobility of the vehicles, we develop a method for base station selection. Moreover, we propose a relaying mechanism for the selected network, which operates based on the sojourn time of the vehicles. Through intensive numerical analysis, we demonstrate that the proposed learning-based solutions adapt to the traffic changes of the network by selecting the least congested network, thereby reducing the latency of offloaded tasks. Moreover, we demonstrate that the proposed joint base station selection and the relaying mechanism minimize the task loss in a vehicular environment.

关键词： Task analysis Edge computing Servers Base stations Heuristic algorithms Delays Vehicle dynamics Vehicular edge computing (VEC) computation offloading heterogeneous networks off-policy learning on-line learning bandit theory

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Deep Reinforcement Learning for computation offloading in Autonomous Multi-Robot Systems

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第1期10卷 540-547页

作者： Gao, Wen Yu, Zhiwen Wang, Liang Cui, Helei Guo, Bin Xiong, Hui Northwestern Polytech Univ Sch Comp Sci Xian 710072 Peoples R China Hong Kong Univ Sci & Technol Guangzhou Thust Artificial Intelligence Guangzhou 511453 Peoples R China

To ensure system responsiveness, some compute-intensive tasks are usually offloaded to cloud or edge computing devices. In environments where connection to external computing facilities is unavailable, computation offloading among members within an autonomous multi-robot system (AMRS) becomes a solution. The challenge lies in how to maximize the use of other members' idle resources without disrupting their local computation tasks. Therefore, this study proposes HRL-AMRS, a hierarchical deep reinforcement learning framework designed to distribute computational loads and reduce the processing time of computational tasks within an AMRS. In this framework, the high-level must consider the impact of data loading scales determined by low-level under varying computational device states on the actual processing times. In addition, the low-level employs Long Short-Term Memory (LSTM) networks to enhance the understanding of time-series states of computing devices. Experimental results show that, across various task sizes and numbers of robots, the framework reduces processing times by an average of 4.32% compared to baseline methods.

关键词： Robots Graphics processing units Resource management computational modeling Loading Processor scheduling Load modeling Delays Deep reinforcement learning Collaboration computation offloading multi-robot systems reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Many-objective firefly algorithm with two archives for computation offloading

引用

INFORMATION SCIENCES 2025年 689卷

作者： Wang, Hui Liao, Futao Zhang, Shaowei Xiao, Dong Wang, Yun Wang, Wenjun Nanchang Inst Technol Sch Informat Engn Jiangxi Prov Key Lab Smart Water Conservancy Nanchang 330099 Peoples R China Nanchang Inst Technol Sch Business Adm Nanchang 330099 Peoples R China

Firefly algorithm (FA) has shown good performance over many optimization problems. However, most studies on FA focus on problems with no more than three objectives. For problems with larger number of objectives, i.e. many-objective optimization problems (MaOPs), FA encounters some difficulties in providing sufficient selection pressure and maintaining population diversity. So far, FA has rarely been used to solve MaOPs. In this paper, we try to propose a many- objective FA variant with two archives (called TaMaOFA) to challenge MaOPs. Inspired by the idea of an improved two-archive method (called Two_Arch2), TaMaOFA employs two archives including convergence archive (CA) and diversity archive (DA), which are used to strengthen convergence and diversity, respectively. By utilizing the search information of CA and DA, a convergence and a diversity biased search strategies are designed, respectively. To enhance the search efficiency, a random search model is constructed based on the two biased search strategies and random attraction. To validate the performance of TaMaOFA, the well-known MaF benchmark is utilized. Results show that TaMaOFA obtains competitive performance when compared with ten other state-of-the-art approaches. Finally, TaMaOFA is applied to computation offloading in edge computing environments. Simulation results demonstrate that TaMaOFA still achieves promising performance.

关键词： Firefly algorithm Two-archive computation offloading Edge computing Many-objective optimization

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based strategy for energy-efficient parallel computation offloading in mobile edge networks

引用

AD HOC NETWORKS 2025年 171卷

作者： Khan, Haris Ali, Zaiwar Abbas, Ziaul Haq Abbas, Ghulam Khan, Sheroz Yahya, Muhammad GIK Inst Engn Sci & Technol Telecommun & Networking TeleCoN Res Lab Topi 23640 Pakistan GIK Inst Engn Sci & Technol Fac Elect Engn Topi 23640 Pakistan GIK Inst Engn Sci & Technol Fac Comp Sci & Engn Topi 23640 Pakistan Onaizah Coll Coll Engn & Informat Technol Dept Elect Engn POB 2053 Qasim 56447 Saudi Arabia Univ Galway Data Sci Inst Galway H91 TK33 Ireland

The growing demand for real-time computing applications on mobile devices is burdening their processing power and battery life. Mobile edge computing helps by allowing these tasks to be offloaded to nearby servers having more processing power. However, when it comes to multiple servers and tasks, choosing the optimal components for offloading becomes challenging. This is because we need to balance between reducing the amount of data transferred and keeping communication latency low. To address this problem, an energy- efficient parallel computation offloading mechanism through deep learning (EPCOD), is proposed. An algorithm using deep learning (DL) is developed and trained as a decision-making system. This system selects the best combination of application components taking into account various factors, such as energy consumption, network conditions, computational load, data transfer volume, and communication latency. A cost function that includes all these factors is developed to calculate the cost for each possible offloading policy combination. By analyzing a large dataset, we find the best policies. Additionally, we use a DL network to efficiently handle this computational task. Simulation results demonstrate that EPCOD effectively minimizes both latency and energy consumption, achieving a high accuracy of deep neural network of up to 73.5%.

关键词： Mobile edge computing computation offloading Deep learning Parallel task offloading Mobile devices

来源：评论

学校读者我要写书评

暂无评论

DDQN-based online computation offloading and application caching for dynamic edge computing service management

引用

AD HOC NETWORKS 2025年 166卷

作者： Wang, Shudong Lu, Zhi Gui, Haiyuan He, Xiao Zhao, Shengzhe Fan, Zixuan Zhang, Yanxiang Pang, Shanchen China Univ Petr East China Coll Comp Sci & Technol Qingdao Peoples R China

Multi-access Edge Computing (MEC) reduces task service latency and energy consumption by offloading computing tasks to MEC servers. However, constrained by the limited bandwidth and computing resources, MEC servers often cannot parallelly process all computing tasks. Simultaneously, the high dynamism of service popularity necessitates MEC servers to dynamically update cached applications, under ensuring compliance with storage resource constraints and the system cache updating cost budget for service providers. In response to the above two issues, this paper firstly formulates computation offloading and application caching as a dual-timescale decision optimization problem, aiming to minimize the average service latency for users by obtaining optimal offloading decision, cache decision, transmission bandwidth, and computing resource. Then, we propose a Deep Reinforcement Learning (DRL)-based two-stage online computation offloading and application caching (DTSO2C) algorithm, effectively stabilizing application cache update costs and enhancing Quality of Service (QoS) for users. Furthermore, we utilize convex optimization algorithms to derive the optimal communication bandwidth and computing resource allocation strategy, further reducing the average service latency for users. Simulation results demonstrate that the DTSO2C algorithm outperforms the compared algorithms, achieving an average reduction in service latency of 66.2%, with an average cache update cost of only 0.15 USD per time frame.

关键词： Multi-access edge computing computation offloading Application caching Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-User computation offloading in Dynamic Environment for LEO Constellation Networks

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年第3期73卷 4453-4458页

作者： Gao, Yufang Zhao, Kanglian de Cola, Tomaso Li, Wenfeng Cui, Yan Hu, Peicong Nanjing Univ Sch Elect Sci & Engn Nanjing 210046 Peoples R China Inst Commun & Nav German Aerosp Ctr D-82234 Wessling Germany Vivo Mobile Commun Shenzhen Co Ltd Shenzhen Peoples R China PLA 63893 Troops Luoyang 471003 Peoples R China

In this paper, we examine the problem of multi-user computation offloading for Low Earth Orbit (LEO) constellation networks under dynamic environment. To solve the puzzle of in-orbit computing performance degradation caused by multi-user access interference, we focus on minimizing channel interference while considering the stochastic characteristic of satellite-ground channels and the dynamic nature of ground user access. From a game-theoretic perspective, we model the interference mitigation problem as a potential game, and demonstrate that the Nash Equilibrium (NE) minimizes the channel interference. Meanwhile, we design an intelligent stochastic learning algorithm (ISLA) based on the stochastic learning method. Finally, simulation results show that the proposed algorithm can significantly reduce co-channel interference and system overhead compared with the benchmark algorithms, and achieve near-optimal performance.

关键词： Low Earth Orbit (LEO) constellation network computation offloading dynamic environment potential game

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning based computation offloading for xURLLC services with UAV-assisted IoT-based multi-access edge computing system

引用

WIRELESS NETWORKS 2024年第9期30卷 7275-7291页

作者： Fatima, Nida Saxena, Paresh Giambene, Giovanni BITS Pilani Dept Comp Sci & Informat Syst Hyderabad Campus Hyderabad 500078 India Univ Siena Dept Informat Engn & Math Sci I-53100 Siena Italy

New Internet of Things (IoT) based applications with stricter key performance indicators (KPI) such as round-trip delay, network availability, energy efficiency, spectral efficiency, security, age of information, throughput, and jitter present unprecedented challenges in achieving next-generation ultra-reliable and low-latency communications (xURLLC) for sixth-generation (6 G) communication systems and beyond. In this paper, we aim to collaboratively utilize technologies such as deep reinforcement learning (DRL), unmanned aerial vehicle (UAV), and multi-access edge computing (MEC) to meet the aforementioned KPIs and support the xURLLC services. We present a DRL-empowered UAV-assisted IoT-based MEC system in which a UAV carries a MEC server and provides computation services to IoT devices. Specifically, we have employed twin delay deep deterministic policy gradient (TD3), a DRL algorithm, to find optimal computation offloading policies while simultaneously minimizing both the processing delay and the energy consumption of IoT devices, which inherently influence the KPI requirements. Numerical results illustrate the effectiveness of the proposed approach that can significantly reduce the processing delay and energy consumption, and converge quickly, outperforming the other state-of-the-art DRL-based computation offloading algorithms including Double Deep Q-Network(DDQN) and Deep Deterministic Policy Gradient (DDPG).

关键词： Deep reinforcement learning computation offloading Internet of Things Multi-access edge computing Unmanned aerial vehicles Next-generation ultra-reliable and low-latency communications

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning-based computation offloading in edge computing: Principles, methods, challenges

引用

ALEXANDRIA ENGINEERING JOURNAL 2024年 108卷 89-107页

作者： Luo, Zhongqiang Dai, Xiang Sichuan Univ Sci & Engn Sch Automat & Informat Engn Yibin 644000 Sichuan Peoples R China Sichuan Univ Sci & Engn Artificial Intelligence Key Lab Sichuan Prov Yibin 644000 Sichuan Peoples R China

With the rapid development of mobile communication technologies and Internet of Things (IoT) devices, Multi- Access Edge Computing (MEC) has become one of the most potential technologies for wireless communication. In MEC systems, faster and more reliable data processing can be provided to IoT devices through computation offloading, but edge servers have limited computing and storage resources. The prerequisite for whether an IoT device can offload a computation task to an edge server for processing is whether the edge server has enough remaining available resources and whether the edge server caches the services related to the task, followed by finding the best way to offload the task. Therefore, to process tasks efficiently, offloading decisions, resource allocation, and edge caching need to be jointly considered during offloading tasks to edge servers. Reinforcement Learning (RL) has recently emerged as a key technique for solving the computation offloading problem in MEC, and a large number of optimization methods have emerged. In this context, we provide a comprehensive survey of RL-based computation offloading fundamental principles and theories in MEC, including mechanisms for finding optimal offloading decisions, methods for joint resource allocation, and means for joint edge caching. In addition, we also discuss the challenges and future work of RL-based computation offloading methods.

关键词： Edge computing Reinforcement learning computation offloading offloading decision Edge caching Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Dynamic Resource Allocation for computation offloading in LEO Satellite Networks

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第11期11卷 19470-19484页

作者： Gao, Xiangqiang Hu, Yingmeng Shao, Yingzhao Zhang, Hangyu Liu, Yang Liu, Rongke Zhang, Jianhua China Acad Space Technol Xian Xian 710100 Peoples R China Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China China Satellite Network Innovat Co Ltd Beijing 100029 Peoples R China

With the rapid development of large low Earth orbit (LEO) satellite constellations, satellite edge computing is an emerging topic to provide computing services for Internet of Things (IoT) users, which are not in the coverage of terrestrial networks. For computation offloading in satellite edge computing, it is still challenging to allocate the network resources on-demand for IoT users to improve service experience while reducing energy consumption, since user tasks may be offloaded between different satellites by inter-satellite links (ISLs). In this article, we study the joint optimization problem of computation offloading and resource allocation in cooperative satellite edge computing. Then, a hierarchical dynamic resource allocation (HDRA) algorithm for computation offloading is proposed by introducing breadth first search (BFS) and greedy to tackle the problem, the aim is to minimize service delay and energy consumption jointly. We conduct the experiments to evaluate the performance of the proposed HDRA algorithm, compared with two baselines of BFS-PSO and Gurobi. Experimental results show that the proposed HDRA algorithm can address the formulated problem effectively in satellite edge computing and obtain the results of computation offloading and resource allocation in a low running time.

关键词： Satellites Edge computing Low earth orbit satellites Routing Resource management computational modeling Delays computation offloading energy consumption resource allocation satellite edge computing service delay

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：