检索结果-内蒙古大学图书馆

Minimizing makespan in two-stage assembly additive manufacturing: A reinforcement learning iterated greedy algorithm

引用

APPLIED SOFT COMPUTING 2023年 138卷

作者： Ying, Kuo-Ching Lin, Shih-Wei Natl Taipei Univ Technol Dept Ind Engn & Management Taipei 10608 Taiwan Chang Gung Univ Dept Informat Management Taoyuan 333 Taiwan Keelung Chang Gung Mem Hosp Dept Emergency Med Keelung 204 Taiwan Ming Chi Univ Technol Dept Ind Engn & Management New Taipei 243 Taiwan

Additive manufacturing (AM) is becoming increasingly important for producing mass-customized, small-quantity products with relatively low geometric constraints. Although some AM machine scheduling problems have been proposed in recent years, no research has addressed the parallel AM machine scheduling problem with an integrated assembly stage. In this study, a two-stage assembly additive manufacturing scheduling problem is considered, in which multiple parts are produced in job batches using identical parallel AM machines in the first stage and then assembled into the desired products in the second stage. Further, a mixed-integer linear programming model and an innovative reinforcement learning metaheuristic, called the iterated epsilon-greedy algorithm, are proposed to minimize the makespan of this significant scheduling extension. The computational results based on 810 test instances show that the developed approaches are highly effective, efficient, and robust in solving the addressed problem. Notably, the research results can effectively reduce the gap between the theory and practice of AM production planning by integrating the production stage with the assembly stage.& COPY;2023 Elsevier B.V. All rights reserved.

关键词： Scheduling Two -stage assembly scheduling problems Additive manufacturing reinforcement learning algorithm Iterated epsilon -greedy algorithm

来源：评论

学校读者我要写书评

暂无评论

On the importance of hyperparameters tuning for model-free reinforcement learning algorithms 12

On the importance of hyperparameters tuning for model-free r...

引用

12th International Conference on Control Mechatronics and Automation

作者： Tejer, Mateusz Szezepanski, Rafal Nicolaus Copernicus Univ Inst Engn & Technol Torun Poland

ISBN: (纸本)9798331517519;9798331517526

In the rapidly evolving field of artificial intelligence (AI), particularly in reinforcement learning (RL), the focus often shifts towards developing and selecting increasingly complex algorithms. However, this paper argues that for model-free reinforcement learning (MFRL) algorithms, effective hyperparameter tuning is frequently more critical to achieving high performance than choosing a more sophisticated algorithm. With advancements such as ChatGPT, people nowadays have unprecedented access to experiment with various RL algorithms using powerful open-source machine learning libraries with little to no coding experience. This dissemination of AI tools has highlighted that, while algorithmic innovation is important, the performance gains achievable through meticulous hyperparameter tuning can outweigh those from adopting more complex models. Through empirical analysis of the robotic arm scheduling problem, we demonstrate that well-tuned simple MFRL algorithms can outperform more complicated but not-tuned counterparts. The simulational validation using MATLAB software is utilized to compare five model-free reinforcement learning algorithms.

关键词： Task scheduling robotic arm reinforcement learning algorithm performance analysis model-free hyper-parameter tuning

来源：评论

学校读者我要写书评

暂无评论

A reinforcement learning-based metaheuristic algorithm for solving global optimization problems

引用

ADVANCES IN ENGINEERING SOFTWARE 2023年第1期178卷

作者： Seyyedabbasi, Amir Istinye Univ Fac Engn & Nat Sci Software Engn Dept Istanbul Turkiye

The purpose of this study is to utilize reinforcement learning in order to improve the performance of the Sand Cat Swarm Optimization algorithm (SCSO). In this paper, we propose a novel algorithm for the solution of global optimization problems that is called RLSCSO. In this method, metaheuristic algorithm is combined with rein-forcement learning techniques to form a hybrid metaheuristic algorithm. This study aims to provide search agents with the opportunity to perform efficient exploration of the search space in order to find a global optimal solution by using efficient exploration and exploitation to find optimal solutions within a given search space. A comprehensive evaluation of the RLSCSO has been conducted on 20 benchmark functions and 100-digit chal-lenge basic test functions. Additionally, the proposed algorithm is applied to the problem of localizing mobile sensor nodes, which is NP-hard (nondeterministic polynomial time). Several extensive analyses have been conducted in order to determine the effectiveness and efficiency of the proposed algorithm in solving global optimization problems. In terms of cost values, the RLSCSO algorithm provides the optimal solution, along with tradeoffs between exploration and exploitation.

关键词： Metaheuristic algorithm reinforcement learning algorithm Sand cat swarm optimization Q-learning Machine learning

来源：评论

学校读者我要写书评

暂无评论

A novel game approach to integrating traffic assignment and signal control for enhanced efficiency and environmental performance in mixed networks

引用

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES 2025年 171卷

作者： Yang, Hang Ma, Wanjing Cheng, Rongjun Wu, Bing Wang, Yibing Zheng, Pengjun Ningbo Univ Fac Maritime & Transportat Ningbo 315211 Peoples R China Southeast Univ Jiangsu Prov Collaborat Innovat Ctr Modern Urban T Rd 2 Nanjing 211189 Peoples R China Ningbo Univ Natl Traff Management Engn & Technol Res Ctr Sub Ctr Ningbo 315832 Peoples R China Tongji Univ Key Lab Rd & Traff Engn Minist Educ Shanghai 201804 Peoples R China Zhejiang Univ Inst Intelligent Transportat Syst Hangzhou 310058 Peoples R China

The combined traffic assignment and signal control (CAC) has proven to be effective in enhancing the wholistic performance of mixed networks, which includes both expressways and surface streets. This study focuses on addressing the limitations of traditional Stackelberg game-based CAC models, particularly the rigid leader-follower dynamic. We propose an integrated LevelChange-MPC (Model Predictive Control)-VT-Meso-Emission Model (LCMVTM), which incorporates a dynamic role-change function triggered by the compliance rate of users to variable message signs (VMS). This role-change mechanism offers greater flexibility under varying road conditions and simplifies the authority's task of predicting user routing behavior. Additionally, a Q-learning-based algorithm is developed to balance travel costs and emissions by managing the rate of emission accumulation across control horizons. The results demonstrate a reduction in total travel costs by 11% to over 30%, while emissions decrease by 16.98% to approximately 40% compared to the other different combination of control strategies and MAS/non MAS structured network. The emission accumulation rate also drops by 20% to 43.69%. LCMVTM outperformed the other benchmarks by reducing the number of stop&go per vehicle, resulting in improved efficiency and environmental outcomes.

关键词： Integrated Traffic Control Novel Stackelberg Games Model Signal Control Traffic Assignment reinforcement learning algorithm Urban Mixed Network

来源：评论

学校读者我要写书评

暂无评论

Intelligent Orchestrating of IoT Microservices Based on reinforcement learning

引用

Chinese Journal of Electronics 2022年第5期31卷 930-937页

作者： WU Yuqin SHEN Congqi CHEN Shuhan WU Chunming LI Shunbin WEI Ruan College of Computer Science and Technology Zhejiang University College of Information and Electrical Engineering Ningde Normal University Zhejiang Lab College of Control Science and Engineering Zhejiang University

With the recent increase in the number of Internet of things(IoT) services, an intelligent scheduling strategy is needed to manage these services. In this paper, the problem of automatic choreography of microservices in IoT is explored. A type of reinforcement learning(RL) algorithm called TD3 is used to generate the optimal choreography policy under the framework of a softwaredefined network. The optimal policy is gradually reached during the learning procedure to achieve the goal, despite the dynamic characteristics of the network environment. The simulation results show that compared with other methods, the TD3 algorithm converges faster after a certain number of iterations, and it performs better than other non-RL algorithms by obtaining the highest reward. The TD3 algorithm can effciently adjust the traffic transmission path and provide qualified IoT services.

关键词： software-defined network telecommunication scheduling intelligent orchestrating nonRL algorithms reinforcement learning software defined networking optimal choreography policy reinforcement learning algorithm Internet of things services network environment IoT microservices TD3 algorithm traffic transmission path Internet of Things qualified IoT services intelligent scheduling strategy dynamic characteristics

来源：评论

学校读者我要写书评

暂无评论

reinforcement learning based fractional fuzzy controller for photovoltaic systems

引用

APPLIED SOFT COMPUTING 2024年 162卷

作者： Sharifi, Ali Delavari, Hadi Hamedan Univ Technol Dept Elect Engn Hamadan Iran

This article presents an innovative artificial nonlinear control technique for photovoltaic (PV) systems. A boost converter extracts maximum power from the PV system under different weather conditions. A fuzzy logic maximum power point (MPP) finding algorithm is used to determine the reference voltage of the PV system under various atmospheric conditions. It is assumed that the nonlinear dynamic model, parameters, and uncertainties of the converter are unknown. To estimate a precise model that contains nonlinearities, model uncertainties, and disturbances of the converter, proximal policy optimization (PPO) with a special reward function is applied. PPO is optimal in policy learning and sampling, fast to implement, and is a simple reinforcement learning (RL) algorithm. Then, estimations of dynamics and uncertainties are used to enhance the robustness of the suggested fractional order sliding mode controller. Furthermore, the controller coefficients are optimally adjusted by the PPO algorithm. The Lyapunov theorem is used for proving the control system ' s closed-loop stability. Also, the proposed methods can be generalized and used for other control systems. The simulation is conducted by MATLAB to evaluate the suggested controller ' s performance effectiveness. Robustness against the presence of parameter uncertainty is investigated. Moreover, the suggested technique is also compared with sliding mode controller.

关键词： reinforcement learning algorithm Fuzzy logic Photovoltaic system Fractional order sliding control

来源：评论

学校读者我要写书评

暂无评论

Speed harmonisation and merge control using connected automated vehicles on a highway lane closure: a reinforcement learning approach

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2020年第8期14卷 947-958页

作者： Ko, Byungjin Ryu, Seunghan Park, Byungkyu Brian Son, Sang Hyuk Daegu Gyeongbuk Inst Sci & Technol DGIST Dept Informat & Commun Engn 333 Techno Jungang Daero Daegu South Korea Univ Virginia Link Lab POB 400747 Charlottesville VA 22903 USA Univ Virginia Dept Engn Syst & Environm POB 400747 Charlottesville VA 22903 USA

A lane closure bottleneck usually leads to traffic congestion and a waste of fuel consumption on highways. In mixed traffic that consists of human-driven vehicles and connected automated vehicles (CAVs), the CAVs can be used for traffic control to improve the traffic flow. The authors propose speed harmonisation and merge control, taking advantage of CAVs to alleviate traffic congestion at a highway bottleneck area. To this end, they apply a reinforcement learning algorithm called deep Q network to train behaviours of CAVs. By training the merge control Q-network, CAVs learn a merge mechanism to improve the mixed traffic flow at the bottleneck area. Similarly, speed harmonisation Q-network learns speed harmonisation to reduce fuel consumption and alleviate traffic congestion by controlling the speed of following vehicles. After training two Q-networks of the merge mechanism and speed harmonisation, they evaluate the trained Q-networks under various conditions in terms of vehicle arrival rates and CAV market penetration rates. The simulation results indicate that the proposed approach improves the mixed traffic flow by increasing the throughput up to 30% and reducing the fuel consumption up to 20%, when compared to the late merge control without speed harmonisation.

关键词： traffic engineering computing road vehicles road traffic control road traffic traffic control learning (artificial intelligence) speed harmonisation connected automated vehicles highway lane closure reinforcement learning approach lane closure bottleneck traffic congestion fuel consumption human-driven vehicles traffic control highway bottleneck area reinforcement learning algorithm Q-network mixed traffic flow trained Q-networks vehicle arrival rates CAV market penetration rates

来源：评论

学校读者我要写书评

暂无评论

Environmentally Sustainable and Multifunctional Chrome-like Coatings Having No Chromium Designed with reinforcement learning

引用

ACS APPLIED MATERIALS & INTERFACES 2023年第23期15卷 28772-28780页

作者： Saha, Anwesha Ma, Taigao Wang, Haozhu Guo, L. Jay Univ Michigan Dept Appl Phys Ann Arbor MI 48109 USA Univ Michigan Dept Phys Ann Arbor MI 48109 USA Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48109 USA

Decorative chrome plating (DCP) continues to be ubiquitousin creatinghighly appealing metal finishings and coatings, beating out otherorganic dye-based finishes. However, the hazardous chrome platingprocess is fraught with adverse health effects for the workers involvedand causes significant environmental damage. In this work, we presenta multilayer thin film structure to mimic the chrome appearance. Tofind a design efficiently, we employ a reinforcement learning (RL)algorithm to perform an automatic inverse design. This results instructures composed of environmentally friendly materials that notonly have the chrome color but can also achieve additional functionsbeyond decoration. As an example, one structure is designed to havehigh transmission in the radio frequency regime, a property that generalmetals cannot have, which can broaden the decorative chrome applicationsto include microwave operating devices. The experimental structuresare fabricated by physical vapor deposition to demonstrate the indistinguishablechrome color and validate the effectiveness of the RL inverse designapproach.

关键词： chrome replacement inverse design structuralcolor optical coating reinforcement learning algorithm

来源：评论

学校读者我要写书评

暂无评论

reinforcement learning based mainline dynamic speed limit adjustment of expressway off-ramp upstream under connected and autonomous vehicles environment

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2022年第12期16卷 1809-1819页

作者： Xiao, Daiquan Kang, Shengyang Xu, Xuecai Shen, Zhenwu Huazhong Univ Sci & Technol Sch Civil & Hydraul Engn Wuhan 430074 Peoples R China Shenzhen Urban Transport Planning Ctr Co Ltd Shenzhen Peoples R China Wuhan Huake Quanda Transport Planning & Design Co Wuhan Peoples R China

With the rapid progress of urbanization and continuous increasing of automobiles, expressway on- and off-ramp area becomes the bottleneck, and recurrent congestion occurs frequently. In order to solve the problem of traffic jam caused around off-ramps, various methods have been employed. Among all, mainline variable speed limit (VSL) control accounts for some proportion. In this study, mainline VSL adjustment of off-ramp upstream is investigated with the reinforcement learning algorithm under the connected vehicles environment to alleviate the traffic congestion. First, the assumptions are made to be suitable for the traffic conditions of mainline VSL control on off-ramp upstream, and then VSL algorithm based on reinforcement learning is presented, and Q-learning is chosen as the main algorithm. Next, the state space, action space, and reward function required by Q-learning are constructed orderly, and the related parameters are labelled. After that, according to the platform based on Python and VISSIM, three schemes, free control (Scheme 0), mainline VSL adjustment of off-ramp upstream based on rule (Scheme 1), and mainline VSL adjustment of off-ramp upstream based on Q-learning algorithm (Scheme 2), are designed, and the three schemes are simulated and compared quantitatively to reflect the off-ramp travel efficiency. The results indicate that mainline dynamic VSL adjustment of off-ramp upstream based on Q-learning algorithm performs the best in terms of general and specific indexes. The results provide potential insights for relieving the traffic congestion and traffic flow control under CAVs environment.

关键词： mobile robots road vehicles mainline VSL control intelligent transportation systems reinforcement learning algorithm traffic jam connected vehicles environment off-ramp area mainline dynamic speed limit adjustment learning (artificial intelligence) mainline VSL adjustment VSL algorithm traffic flow control mainline variable speed limit control accounts automobiles off-ramp travel efficiency traffic congestion mainline dynamic VSL adjustment road traffic road traffic control reinforcement learning Python traffic engineering computing Q-learning algorithm autonomous vehicles environment

来源：评论

学校读者我要写书评

暂无评论

reinforcement learning based on routing with infrastructure nodes for data dissemination in vehicular networks (RRIN)

引用

WIRELESS NETWORKS 2022年第5期28卷 2169-2184页

作者： Lolai, Arbelo Wang, Xingfu Hawbani, Ammar Dharejo, Fayaz Ali Qureshi, Taiyaba Farooq, Muhammad Umar Mujahid, Muhammad Babar, Abdul Hafeez Univ Sci & Technol China Sch Comp & Technol Hefei 230027 Anhui Peoples R China Chinese Acad Sci Univ Chinese Acad Sci Comp Network Informat Ctr Beijing 100190 Peoples R China

Vehicular-Ad hoc Networks are extremely important due to the potential for improving road safety, traffic monitoring, and in-vehicle infotainment services. A novel Q-learning-based routing protocol named reinforcement learning-based Routing with Infrastructure Node Data Dissemination in Vehicular Network (RRIN) is proposed to efficiently address such a dynamic network. RRIN is a routing protocol that aims to achieve low end-to-end communication latency and a high data delivery ratio. To meet the objectives, we proposed two Q-routing functions for Road Model Segment Selection (RMSS) and Intermediate Vehicle Selection (IVS). The network environment is separated into road model segments, and Road Side Units at each road junction to assist nodes in data dissemination was deployed. The exploration feature of the Q-learning algorithm allowed the vehicles to randomly explore and interact with the dynamic environment in the vehicular network. Our findings show that the proposed RRIN routing protocol is highly beneficial compared to other efficient routing protocols with high packet delivery, high throughput, and low end-to-end communication latency. Due to the exploration and exploitation phases of Q-learning, the proposed RRIN routing protocol enhances the reliability and the efficiency of the vehicular network in terms of high throughput, low communication latency, and low packet and high packet delivery ratio. For RMSS, the shortest distance and higher connectivity distribution are considered parameters;whereas, the parameters for IVS are vehicle speed difference, link reliability, moving direction, and buffer size.

关键词： Q-learning VANET routing protocol reinforcement learning algorithm V2V V2I I2V

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：