检索结果-内蒙古大学图书馆

Neural network-based adaptive reinforcement learning for optimized backstepping tracking control of nonlinear systems with input delay

引用

APPLIED INTELLIGENCE 2025年第2期55卷 1-16页

作者： Zhu, Boyan Karimi, Hamid Reza Zhang, Liang Zhao, Xudong Bohai Univ Coll Control Sci & Engn Jinzhou 121013 Liaoning Peoples R China Politecn Milan Dept Mech Engn Via Masa 1 I-20156 Milan Italy DaLian Univ Technol Fac Elect Informat & Elect Engn Dalian 116024 Liaoning Peoples R China

In this paper, the problem of adaptive optimized tracking control design is addressed for a class of nonlinear systems in strict-feedback form. The system under consideration contains input delay and has unmeasurable and restricted states within predefined compact sets. First, neural networks (NNs) are employed to approximate the unknown nonlinear dynamics, and an adaptive neural network (NN) state observer is constructed to compensate for the absence of state information. Additionally, by utilizing an auxiliary system compensation method alongside the backstepping technique, the impact of input delay is eliminated, and the generation of intermediate variables is prevented. Second, tan-type barrier optimal cost functions are established for each subsystem within the backstepping method to prevent the state variables from exceeding preselected sets. Moreover, by establishing both actor and critic NNs to execute a reinforcement learning algorithm, the optimal controller and optimal performance index function are evaluated, while relaxing the persistence of excitation condition. According to the Lyapunov stability theorem, it is demonstrated that all signals in the closed-loop system are semi-globally uniformly ultimately bounded (SGUUB), and the output signal accurately tracks a reference trajectory with the desired precision. Finally, a practical simulation example is provided to verify the effectiveness of the proposed control strategy, demonstrating its potential for real-world implementation.

关键词： reinforcement learning algorithm Auxiliary system State observer Input delay Optimized backstepping technique

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

Short-Term Load Forecasting algorithm Using a Similar Day Selection Method Based on reinforcement learning

引用

ENERGIES 2020年第10期13卷 2640-2640页

作者： Park, Rae-Jun Song, Kyung-Bin Kwon, Bo-Sung Soongsil Univ Dept Elect Engn Seoul 06978 South Korea

Short-term load forecasting (STLF) is very important for planning and operating power systems and markets. Various algorithms have been developed for STLF. However, numerous utilities still apply additional correction processes, which depend on experienced professionals. In this study, an STLF algorithm that uses a similar day selection method based on reinforcement learning is proposed to substitute the dependence on an expert's experience. The proposed algorithm consists of the selection of similar days, which is based on the reinforcement algorithm, and the STLF, which is based on an artificial neural network. The proposed similar day selection model based on the reinforcement learning algorithm is developed based on the Deep Q-Network technique, which is a value-based reinforcement learning algorithm. The proposed similar day selection model and load forecasting model are tested using the measured load and meteorological data for Korea. The proposed algorithm shows an improvement accuracy of load forecasting over previous algorithms. The proposed STLF algorithm is expected to improve the predictive accuracy of STLF because it can be applied in a complementary manner along with other load forecasting algorithms.

关键词： short-term load forecasting deep Q-network (DQN) backpropagation neural network (BPNN) long short-term memory (LSTM) reinforcement learning algorithm

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

Dynamic Coordination of Energy and Hops in WSNs Using reinforcement learning Routing algorithm

Dynamic Coordination of Energy and Hops in WSNs Using Reinfo...

引用

International Conference on Information Sciences,Machinery,Materials and Energy（ICISMME 2015）

作者： Jianyong Li Huang Wei Department of Computer and Information Science Southwest University

In wireless sensor network,the existing reinforcement learning routing algorithm usually optimize single goal and the process of route establishment is *** also has problem of data forwarding control *** this paper,we present a dynamic adaptive routing algorithm with feedback learning ability to balance the energy of wireless sensor network,to reduce the routing hops,and to reduce the establishment *** algorithm will use the local routing information and the method of feedback to learn neighbors' state;routing reward values will be obtained by weighted calculation according to the energy information and the hop counts information;the optimal routing strategy will be obtained by updating the Q-value of routing table.

关键词： Wireless sensor network Routing algorithm reinforcement learning algorithm Energy consumption

来源：评论

学校读者我要写书评

暂无评论

Online Automatic Parameter Optimization of Marine Permanent Magnet Synchronous Motor Speed Controller Based on reinforcement learning 39

Online Automatic Parameter Optimization of Marine Permanent ...

引用

39th Youth Academic Annual Conference of Chinese-Association-of-Automation (YAC)

作者： Peng, Tianyu Li, Xuemin Zhang, Jian Wang, Chi Yin, He Harbin Engn Univ Coll Power & Energy Engn Harbin 15001 Peoples R China Natl Key Lab Marine Engine Sci & Technol Shanghai 201108 Peoples R China Shanghai Marine Diesel Engine Res Inst Shanghai 201108 Peoples R China

ISBN: (纸本)9798350390780;9798350379228

For the ship electric propulsion system, it is very important to maintain the stability of the speed. In this paper, the vector control system of permanent magnet synchronous motor (PMSM) is introduced. At the same time, aiming at the shortcomings of traditional proportional integral (PI) control, such as sensitivity to motor parameters and insufficient control performance when the load torque fluctuation is relatively large, a speed control strategy based on Q-learning reinforcement learning theory is proposed, which replaces the manual debugging process with intelligent algorithm online debugging.

关键词： PMSM reinforcement learning algorithm rotary speed control

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 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

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

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：