检索结果-内蒙古大学图书馆

reinforcement learning method for plug-in electric vehicle bidding

IET SMART GRID 2019年第4期2卷 529-536页

作者： Najafi, Soroush Shafie-khah, Miadreza Siano, Pierluigi Wei, Wei Catalao, Joao P. S. Isfahan Univ Technol Dept Elect & Comp Engn Esfahan Iran Univ Vaasa Sch Technol & Innovat Vaasa 65200 Finland Univ Salerno Dept Management & Innovat Syst Fisciano SA Italy Tsinghua Univ Dept Elect Engn State Key Lab Power Syst Beijing Peoples R China Univ Porto Fac Engn Porto Portugal INESC TEC Porto Portugal

This study proposes a novel multi-agent method for electric vehicle (EV) owners who will take part in the electricity market. Each EV is considered as an agent, and all the EVs have vehicle-to-grid capability. These agents aim to minimise the charging cost and to increase the privacy of EV owners due to omitting the aggregator role in the system. Each agent has two independent decision cores for buying and selling energy. These cores are developed based on a reinforcement learning (RL) algorithm, i.e. Q-learning algorithm, due to its high efficiency and appropriate performance in multi-agent methods. Based on the proposed method, agents can buy and sell energy with the cost minimisation goal, while they should always have enough energy for the trip, considering the uncertain behaviours of EV owners. Numeric simulations on an illustrative example with one agent and a testing system with 500 agents demonstrate the effectiveness of the proposed method.

关键词： electric vehicles power markets learning (artificial intelligence) multi-agent systems plug-in electric vehicle novel multiagent method electric vehicle owners electricity market vehicle-to-grid capability charging cost EV owners aggregator role independent decision cores buying selling energy reinforcement learning algorithm q-learning algorithm multiagent methods cost minimisation goal

来源：评论

学校读者我要写书评

暂无评论

Burden Control Strategy Based on reinforcement learning for Gas Utilization Rate in Blast Furnace 21st

Burden Control Strategy Based on Reinforcement Learning for ...

引用

21st IFAC World Congress on Automatic Control - Meeting Societal Challenges

作者： Shen, Xiaoling An, Jianqi Wu, Min She, Jinhua China Univ Geosci Sch Automat Wuhan 430074 Peoples R China Hubei Key Lab Adv Control & Intelligent Automat C Wuhan 430074 Peoples R China Tokyo Univ Technol Sch Engn Hachioji Tokyo 1920982 Japan

Gas utilization rate (GUR) is an important state parameter to reflect the energy consumption, the quality and production of the pig iron, and the distribution of the gas flow in a blast furnace. The GUR is mainly adjusted by burden distribution and hot-blast supply. According to the analysis of mechanism and data, burden distribution and hot-blast supply affect the GUR on a long-time scale and short-time scale, respectively. However, few of the previous researches proposed the control method for the GUR and they did not consider multi-time-scale characteristics. Thus, it is necessary to design a control strategy or system for the GUR considering the multi-time-scale characteristics, which can make the GUR have a reasonable development trend. This paper presented a burden control strategy based on a reinforcement learning algorithm for the GUR. The method improved the development trend of the GUR on a long-time scale. The experimental results demonstrated that the sequence of the parameters of the burden distribution given by the presented method ensured a reasonable development trend of the GUR on a long-time scale. Copyright (C) 2020 The Authors.

关键词： Blast furnace gas utilization rate burden control strategy reinforcement learning algorithm long-time scale

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

reinforcement learning for the Soccer Dribbling Task

Reinforcement Learning for the Soccer Dribbling Task

引用

IEEE Conference on Computational Intelligence and Games (CIG)

作者： Carvalho, Arthur Oliveira, Renato Univ Waterloo David Cheriton Sch Comp Sci Waterloo ON N2L 3G1 Canada Univ Fed Pernambuco Ctr Informat Recife PE Brazil

ISBN: (纸本)9781457700095

We propose a reinforcement learning solution to the soccer dribbling task, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball, as an adversary attempts to gain possession. While the adversary uses a stationary policy, the dribbler learns the best action to take at each decision point. After defining meaningful variables to represent the state space, and high-level macro-actions to incorporate domain knowledge, we describe our application of the reinforcement learning algorithm Sarsa with CMAC for function approximation. Our experiments show that, after the training period, the dribbler is able to accomplish its task against a strong adversary around 58% of the time.

关键词： Approximation algorithms CMAC Computational intelligence Equations Function approximation Games learning Sarsa Training cerebellar model arithmetic computers function approximation function approximation learning (artificial intelligence) multi-robot systems reinforcement learning algorithm soccer agent soccer dribbling task sport stationary policy

来源：评论

学校读者我要写书评

暂无评论

Web Service Composition Based on reinforcement learning

Web Service Composition Based on Reinforcement Learning

引用

IEEE International Conference on Web Services (ICWS)

作者： Yu Lei Zhou Jiantao Wei Fengqi Gao Yongqiang Yang Bo Inner Mongolia Univ Inner Mongolia Engn Lab Cloud Comp & Serv Softwar Hohhot Peoples R China

ISBN: (纸本)9781467372725

How we manage Web services depends on how we understand their variable parts and invariable parts. Studying them separately could make Web service research much easier and make our software architecture much more loose-coupled. We summarize two variable parts that affect Web service compositions: uncertain invocation results and uncertain quality of services. These uncertain factors affect success rate of service composition. Previous studies model the Web service problem as a planning problem, while this problem is considered as an uncertain planning problem in this paper. Specifically, we use Partially Observable Markov Decision Process to deal with the uncertain planning problem for service composition. According to the uncertain model, we propose a reinforcement learning method, which is an uncertainty planning method, to compose web services. The proposed method does not need to know complete information of services, instead it uses historical data and estimates the successful possibilities that services are composed together with respect to service outcomes and QoS. Simulation experiments verify the validity of the algorithm, and the results also show that our method improves the success rate of the service composition.

关键词： Web service composition optimal policy partially observable markov decision process reinforcement learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Identifying Most Probable Negotiation Scenario in Bilateral Contracts with reinforcement learning

Identifying Most Probable Negotiation Scenario in Bilateral ...

引用

World Conference on Information Systems and Technologies (WorldCIST)

作者： Silva, Francisco Pinto, Tiago Praca, Isabel Vale, Zita Polytech Porto ISEP IPP GECAD Res Grp Intelligent Engn & Comp Adv Innovat Porto Portugal Univ Salamanca BISITE Res Ctr Salamanca Spain Polytech Porto ISEP IPP Porto Portugal

ISBN: (纸本)9783030161804;9783030161811

This paper proposes an adaptation of the Q-learning reinforcement learning algorithm, for the identification of the most probable scenario that a player may face, under different contexts, when negotiating bilateral contracts. For that purpose, the proposed methodology is integrated in a Decision Support System that is capable to generate several different scenarios for each negotiation context. With this complement, the tool can also identify the most probable scenario for the identified negotiation context. A realistic case study is conducted, based on real contracts data, which confirms the learning capabilities of the proposed methodology. It is possible to identify the most probable scenario for each context over the learned period. Nonetheless, the identified scenario might not always be the real negotiation scenario, given the variable nature of such negotiations. However, this work greatly reduces the frequency of such unexpected scenarios, contributing to a greater success of the supported player over time.

关键词： Automated negotiation Bilateral contracts Decision Support System Electricity Markets reinforcement learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Research of reinforcement learning Control of Intelligent Robot based on Fuzzy-CMAC Network

Research of Reinforcement Learning Control of Intelligent Ro...

引用

1st International Symposium on Computer Network and Multimedia Technology

作者： Pan Lian Tong Yao-bin Wuhan Univ Sci & Technol Coll Informat Sci & Engn Wuhan Peoples R China

ISBN: (纸本)9781424452729

Intelligent grasping by servo robot-hand of monocular vision is a complex nonlinear control problem. In order to achieve high accuracy, model structure and parameters design of Fuzzy-CMAC are studied in this paper, and improved reinforcement learning algorithm is introduced into FCMAC. According to the reinforcement signals, different strategies are used to improve convergence speed and algorithm optimization. Based on the theory research, we do experimental research and try FCMAC to approach the nonlinear part of the dynamic model of the robot-hand. By analyzing the experimental results, it is concluded that this control strategy can solve the nonlinear problem effectively and the trained robot-hand can grasp the target object fleetly and accurately.

关键词： servo robot-hand intelligent grasping Fuzzy-CMAC network membership function reinforcement learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Hybrid algorithms based on combining reinforcement learning and metaheuristic methods to solve global optimization problems

引用

KNOWLEDGE-BASED SYSTEMS 2021年 223卷 107044-107044页

作者： Seyyedabbasi, Amir Aliyev, Royal Kiani, Farzad Gulle, Murat Ugur Basyildiz, Hasan Shah, Mohammed Ahmed Beykent Univ Fac Engn & Architecture Dept Comp Engn Istanbul Turkey Istanbul Aydin Univ Fac Engn Dept Comp Engn Istanbul Turkey Istanbul Arel Univ Fac Engn & Architecture Dept Comp Engn Istanbul Turkey Istanbul Ayvansaray Univ Fac Engn Dept Comp Engn Istanbul Turkey Istinye Univ Fac Engn Software Engn Dept Istanbul Turkey

This paper introduces three hybrid algorithms that help in solving global optimization problems using reinforcement learning along with metaheuristic methods. Using the algorithms presented, the search agents try to find a global optimum avoiding the local optima trap. Compared to the classical metaheuristic approaches, the proposed algorithms display higher success in finding new areas as well as exhibiting a more balanced performance while in the exploration and exploitation phases. The algorithms employ reinforcement agents to select an environment based on predefined actions and tasks. A reward and penalty system is used by the agents to discover the environment, done dynamically without following a predetermined model or method. The study makes use of Q-learning method in all three metaheuristic algorithms, so-called RLI-GWO, RLEx-GWO, and RLWOA algorithms, so as to check and control exploration and exploitation with Q-Table. The Q-Table values guide the search agents of the metaheuristic algorithms to select between the exploration and exploitation phases. A control mechanism is used to get the reward and penalty values for each action. The algorithms presented in this paper are simulated over 30 benchmark functions from CEC 2014, 2015 and the results obtained are compared with well-known metaheuristic and hybrid algorithms (GWO, RLGWO, I-GWO, Ex-GWO, and WOA). The proposed methods have also been applied to the inverse kinematics of the robot arms problem. The results of the used algorithms demonstrate that RLWOA provides better solutions for relevant problems. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Metaheuristic algorithm reinforcement learning algorithm Grey wolf optimization algorithm Whale optimization algorithm Q-learning

来源：评论

学校读者我要写书评

暂无评论

Robust and efficient task scheduling for robotics applications with reinforcement learning

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartA期127卷

作者： Tejer, Mateusz Szczepanski, Rafal Tarczewski, Tomasz Nicolaus Copernicus Univ Inst Engn & Technol Grudziadzka 5 PL-87100 Torun Poland

Effective task scheduling can significantly impact on performance, productivity, and profitability in many real-world settings, such as production lines, logistics, and transportation systems. Traditional approaches to task scheduling rely on heuristics or simple rule-based methods. However, with the emergence of machine learning and artificial intelligence, there is growing interest in using these methods to optimize task scheduling. In particular, reinforcement learning is a promising task scheduling approach, because it can learn from experience and adapt to changing conditions. One step often missed or neglected is choosing optimal algorithm parameters and different ways the environment could be implemented. The study analyzes the performance possibilities of task scheduling using reinforcement learning. The deep analysis allows to select highly efficient environment models and Q-learning parameters. Moreover, automatic selection based on optimization algorithms has been proposed. Regardless of the selected optimal parameters, the resilience to environmental changes seems poor. The deducted analysis motivated the Authors to develop a novel Hybrid Q-learning approach. It allows to provide superior efficiency regardless of the environmental parameters.

关键词： Task scheduling Robotic arm Sorting problem reinforcement learning algorithm Performance analysis Predictive strategies Task scheduling Robotic arm Sorting problem reinforcement learning algorithm Performance analysis Predictive strategies

来源：评论

学校读者我要写书评

暂无评论

reinforcement learning vibration control for a flexible hinged plate

引用

AEROSPACE SCIENCE AND TECHNOLOGY 2021年 118卷 107056-107056页

作者： Qiu, Zhi-cheng Chen, Guo-hao Zhang, Xian-min South China Univ Technol Sch Mech & Automot Engn Guangzhou 510641 Peoples R China

A reinforcement learning (RL) vibration control method for a flexible hinged plate is developed, including combined bending and torsional vibrations. The experimental setup is constructed. Two laser displacement sensors are used as detection sensors, and two-channel piezoelectric actuators are used to suppress both bending and torsional vibrations simultaneously. A method combining finite element modeling (FEM) and experimental identification is applied to obtain an accurate model of the system. The obtained model is constructed as an RL environment, and a deep deterministic policy gradient (DDPG) RL algorithm based on the priority experience replay (PER) is designed to train modal controllers. The RL modal controllers were transferred to the real experimental system by using the parameter transfer method, and the vibration control experiments were conducted by combining the bending and torsional vibration control method. Simulation and experimental results demonstrate that the controller trained by the proposed deep RL algorithm has better control effects compared with PD control, especially for small amplitude vibration. (C) 2021 Elsevier Masson SAS. All rights reserved.

关键词： Flexible hinged plate Active vibration control Model identification reinforcement learning algorithm Deep deterministic policy gradient (DDPG)

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：