检索结果-内蒙古大学图书馆

Optimal operation of regional integrated energy system based on multi-agent deep deterministic policy gradient algorithm

引用

ENERGY REPORTS 2022年 8卷 932-939页

作者： Xu, Bohan Xiang, Yue Sichuan Univ Coll Elect Engn Chengdu Peoples R China

The complex energy coupling and uncertainties of renewable energy and load make the dynamic scheduling of the integrated energy system (IES) very difficult. Therefore, an optimal operation method based on the multi-agent deep deterministic policy gradient algorithm (MADDPG) is proposed. Firstly, the IES model is established, and the optimal scheduling problem is transformed into the Markov decision problem;Then, the action-space, state-space and reward function of agents are designed which control energy conversion equipment and energy storage equipment respectively. Furtherly, a multi-agent framework is established based on the MADDPG;Finally, a scheduling simulation example was carried out. The simulation results indicate that compared with the single agent, the multi-agent framework can improve the stability of training for agents and the ability to explore the optimal solution. (C) 2022 The Author(s). Published by Elsevier Ltd.

关键词： Integrated energy system deep deterministic policy gradient algorithm Multi-agent scheduling

来源：评论

学校读者我要写书评

暂无评论

Information-Based Patrol Speed Control Method for Rail-Guided Robot System Using deep deterministic policy gradient algorithm 18th

Information-Based Patrol Speed Control Method for Rail-Guide...

引用

18th International Conference on Intelligent Autonomous Systems (IAS)

作者： Lee, Hosun Kwon, Jaesung Lee, Sungon Chong, Nak Young Yang, Woosung Japan Adv Inst Sci & Technol Sch Informat Sci Nomi Ishikawa Japan Kwangwoon Univ Sch Robot Seoul South Korea Hanyang Univ Dept Robot Ansan South Korea

ISBN: (纸本)9783031449802;9783031449819

To manage the safety of multi-use facilities, many CCTVs and alarm sensors are used, however, they cannot replace patrol tasks to check site conditions from multiple directions. The developed rail-guided smart patrol robot helps alleviate the workload of managers by capturing images and measuring sensors at a desired location at a scheduled time in a separate space from visitors or workers. This paper proposes an adaptive patrol speed control algorithm to improve patrol performance in the facility environment. By applying the deep deterministic policy gradient (DDPG)-based learning model, the smart patrol robot can be allowed to move at an optimal speed according to the congestion of images captured in the field. The designed model can be trained by defining the reward function based on the entropy to maintain the obtained information. The proposed algorithm demonstrated performance in controlling patrol speed according to situation changes in a virtual multi-use facility environment.

关键词： Rail-guided robot Safety patrol robot Reinforcement learning deep deterministic policy gradient algorithm Patrol speed control

来源：评论

学校读者我要写书评

暂无评论

A deep deterministic policy gradient algorithm Based Controller with Adjustable Learning Rate for DC-AC Inverters 2

A Deep Deterministic Policy Gradient Algorithm Based Control...

引用

2nd IEEE International Power Electronics and Application Symposium, PEAS 2023

作者： Ye, Jian Mei, Sen Guo, Huanyu Zhao, Di Zhang, Xinan School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen China School of Electrical Electronic and Computer Engineering University of Western Australia Perth Australia

ISBN: (纸本)9798350313765

This paper proposes an inverter control algorithm based on the deep deterministic policy gradient (DDPG) with adjustable learning rates. This algorithm retains the advantages of model-free control of the inverter and solves the inherent problem of learning rate setting in deep neural networks. As a result, the control algorithm can quickly converge to the desired state during training, accelerate the training process, and not be affected by the control effect. Through simulation, the training results of the adjustable learning rate DDPG algorithm are compared with those of the constant small learning rate and constant large learning rate DDPG algorithms. The simulation results show that the training efficiency is improved by 75%, while the control effect on the inverter is almost unaffected. © 2023 IEEE.

关键词： deep deterministic policy gradient algorithm learning rate reinforcement learning Three-Phase DC-AC Inverters

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning control method for real-time hybrid simulation based on deep deterministic policy gradient algorithm

引用

STRUCTURAL CONTROL & HEALTH MONITORING 2022年第10期29卷 e3035-e3035页

作者： Li, Ning Tang, Jichuan Li, Zhong-Xian Gao, Xiuyu Tianjin Univ Sch Civil Engn Tianjin 300350 Peoples R China Nanyang Technol Univ Sch Civil & Environm Engn Singapore Singapore Tianjin Univ Minist Educ Key Lab Coast Civil Struct Safety Tianjin Peoples R China Tianjin Univ Key Lab Earthquake Engn Simulat & Seism Resilienc China Earthquake Adm Tianjin Peoples R China MTS Corp Eden Prairie MN USA

The tracking performance of an actuation transfer system in a real-time hybrid simulation (RTHS) frequently faces accuracy and robustness challenges under constraints and complicated environments with uncertainties. This study proposes a novel control approach based on the deep deterministic policy gradient algorithm in reinforcement learning (RL) combined with feedforward (FF) compensation, which emphasizes the implementation of shaking table control and substructure RTHS. The proposed method first describes the control plant within the RL environment. Then, the agent is trained offline to develop optimized control policies for interaction with the environment. A series of validation tests were conducted to assess the performance of the proposed method, starting with the dynamic testing of underwater shaking table control and then a virtual RTHS benchmark problem. For complex systems, such as controlling the underwater shaking table, the proposed algorithm, FF, and adaptive time series (ATS) compensation methods are compared under various water depths and motions. The results show better performance and wider broadband frequency applicability under different shaking table dynamic-coupling effects. Next, a controller based on the proposed method was designed by extending the virtual RTHS via the configuration of the control plant and substructure division, as provided in the RTHS benchmark problem. The proposed RL controller also improved the tracking accuracy and robustness of conventional FF compensators against unmodeled dynamics and perturbation uncertainties. This controller can be extended to further advanced control strategies as a component of model-based control methods.

关键词： deep deterministic policy gradient algorithm hybrid control real-time hybrid simulation reinforcement learning underwater shaking table

来源：评论

学校读者我要写书评

暂无评论

Control Method for PEMFC Using Improved deep deterministic policy gradient algorithm

引用

FRONTIERS IN ENERGY RESEARCH 2021年 9卷

作者： Li, Jiawen Li, Yaping Yu, Tao South China Univ Technol Coll Elect Power Guangzhou Peoples R China China Elect Power Res Inst Nanjing Peoples R China

A data-driven PEMFC output voltage control method is proposed. Moreover, an Improved deep deterministic policy gradient algorithm is proposed for this method. The algorithm introduces three techniques: Clipped multiple Q-learning, policy delay update, and policy smoothing to improve the robustness of the control policy. In this algorithm, the hydrogen controller is treated as an agent, which is pre-trained to fully interact with the environment and obtain the optimal control policy. The effectiveness of the proposed algorithm is demonstrated experimentally.

关键词： output voltage proton exchange membrane fuel cell deep deterministic policy gradient algorithm robustness PEMFC

来源：评论

学校读者我要写书评

暂无评论

Continuous decision-making for autonomous driving at intersections using deep deterministic policy gradient

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2022年第12期16卷 1669-1681页

作者： Li, Guofa Li, Shenglong Li, Shen Qu, Xingda Shenzhen Univ Coll Mechatron & Control Engn Inst Human Factors & Ergon 3688 Nanhai Ave Shenzhen Guangdong Peoples R China Univ Wisconsin Dept Civil & Environm Engn Madison WI 53706 USA

Intersections have been identified as the most complex and accident-prone traffic scenarios on road. Making appropriate decisions at intersections for driving safety, efficiency, and comfort become a challenging task for autonomous vehicles (AVs). The existing research on AV decision-making at intersections either considers a single scenario only with discrete behaviour outputs or ignores the requirements for driving efficiency and comfort. To address these problems, this study proposed a deep reinforcement learning based continuous decision-making method to make AVs drive through intersections. The proposed method establishes an end-to-end decision-making framework by using a convolutional neural network to map the relationship between traffic images and vehicle operations. The interaction between the AV and other vehicles was modelled as a Markov decision process (MDP), and a deep deterministic policy gradient algorithm was employed to solve the MDP problem and obtain the optimal driving policy. The top three accident-prone crossing path crash scenarios at intersections were realized in CARLA to verify the effectiveness of the proposed method. The experimental results demonstrated that the developed method could provide effective policies to ensure driving safety and efficiency while considering driving comfort for autonomous driving at intersections in all the examined scenarios.

关键词： appropriate decisions optimal driving policy road accidents autonomous vehicles driving safety Markov decision process learning (artificial intelligence) deep deterministic policy gradient algorithm driver information systems neural nets complex accident-prone traffic scenarios other vehicles AV decision-making road safety road traffic control end-to-end decision-making framework deep reinforcement learning continuous decision-making method decision making autonomous driving collision avoidance Markov processes gradient methods accident-prone crossing path crash scenarios

来源：评论

学校读者我要写书评

暂无评论

Experimental validation of a semi-active fuzzy control strategy based on deep reinforcement learning for a piezoelectric smart isolation system

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 144卷

作者： Lin, Tzu-Kang Tappiti, Chandrasekhara Lu, Lyan-Ywan Lin, Ting-Kuan Natl Yang Ming Chiao Tung Univ Dept Civil Engn Hsinchu City Taiwan Natl Cheng Kung Univ Dept Civil Engn Tainan Taiwan

The high-tech industry, commanding a substantial portion of the global market, remains highly susceptible to disruptions caused by earthquakes because its products rely heavily on vibration-sensitive equipment. Moreover, the characteristics of seismic ground motions are usually difficult to predict;therefore, seismic protection of high-tech equipment is a challenging task. In this context, this study leverages the robustness and adaptability of artificial intelligence techniques, particularly deep reinforcement learning (DRL) and a piezo-electric smart isolation system (PSIS) to protect high-tech equipment. The control objective of the PSIS is to dynamically optimize the isolation performance of the PSIS in real time, accommodating diverse ground motion characteristics. The proposed control strategy for PSIS involves a DRL framework integrated with a fuzzy inference system (FIS) and non-striking friction (NSF) control technique. In the DRL framework, a deep deterministic policy gradient (DDPG) algorithm is utilized to train the DRL model, employing tailored reward functions to achieve diverse control objectives under varying seismic conditions. The efficacy of the proposed PSIS control strategy is evaluated through numerical simulations and experimental validation. The proposed DRL control module demonstrated superior isolation performance compared to other control algorithms, particularly in reducing isolation displacement by approximately 24% during near-fault earthquakes and superstructure acceleration of 39% reduction under far-field earthquakes. The research outcomes underscore the effectiveness of the proposed approach, positioning it as a promising solution for fortifying the seismic resilience of vibration-sensitive equipment and a strong support of advancing the current nano-scale manufacturing process in the high-tech industry.

关键词： Semi-active control Ground motion characteristics deep reinforcement learning deep deterministic policy gradient algorithm Fuzzy control System identification Variable friction damper Non-sticking friction

来源：评论

学校读者我要写书评

暂无评论

Cyber Attack Detection Using deep Multi-agent Reinforcement Learning with Beth Dataset

引用

SN Computer Science 2025年第5期6卷 1-16页

作者： Manikandan, A. Rajan, S. deepa Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies VISTAS Tamil Nadu Chennai India

The Internet of Things (IoT) transforms connectivity, enabling devices to share data seamlessly via the cloud or wireless networks. However, IoT systems remain vulnerable to sophisticated cyberattacks, and traditional detection methods often fail due to inadequate fine-tuning and ineffective feature extraction. This study addresses these challenges by proposing a novel cyberattack detection framework based on deep multi-agent reinforcement learning (MARL). The framework employs the deep deterministic policy gradient (DDPG) algorithm to enhance the adaptive capabilities of multiple agents within an IoT network environment. A newly curated dataset, BETH, is introduced, encompassing diverse cyberattack scenarios specifically designed for training and evaluating MARL-based systems. Through deep reinforcement learning, the framework autonomously learns to detect and mitigate known and emerging threats. To assess the robustness and generalizability of the proposed model, a fivefold cross-validation process was conducted. Experimental results reveal that the proposed approach achieves an exceptional detection accuracy of 99.95%, demonstrating its ability to adapt to dynamic attack patterns while minimizing error rates. The findings highlight the framework’s potential to improve network security significantly, advancing the field of intelligent, autonomous cyber defence for IoT systems. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Anomaly detection agents (ADA) BETH dataset Collaboration and communication buffer (CCB) Cyber-attack detection deep deterministic policy gradient algorithm Internet of Things (IoT) Intrusion detection agents (IDA) Multi-agent reinforcement learning (MARL)

来源：评论

学校读者我要写书评

暂无评论

Energy management strategy for hybrid electric vehicles based on deep reinforcement learning with consideration of electric drive system thermal characteristics

引用

ENERGY CONVERSION AND MANAGEMENT 2025年 332卷

作者： Qin, Juhuan Huang, Haozhong Lu, Hualin Li, Zhaojun Guangxi Univ Coll Mech Engn Nanning 530004 Peoples R China

deep reinforcement learning has emerged as a promising candidate for online optimised energy management in hybrid vehicles. However, previous studies have not considered the impact of the overall thermal characteristics of key components in a hybrid electric system on the system performance. In this paper, an energy management strategy based on deep deterministic policy gradient algorithm considering the thermal characteristics of the electric drive system is proposed for plug-in hybrid electric vehicles, aiming at controlling the battery and motor temperatures within a safe range and improving the vehicle's overall performance of the vehicle. Firstly, the temperature models of battery and motor are constructed and introduced into the energy management strategy framework. Secondly, the weight coefficients are adjusted using an intelligent algorithm based on deep deterministic policy gradient to achieve the trade-off between multiple objectives. Simulation experiments are carried out based on a variety of typical cycling conditions, and the results show that the proposed strategy maintains the powertrain in the optimal operating temperature range by dynamically adjusting the operating states of the battery and motor. Compared with the original strategy, the final battery temperature is reduced by 2.557 degrees C, the motor temperature is reduced by 1.806 degrees C, and the fuel consumption is reduced by about 8.46 %. Moreover, the energy consumption can reach 95.82 % of the dynamic planning. These results not only verify the effectiveness of the proposed strategy in energy optimization, but also fully demonstrates its robustness by maintaining a stable output in stress tests with different boundary conditions.

关键词： deep deterministic policy gradient algorithm Plug-in hybrid electric vehicles Battery temperature management Motor temperature management

来源：评论

学校读者我要写书评

暂无评论

Trajectory Optimization and Power Allocation Scheme Based on DRL in Energy Efficient UAV-Aided Communication Networks

引用

Chinese Journal of Electronics 2022年第3期31卷 397-407页

作者： WANG Chaowei CUI Yuling DENG Danhao WANG Weidong JIANG Fan School of Electronic Engineering Beijing University of Posts and Telecommunications Key Laboratory of Universal Wireless Communications Ministry of Education School of Telecommunications and Information Engineering Xi'an University of Posts and Telecommunications

With flexibility, convenience and mobility, unmanned aerial vehicles(UAVS) can provide wireless communication networks with lower costs, easier deployment, higher network scalability and larger *** paper proposes the deep deterministic policy gradient algorithm to jointly optimize the power allocation and flight trajectory of UAV with constrained effective energy to maximize the downlink throughput to ground users. To validate the proposed algorithm, we compare with the random algorithm, Q-learning algorithm and deep Q network algorithm. The simulation results show that the proposed algorithm can effectively improve the communication quality and significantly extend the service time of UAV. In addition, the downlink throughput increases with the number of ground users.

关键词： unmanned aerial vehicles remotely operated vehicles trajectory optimization Q-learning algorithm power allocation scheme flight trajectory communication quality optimisation mobile robots random algorithm deep Q network algorithm learning systems constrained effective energy ground users autonomous aerial vehicles network scalability resource allocation UAVS energy efficient UAV-aided communication networks gradient methods deep deterministic policy gradient algorithm trajectory control radio networks wireless communication networks

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：