检索结果-内蒙古大学图书馆

14th Asian Control Conference (ASCC)

作者： Wu, Ting Wang, Ronghao Zhang, Yan Meng, Yuhang Xiang, Yuzhu Xiang, Zhengrong Nanjing Univ Sci & Technol Sch Automat Nanjing Peoples R China Army Engn Univ PLA Coll Def Engn Nanjing Peoples R China

ISBN: (纸本)9798331540845;9789887581598

In this paper, a deep reinforcement learning (DRL) method for the global path planning of the water-air amphibious unmanned vehicle (WAAUV) is proposed. Firstly, the mathematical model of the WAAUV is constructed in line with the characteristics of an unmanned surface vehicle (USV) and a quadrotor unmanned aerial vehicle (UAV). Secondly, a Markov decision process (MDP) framework of the deep deterministic policy gradient (DDPG) algorithm is established to plan the path during navigation and flight, including the state space, the action space, and reward functions. In particular, the novel reward functions which overcome the sparse reward problem, are designed by fully considering the multiple constraints, such as reaching the goal point, energy consumption, obstacle avoidance, and so on. The control policy is trained with repeated trials by adjusting relevant parameters. Finally, through the simulations of the WAAUV in two modes, the feasibility and effectiveness of the proposed method is demonstrated.

关键词： Water-air amphibious unmanned vehicle global path planning deep reinforcement learning deep deterministic policy gradient algorithm multiple constraints

来源：评论

学校读者我要写书评

暂无评论

Distributed deep reinforcement learning-based gas supply system coordination management method for solid oxide fuel cell

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第1期120卷

作者： Li, Jiawen Cui, Haoyang Jiang, Wei Shanghai Univ Elect Power Sch Elect & informat Engn Shanghai 201306 Peoples R China Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Dept Elect Engn Shanghai 200240 Peoples R China

In order to sustain solid oxide fuel cell (SOFC) net output power and prevent violation of oxygen excess ratio (OER) constraint and fuel utilization (FU) constraint, a data-driven gas supply system coordination management method is proposed. Accordingly, a population evolution-based multi-agent double delay deep deterministic policy gradient (PE-MA4DPG) algorithm is introduced. The artificial intelligence design of the algorithm is guided by the concepts of imitation learning and curriculum learning, whereby different agents of different combinations are trained in different environments, thus improving the robustness of the coordination strategy. In this algorithm, the hydrogen controller and the air controller are treated as two agents. The centralized training enables agents with different objectives to coordinate with each other. The effectiveness of the proposed algorithm is demonstrated in three experiments, wherein the proposed algorithm is compared with a group of existing algorithms.

关键词： Solid oxide fuel cell Population evolution multi-agent double delay deep deterministic policy gradient algorithm Gas supply system coordination management method Distributed deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Cluster Content Caching: A deep Reinforcement Learning Approach to Improve Energy Efficiency in Cell-Free Massive Multiple-Input Multiple-Output Networks

引用

SENSORS 2023年第19期23卷 8295页

作者： Tan, Fangqing Peng, Yuan Liu, Qiang Guilin Univ Elect Technol Guangxi Key Lab Wireless Wideband Commun & Signal Guilin 541004 Peoples R China Shandong Univ Sci & Technol Coll Elect & Informat Engn Qingdao 266590 Peoples R China

With the explosive growth of micro-video applications, the transmission burden of fronthaul and backhaul links is increasing, and meanwhile, a lot of energy consumption is also generated. For reducing energy consumption and transmission delay burden, we propose a cell-free massive multiple-input multiple-output (CF-mMIMO) system in which the cache on the access point (AP) is used to reduce the load on the link. In this paper, a total energy efficiency (EE) model of a cache-assisted CF-mMIMO system is established. When optimizing EE, forming the co-operation cluster is critical. Therefore, we propose an energy-efficient joint design of content caching, AP clustering, and low-resolution digital-to-analog converter (DAC) in a cache-assisted CF-mMIMO network based on deep reinforcement learning. This scheme can effectively cache content in APs and select the appropriate DAC resolution. Then, taking into account the channel state information and user equipment (UE)'s content request preference, a deep deterministic policy gradient algorithm is used to jointly optimize the cache strategy, AP clustering, and DAC resolution decisions. Simulation results show that the energy efficiency of the proposed scheme is 4% higher than that of other schemes without the resolution optimization and is much higher than that of the only AP clustering without the joint design of content caching and channel quality.

关键词： content caching cell-free massive MIMO energy efficiency deep deterministic policy gradient algorithm

来源：评论

学校读者我要写书评

暂无评论

Logistics-involved service composition in a dynamic cloud manufacturing environment: A DDPG-based approach

引用

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING 2022年第0期76卷 102323-102323页

作者： Liu, Yongkui Liang, Huagang Xiao, Yingying Zhang, Haifeng Zhang, Jingxin Zhang, Lin Wang, Lihui Xidian Univ Sch Mechanoelect Engn Xian 710071 Peoples R China Changan Univ Sch Elect & Control Xian 710064 Peoples R China Beijing Inst Elect Syst Engn State Key Lab Complex Prod Intelligent Mfg Syst T Beijing 100854 Peoples R China Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China KTH Royal Inst Technol Dept Prod Engn S-10044 Stockholm Sweden

Service composition as an important technique for combining multiple services to construct a value-added service is a major research issue in cloud manufacturing. Highly dynamic environments present great challenges to cloud manufacturing service composition (CMfg-SC). Most of previous studies employ heuristic algorithms to solve service composition issues in cloud manufacturing, which, however, are designed for specific problems and lack adaptability necessary to dynamic environment. Hence, CMfg-SC calls for new adaptive approaches. Recent advances in deep reinforcement learning (DRL) provide a new means for solving this issue. Based on DRL, we propose a deep deterministic policy gradient (DDPG)-based service composition approach to cloud manufacturing, with which optimal service composition solutions can be learned through repeated training. Performance of DDPG in solving CMfg-SC in both static and dynamic environments is examined. Results obtained with another DRL algorithm -deep Q-Networks (DQN) and the traditional Ant Colony Optimization (ACO) are also presented. Comparison indicates that DDPG has better adaptability, robustness, and extensibility to dynamic environments than ACO, although ACO converges faster and its steady QoS value of the service composition solution is higher than that of DDPG by 0.997%. DDPG outperforms DQN in convergence speed and stability, and the QoS value of the service composition solution of DDPG is higher than that of DQN by 3.249%.

关键词： Cloud manufacturing service composition deep reinforcement learning deep deterministic policy gradient algorithm Ant Colony Optimization

来源：评论

学校读者我要写书评

暂无评论

deep Reinforcement Learning-Based Joint Low-Carbon Optimization for User-Side Shared Energy Storage-Distribution Networks

引用

PROCESSES 2024年第9期12卷 1791页

作者： Zhong, Lihua Ye, Tong Yang, Yuyao Pan, Feng Feng, Lei Qi, Shuzhe Huang, Yuping Guangdong Power Grid Co Ltd Metrol Ctr Qingyuan 511545 Peoples R China Chinese Acad Sci Guangzhou Inst Energy Convers Guangzhou 510640 Peoples R China Univ Sci & Technol China Sch Energy Sci & Engn Hefei 230026 Peoples R China

As global energy demand rises and climate change poses an increasing threat, the development of sustainable, low-carbon energy solutions has become imperative. This study focuses on optimizing shared energy storage (SES) and distribution networks (DNs) using deep reinforcement learning (DRL) techniques to enhance operation and decision-making capability. An innovative dynamic carbon intensity calculation method is proposed, which more accurately calculates indirect carbon emissions of the power system through network topology in both spatial and temporal dimensions, thereby refining carbon responsibility allocation on the user side. Additionally, we integrate user-side SES and ladder-type carbon emission pricing into DN to create a low-carbon economic dispatch model. By framing the problem as a Markov decision process (MDP), we employ the DRL, specifically the deep deterministic policy gradient (DDPG) algorithm, enhanced with prioritized experience replay (PER) and orthogonal regularization (OR), to achieve both economic efficiency and environmental sustainability. The simulation results indicate that this method significantly reduces the operating costs and carbon emissions of DN. This study offers an innovative perspective on the synergistic optimization of SES with DN and provides a practical methodology for low-carbon economic dispatch in power systems.

关键词： shared energy storage ladder-type carbon price low-carbon optimal scheduling deep reinforcement learning deep deterministic policy gradient algorithm

来源：评论

学校读者我要写书评

暂无评论

Hierarchical energy management of plug-in hybrid electric trucks based on state-of-charge optimization

引用

JOURNAL OF ENERGY STORAGE 2023年 72卷

作者： Liu, Xin Yang, Changbo Meng, Yanmei Zhu, Jihong Duan, Yijian Chen, Yujin Guangxi Univ Sch Mech Engn Nanning 530004 Peoples R China Dongfeng Liuzhou Motor Co Ltd Liuzhou 545005 Peoples R China Tsinghua Univ Dept Precis Instrument Beijing 100084 Peoples R China

To solve the contradiction between the optimality of the energy management strategy and the adaptability of the driving conditions of the hybrid electric vehicle. This paper proposes a hierarchical energy management strategy for plug-in hybrid electric trucks based on the state of charge (SOC). In the upper hierarchical layer, the deep deterministic policy gradient (DDPG) algorithm is used to generate the SOC reference value for the future driving section based on the historical driving condition information, to guide the SOC of the battery and make the SOC run in a reasonable range. Ultimately, it enables optimal battery discharge for plug-in hybrid electric trucks throughout the journey. In the lower hierarchical layer, the long short-term memory (LSTM) neural network algorithm is used to predict vehicle speed in the short term. Meanwhile, the model predictive control of the vehicle is constructed to distribute the required power of the plug-in hybrid electric truck in real-time, and the penalty factor is introduced into the objective function to accurately follow the SOC reference value. The simulation results show that the control strategy in this paper saves 16.34 % of fuel compared with the chargedepleting/charge-sustaining (CD/CS) strategy, which greatly improves fuel economy. At the same time, the simulation results of different driving conditions show that the fuel-saving rate is about 16 %, which verifies the robustness of the proposed method.

关键词： Plug-in hybrid electric truck deep deterministic policy gradient algorithm Long short -term memory neural network algo rithm Energy management strategy Driving cycle

来源：评论

学校读者我要写书评

暂无评论

Controlling distributed energy resources via deep reinforcement learning for load flexibility and energy efficiency

引用

APPLIED ENERGY 2021年 304卷 117733-117733页

作者： Touzani, Samir Prakash, Anand Krishnan Wang, Zhe Agarwal, Shreya Pritoni, Marco Kiran, Mariam Brown, Richard Granderson, Jessica Lawrence Berkeley Natl Lab Berkeley CA 94720 USA

Behind-the-meter distributed energy resources (DERs), including building solar photovoltaic (PV) technology and electric battery storage, are increasingly being considered as solutions to support carbon reduction goals and increase grid reliability and resiliency. However, dynamic control of these resources in concert with traditional building loads, to effect efficiency and demand flexibility, is not yet commonplace in commercial control products. Traditional rule-based control algorithms do not offer integrated closed-loop control to optimize across systems, and most often, PV and battery systems are operated for energy arbitrage and demand charge management, and not for the provision of grid services. More advanced control approaches, such as MPC control have not been widely adopted in industry because they require significant expertise to develop and deploy. Recent advances in deep reinforcement learning (DRL) offer a promising option to optimize the operation of DER systems and building loads with reduced setup effort. However, there are limited studies that evaluate the efficacy of these methods to control multiple building subsystems simultaneously. Additionally, most of the research has been conducted in simulated environments as opposed to real buildings. This paper proposes a DRL approach that uses a deep deterministic policy gradient algorithm for integrated control of HVAC and electric battery storage systems in the presence of on-site PV generation. The DRL algorithm, trained on synthetic data, was deployed in a physical test building and evaluated against a baseline that uses the current best-in-class rule-based control strategies. Performance in delivering energy efficiency, load shift, and load shed was tested using price-based signals. The results showed that the DRL-based controller can produce cost savings of up to 39.6% as compared to the baseline controller, while maintaining similar thermal comfort in the building. The project team has also int

关键词： deep reinforcement learning deep deterministic policy gradient algorithm Smart buildings Control systems Distributed energy resources Load flexibility Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Data-driven voltage/var optimization control for active distribution network considering PV inverter reliability

引用

ELECTRIC POWER SYSTEMS RESEARCH 2023年第1期224卷

作者： Zhang, Bo Gao, Yuan North China Elect Power Univ Key Lab Distributed Energy Storage & Microgrid Heb Baoding 071003 Peoples R China

Fully exploiting the reactive power support capability of the distributed photovoltaic power supply is helpful to solve the problems of voltage fluctuation, voltage overlimit and new energy consumption in the distribution network. However, the reactive power output of the photovoltaic power supply will seriously threaten the reliable operation of the photovoltaic inverter. Therefore, this paper proposes a data-driven voltage-reactive optimization control strategy considering the reliability of the photovoltaic inverter. Firstly, the data-driven model is used to calculate the insulated gate bipolar transistor junction temperature, which improves the calculation efficiency of the insulated gate bipolar transistor junction temperature and reduces the dependence of the evaluation accuracy on the insulated gate bipolar transistor parameters. Then, the voltage-reactive optimization control model of the distribution network considering the reliability of the photovoltaic inverter is established, and the average junction temperature and junction temperature fluctuation of the insulated gate bipolar transistor are introduced into the model optimization goal. The optimization model is transformed into the reinforcement learning task, and then the deep deterministic policy gradient algorithm is used to realize voltage-reactive control. According to the simulation of IEEE 33 node distribution system, the proposed strategy can increase the minimum and average insulated gate bipolar transistor lifetime of all nodes by 6 years and 4 years. At the same time, it can reduce the minimum and average levelized cost of energy of all nodes by 0.1095 $/W and 0.0318 $/W.

关键词： Distribution network Reliability assessment Voltage-reactive optimization control Reinforcement learning deep deterministic policy gradient algorithm

来源：评论

学校读者我要写书评

暂无评论

Distributed deep reinforcement learning-based coordination performance optimization method for proton exchange membrane fuel cell system

引用

SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS 2022年 50卷

作者： Li, Jiawen Yang, Bo Yu, Tao South China Univ Technol Coll Elect Power Guangzhou 510640 Peoples R China Kunming Univ Sci & Technol Fac Elect Power Engn Kunming 650093 Yunnan Peoples R China

A proton exchange membrane fuel cell (PEMFC) is a multi-input multi-output nonlinear complicated system, the output power and operating efficiency of which are affected by various operating variables. To achieve coor-dinated control of multiple operating variables and thus improve the stability, performance, and efficiency of the PEMFC power system, a data-driven power coordination management method is proposed. Furthermore, a metaverse-based multiagent double delay deep deterministic policy gradient (MET-MADDPG) algorithm is also presented. The design of this algorithm is structured on the concept of the metaverse in that it employs different metaverses during pre-learning and combines imitation learning and curriculum learning to enable agents in different combinations to be fully trained in different environments to improve coordination strategy robustness. In this algorithm, the hydrogen controller, air controller, water pump controller and radiator controller are regarded as four agents;the objective of the training is to enable agents with their different goals to coordinate. The effectiveness of the proposed algorithm is demonstrated in a series of experiments in which it is compared with existing algorithms.

关键词： Metaverse Metaverse-based multi-agent double delay deep deterministic policy gradient algorithm Proton exchange membrane fuel cell (PEMFC) Power coordination management method Distributed deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Experimental Research on the Correction of Vortex Light Wavefront Distortion

引用

PHOTONICS 2024年第12期11卷 1116-1116页

作者： Ge, Yahang Ke, Xizheng Xian Univ Technol Fac Automat & Informat Engn Xian 710048 Peoples R China Shaanxi Civil Mil Integrat Key Lab Intelligence Co Xian 710126 Peoples R China

Wavefront distortion occurs when vortex beams are transmitted in the atmosphere. The turbulence effect greatly affects the transmission of information, so it is necessary to use adaptive optical correction technology to correct the wavefront distortion of the vortex beam at the receiving end. In this paper, a method of vortex wavefront distortion correction based on the deep deterministic policy gradient algorithm is proposed;this is a new correction method that can effectively handle high-dimensional state and action spaces and is especially suitable for correction problems in continuous action spaces. The entire system uses adaptive wavefront correction technology without a wavefront sensor. The simulation results show that the deep deterministic policy gradient algorithm can effectively correct the distorted vortex beams and improve the mode purity, and the intensity correlation coefficient of single-mode vortex light can be increased to about 0.88 and 0.69, respectively, under weak turbulence and strong turbulence, and the intensity coefficient of weak-turbulence multi-mode vortex light can be increased to about 0.96. The experimental results also show that the adaptive correction technology based on the deep deterministic policy gradient algorithm can effectively correct the wavefront distortion of vortex light.

关键词： vortex light wavefront correction atmospheric turbulence deep deterministic policy gradient algorithm

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：