检索结果-内蒙古大学图书馆

Fuzzy line enhancement scheme of computer art image based on drl algorithm

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2023年第2期23卷 949-961页

作者： Guo, Yong Guangzhou Inst Technol Sch Art & Design Guangzhou 510075 Guangdong Peoples R China

In this study, a new blurred line enhancement scheme of computer art image based on Deep Reinforcement Learning (drl) algorithm was proposed. The hard threshold method is adopted to remove the noise of computer art images and the blurred lines are extracted by texture separation method. Based on the line extraction results, the Deep Q-Network (DQN) model was built with drl algorithm, and the sample images were input into the model, and the fuzzy line enhancement results of computer art images were obtained in the output layer. The proposed method exhibits excellent noise reduction effect, and the fuzzy line enhancement quality of computer art image is good. The average enhancement time is 0.58 s, and the practical application effect is good.

关键词： drl algorithm computer art image fuzzy line enhancement texture separation DQN model

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning based active safety control for distributed drive electric vehicles

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2022年第6期16卷 813-824页

作者： Wei, Hongqian Zhao, Wenqiang Ai, Qiang Zhang, Youtong Huang, Tianyi Beijing Inst Technol Sch Mech Engn Beijing 100081 Peoples R China

Distributed drive electric vehicles are regarded as the promising transportation due to the advanced power flow architecture. Optimizing the yaw motion to enhance vehicle safety is a challenging job. Besides, the nonlinear features in vehicles affect the control accuracy of the yaw motion controllers. To this end, a deep reinforcement learning (drl) based direct yaw moment control (DYC) strategy is put forward here. Vehicle dynamics can be approximated with the drl algorithm, which reduces the complex nonlinear solving process. Concretely, the DYC problem is formulated as Markov Decision Process in which the observed signals and external yaw moment are incorporated as the state and action sets. Thereupon, actor-critic network is exhibited to approximate action-value function and policy function for better control performance. Furthermore, to guarantee the continuous solution of external yaw moment, the deep deterministic policy gradient algorithm is employed, in which target and online network parameters are simultaneously trained to maintain learning process stability. The proposed drl based DYC strategy is verified using the Carsim/Simulink platform under the typical lane change manoeuvres. Numerical test results demonstrate that the proposed DYC strategy outperforms the linear approaches on taking full advantage of understeer features and enhancing the lateral stability, especially under the critical steering manoeuvres.

关键词： steering systems external yaw moment electric vehicles road vehicles DYC problem nonlinear features deep learning (artificial intelligence) control performance control engineering computing Markov decision process optimisation deep deterministic policy gradient algorithm Carsim platform complex nonlinear solving process yaw motion controllers drl algorithm learning process stability road safety vehicle safety critical steering manoeuvres DYC strategy reinforcement learning deep reinforcement learning distributed drive electric vehicles lateral stability vehicle dynamics stability motion control Markov processes control accuracy active safety control Simulink platform gradient methods direct yaw moment control strategy advanced power flow architecture approximate action-value function traffic engineering computing

来源：评论

学校读者我要写书评

暂无评论

Deep reinforced learning-based inductively coupled DSTATCOM under load uncertainties

引用

ELECTRICAL ENGINEERING 2024年 1-12页

作者： Mangaraj, Mrutyunjaya Muyeen, S. M. Babu, B. Chitti Nizami, Tousif Khan Singh, Satyavir Chakravarty, Arghya SRM Univ Dept Elect & Elect Engn Amaravati 522502 Andhra Pradesh India Qatar Univ Dept Elect Engn Doha 2713 Qatar Indian Inst Informat Technol Design & Mfg Dept Elect & Commun Engn Chennai 600127 India

Concerning the power quality issues in the power distribution network due to load uncertainties and improper impedance matching of the inductances, deep reinforced learning (drl)-based inductively coupled DSTATCOM (IC-DSTATCOM) is proposed. First, by analyzing the impedance matching principle, the expression of source, load and filter current is derived with the help of inductive filtering transformer. And second, an individual drl subnet structure is accumulated for each phase using mathematical equations to perform the better dynamic response. A 10-kVA, 230-V, 50-Hz prototype direct coupled distributed static compensator (DC-DSTATCOM) and IC-DSTATCOM experimental setup is buit to verify the experimental performance under uncertainties of loading. The IC-DSTATCOM is augmented better dynamic performance in terms of harmonics curtailment, improvement in power factor, load balancing, potential regulation, etc. The benchmark IEEE-519-2017, IEC-61727 and IEC-61000-1 grid code are used to evaluate the effectiveness of the simulation and experimental study.

关键词： drl algorithm IC-DSTATCOM DC-DSTATCOM PCC

来源：评论

学校读者我要写书评

暂无评论

Smart Energy Management in Green IoT Applications 24

Smart Energy Management in Green IoT Applications

引用

International Conference on Machine Intelligence and Digital Applications (MIDA)

作者： Liu, Kailun Zhou, Mengxue Wang, Di State Grid Henan Informat & Telecommun Co Zhengzhou 450000 Henan Peoples R China

ISBN: (纸本)9798400718144

This article explored the application of smart energy management in the green Internet of Things (IoT), with the goal of improving energy utilization efficiency and achieving energy conservation and emission reduction. Through analysis of existing research, it was found that traditional energy management methods had many shortcomings in real-time monitoring, data processing speed, and intelligence level. To address these issues, this article proposed an intelligent energy management method based on the drl (Deep Reinforcement Learning) algorithm. Based on the drl algorithm, the average energy consumption was 11.5 kWh. Secondly, in terms of device collaboration capability, the drl algorithm significantly reduced data transmission latency. In the final reliability evaluation of intelligent energy management system based on drl algorithm, the average recovery time of drl algorithm was 40 seconds, and the average task completion rate was 90.2%. From the data conclusion, it can be seen that the intelligent energy management system based on drl algorithm has significant advantages in improving energy utilization efficiency, optimizing equipment collaboration ability, and enhancing system reliability.

关键词： Smart Energy Management Green Internet of Things drl algorithm Energy Utilization Efficiency Simple Scheduling algorithm

来源：评论

学校读者我要写书评

暂无评论

Intelligent Dispatching of Electricity Consumption Information Collection in the Electricity Market Environment 2

Intelligent Dispatching of Electricity Consumption Informati...

引用

2nd IEEE International Conference on Electrical, Automation and Computer Engineering, ICEACE 2024

作者： Zheng, Xiaohui Chen, Li Liu, Yuluan Gao, Qiangqiang State Grid Info-Telecom Great Power Science and Technology Co. Ltd. Fuzhou350003 China Economic and Technical Research Institute of State Grid Fujian Electric Power Co. Ltd Fuzhou350001 China

ISBN: (纸本)9798350368208

Factors affecting data collection are varied, with the continuous innovation of technology, management measures continue to improve, electric power data collection is reliably guaranteed, the success rate of data collection will play a water to the effectiveness of the improvement. This article studies how to optimize the collection of electricity consumption information through intelligent scheduling systems in the electricity market environment. A collection and scheduling algorithm based on Deep Reinforcement Learning (drl) is proposed to improve the overall efficiency and reliability of the power system by analyzing the demand and supply fluctuations in the electricity market. In the experiment, a comprehensive evaluation of the intelligent power collection and scheduling system based on drl was conducted through three experiments, and the accuracy of the collection method based on drl algorithm was 0.84. In the real-time response speed evaluation experiment, the average response time of the scheduling system based on drl algorithm was 0.83 seconds. In the final experiment, the intelligent power collection system based on drl algorithm achieved a power resource utilization efficiency of 0.87. In the above data conclusions, the intelligent power collection system based on drl algorithm has significant advantages in accuracy, real-time performance, and efficiency improvement. © 2024 IEEE.

关键词： Accuracy of Data Collection drl algorithm Electricity Market Dispatch Electricity Usage Information Collection

来源：评论

学校读者我要写书评

暂无评论

An Uncertainty-Aware Transfer Learning-Based Framework for COVID-19v Diagnosis 2

An Uncertainty-Aware Transfer Learning-Based Framework for C...

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Mishra, Saket Centre for Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350308846

More and more studies are looking at the use of dynamic off-chain transportation in IoT systems that are based on payment channel networks (PCNs). Flexible routing in PCN-based IoT, where devices often have little resources, has two key challenges, however. The primary problem is figuring out how to make PCNs with variable channel capacity work efficiently for long-term transactions. The second issue is how to maximise transaction efficiency (the number of successful payments and the proportion of those that go through) by employing a lightweight routing strategy on IoT gadgets. To achieve this objective, we propose a powerful deep reinforcement training method for learning the combined flexible and lightweight routing approach. We use a proximal policy optimising strategy to attain the best effectiveness in dynamic routing problems for off-chain systems via an actorcritic learning structure to train the instructor's drl model. By using an adaptive pruning strategy to remove superfluous network parameters from the teacher model without compromising the latter's receptiveness to new information, we are able to generate a compact and effective drl model for the student. The effectiveness of the pupil's network is also improved by the use of knowledge distillation. Therefore, it may be possible to construct a small and efficient pupil drl model and utilise it to optimise the long-term efficacy of operations in off-chain networks on limited-resource IoT devices. Results from computer simulations show that the suggested drl algorithm improves PCN transaction performance compared to the baseline techniques, while using just 10% of the resources available in the original instructor model. © 2023 IEEE.

关键词： Covid 19 diagnosis drl algorithm PCN and optimization transfer learning

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：