检索结果-内蒙古大学图书馆

1st electrical Artificial Intelligence Conference, EAIC 2024

作者： Peng, Ziran He, Zhenyu Xiao, Shenping School of Electrical and Information Engineering Hunan University of Technology Hunan Zhuzhou412007 China Hunan Provincial Key Laboratory of Electric Drive Control and Intelligent Equipment Hunan Zhuzhou412007 China

ISBN: (纸本)9789819640584

Deep Reinforcement Learning (DRL) methods have been applied in several areas of electric vehicle charging scheduling. This paper reviews and summarizes the application of DRL in cluster EV charging scheduling. Firstly, the article has reviewed the development history of reinforcement learning and the key techniques of multi-agent reinforcement learning, focusing on the relevant techniques of multi-agent. Secondly, the study analyzes the characteristics of distributed charging scheduling for cluster EVs and analyzes the application of MADRL in distributed scheduling. This article introduces and analyzes the existing research foundation and current practical application status, aiming to provide references and insights for future research and application of MADRL in the field of electric vehicle charging scheduling. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Development of Customer Side Electric Safety Perception Module 22

Development of Customer Side Electric Safety Perception Modu...

引用

Proceedings of the 5th International Conference on Information Technologies and electrical Engineering

作者： Yu Xiao Xiaoping Liu Xiangqi Xiao Wenxian Wu Yujian Luo Pei Peng Hongyu Liu Hunan Province Key Laboratory of Intelligent Electrical Measurement and Application Technology State Grid Hunan Electric Power Company Limited Power Supply Service Center (Metrology Center) China

ISBN: (纸本)9781450396806

With the development of power Internet of things, as an important sensing device at the end of the perception layer of the power Internet of things, the technical function of the smart meter is given more requirements; Aiming at the problems of electric shock, fire and other problems that endanger the safety of power grid and personal safety caused by the potential safety hazards of customer-side electricity consumption, improve the safety management ability of customer-side electricity consumption, and support the realization of considerable and controllable safety of customer-side electricity consumption, this paper proposes an electricity safety perception module that meets the technical specifications of the extended module of intelligent internet of things energy meter.

关键词： Customer Side Electricity Safety perception Module intelligent

来源：评论

学校读者我要写书评

暂无评论

A new method of short-term load forecasting based on the selection of compound variables

A new method of short-term load forecasting based on the sel...

引用

2021 IEEE International Conference on electrical Engineering and Mechatronics technology, ICEEMT 2021

作者： Yu, Xiao Wei, Zou Zhi, Ye Xiaoping, Liu Taoming, Zeng Huang, Rui Wenwei, Zeng Weijie, Zeng State Grid Hunan Electric Power Limited Company Changsha410004 China Hunan Province Key Laboratory of Intelligent Electrical Measurement and Application Technology Changsha410004 China

ISBN: (纸本)9781665441285

Accurate short-term load forecasting is an important guarantee for achieving lean operation and management of the power grid. However, there are difficulties in precise forecasting such as short-term load variability and selecting key factors of load forecasting. We establish a short-term load forecasting method based on variational modal decomposition and compound variable selection. The method is used to decompose the original power load data into multiple sub-sequences, and mine short-term load change characteristics while avoiding mode aliasing problems. Meanwhile, a complex variable selection algorithm is proposed to analyze and screen the key factors affecting load changes, effectively eliminating undesired data and further simplifying the complexity of the prediction model. Each sub-sequence is predicted and merged through the long and short-term memory neural network, achieving the final short-term load forecast. The verification results of the actual data of Changsha City selected for the entire year of 2019 show that the algorithm proposed here can accurately select the key influencing factors of load forecasting under complex external influence factors. With traditional forecasting models, the proposed model structure is simpler. The prediction accuracy is higher. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Implementation of Asset Inventory Model Based on intelligent Algorithm

Implementation of Asset Inventory Model Based on Intelligent...

引用

Global Conference for Advancement in technology (GCAT)

作者： Liuqing Ye Canhui Zhang Dan Zhao Longmin Bu Huiting Xu State Grid Hunan Electric Power Company Limited Power Supply Service Center(Metrology Center) Hunan Province Key Laboratory of Intelligent Electrical Measurement and Application Technology Changsha China

Asset inventory is an important part of internal management in an organization, and it is of great significance for the smooth operation and normal development of the organization. The traditional manual inventory method has problems of low inventory efficiency and low accuracy. The asset inventory model based on intelligent algorithms can overcome the shortcomings of traditional methods and improve inventory efficiency and accuracy. This article introduces the implementation process of an asset inventory model based on deep learning algorithms. Firstly, the YOLOv4 algorithm is used for object detection to obtain the position and category information of the target object in the asset image. Then, the Faster R-CNN algorithm is used to locate the target, further improving accuracy. Finally, a neural network model trained on large-scale data is used to classify, recognize, and count assets. Using the actual data, this paper constructs the optimal portfolio model based on different risk measures and termination conditions: the maximization model of unit risk return, the VaR risk control model, and the risk return preference model. Genetic algorithm and Simulated annealing algorithm are used to optimize the model. Through experimental verification, the recognition rate of this model reaches over 90%, and the inventory efficiency and accuracy are greatly improved compared to traditional manual inventory methods. In summary, asset inventory models based on intelligent algorithms have unique advantages in inventory efficiency and accuracy, and have broad application prospects in the future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Scheduling Method for Battery Energy Storage Based on Adaptive Time Granularity 7

Optimal Scheduling Method for Battery Energy Storage Based o...

引用

7th IEEE International Conference on Power and Renewable Energy, ICPRE 2022

作者： Luo, Shuchen Wen, Ming Li, Wenying Liao, Jing Xiong, Dezhi Zhong, Yuan Power Economic and Technology Research Institute Key Laboratory of Hunan Province for Energy Internet Supply and Demand Operation State Grid Hunan Electric Changsha China Hunan Province Key Laboratory of Intelligent Electrical Measurement and Application Technology State Grid Hunan Electric Power Limited Company Power Supply Service Center Metrology Center Changsha China State Grid Hunan Electric Power Economic and Technology Research Institute Key Laboratory of Hunan Province for Energy Internet Supply and Demand Operation Changsha China

ISBN: (数字)9781665450638

ISBN: (纸本)9781665450638

With the integration of many intermittent and distributed new energy sources into the power grid, the safe and stable operation of the power system is facing huge challenges. HVAC (Heating, Ventilation and Air Conditioning, HVAC), electric vehicles (EV), and battery energy storage (BESS) can be a solution to this problem due to high flexibility and strong controllability. Aiming at the problem of power imbalance caused by large-scale wind power integration, this paper proposed an optimal scheduling method of HVAC and BESS based on adaptive time granularity. Time granularity is critical to the optimization of scheduling methods, which is decided by the load fluctuation in this paper. The simulation results showed that reducing the time granularity can smooth the fluctuation of the tie-line but would increase the scheduling cost and the amount of calculation. © 2022 IEEE.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Modality Unified Attack for Omni-Modality Person Re-Identification

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5577-5587页

作者： Bian, Yuan Liu, Min Yi, Yunqi Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning based person re-identification (re-id) models have been widely employed in surveillance systems. Recent studies have demonstrated that black-box single-modality and cross-modality re-id models are vulnerable to adversarial examples (AEs), leaving the robustness of multi-modality re-id models unexplored. Due to the lack of knowledge about the specific type of model deployed in the target black-box surveillance system, we aim to generate modality unified AEs for omni-modality (single-, cross- and multi-modality) re-id models. Specifically, we propose a novel Modality Unified Attack method to train modality-specific adversarial generators to generate AEs that effectively attack different omni-modality models. A multi-modality model is adopted as the surrogate model, wherein the features of each modality are perturbed by metric disruption loss before fusion. To collapse the common features of omnimodality models, Cross Modality Simulated Disruption approach is introduced to mimic the cross-modality feature embeddings by intentionally feeding images to non-corresponding modality-specific subnetworks of the surrogate model. Moreover, Multi Modality Collaborative Disruption strategy is devised to facilitate the attacker to comprehensively corrupt the informative content of person images by leveraging a multi modality feature collaborative metric disruption loss. Extensive experiments show that our MUA method can effectively attack the omni-modality re-id models, achieving 55.9%, 24.4%, 49.0% and 62.7% mean mAP Drop Rate, respectively. © 2005-2012 IEEE.

关键词： Feature extraction Perturbation methods measurement Generators Collaboration Robustness Identification of persons Data mining Closed box Training

来源：评论

学校读者我要写书评

暂无评论

A Method and System for Evaluating Health Status of Low-voltage Power Supply Lines based on Clustering Algorithm 2021

A Method and System for Evaluating Health Status of Low-volt...

引用

The 4th International Conference on Information Technologies and electrical Engineering

作者： Minqi Yu Rui Huang Qin Liu Wenwei Zeng Maotao Yang Grid Hunan Electric Power Corporation Limited China and Hunan Province Key Laboratory of Intelligent Electrical Measurement and Application Technology China

ISBN: (纸本)9781450386494

In order to solve the problems of complex evaluation process and slow processing speed of existing low-voltage power supply line health evaluation methods, an evaluation method of low-voltage power supply lines health status based on Fuzzy C-Mean (FCM) clustering algorithm and Euclidean distance is proposed. First, the voltage and current values before and after the voltage and current changes are collected according to the equivalent circuit diagram of the low-voltage power supply lines, the loop impedance is obtained by the voltage and current values before and after the change. Then the loop impedance of a single user is clustered using the FCM clustering algorithm to find out the data that may have abnormal health conditions. Finally, based on the Euclidean distance, the above-mentioned data that may have abnormal health conditions are analyzed again to further determine whether the line is abnormal. The results of the case analysis show that this method has the advantages of accurate impedance data measurement, less workload, and ensuring normal power supply for users.

关键词： Line health status evaluation FCM clustering algorithm Low-voltage power supply line Euclidean distance

来源：评论

学校读者我要写书评

暂无评论

Research on Vehicle Engine Cooling System Based on Self-adjusting Fuzzy Control Strategy 4

Research on Vehicle Engine Cooling System Based on Self-adju...

引用

4th IEEE China International electrical and Energy Conference, CIEEC 2021

作者： Wu, Wenxiu Gui, Chengdong Yang, Puqiong Chen, Wenguang Tan, Yanliang University of South China School of Electrical Engineering Hengyang China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang China

ISBN: (纸本)9781728171494

A simplified mathematical model of the vehicle engine electronic control cooling system is established by using the lumped parameter method, and non-linear control strategy and fuzzy control strategy are introduced to simulate the cooling system. Taking the optimal coolant temperature of the vehicle engine outlet as the research objective, non-linear controller, fuzzy controller and self-adjusting fuzzy controller are designed to control the engine coolant temperature and to study the energy consumption optimization of the cooling system. Experiments show that compared with non-linear control, self-adjusting fuzzy control, and fuzzy control strategy, When the engine is in the maximum heat load and the electronic valve is fully open, the energy consumption of the cooling system can be reduced by 33% by using self-adjusting fuzzy control strategy. © 2021 IEEE.

关键词： Linear control systems

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-objective Coordination Strategies for Active Distribution Networks Based on Dynamic Energy Storage Management

Research on Multi-objective Coordination Strategies for Acti...

引用

Clean Energy and Electric Power Engineering (ICCEPE), International Conference on

作者： Huaping Yin Yeqin Ma Mouhai Liu Jiale Li State Grid Hunan Electric Power Limited Company Changsha China Hunan Province Key Laboratory of Intelligent Electrical Measurement and Application Technology (Power Supply Service Center (Metrology Center) State Grid Hunan Electric Power Limited Company Changsha China School of Electrical & Information Engineering Changsha University of Science & Technology Changsha China

ISBN: (数字)9798350390315

ISBN: (纸本)9798350390322

Aimed at the challenges posed by the increasing penetration of renewable energy sources (RES) in active distribution networks, particularly concerning local consumption and transmission barriers of harvested RES, this study investigates a coordination control methodology between distributed energy storage systems (ESS), volatile renewable power generation systems, and highly stable large-scale grid systems under secure operational conditions. Initially, the dynamic variations in charging and discharging depths during operation are considered, leading to a dynamic modeling of the state-of-charge (SOC) for ESS batteries. On the premise of ensuring the safety of distributed ESS, a multi-objective comprehensive optimization strategy is developed to enhance RES accommodation, augment regional grid RES export capability, and maximize economic benefits. Ultimately, the feasibility and rationality of the proposed strategy are validated through simulations, which demonstrate that the approach enables different storage units to adjust their charge-discharge depths, significantly improving the capacity for integrating renewable energy.

关键词： Economics Renewable energy sources Storage management Batteries Safety Power systems Active distribution networks State of charge Resource management Power generation

来源：评论

学校读者我要写书评

暂无评论

New approach to select the fault line based on transient energy features of fault phase

New approach to select the fault line based on transient ene...

引用

2021 IEEE International Conference on Computer Science, Electronic Information Engineering and intelligent Control technology, CEI 2021

作者： Xiao, Yu Ye, Zhi Huang, Ru Liu, Mouhai Ma, Yeqing Wang, Jianzhong Zhao, Yantao Xu, Yong Wei, Xiongfei Teng, Zhaosheng Gao, Yunpeng State Grid Hunan Electric Power Limited Company Hunan Province Key Laboratory of Intelligent Electrical Measurement and Application Technology Changsha China Wasion Group Limited Changsha China College of electrical and information engineering Hunan University Changsha China

ISBN: (纸本)9780738146492

A new approach for fault line detection using Wavelet energy feature of fault-phase transient current is proposed. This novel method utilizes the phase selection function of insulation monitoring system and the differences of transient current between fault line and non-fault line. Firstly, the transient current signals of each phase fault are extracted to identify the faulty phase effectively. The pure fault component is obtained by noise elimination. Then, each phase wavelet energy feature can be achieved by the decomposition and reconstruction of wavelet packet. The fault line can be detected by comparing energy feature of each phase for the reason that the fault line's energy characteristics of fault phase are much greater than that of non-fault line under single phase grounding fault. This approach is clear in physical mechanism and unaffected by operating mode, circuit components, fault conditions and other factors. It can also effectively overcome the system noise, the interference of asymmetrical component. The line selection method has broad margin and high reliability, which is practical to applications. © 2021 IEEE.

关键词： Wavelet decomposition

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：