检索结果-内蒙古大学图书馆

8th International Conference on Electrical, Mechanical and Computer Engineering, ICEMCE 2024

作者： Hong, Zeqi Huang, Libin Hu, Yufeng Guo, Haiping Lu, Yuanhong Hu, Binjiang Zhang, Jingyue Luo, Hui Electric Power Research Institute China Southern Power Grid State Key Laboratory of Hvdc Guangzhou China National Energy Power Grid Technology R and D Centre Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China Institute China Southern Power Grid Csg Key Laboratory for Power System Simulation Electric Power Research Guangzhou China

ISBN: (纸本)9798331506230

With the escalating demand for power inspection and equipment maintenance, developing effective algorithms for power system fault detection is crucial for ensuring the safety and stability of power systems. This paper leveragesthe Trellis network, enhanced with an attention module, to significantly improve the Trellis network's capability in recognizing power fault images, thus better addressing fault identification tasks within power systems. Through testing on a self-constructed dataset and comparative experiments with models such as DCNN, RCNN, and DenseNet, the proposed attention mechanismenhanced Trellis network algorithm has demonstrated its effectiveness and superiority in fault detection. © 2024 IEEE.

关键词： power distribution faults

来源：评论

学校读者我要写书评

暂无评论

Fault Location Method for Dc Distribution Network Based on Compressed Sensing Group Sparse Representation

SSRN

引用

SSRN 2024年

作者： Wang, He Liu, Yiqi Li, Shiqiang Yu, Huanan Bian, Jing Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Northeast Electric Power University Ministry of Education Jilin Province Jilin132012 China

The common faults in a direct current (DC) distribution network consist of pole-to-pole faults and pole-to-ground faults. Under conditions of sparse configuration of measurement devices, existing fault location methods are unable to simultaneously locate pole-to-ground faults and pole-to-pole faults, and issues such as indistinct fault characteristics under the influence of transition resistance and noise are encountered. In response to these challenges, a fault location method for DC distribution networks is proposed based on compressed sensing group sparse representation. Firstly, the pole-to-mode transformation is utilized to convert the positive and negative pole electrical quantities of the DC distribution network into zero-mode and one-mode electrical quantities. Equivalent circuits for pole-to-ground faults and pole-to-pole faults are established separately, enhancing the fault characteristics corresponding to the two different short circuit faults. Secondly, the obtained impedance matrices for zero-mode and one-mode are constructed into a group sparse dictionary. By utilizing compressed sensing group sparse representation, the sparse current vector of high-frequency mode quantities is obtained, enabling the correct identification of fault types and accurate location of fault sections. Finally, a simulation model of the DC distribution network is built on the PSCAD platform to validate the effectiveness of the proposed fault location method. © 2024, The Authors. All rights reserved.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

Info-Hkelm Wind power Short-Term Prediction Based on Wind power Low Output Event Identification and Multi-Scenario Error Compensation

SSRN

引用

SSRN 2023年

作者： Yang, Mao Guo, Yunfeng Huang, Yutong Gu, Dake Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin Province Jilin132012 China

The penetration of a high percentage of renewable energy poses a challenge to the safe and stable operation of the power system, frequent wind power low output events have seriously affected power dispatch and power supply reliability, it becomes necessary to anticipate the occurrence of wind power low output events in advance and to develop effective supply assurance measures. In this paper, we propose a method for identifying and accurately predicting wind power low output events, firstly, we define wind power low output events and identify low output event types based on CNN-BiGRU. Secondly, A weighted clustering comprehensive assessment indicator is proposed to evaluate the effect of clustering of low output events, hybrid kernel extreme learning machine based on weighted mean of vectors algorithm optimization (INFO-HKELM) is used for preliminary prediction of low output events in different scenarios, and a multi-scenario error compensation mechanism based on similar fragment matching is proposed for further correction of power prediction results. The proposed method was applied to a wind farm in Inner Mongolia Autonomous Region for validation. Compared with the rest of the methods, the NRMSE of the method in this paper decreases by 1.56%~1.7%, NMAE decreases by 0.6%~1.11%, and R2 increases by 2.50%~2.92%. The multi-scenario error compensation mechanism reduces the NRMSE and NMAE of the preliminary power prediction results by 1.3% and 1.4%, respectively, which further improves the prediction accuracy and proves the effectiveness of the proposed method in this paper. © 2023, The Authors. All rights reserved.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Emergency Direct Current power Support for High-Percentage renewable energy systems Based on Deep Reinforcement Learning

SSRN

引用

SSRN 2024年

作者： Sun, Zhenglong Zhuang, Junzhi Chao, Pan Chao, Jiang Cai, Guowei The Department of Electrical Engineering Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin China

As a low-cost emergency frequency control method, emergency direct current power support (EPS) is crucial for frequency stabilization of alternating current (AC)–direct current (DC) hybrid systems. In the context of highly integrated renewable energy sources, the uncertainty of AC-DC hybrid systems increases and the inertia decreases during the transition process, and the existing EPS methods face prominent adaptation and mismatch problems in meeting the frequency restoration requirements. To fill this gap, this study proposes a deep reinforcement learning (DRL)-based EPS frequency control method. The EPS decision is transformed into a Markov decision process (MDP) and solved using the proximal policy optimization (PPO) algorithm. This paper designs a DRL reward function for EPS while taking into account the EPS line overload and phase change failure problems. In order to solve the contradiction between limited observation and global safety, this paper designs a data characterization method based on mechanism fusion. Meanwhile, this paper develops an open-source power system simulation platform with DRL control function by using Python and the power system simulation software DIgSILENT/powerFactory to realize the EPS frequency stabilization decision based on DRL control. Through a case study of the IEEE 39-bus system and a real power system in Northwest China, it is verified that the proposed DRL-based EPS agent is able to quickly, accurately, and securely restore the frequency and reduce the frequency oscillations while considering the security constraints. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on Active Support control Strategy and its Performance of renewable energy power Station with Multiple energy Sources 7

Research on Active Support Control Strategy and its Performa...

引用

7th IEEE Conference on energy Internet and energy system Integration, EI2 2023

作者： Zeng, Guanming Tu, Liang Zhu, Yihua Hu, Yun Luo, Chao Li, Shengnan State Key Laboratory of Hvdc Electric Power Research Institute China Southern Power Grid National Energy Power Grid Technology R&d Centre Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control For New Energy Power System Csg Key Laboratory For Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou China State Key Laboratory of Hvdc Electric Power Research Institute China Southern Power Grid Csg Key Laboratory For Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou China National Energy Power Grid Technology R&d Centre Guangdong Provincial Key Laboratory of Intelligent Operation and Control For New Energy Power System Guangzhou China Yunnan Power Grid Co. Ltd. Electric Power Research Institute Yunnan Kunming China

ISBN: (纸本)9798350345094

The increasing integration of renewable energy reduces the inertia and frequency support capacity of the power system. The issue of frequency stability has become one of the core issues in the security and stability of power system and the efficient consumption of renewable energy nowadays. To improve the performance of renewable energy power station (REPS), based on the analysis of typical active support control logic and relative performance requirements of REPS with single energy source (SES), an active support control strategy and coordinated control logic of active power of REPS with multiple energy sources (MES) are proposed in this paper. The performance of proposed strategy is theoretically analyzed from the aspect of dominant energy source and the effect of the capacity of energy storage. The effectiveness of the proposed strategy and the accuracy of the theoretical analysis of performance are verified by realtime simulation. © 2023 IEEE.

关键词： renewable energy

来源：评论

学校读者我要写书评

暂无评论

The design and simulation of the 3MW direct drive wind turbine's controller to decrease vibration of the tower 32

The design and simulation of the 3MW direct drive wind turbi...

引用

32nd Youth Academic Annual Conference of Chinese Association of Automation, YAC 2017

作者： Zhenghou, Yang Guoqiang, Zhang Yuan, Wen Ying, Deng Beijing Huaneng Xinrui Control Technology Co. Ltd. Beijing102209 China State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Renewable Energy North China Electric Power University Beijing102206 China

ISBN: (纸本)9781538629017

Because the environment that the wind turbine runs in is severe, the generating efficiency is low and the vibration of tower is very obvious. The consequence not only causes economic loss but also lead to the reduction of the wind turbine's lifetime. Basing on the traditional PI controlling system, this passage mainly studies to decrease the vibration of the tower by adjusting the controlling PI parameters and adding the tower damper. Establishing the wind turbine's linear, constant, SISO model, selecting the controlling parameters by MATLAB simulation at different isolate wind speed to achieve stable and fast controlling. At different isolate wind speeds, adding the tower damper to decrease the acceleration of tower. At last making global simulation with Bladed to verify and compare the traditional PI strategy with the new strategy. The result of the simulation with Bladed shows the strategy decreases the vibration of the tower and protect the wind turbine. © 2017 IEEE.

关键词： Towers

来源：评论

学校读者我要写书评

暂无评论

Research on Automatic Construction and Correlation Method of Virtual and Real Loops in UHV DC control and Protection system

Research on Automatic Construction and Correlation Method of...

引用

2021 IEEE Sustainable power and energy Conference, iSPEC 2021

作者： Lu, Yuanhong Guo, Qi Liu, Zhijiang Li, Shuyong Guo, Haiping Zeng, Guanming China Southern Power Grid State Key Laboratory of Hvdc Electric Power Research Institute Guangzhou China National Energy Power Grid Technology R&d Centre Guangzhou China Guangdong Prov. Key Laboratory O F Intelligent Operation and Control for New Energy Power System Guangzhou China Csg Key Laboratory for Power System Simulation Electric Power Research Institute Guangzhou China

ISBN: (纸本)9781665414395

At present, in the research on virtual and real loops of control and protection systems, scholars at home and abroad are mainly focusing on the field of AC digital substations, and there is less research on the virtual and real loops of UHV DC control and protection systems. Aiming at this problem, this paper proposes an automatic construction and correlation method for virtual and real loops of UHV DC control and protection system. This method automatically constructs the real circuit by analyzing the design drawings and the optical cable inventory, analyzing the DC visualization program to automatically construct the virtual circuit, and then automatically correlates the virtual and real circuits based on the graph depth traversal algorithm. The practical application in UHV DC engineering shows that this method can help relevant personnel complete the automatic construction and correlation of virtual and real loops, and improve the convenience of operation and maintenance of the UHV DC control and protection system. © 2021 IEEE.

关键词： Correlation methods

来源：评论

学校读者我要写书评

暂无评论

Influence Analysis and Countermeasure Research of Dynamic Characteristics of Measurement system on Bridge Arm Current Differential Protection in MMC-HVDC system 18

Influence Analysis and Countermeasure Research of Dynamic Ch...

引用

18th International Conference on AC and DC power Transmission, ACDC 2022

作者： Chen, Qinlei Guo, Qi Lin, Xuehua Huang, Libin Li, Shuyong State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid Guangzhou China National Energy Power Grid Technology R&D Centre Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China CSG Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou China

ISBN: (数字)9781839537615

ISBN: (纸本)9781839537615

Aiming at the action phenomenon of bridge arm current differential protection after AC fault recovery of a modular multilevel converter high voltage direct current (MMC-HVDC) project, the characteristics of differential current are *** influence of temporary block strategy and dynamic characteristics of measurement system on differential current are studied, and the mechanism of differential current and the reasons for the action of bridge arm current differential protection are revealed. Based on the real-time digital physics closed-loop simulation platform, the action phenomenon of bridge arm current differential protection in the field is reproduced and the influence of the dynamic characteristics of the measurement system on the bridge arm current differential protection of the bridge arm is analyzed. The optimization measures are proposed from two aspects: the dynamic performance of the measurement system and the configuration of bridge arm current differential protection. The research results provide technical support for the design of MMC-HVDC project and the impact assessment of dynamic performance of measurement system on MMC-HVDC protection. © ACDC 2022. All rights reserved.

关键词： simulation platform

来源：评论

学校读者我要写书评

暂无评论

The Development of simulation Mirror system and its Application in HVDC 6

The Development of Simulation Mirror System and its Applicat...

引用

6th International Conference on HVDC, HVDC 2024

作者： Ou, Kaijian Wu, Wencong Cai, Haiqing State Key Laboratory of Hvdc Electric Power Research Institute China Southern Power Grid National Energy Power Grid Technology R&d Centre. Guangzhou China Guangdong Prov. Key Laboratory of Intelligent Operation and Control for New Energy Power System. Guangzhou China Csg Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou China

ISBN: (纸本)9798350387759

The testing of HVDC new control function and training of HVDC operation personnel require the integration of power system simulation and dispatching automation. This paper presents and builds AC&DC power system simulation mirror system, which is the closed-loop of real-time digital simulation and dispatching automation. Moreover, the applications of simulation mirror system on HVDC new control function testing and HVDC simulation training cabinet are also introduced in this paper. © 2024 IEEE.

关键词： automatic generation control (A GC) automatic HVDC control (ADC) dispatching automation high voltage direct curren t(HVD C) real-time digital simulator(RTDS)

来源：评论

学校读者我要写书评

暂无评论

Application of deep reinforcement learning in power system scheduling strategy simulation 4

Application of deep reinforcement learning in power system s...

引用

4th International Conference on energy, power and Electrical Engineering, EPEE 2024

作者： Hu, Binjiang Huang, Libin Hu, Yufeng Zhang, Jie Guo, Haiping Lu, Yuanhong Hong, Zeqi Zhang, Jingyue Luo, Hui Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China Electric Power Research Institute China Southern Power Grid State Key Laboratory of Hvdc Guangzhou China National Energy Power Grid Technology R&d Centre Guangzhou China Electric Power Research Institute China Southern Power Grid Csg Key Laboratory for Power System Simulation Guangzhou China

ISBN: (纸本)9798331518066

With the increasing scale and complexity of power system, the current scheduling strategy methods often have the problems of limited adaptability and unsatisfactory results. Therefore, a power system scheduling method using DQN (Deep Q Network) is introduced in this study. This method uses neural network model to learn and optimize scheduling strategy, and has strong adaptability and enhanced global optimization ability. Comparative evaluations with genetic algorithms and particle swarm algorithms on IEEE-118 and SG-126 datasets show that the proposed method has significant advantages in terms of cumulative reward and stable runtime. © 2024 IEEE.

关键词： Deep reinforcement 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：