检索结果-内蒙古大学图书馆

2024 7th International Conference on Mechanical, Electrical and Material Application, MEMA 2024

作者： Wang, Haobo Wang, Hongtao Xin, Peiqi Xu, Changmeng Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Shandong University Jinan China

In the field of wind power generation, the significant geographical separation between wind farms and load centers often necessitated the long-distance and large-scale transmission of wind energy, which was typically achieved through transmission lines equipped with series compensation capacitors. However, this setup led to interactions between the series compensation capacitors and the control systems of doubly-fed induction generators (DFIGs), potentially causing sub-synchronous oscillations in grid-connected systems. To address this issue, our study focused on a DFIG-based wind farm interconnected via a series-compensated line. We proposed an innovative suppression strategy that incorporated additional virtual damping on the grid side. This strategy was effectively combined with an ancillary approach of adding virtual inductance on the rotor side, offering a robust solution to mitigate sub-synchronous oscillations. The simulation results showed that the joint application of these two strategies was more effective than implementing them individually. Notably, the strategy involving additional virtual damping on the grid side outperformed the approach of adding virtual inductance on the rotor side. © Published under licence by IOP Publishing Ltd.

关键词： Inductance

来源：评论

学校读者我要写书评

暂无评论

An Improved Solov2 Based on Attention Mechanism and Weighted Loss Function for Electrical Equipment Instance Segmentation

引用

Computers, Materials & Continua 2024年第1期78卷 677-694页

作者： Junpeng Wu Zhenpeng Liu Xingfan Jiang Xinguang Tao Ye Zhang Key Laboratory of Modern Power System Simulation and Control&Renewable Energy Technology Ministry of EducationNortheast Electric Power UniversityJilin132012China School of Electrical Engineering Northeast Electric Power UniversityJilin132012China Baishan Power Supply Company State Grid Jilin Electric Power CoLtd.Jilin134300China

The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low *** of the reliable,safe and easy-to-operate technology provided by deep learning-based video surveillance for unmanned inspection of electrical equipment,this paper uses the bottleneck attention module(BAM)attention mechanism to improve the Solov2 model and proposes a new electrical equipment segmentation ***,the BAM attention mechanism is integrated into the feature extraction network to adaptively learn the correlation between feature channels,thereby improving the expression ability of the feature map;secondly,the weighted sum of CrossEntropy Loss and Dice loss is designed as the mask loss to improve the segmentation accuracy and robustness of the model;finally,the non-maximal suppression(NMS)algorithm to better handle the overlap problem in instance *** results show that the proposed method achieves an average segmentation accuracy of mAP of 80.4% on three types of electrical equipment datasets,including transformers,insulators and voltage transformers,which improve the detection accuracy by more than 5.7% compared with the original Solov2 *** segmentation model proposed can provide a focusing technical means for the intelligent management of power systems.

关键词： Deep learning electrical equipment attention mechanism weighted loss function

来源：评论

学校读者我要写书评

暂无评论

Optimal Dispatch for Large-Scale Renewable Energy Bases Without Conventional power Support

Optimal Dispatch for Large-Scale Renewable Energy Bases With...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Zhang, Kunpeng Liu, Tianhao Liu, Yutian Shandong University Key Laboratory of Power System Intelligent Dispatch and Control Ministry of Education Jinan China

ISBN: (纸本)9798350350821

In large-scale renewable energy base and HVDC systems, the absence of conventional power support makes commutation failures a significant threat to system security and stability. An optimal dispatch method based on Kolmogorov-Arnold Networks (KAN) is proposed, which considers voltage and frequency dynamic security constraints. First, a time-domain simulation model of the system is developed to generate training data for KAN. The KAN is then designed to estimate the transient overvoltage at the point of common coupling in the renewable energy base after the occurrence of commutation failure. Frequency fluctuation is calculated by frequency nadir prediction model. Thirdly, an optimal dispatch model is formulated to maximize the delivered power of HVDC, which considers both operational and dynamic security constraints. simulation results demonstrate that the proposed optimal dispatch model enhances system security with an acceptable reduction in delivered power. © 2024 IEEE.

关键词： commutation failure Kolmogorov-Arnold Networks LCC-HVDC power generation dispatch renewable energy base transient overvoltage estimation

来源：评论

学校读者我要写书评

暂无评论

Acceleration of power system Dynamic simulation with High-Penetration Renewable Generation via Time-Step Adjustment Based on ETFBs 7

Acceleration of Power System Dynamic Simulation with High-Pe...

引用

7th IEEE Student Conference on Electric Machines and systems, SCEMS 2024

作者： Cao, Jiawen Lv, Dongbao Liu, Xindi Li, Changgang Shandong University Key Laboratory of Power System Intelligent Dispatch and Control Ministry of Education Jinan China

ISBN: (纸本)9798350366945

With the widespread integration of renewable energy sources (REs), the number of power system scenarios to be analyzed has increased significantly, and the system structure has become increasingly complex, which increases the computational burden of power system dynamic simulations and leads to substantial computation time. Therefore, there is an urgent need to improve the efficiency of dynamic simulation to meet the requirements of advanced applications. The uEITSA method adopts a fixed system time-step in the overall simulation, which makes it challenging to balance simulation accuracy and efficiency. Therefore, a system time-step adjustment strategy is proposed in this paper to optimize the uEITSA method, implemented in the open-source simulation Toolkit for Electrical power systems (STEPS). Firstly, the system time-step adjustment strategy based on elementary transfer function blocks (ETFBs) is introduced. Secondly, the implementation of the proposed strategy in STEPS software is described in detail. Finally, the simplified Shandong power Grid model is tested to demonstrate that the proposed system time-step adjustment strategy can improve simulation efficiency without jeopardizing simulation accuracy. © 2024 IEEE.

关键词： power systems computer aided design

来源：评论

学校读者我要写书评

暂无评论

Research on Microgrid Energy Storage Scheduling Strategy Incorporating Electric Vehicles Based on the DQN Algorithm 9

Research on Microgrid Energy Storage Scheduling Strategy Inc...

引用

9th Asia Conference on power and Electrical Engineering, ACPEE 2024

作者： Xin, Peiqi Wang, Hongtao Wang, Haobo Song, Zhen Intelligent Dispatch and Control of Ministry of Education Shandong University Key Laboratory of Power System Jinan China

ISBN: (纸本)9798350309638

This study focuses on the scheduling of a microgrid integrated with electric vehicles, employing a reinforcement learning algorithm to devise an optimal economic operation strategy. The approach addresses the challenges of renewable energy generation's randomness and the economic and safety concerns arising from the extensive integration of electric vehicles into the microgrid. The paper explores the reinforcement learning-based energy management of storage devices within the microgrid. A Deep Q-Network (DQN) method is utilized to formulate the microgrid storage scheduling problem as a Markov Decision Process (MDP). The study involves a detailed simulation of a residential user microgrid, considering various parameters such as battery storage capacity, charging and discharging rates, and electric vehicle load models. The reinforcement learning algorithm demonstrates the capability of real-time response to power changes in the microgrid, ensuring operational cost minimization even under multiple input uncertainties. © 2024 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Frequency Domain Stability Analysis and simulation of New Energy power Generation systems 9

Frequency Domain Stability Analysis and Simulation of New En...

引用

9th Asia Conference on power and Electrical Engineering, ACPEE 2024

作者： Wang, Haobo Wang, Hongtao Xin, Peiqi Song, Zhen Shandong University Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Jinan China

ISBN: (纸本)9798350309638

Stability analysis of grid-connected inverters is advanced through impedance analysis in this study, which leads to the development of a comprehensive mathematical model and simulation. control parameters, notably the voltage inner-loop control parameter Kv, the proportional gain Kp of the phase-locked loop (PLL), and the integral gain K1, were meticulously adjusted to assess their effects on subsynchronous oscillations. It was determined that while the proportional gain p and integral gain K1 have a marginal impact on sub-synchronous oscillations, the voltage inner-loop control parameter K1 significantly influences these oscillations. The insights gained from this analysis contribute to a deeper understanding of, and potential solutions for, synchronous oscillation issues. The ability to mitigate such oscillations facilitates the integration of a higher proportion of renewable energy sources, thereby enhancing the stability and reliability of the electrical power system. This enhancement is of critical importance in the pursuit of sustainable energy transitions and the advancement of clean energy sources. © 2024 IEEE.

关键词： Phase locked loops

来源：评论

学校读者我要写书评

暂无评论

Microgrid energy management strategy based on LSTM-DDQN 3

Microgrid energy management strategy based on LSTM-DDQN

引用

2024 3rd International Conference on Electrical, control and Information Technology, ECITech 2024

作者： Xin, Peiqi Wang, Hongtao Wang, Haobo Xu, Changmeng Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Shandong University Jinan China

This paper introduces a novel algorithm, LSTM-DDQN, designed to address the stochastic economic dispatch problem in microgrids. The inherent variability and randomness of photovoltaic (PV) energy pose challenges for accurate output prediction. Traditional approaches, including physical and statistical methods, often fall short in terms of accuracy. For microgrids with a high proportion of PV generation, we propose a new algorithm that combines Long Short-Term Memory (LSTM) neural networks with the Double Deep Q-Network (DDQN) algorithm. The algorithm leverages the LSTM model to capture the uncertainty of the learning environment and optimizes the Q-value iteration rules in the DDQN algorithm, thereby enhancing the training speed of the neural network. Experimental results demonstrate the algorithm's remarkable dispatch capabilities in managing the interplay between PV generation, battery capacity, and overall load demand. This algorithm provides robust support for the stable operation of microgrids. © 2024 Published under licence by IOP Publishing Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Virtual Oscillator Grid-Forming Inverter Stability Analysis Based on Impedance Model 7

Virtual Oscillator Grid-Forming Inverter Stability Analysis ...

引用

7th IEEE International Electrical and Energy Conference, CIEEC 2024

作者： Guo, Shuiyuan Ye, Hua Yang, Jialun Chu, Xiaodong Mou, Qianying Shandong University Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Jinan China

ISBN: (纸本)9798350359558

Grid-forming (GFM) inverters are DC-AC converters that regulate their AC terminal frequency and voltage in response to real-time measurements. Virtual oscillator control (VOC) is an emerging strategy of grid-forming controllers. Unlike conventional phasor-based control methods such as droop control and virtual synchronous machine control, VOC is a time-domain controller that global convergence can be almost guaranteed by adding a nonlinear element. In this article, the state space model of a VOC-based inverter system connected to an infinite bus is established to access the steady-state values. In order to study the effect of nonlinear terms on the system stability, a detailed impedance model of the VOC controller is proposed. Numerical simulations validate the impedance model. Through the impedance-based method, how the nonlinear term can influence system stability is analyzed. © 2024 IEEE.

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

Voltage control in Distributed Photovoltaic power Distribution Networks Using Multi-Agent Deep Reinforcement Learning 7

Voltage Control in Distributed Photovoltaic Power Distributi...

引用

2024 7th International Conference on Mechanical, Electrical and Material Application, MEMA 2024

作者： Xin, Peiqi Wang, Hongtao Wang, Haobo Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Shandong University Jinan China

This study introduces a unique method employing the Multi-Agent Deep Deterministic Policy Gradient (MADDPG), a sophisticated deep reinforcement learning algorithm, for efficient voltage control in photovoltaic (PV) power distribution networks. The algorithm's design emphasizes minimizing the need for communication and effectively managing delays, which are pivotal in ensuring consistent and reliable control in environments with fluctuating renewable energy sources. In simulations using the IEEE-33 power distribution system, the research demonstrates the algorithm's ability to ensure stable and efficient network functioning, even under varying environmental and load conditions. This highlights its potential as a robust solution for modern and renewable energy-integrated power systems. © Published under licence by IOP Publishing Ltd.

关键词： Renewable energy

来源：评论

学校读者我要写书评

暂无评论

Transient Overvoltage Quantitative Analysis Based on Short-Circui Ratio of New Energy Generation Stations 3

Transient Overvoltage Quantitative Analysis Based on Short-C...

引用

3rd Asia power and Electrical Technology Conference, APET 2024

作者： Wu, Yuhan Li, Yajie Shandong University Key Laboratory of Power System Intelligent Dispatch and Control The Ministry of Education Jinan China

ISBN: (纸本)9798350367690

With the increasing proportion of grid-connected renewable energy sources such as photovoltaic and wind power, the stability issues caused by large-scale development of new energy sources have become prominent. Among these issues, transient overvoltage is the primary constraint limiting the large-scale development of new energy sources. Studies have shown that the occurrence of transient overvoltage is closely related to the system strength of grid-connected points for new energy sources. The weaker the system strength, the greater the risk of stability problems such as transient overvoltage. The short-circuit ratio is an important indicator for assessing the grid strength of new energy integration points. Monitoring the short-circuit ratio can effectively evaluate the strength of the new energy station's integration into the system. Therefore, based on the short-circuit ratio of new energy generation stations, this paper quantitatively analyzes the relationship between the short-circuit ratio and transient overvoltage. In future research, the short-circuit ratio can be used as a constraint condition, with transient overvoltage as an indicator, to facilitate the determination of reactive power compensation solutions for high-proportion new energy integration systems. Finally, MATLAB/simulink simulations validate the accuracy of the analysis. © 2024 IEEE.

关键词： Wind power integration

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：