检索结果-内蒙古大学图书馆

Energy, power and Electrical Engineering (EPEE), International Conference on

作者： Jie Zhang Haiping Guo Yanjun Zhao Libin Huang Binjiang Hu Hui Luo Jingyue Zhang 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)9798331518066

ISBN: (纸本)9798331518073

With the rapid expansion of smart grids, there is a growing complexity in power system dynamics, which increases the availability of real-time operational data and underscores the need for advanced transient stability simulations. Traditional transient stability analysis methods are constrained by their computational demands and may compromise accuracy. Furthermore, deep learning-based methods often focus on the application of a single algorithm, lacking a systematic consideration of the entire simulation process. To address these challenges, this study proposes a novel approach that leverages big data to enhance transient stability simulations. By integrating deep learning and ensemble learning techniques, the model significantly improves the accuracy and efficiency of predicting transient instabilities. The methodology utilizes a multi-source data acquisition and fusion scheme to ensure data comprehensiveness and a distributed storage architecture to handle large-scale datasets effectively. Advanced visualization technologies are also employed to enhance the interpretability of the simulation results. This comprehensive framework aims to support the safe and stable operation of power systems amid increasing complexity and data availability.

关键词： Accuracy Computational modeling power system stability Big Data Predictive models Stability analysis Data models Real-time systems Transient analysis Thermal stability

来源：评论

学校读者我要写书评

暂无评论

Adaptive Time Period Aggregation for Day-ahead Unit Commitment

Adaptive Time Period Aggregation for Day-ahead Unit Commitme...

引用

2022 Tsinghua-IET Electrical Engineering Academic Forum, TDF 2022

作者： Yu, Zekuan Zhong, Haiwang Yan, Xinfei Department of Electrical Engineering Tsinghua University Beijing China State Key Laboratory of Control and Simulation of Power Systems and Generation Equipments Beijing China

ISBN: (数字)9781839537998

ISBN: (纸本)9781839537998

The growing penetration of renewables calls for finer temporal resolutions of the day-ahead unit commitment (DA-UC) problem in order to accommodate the fluctuations and improve the performance of UC schedules, leading to the expansion of the DA-UC problem scale. However, due to its high computational burden, the viability of adopting larger UC models in practice becomes a challenge. In this paper, an adaptive time period aggregation strategy and a corresponding DA-UC model are proposed to reduce the model scale while preserving feasibility and accuracy. The aggregation strategy integrates the statistical characteristics of net demand with the operational characteristics of thermal units to effectively capture the consistency in on/off statuses. Case study based on the IEEE 118-bus system validates that, combined with a post-processing procedure, the proposed strategy and model can provide near-optimal UC schedules with approximately 5 times acceleration for various demand profiles, enhancing computational efficiency. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

The Regional Distributed PV Ultra-short-term power Forecasting Based on Static-dynamic Spatiotemporal Correlation Modeling

The Regional Distributed PV Ultra-short-term Power Forecasti...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Zhu, Yu Yang, Le Yang, Xizai Xu, Fei Su, Zinuo Zhen, Zhao Information and Communication Technology R & D Center State Grid Shaanxi Electric Power Co. Ltd. Information and Communication Company Xi'an710048 China State Key Laboratory of Power System Operation and Control Tsinghua University Beijing100084 China

ISBN: (纸本)9781665471640

Accurate prediction of distributed photovoltaic power can help the arrange the scheduling plan reasonably to Maintain the safe and stable operation of the distribution network. However, distributed photovoltaic power generation exists lack of meteorological data and real-time monitoring data, the distribution range is large and dispersed, the installed capacity is relatively small and so on, the centralized photovoltaic power prediction method is not applicable to distributed photovoltaic power prediction, so it is necessary to carry out a regional power prediction study for distributed photovoltaic. Distributed PV is located in close proximity, in a similar external environment, and the power output between stations has strong spatial and temporal correlation, which can be captured to improve the accuracy of power forecasting. To this end, a regional distributed PV power prediction model based on static-dynamic spatiotemporal correlation modeling is proposed. The k-means is firstly used to cluster the regional distributed photovoltaic sites into several sub-regions, according to the geographical location and output characteristics that reflect the long-term static correlation between power stations. Then, graph convolutional neural network are applied to capture the dynamic correlation between subregions according to the power. In this way, the static and dynamic correlation are effectively considered in power prediction modeling, and the prediction accuracy has been improved. The superiority of the proposed method is verified by a real world dataset in China. © 2023 IEEE.

关键词： distributed photovoltaic graph convolution Regional power prediction

来源：评论

学校读者我要写书评

暂无评论

STDHL: Spatio-Temporal Dynamic Hypergraph Learning for Wind power Forecasting

arXiv

引用

arXiv 2024年

作者： Dong, Xiaochong Zhang, Xuemin Yang, Ming Mei, Shengwei State Key Laboratory of Power System Operation and Control Department of Electrical Engineering Tsinghua University Beijing100084 China Key Laboratory of Power System Intelligent Dispatch and Control Shandong University Jinan250061 China

Leveraging spatio-temporal correlations among wind farms can significantly enhance the accuracy of ultra-short-term wind power forecasting. However, the complex and dynamic nature of these correlations presents significant modeling challenges. To address this, we propose a spatio-temporal dynamic hypergraph learning (STDHL) model. This model uses a hypergraph structure to represent spatial features among wind farms. Unlike traditional graph structures, which only capture pair-wise node features, hypergraphs create hyperedges connecting multiple nodes, enabling the representation and transmission of higher-order spatial features. The STDHL model incorporates a novel dynamic hypergraph convolutional layer to model dynamic spatial correlations and a grouped temporal convolutional layer for channel-independent temporal modeling. The model uses spatio-temporal encoders to extract features from multi-source covariates, which are mapped to quantile results through a forecast decoder. Experimental results using the GEFCom dataset show that the STDHL model outperforms existing state-of-the-art methods. Furthermore, an in-depth analysis highlights the critical role of spatio-temporal covariates in improving ultra-short-term forecasting accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

DOFF-RLS-Based Equivalent Inertia Estimation for power system with PV 4

DOFF-RLS-Based Equivalent Inertia Estimation for Power Syste...

引用

4th IEEE International Conference on power, Intelligent Computing and systems, ICPICS 2022

作者： Ma, Huan Yang, Dong Qin, Hao Cao, Yongji Gao, Zhimin Zhang, Bing Cheng, Dingyi Zhang, Zhixuan State Grid Shandong Electric Power Research Institute State Grid Shandong Electric Power Company Jinan China Key Laboratory of Power System Intelligent Dispatch and Control The Ministry of Education Shandong University Jinan China Shandong Power Dispatch & Control Center State Grid Shandong Electric Power Company Jinan China

ISBN: (数字)9781665467735

ISBN: (纸本)9781665467735

With the use of photovoltaic (PV) generation, a large number of synchronous generation units have been replaced, resulting in obvious decline in the equivalent inertia of power system. Facing a lack of inertia, virtual inertia control techniques are applied to PV, but there is a lack of methods to estimate the equivalent inertia of PV in real time, making it difficult to quantitatively estimate the effect of control method with virtual inertia. Therefore, this paper adopts the controlled autoregressive (CAR) identification model and the recursive least square algorithm of dynamic optimal forgetting factor (DOFF-RLS) to estimate the PV equivalent inertia, in order to address the time varying characteristics of the PV equivalent virtual inertia. The proposed identification model and solution algorithm have superior tracking capability and good convergence. All that is required is to obtain the disturbance data of frequency and active power from the point of common coupling from the phasor measurement unit (PMU). Finally, the accuracy and suitability of the identification model and method are verified by simulation. © 2022 IEEE.

关键词： Virtual addresses

来源：评论

学校读者我要写书评

暂无评论

power system Equivalent Inertia Estimation Method Using system Identification 5

Power System Equivalent Inertia Estimation Method Using Syst...

引用

5th IEEE International Conference on Electronics Technology, ICET 2022

作者： Ma, Huan Yang, Dong Qin, Hao Cao, Yongji Cheng, Dingyi Zhang, Bing Hao, Xudong Zhou, Ning State Grid Shandong Electric Power Research Institute State Grid Shandong Electric Power Company Jinan China Shandong University Key Laboratory of Power System Intelligent Dispatch and Control Ministry of Education Jinan China Shandong Power Dispatch & Control Center State Grid Shandong Electric Power Company Jinan China

ISBN: (纸本)9781665485081

As the proportion of renewable energy sources increase, the inertia of the power system continues to decrease, leading to a serious impact on frequency security and stability. There is an urgent need for an online estimation of the equivalent inertia of power systems. Most of the existing inertia estimation methods are based on the rate of change of frequency under large disturbance scenarios. According to the measurement data under normal operation, this paper estimates the equivalent inertia using system identification. The inertia response of the power system is analysed and an expression for the equivalent inertia is derived. An improved numerical algorithm based on subspace state space system identification and a least squares estimation method is used to calculate the equivalent inertia of the system. The validity of the proposed method is verified in a WSCC 9-bus power system case, showing that the proposed method has a high identification accuracy and can be adapted to different forms of load fluctuations. © 2022 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Virtual inertia control strategy for PV using DC capacitive and electrochemical energy storage 4

Virtual inertia control strategy for PV using DC capacitive ...

引用

4th IEEE International Conference on power, Intelligent Computing and systems, ICPICS 2022

作者： Jiang, Zhe Ma, Linlin Gao, Zhimin Cao, Yongji Qin, Hao Yang, Dong Ma, Huan Fang, Qiao State Grid Shandong Electric Power Research Institute State Grid Shandong Electric Power Company Jinan China Shandong Power Dispatch & Control Center State Grid Shandong Electric Power Company Jinan China Key Laboratory of Power System Intelligent Dispatch and Control of the Ministry of Education Shandong University Jinan China

ISBN: (数字)9781665467735

ISBN: (纸本)9781665467735

With the increasing penetration of renewable energies, the power system inertia is decreasing, and there is an urgent need for wind and PV generations to participate in frequency response. PV units are stationary power generating units and usually work in maximum power tracking mode. It is difficult to provide inertia support to enhance the power system frequency characteristics. Therefore, this paper proposes a frequency control strategy based on the DC capacitor energy storage on the high voltage side of PV generation, using its transient discharge process to make it participate in the frequency response. Considering the limited energy stored in the capacitor, droop control and virtual inertia control are added to the electrochemical energy storage for inertia compensation, and a cooperative inertia control strategy is proposed for PV and energy storage system. A case study is carried out to verify the effectiveness of the proposed control strategy. © 2022 IEEE.

关键词： Frequency response

来源：评论

学校读者我要写书评

暂无评论

Voltage Stability Evaluation Considering Successive Commutation Failure Risk

Voltage Stability Evaluation Considering Successive Commutat...

引用

2023 IEEE International Conference on control, Electronics and Computer Technology, ICCECT 2023

作者： Ding, Rui Wang, Hengtong Jia, Zhaohao Zhu, Yuanzhen Li, Changgang Cao, Yongji State Grid Shandong Electric Power Company State Grid Huangdao Power Supply Company Qingdao China State Grid Shandong Electric Power Company State Grid Zibo Power Supply Company Zibo China State Grid Shandong Electric Power Company State Grid Jinan Power Supply Company Jinan China State Grid Shandong Electric Power Research Institute State Grid Shandong Electric Power Company Jinan China Shandong University Key Laboratory of Power System Intelligent Dispatch and Control of the Ministry of Education Jinan China Shandong University Academy of Intelligent Innovation Jinan China

ISBN: (纸本)9798350399028

In order to evaluate the risk of successive commutation failure caused by voltage drop, a deep learning-based method is proposed in this paper. First, the mechanism of successive commutation failures is analyzed and the minimum second voltage drop value of the commutation bus after short-circuit fault is utilized as the index to quantify the severity of line outage contingencies. Then, to quickly evaluate the impact of multi-line outage failures on DC systems, a deep learning-based assessment network is built, of which the output is the minimum second voltage drop value of the commutation bus and inputs are steady-state features related to network structure. Moreover, a bus impedance matrix formation approach based on Woodbury formula is proposed, which is used in the calculation of input features and search index. Finally, simulation results based on a real-life AC/DC power system demonstrate that the proposed method significantly improves the risk evaluation efficiency of successive commutation failure. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Cross-Platform Real-Time power system simulation Software for the New power system

Design and Implementation of a Cross-Platform Real-Time Powe...

引用

Intelligent power and systems (ICIPS), International Conference on

作者： Ying Huang Yuanhong Lu Jingyue Zhang Jie Zhan Yanjun Zhao Yufeng Hu State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid Guangzhou 510663 China Southern Power Grid Guangzhou China CSG Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou 510663 China Southern Power Grid Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou 510663 China Southern Power Grid Guangzhou China National Energy Power Grid Technology R&D Centre Guangzhou 510663 China Southern Power Grid Guangzhou China CSG Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou Guangzhou China

ISBN: (数字)9798331532765

ISBN: (纸本)9798331532772

With the rapid increase in renewable energy installation nodes and the substantial enhancement of switching frequencies in the new power system, this paper proposes a design scheme for a cloud simulation software that employs the Latency Insertion Method (LIM) to decompose large-scale new power system models into several subsystems, enabling multi-platform integrated parallel computing. The self-developed platform meets the demands of ultra-large simulation scales, ultra-small simulation time steps, and massive simulation computations in power systems. Experimental results demonstrate that the accelerated simulation technology, which integrates model segmentation using LIM with multi-core parallel execution, can enhance the simulation speed by up to 858 times while maintaining simulation accuracy. This significantly improves simulation efficiency and is suitable for large-scale simulations of new power systems.

关键词： Renewable energy sources Accuracy Computational modeling Switching frequency Software algorithms Random access memory Parallel processing Software Real-time systems power systems

来源：评论

学校读者我要写书评

暂无评论

MARS: Multi-Agent Deep Reinforcement Learning for Real-Time Workflow Scheduling in Hybrid Clouds with Privacy Protection 30

MARS: Multi-Agent Deep Reinforcement Learning for Real-Time ...

引用

30th IEEE International Conference on Parallel and Distributed systems, ICPADS 2024

作者： Cheng, Long He, Haoyang Gu, Yan Liu, Qingzhi Zhao, Zhiming Fang, Fang North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering Beijing China Wageningen University and Research Information Technology Group Netherlands University of Amsterdam Research Group of Multi-Scale Networked Systems Netherlands

ISBN: (纸本)9798331515966

Scheduling workflows in hybrid cloud environments presents significant challenges due to the inherent complexity of workflows and the dynamic nature of cloud resources. This complexity is further increased when attempting to balance workflow performance with privacy protection. Recent efforts have leveraged deep reinforcement learning (DRL) to address these challenges. However, most of these approaches rely on single-agent models, which can lead to security issues and scalability problems due to their centralized processing. Specifically, the properties of workflows are transferred to the single agent, which risks leaking privacy information. Our paper addresses these issues by introducing MARS, a real-time workflow scheduling method that prioritizes privacy protection in hybrid clouds. MARS leverages multi-agent deep reinforcement learning (MADRL) to optimize the workflow scheduling of cloud virtual machines (VMs). The benefit of our solution is that it relies on the collaborative learning of multi-agents on multiple VMs, which could assign user data to specific cloud servers for privacy protection while sharing training experiences between agents. In our implementation, MARS aims to reduce workflow completion time and operational costs while complying with strict privacy protection guidelines. The experimental results demonstrate that MARS can significantly surpass existing methods, reducing makespan by an average of 53.18% and costs by 61.98% compared to basic techniques, and achieving 20.26% and 25.71% improvements over the latest advanced methods, respectively. © 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：