检索结果-内蒙古大学图书馆

IEEE Power and Energy Society General Meeting

作者： Jixiang LU Zhihong YANG Qipei ZHANG Mengfu TU Technology Research Center NARI Group Corporation Nanjing China State Key Laboratory of Intelligent Power Grid Protection and Operation Control Nanjing China

To better mine the effective information contained in massive data and improve the accuracy of short-term load forecasting, this paper proposes a hybrid model based on convolutional neural network and long short-term memory network (CNN-LSTM) for short-term load forecasting (STLF), which takes massive historical load data, meteorological data, date information, and peak-valley electric price data as input by constructing continuous feature maps with time sliding window. Convolutional neural network (CNN) is used to extract features and reshape them into vectors. The feature vectors are constructed in temporal and fed into long short-term memory network (LSTM) which is used to predict STLF. To the best of our knowledge, this is the first work to predict STLF using deep learning in both spatial and temporal domains. It is shown that the forecasting accuracy can be notably improved by CNN-LSTM hybrid model method. The effectiveness of the proposed method is validated through extensive comparison studies on a real-world dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast Fault protection Design and control of DC Trnasformer

Fast Fault Protection Design and Control of DC Trnasformer

引用

Sustainable Power and Energy Conference (iSPEC)

作者： Guoning Wang Zhigang Wang Xiaoming Zeng Yongwei Wang Weimei Ge State Key Laboratory of Smart Grid Protection and Control NARI Group Corporation (State Grid Electric Power Reasearch Insitute) Nanjing China State Grid Xinyuan Company Shandong TaIshan Pumped Storage Power Station Co. LTD Tai’an China

ISBN: (纸本)9781665414401

With the diversification of loads and the development of distributed energy, DC system and DC transformer attracted more and more attention in modern power system. However, bipolar short-circuit faults threatened the safety of DC power system operation due to the surge current caused by them. When DC transformer low voltage output has short circuit fault, it must block fault current quickly. This paper proposed a fault protection control method in DC transformer. Through the design and control, the fault current can be quickly blocked, and the fault current output can be maintained to support the rapid recovery of the system. After adding the fault protection circuit and control in DC transformer, the protection performance is greatly improved. Finally, the real-time simulation of RTDS verifies that the proposed short-circuit protection current-limiting control can well achieve the design goals.

关键词： Low voltage Conferences Fault protection Surge protection Transformers Real-time systems Safety

来源：评论

学校读者我要写书评

暂无评论

Instantaneous Frequency Measurement and Tracking under Out of Step Oscillation

Instantaneous Frequency Measurement and Tracking under Out o...

引用

IEEE International Conference on smart grid and smart Cities (ICSGSC)

作者： Ke Su Cai Gan Feng Zhang Rong Rong Ji Sui Sheng Zheng Cheng Lin Xia Tian Yu Lan State Key Laboratory of Smart Grid Protection and Control NARI Group Corporation State Grid Electric Power Research Institute NanJing China Ultra High Voltage Branch Company State Grid Zhejiang Powe Company HangZhou China NARI Group Corporation State Grid Eelectric Power Research Institute NanJing China

As an important operating parameter of the power system, the instantaneous frequency of the current can reflect the actual operating state of the current system, especially when the system is out of step. The characteristics of the current in the oscillation line are analyzed in this paper. An algorithm for measuring instantaneous frequency of current while power system swings is presented, based on the broad definition of angular frequency. According to the feature of the actual power system, a new method for measuring the instantaneous current frequency by real-time sampling is proposed. Finally, the algorithm is simulated on the model of the equivalent systems. When the system swings, the real-time frequency is gained by sampling the current in the line, combined with the frequency of the equivalent machine of both sides. It shows that the obtained current frequency is reasonable and effective, compared to the characteristics of the system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Workload-Aware Scheduling for Data Analytics upon Heterogeneous Storage

Workload-Aware Scheduling for Data Analytics upon Heterogene...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Zhuzhong Qian Yuan Gao Mingtao Ji Hui Peng Peng Chen Yibo Jin Sanglu Lu State Key Laboratory for Novel Software Technology Nanjing University Nanjing China NARI Research Institute NARI Group Corporation(State Grid Electric Power Research Institute) Nanjing System R&D Center NARI Technology Co. Ltd. Nanjing State Key Laboratory of Smart Grid Protection and Control NARI Group Corporation Nanjing

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

A trend in nowadays data centers is that equipped with SSD, HDD, etc., heterogeneous storage devices are widely deployed to meet diverse demands of various big data workloads. Since the reading performance of various storage devices are quite different, traditional concurrent data fetching easily incurs unbalanced use among devices. As a result, the straggler in terms of the data fetching, derived from the unbalanced use, directly increases the overall latency of data analytics. To avoid such unbalanced use on fetching large volume of data concurrently from storage devices, we formulate Workload-Aware Scheduling problem for Heterogeneous storage devices (WASH), the goal of which is to minimize the maximum data fetching time for parallel data analytical tasks. We design a randomized algorithm (rWASH) to select a proper source device for each task based on delicate calculated probabilities, which can be proved concentrated on its optimum with high probability. Extensive experiments show that rWASH reduces the average data fetching time for tasks by up to 55% over the state-of-the-art algorithms.

关键词： Task analysis Performance evaluation Data analysis Scheduling Data centers Probability Hardware

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control Based Active Frequency Support Strategy for Combined Wind/Photovoltaic/Storage Power Station

Model Predictive Control Based Active Frequency Support Stra...

引用

China International Electrical and Energy Conference (CIEEC)

作者： Manliang Wang Bingtuan Gao Yingwei Jiang Yunfeng Tian Wenqi Dong Xuewei Shi School of Electrical Engineering Southeast University Nanjing China State Key Laboratory of Smart Grid Protection and Control Nari Group Corporation Nanjing China State Grid Hebei Zhangjiakou Scenery Storage and Transmission New Energy Co. Ltd Zhangjiakou China

The high penetration of renewable energy sources connected to the grid has brought great challenges to the frequency stability of the power system. For the combined wind/pohotovoltaic/storage power station, it is of great significance for better frequency performance to realize the coordination control of active power. Therefore, this paper presents a frequency active support strategy for combined wind/pohotovoltaic/storage power station. By establishing the model of combined wind/pohotovoltaic/storage power station, this strategy applies model predictive control (MPC) to optimize the total active power reference value and the allocation of response power of the combined wind/pohotovoltaic/storage power station. For obtaining better frequency performance, this strategy aims at absorbing wind and solar energy resources and improving the economy of energy storage station. In order to verify the performance of the proposed strategy, it is compared with droop control using MATLAB/Simulink when the load increasing and decreasing respectively. The simulation results clearly show the effectiveness of the active frequency support strategy proposed in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Assistant Reactive Shielding Coil for Electric Vehicle Wireless Charging System

Analysis of Assistant Reactive Shielding Coil for Electric V...

引用

Information Technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Shiliang Hou Bo Yu Wei Yan Chongming Zhu Ke Wang Zhenghao Wu College of Electrical and Automation Engineering Nanjing Normal University Nanjing China State Key Laboratory of Start Grid Protection and Control of NARI Group Corporation Nanjing China

ISBN: (数字)9781728152240

ISBN: (纸本)9781728152257

To realize electromagnetic safety of wireless power transmission (WPT) system for electric vehicle (EV), the shielding methods should be analyzed. This paper proposes a method of using assistant reactive shielding coils to cancel the electromagnetic field (EMF) outside the working area of WPT system. By tuning compensation capacitance of shielding coil automatically, we design 3 cases with different location and shape of coils to achieve reactive shielding. By comparison and simulation, placing ring shielding coils above receiving (Rx) pad and under transmitting (Tx) pad is the best way to suppress EMF of WPT system's non-working area. The shielding coils' radius is slightly bigger than coupling coils' outer radius. This paper also provides a new method to realize WPT shielding system's automatic adjustment for resonance. Besides, assistant reactive shielding coils' cost is lower than traditional aluminum plate.

关键词： Capacitance Capacitors control systems Couplings Magnetic shielding Ferrites Topology

来源：评论

学校读者我要写书评

暂无评论

Research on control Strategy and Simulation of MMC-HVDC System Based on Battery Energy Storage System

Research on Control Strategy and Simulation of MMC-HVDC Syst...

引用

Electrical Engineering and control Science (IC2ECS), International Conference on

作者： Liyu Dai Chaoping Deng Wujie Chao Jinke Wang Junwei Huang Electric Power Research Institute State Grid Fujian Electric Power Co. Ltd Fujian Key Laboratory of Smart Grid Protection and Operation Control Fuzhou China

This paper presents a method of applying MMC based on battery energy storage system (BESS) to HVDC system to realize power decoupling control on AC and DC side. Firstly, the basic structure and working principle of MMC-HVDC system based on BESS are analyzed. Then, based on the mathematical equivalent model, the MMC-BESS decoupling control method based on DC power control is derived, and the AC-DC power decoupling control is realized. Finally, a +400kV MMC-HVDC system is built on the RTDS platform, and the proposed control strategy and power decoupling effect are verified. The results show that the MMC-BESS control strategy proposed in this paper is effective. The MMC-HVDC system based on BESS can realize active power decoupling control between AC side and DC side, and the unbalanced power between AC side and DC side can be compensated by the charge and discharge of BESS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Best practices in China Southern Power grid competition of AI short-term load forecasting

Best practices in China Southern Power Grid competition of A...

引用

IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC)

作者： Jixiang Lu Junxia Qian Qipei Zhang Shaobo Liu Feng Xie Hongsheng Xu State Key Laboratory of Smart Power Grid Protection and Control Nanjing China Jiangsu Keneng Electric Power Engineering Consultant Co. Ltd Nanjing China Technology Research Center NARI Group Corporation Nanjing China

ISBN: (数字)9781728157481

ISBN: (纸本)9781728157498

China Southern Power grid (CSG) hosted a competition of AI short-term load forecasting with real-world load data in Sept 2019. NARI Technology was invited for the 10 days closed match and got the 2 nd prize among 28 top players in China, such as research institutes, universities, and system suppliers. This paper highlights the best practices we did in the competition: feature selection of short-term load forecasting, outlier data preprocessing for both load data and meteorological data, multiple head long short term memory (LSTM) neural network innovation and data augmentation with the benchmark. opportunities for improvements are considered as well.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ultra-short-term wind speed forecasting method based on spatial and temporal correlation models

引用

The Journal of Engineering 2017年第13期2017卷 1071-1075页

作者： Zhou Haiqiang Xue Yusheng Guo Jizhu Chen Jiehui Energy and Electrical Engineering School Hohai University Nanjing 211100 Jiangsu Province People's Republic of China NARI Group Corporation (State Grid Electric Power Research Institute) Nanjing 211106 People's Republic of China State Key Laboratory of Smart Grid Protection and Control Nanjing 211106 People's Republic of China

An ultra-short-term wind speed forecasting method based on spatial and temporal correlation models is proposed. Firstly, the temporal correlation model was studied. The generalised distance of wind speed time series is defined based on the dynamic time warping distance and correlation coefficient. Samples with similar wind dynamic patterns are classed into the same group. Time series in one group are depicted with a representative time series which is modelled by an autoregressive moving average (ARMA) model. For time series which cannot be classed to any of these groups, a special group was defined. It was modelled by artificial neural network (ANN). Secondly, the spatial correlation between the target wind farm and the reference wind farm was investigated with the meteorological data taking into consideration. The grey prediction method is utilised to predict the wind speed. Finally, the combined ultra-short-term wind speed forecasting method is proposed. It takes into account the inherent time correlation of the target wind speed and its spatial correlation with reference wind farm. The wind speed prediction of wind farms in northwest USA verifies the effectiveness and feasibility of the proposed method.

关键词： wind neural nets time series grey systems autoregressive moving average processes wind power plants power engineering computing ultra-short-term wind speed forecasting method wind farms wind speed prediction target wind speed inherent time correlation ultra-short-term wind speed combination forecasting method corresponding spatial correlation model grey prediction method reference wind farm target wind farm ARMA model representative time series similar wind dynamic patterns sliding time window correlation coefficient dynamic time warping distance wind speed time series temporal correlation model temporal correlation models spatial correlation models

来源：评论

学校读者我要写书评

暂无评论

Wind-Storage Coordinated control Strategy for Inertia Enhancement of High Ratio Renewable Energy Power Systems

SSRN

引用

SSRN 2024年

作者： Shu, Hongchun Dong, Haifei Wang, Guangxue Chen, Jing Shi, Botao Tang, Yutao the State Key Laboratory Collaborative Innovation Center for Smart Grid Fault Detection Protection and Control Jointly Yunnan Key Laboratory of Green Energy and Digital Power Measurement Control and Protection Kunming University of Science and Technology Kunming650500 China

The replacement of thermal power units with renewable energy power generation equipment like wind and photovoltaics has decreased the inertia level of power systems and weakened the frequency stability of the power grid. In order to improve the inertia level of the new power systems and strengthen the inertia support capability of the renewable energy power system to the grid, a wind-storage coordinated control strategy for the inertia enhancement of high-proportion renewable energy power system is proposed in this paper. A time domain model of the inertia response of the wind-storage coordinated control system is also established. An inertia level enhancement strategy of virtual inertia and virtual sag coordinated control of wind-storage joint system is proposed. It improves the system inertia using the analysis results of system inertia requirements as data support and considering the characteristics of battery storage with fast charging and discharging response, and flexible capacity configuration. In addition, the effectiveness of energy storage system (ESS) participation in system inertia enhancement is guaranteed by proposing energy storage based on the ESS state of charge (SOC), which participates in the inertia of the new energy power system to enhance the control coefficient adaptive strategy. Finally, a comparative analysis is carried out using RTLAB simulation test to verify the effectiveness of the method proposed in this paper. © 2024, The Authors. All rights reserved.

关键词： Frequency response

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：