检索结果-内蒙古大学图书馆

4th IEEE International Conference on power, Electronics and Computer Applications, ICPECA 2024

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

ISBN: (纸本)9798350359589

The unpredictable and highly variable nature of wind power generation demands advanced predictive models to enhance the operational stability of power systems under non-stationary wind conditions. This study presents an innovative approach for short-term wind power prediction, ingeniously integrating Variational Mode Decomposition (VMD), Quantum Particle Swarm Optimization (QPSO), and Long Short-Term Memory (LSTM) network into a cohesive forecasting methodology. Initially, VMD is applied to deconstruct wind power data into distinct sub-modes, thus reducing data complexity and facilitating more accurate analysis. The LSTM model is then fine-tuned using QPSO to refine its hyperparameters, thereby optimizing forecast performance. Each sub-mode is forecasted through a specialized LSTM model, and the collective forecasts are compounded to form the final prediction. Comparative analyses with conventional LSTM, PSO-enhanced LSTM, and QPSO-LSTM models reveal that our proposed VMD-QPSO-LSTM approach yields significantly higher accuracy in forecasting, highlighting its potential to efficiently navigate the uncertainties associated with wind power generation. © 2024 IEEE.

关键词： deep learning long short-term memory network variational mode decomposition wind power forecasting

来源：评论

学校读者我要写书评

暂无评论

Implementation of Vector Oriented control of DFIG based on FPGA 3

Implementation of Vector Oriented Control of DFIG based on F...

引用

3rd International Conference on power and Energy Applications, ICPEA 2020

作者： Wang, Zelin Zhao, Haoran Li, Bing Gao, Shuning Shandong University Key Laboratory of Power System Intelligent Dispatch and Control Ministry of Education Jinan China

ISBN: (纸本)9781728190297

control strategy is indispensable in the use of doubly fed induction generator (DFIG). Vector oriented control (VOC) is a control strategy that has been tested by many scholars in DFIG on software. Field-Programmable Gate Array (FPGA), with the powerful capability of parallel computing and satisfying clocking frequency up to 200MHz, has widely applications in the high-speed data processing. Moreover, system Generator, as a tool developed by Xilinx, is a Simulink-based toolkit for FPGA developers. Thus, this paper implements VOC on FPGA by using system Generator. The simulation result shows that FPGA works well on VOC under the clocking frequency of 100MHz. This research solves the timing problem of loop design in system Generator and lays the foundation of real-time simulation of DFIG. © 2020 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Hierarchical reserve allocation with air conditioning loads considering lock time using Benders decomposition

引用

INTERNATIONAL JOURNAL OF ELECTRICAL power & ENERGY systemS 2019年 110卷 293-308页

作者： Cheng, Dingyi Zhang, Wen Wang, Kai Shandong Univ Minist Educ Key Lab Power Syst Intelligent Dispatch & Control Jinan 250061 Shandong Peoples R China State Grid Jibei Elect Power Co Ltd Dispatch Ctr Beijing 100054 Peoples R China

With the integration of more and more renewable energy in the power system, more reserves are needed to cope with the intermittent and stochastic characteristics of the renewable energy. To relieve the stress of the reserve supply by the generation side, air conditioning loads can be considered to participate in reserve allocation in dynamic economic dispatch owing to their high proportion in the demand and thermal energy storage characteristics. The lock time of air conditioners should not be ignored since it can avoid the short cycling of compressor. This paper proposes a hierarchical reserve allocation model with air conditioning loads considering lock time to coordinate the power system dispatch and the control of air conditioning loads. An aggregate model of air conditioning loads considering the lock time is proposed and linear constraints of the air conditioning loads are developed. Among these constraints, lockout constraints are linear slack constraints for convenient in computation and the validity of the slack form has been proved. These constraints are integrated into the reserve allocation in dynamic economic dispatch. In such a state, the problem has multi-time scale characteristics and thus, is difficult to solve;therefore, this problem is reconstructed as a three-level hierarchical problem, and Benders decomposition is applied. The first level (operation level) represents the operation of the power system in normal conditions. Each N-1 contingency is placed in the second level (contingency level). The third level (load control level) considers the constraints of the air conditioning loads. To increase the calculation efficiency, we propose three methods, which are adding necessary conditions, adjusting upper bound and applying parallel computing. The simulation results show that air conditioning loads can realize load reserve, and the proposed hierarchical solving method is effective to solve the reserve allocation problem with air conditioning loads

关键词： Air conditioning loads Lock time Reserve allocation Hierarchical Benders decomposition

来源：评论

学校读者我要写书评

暂无评论

Transient Characteristics Analysis of Shunt Capacitor Asynchronous Energizing

引用

IEEE TRANSACTIONS ON power DELIVERY 2020年第5期35卷 2186-2195页

作者： Liang, Jiabi Zhu, Ke Shandong Univ Sch Elect Engn Minist Educ Key Lab Power Syst Intelligent Dispatch & Control Jinan 250061 Shandong Peoples R China

The capacitor energizing transient as a kind of typical disturbance is used in the studies of power quality, condition monitoring, and other fields, and all studies heavily rely on transient characteristics. However, most characteristics are established based on the three-phase capacitor synchronous energizing (SE), and the effect of asynchronous energizing (AE) is neglected, which may affect the relevant studies. In this paper, the main characterizations of the capacitor AE transient, such as the oscillation frequency, time constant, and transient magnitude are analyzed considering the operation modes of the system and capacitor neutral points. The effect of the three-phase circuit asymmetry on the characterizations is investigated. The downstream voltage magnification phenomena in not only positive-sequence circuit but also zero-sequence circuit caused by the capacitor AE are also revealed. The theoretical analysis, computer simulation and lab experiment results have verified the effectiveness of the characteristics.

关键词： Capacitors Transient analysis Time-frequency analysis Integrated circuits Resistance Inductance Capacitor capacitor energizing transient characteristic synchronous asynchronous voltage magnification

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Photovoltaic power Prediction Model Based on Multi-source Data Fusion and Deep Learning

A Hybrid Photovoltaic Power Prediction Model Based on Multi-...

引用

3rd IEEE Student Conference on Electrical Machines and systems (SCEMS)

作者： Si, Zhiyuan Yang, Ming Yu, Yixiao Ding, Tingting Li, Menglin Shandong Univ Key Lab Power Syst Intelligent Dispatch & Control Jinan Peoples R China

ISBN: (纸本)9781728156224

With the rapid development of the world economy, environmental and energy problems have become increasingly prominent. This fact motivates the exploitation of renewable energy, such as solar power. Solar photovoltaic (PV) power has been integrated into modern smart grids on a large scale. Accurate photovoltaic prediction is the key to ensure the stable operation of the power grid. The single prediction model is difficult to be universal due to the limitations of the model. Therefore, this paper proposes a hybrid ultra-short-term photovoltaic power prediction model based on multi-source data fusion and deep learning. First, the satellite cloud images, historical power sequences, and numerical weather prediction (NWP) data are fused. Then, the photovoltaic power prediction models are established by using appropriate deep learning methods (convolutional neural networks (CNN), long-short term memory (LSTM) networks, and Extreme Gradient Boosting (XGBoost)) according to different data. Finally, the three models are combined to get the final prediction result. The results show that the proposed method in this paper has better forecasting performance than other single models.

关键词： convolutional neural networks mapping model photovoltaic power forecasting satellite images XGBoost

来源：评论

学校读者我要写书评

暂无评论

Circulating Current Suppressing Strategy for MMC-HVDC in the Stationary Frame

Circulating Current Suppressing Strategy for MMC-HVDC in the...

引用

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

作者： Wang, Jinyu Liang, Jun Wang, Chengfu Dong, Xiaoming Wang, Zhuodi Liang, Zhengtang Shandong Univ Key Lab Power Syst Intelligent Dispatch & Control Jinan Peoples R China

ISBN: (纸本)9781509054183

Proportional resonant (PR) controllers/repetitive controllers (RC) based circulating current suppressing strategies in the stationary frame are widely used in MMC because of their simpleness and effectiveness. Unfortunately, they cannot be directly used in MMC-HVDC systems since they can result in dcline voltage ripples and thus deteriorate system performance and stability under unbalanced grid conditions. This paper studies the problem in detail and then proposes corresponding improved circulating current suppressing strategies for MMC-HVDC, in which newly designed zero-sequence circulating current controller is employed. The proposed strategies can effectively eliminate both circulating currents and dc-line voltage ripples for MMC-HVDC systems under balanced and unbalanced grid conditions. Hence, they greatly enhance the fault ride-through capability of MMC-HVDC systems without adding any control cost or the number of controllers. The theoretical analysis and the proposed strategies are both verified by an established MMC-HVDC simulation model in MATlab/Simulink.

关键词： Circulating current voltage ripple high voltage direct current (HVDC) modular multilevel converter (MMC) proportional resonant (PR) repetitive controller

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

Multi-dimensional scenario forecast for generation of multiple wind farms

引用

Journal of Modern power systems and Clean Energy 2015年第3期3卷 361-370页

作者： Ming YANG You LIN Simeng ZHU Xueshan HAN Hongtao WANG Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Laboratory of Electric Vehicles Engineering of Shandong ProvinceShandong UniversityJinan 250061China Zaozhuang Power Supply Company Zaozhuang 277800China

A novel multi-dimensional scenario forecast approach which can capture the dynamic temporal-spatial interdependence relation among the outputs of multiple wind farms is *** the proposed approach,support vector machine(SVM)is applied for the spot forecast of wind power *** probability density function(PDF)of the SVM forecast error is predicted by sparse Bayesian learning(SBL),and the spot forecast result is corrected according to the error expectation *** copula function is estimated using a Gaussian copula-based dynamic conditional correlation matrix regression(DCCMR)model to describe the correlation among the *** the multidimensional scenario is generated with respect to the estimated marginal distributions and the copula *** results on three adjacent wind farms illustrate the effectiveness of the proposed approach.

关键词： Wind power generation forecast Multidimensional scenario forecast Support vector machine(SVM) Sparse Bayesian learning(SBL) Gaussian copula Dynamic conditional correlation matrix

来源：评论

学校读者我要写书评

暂无评论

Study of Modeling of Dynamic Components in STEPS

Study of Modeling of Dynamic Components in STEPS

引用

2020 IEEE Sustainable power and Energy Conference, iSPEC 2020

作者： Li, Changgang Wu, Yue Zhang, Hengxu Liu, Yutian Key Laboratory of Power System Intelligent Dispatch and Control Ministry of Education Shandong University Jinan China

ISBN: (纸本)9781728191645

A new open-source power system analysis toolbox developed by us has been released, which is named STEPS and can support both power flow solution and dynamic simulation. To improve the compatibility of STEPS and the convenience of dynamic simulation, many frequently-used dynamic models in PSS/E and PSASP are built-in. In this paper, the defined basic blocks and the currently supported models in STEPS will be introduced firstly. Then, some built-in turbine governor, exciter, and PSS models are selected, introduced, and modeled in Simulink. The same inputs are added to both models in STEPS and Simulink separately, and the outputs of them are compared to verify the validity and acquire the accuracy of the selected built-in models. Finally, a case of dynamic simulation with other built-in dynamic models is tested in STEPS and PSS/E separately to further show the validity of dynamic models. © 2020 IEEE.

关键词： Dynamic models

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection of Wind Turbine Generator Based on LSTM and Kshape Clustering

Anomaly Detection of Wind Turbine Generator Based on LSTM an...

引用

IEEE/IAS Industrial and Commercial power system Asia (IEEE I and CPS Asia)

作者： Jin, Zheyu Yang, Ming Zeng, Xiangjun Feng, Chen Shandong Univ Key Lab Power Syst Intelligent Dispatch & Control Jinan Peoples R China

ISBN: (纸本)9798350339345

Anomaly detection of wind turbine generators helps to detect faults of related components in advance, thus improving the economy and reliability of wind farm operation. This paper presents a generator anomaly detection method using long short-term memory neural network (LSTM) and Kshape clustering algorithm. This work first considers the characteristics of wind turbine supervisory control and data acquisition(SCADA) data, proposes a feature analysis method combining correlation coefficients and feature ranking, then the Kshape clustering algorithm is used to select wind turbines with similar operating states to expand the training dataset. Anomaly detection state estimation model is constructed by combining well-performanced LSTM models trained by selected units' dataset. Finally, the feasibility and accuracy of the proposed method are verified based on the SCADA data of actual wind farms.

关键词： wind turbine generator anomaly detection similarity long short-term memory neural network (LSTM)

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：