检索结果-内蒙古大学图书馆

2019 IEEE PES Innovative Smart Grid Technologies Asia, ISGT 2019

作者： Cui, Yang Zhang, Jiarui Zhong, Wuzhi Key Laboratory of Modern Power System Simulation and Control Renewable Energy Technology Ministry of Education Northeast Electric Power University Ji Lin China China Electric Power Research Institute Beijing China

ISBN: (纸本)9781728135205

With the rapid growth of Photovoltaic (PV) power capacity, how to improve the accuracy of PV output prediction becomes an intensive problem. This paper proposes a prediction model to reduce the error of prediction by combining gray correlation theory to select similar days with BP neural network. Firstly, the factors of weather between sample days selected as similar days and forecast days are calculated to find three similar days which have the highest relevance. After that, different weights are assigned to historical data of similar days according to the degree of relevance from large to small and back propagation (BP) neural network is combined to predict the output of PV. Finally, based on the actual measurement data of a photovoltaic power station in Northeast China, this paper validates the positive effects of this model on MATLAB simulation platform. Results show that selecting similar days by grey correlation and combining BP neural network can effectively improve the prediction accuracy of short-term PV output. © 2019 IEEE.

关键词： simulation platform

来源：评论

学校读者我要写书评

暂无评论

Planning of active power distribution network based on source-network-load collaborative optimization

Planning of active power distribution network based on sourc...

引用

The 16th IET International Conference on AC and DC power Transmission (ACDC 2020)

作者： Z. Jiang Q. Yu A. Li Y. Xiong G. Long Y. Liu Ministry of Education (Northeast Electric Power University) Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Jilin 132012 China Tsinghua University State Key Laboratory of Power Systems Department of Electrical Engineering Beijing China

With the fast development of renewable energy generation, the randomness and volatility seriously threaten the stability of the power system. In order to improve the consumption rate of renewable energy and the economic benefit, the source-network-load collaborative optimization is put forward and widely used in the power system. And the active power distribution network which consists of the energy storage devices and flexible load is the best carrier to realize it. Based on the active power distribution network planning, this paper firstly designs an economic index covering construction cost and operation cost as the optimization objective. Then with the physical constraints consisting of the physical features of generation units, energy storage devices and flexible load, the source-network-load collaborative optimization model of active power distribution network is established. Finally, a case of city distribution network is presented to verify the effect of source-network-load collaborative optimization and the efficiency of the optimization model.

关键词： power distribution planning power distribution reliability distributed power generation power distribution economics renewable energy sources optimisation energy storage

来源：评论

学校读者我要写书评

暂无评论

An Optimization Method Based on Time-Sharing energy Complementation to Determine Transmission Capacity of Wind-CSP Plants Combined system

An Optimization Method Based on Time-Sharing Energy Compleme...

引用

2019 IEEE PES Innovative Smart Grid Technologies Asia, ISGT 2019

作者： Cui, Yang Zhang, Huiquan Huang, Siyu Xu, Boyang Key Laboratory of Modern Power System Simulation and Control Renewable Energy Technology Ministry of Education Northeast Electric Power University Ji Lin China Shenzhen Power Supply Co.ltd Shenzhen China

ISBN: (纸本)9781728135205

Since northwest China has abundant wind and solar resources, constructing the concentrating solar power (CSP) plant near to the wind-generated electricity factory tend to a common form of energy exploiting. How to size for the capacity of the transmission line to meet the demand of delivery of the wind-concentrated solar power (CSP) plant system becomes an intensive problem. Based on the theory of time-sharing energy complementarity, this paper proposes a mathematical optimization model of the integrated output of Wind farm and CSP plant to suppress the power fluctuations. Then, by independently considering the impacts of the thermal storage capacity of CSP plant, the capacity optimization model of transmission line of wind power-CSP combined system is established. The case result demonstrates that the proposed method can reduce the investment cost of transmission line by reasonably configuring the thermal storage capacity of CSP. Moreover, the proposed strategy significantly improves the utilization rate of the transmission line and increases the comprehensive income of the joint generation system. © 2019 IEEE.

关键词： Concentrated solar power

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model for Building-level Day Ahead power Load Forecasting Based on Gated Recurrent Unit Networks

A Hybrid Model for Building-level Day Ahead Power Load Forec...

引用

Sustainable power and energy Conference (iSPEC)

作者： Hualu Zhang Boya Deng Jie Shi Key Laboratory of Modern Power System Simulation Control and Green Power New Technology of Ministry of Education Northeast Electric Power University Jilin Jilin Nanjing Nanrui Information Communication Technology Co. Ltd. NARI Group Corporation/State Grid Electric Power Research Institute Nanjing

ISBN: (纸本)9781665414401

Accurate forecasting of day-ahead electrical load is a key to optimize the operation of the integrated energy system (IES) and a fundamental function of the cyber-physical system (CPS) of IES. Due to the characteristics of different features, data collected by CPS often have different sampling frequencies, resulting in mining data trends inadequately when making a load forecast. This paper proposes an GRU-based model to combine historical data with different sampling frequencies in forecasting day-ahead building-level load. First, day-level features are clustered by K-means. Hour-levels features are then partitioned according to clustering results and inputted separately into a gated recurrent unit (GRU) based neural network to capture relationships between external features and load fluctuations. The temporal dependencies of minute-level data are captured by the GRU network directly without any external features. Finally, the least square method is used to combine forecasting results at each hour of two models. The simulation results present that the proposed model performs better than a single model when applying to real-world data.

关键词： Load forecasting simulation Neural networks Training data Predictive models Logic gates Data models

来源：评论

学校读者我要写书评

暂无评论

Generator model validation and parameter calibration based on PMU measurement data 3

Generator model validation and parameter calibration based o...

引用

3rd IEEE International Conference on energy Internet, ICEI 2019

作者： Zhang, Yanjun Jiang, He Gao, Kai Zhang, Jian Liu, Jiaqi Wang, Yupeng State Grid Liaoning Electric Power Co Ltd. Shenyang China Key Laboratory of Modern Power System Simulation and Control and Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin China

ISBN: (纸本)9781728114934

power system dynamic simulation is an important tool for us to master the dynamic behavior of power systems. It is very important to ensure the credibility of simulation results. Dynamic model validation and calibration has become one of the important applications of concern. In this paper, the method of using the dynamic data recorded by the phasor measurement unit (PMU) to improve the accuracy of the generator model is proposed, including model validation and model parameter id-entifycation. In model validation, the playback of the distur-bance event is used to simulate the response of the model for comparison with the measurement information of the PMU. If the simulation result is inconsistent with the actual mea-surements, the model parameters are not accurate. In the parameter identification step, the perturbation method is used to calculate the trajectory sensitivity of the parameter, and the problematic parameters causing the simulation error is iden-tified, then artificial intelligent method is used to automatically calib-ration the problematic parameters. Finally, other perturbation data is used to validate the credibility of the calibrated generator model, and the results obtained proved that the final calibration model is superior to the existing model. © 2019 IEEE.

关键词： Phasor measurement units

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

Sustainable power and energy Conference (iSPEC)

作者： Yuanhong Lu Qi Guo Zhijiang Liu Shuyong Li Haiping Guo Guanming Zeng State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid National Energy Power Grid Technology R&D Centre Guangzhou China State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System 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 Guangzhou China

ISBN: (纸本)9781665414401

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.

关键词： Visualization Correlation Substations Optical design Conferences Focusing Maintenance engineering

来源：评论

学校读者我要写书评

暂无评论

Real-time object detection method based on improved YOLOv4-tiny

arXiv

引用

arXiv 2020年

作者： Jiang, Zicong Zhao, Liquan Li, Shuaiyang Jia, Yanfei Key Laboratory of Modern Power System Simulation and Control and Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China College of Electrical and Information Engineering Beihua University Jilin132013 China

The "You only look once v4" (YOLOv4) is one type of object detection methods in deep learning. YOLOv4-tiny is proposed based on YOLOv4 to simple the network structure and reduce parameters, which makes it be suitable for developing on the mobile and embedded devices. To improve the real-time of object detection, a fast object detection method is proposed based on YOLOv4-tiny. It firstly uses two ResBlock-D modules in ResNet-D network instead of two CSPBlock modules in Yolov4-tiny, which reduces the computation complexity. Secondly, it designs an auxiliary residual network block to extract more feature information of object to reduce detection error. In the design of auxiliary network, two consecutive 3x3 convolutions are used to obtain 5x5 receptive fields to extract global features, and channel attention and spatial attention are also used to extract more effective information. In the end, it merges the auxiliary network and backbone network to construct the whole network structure of improved YOLOv4-tiny. simulation results show that the proposed method has faster object detection than YOLOv4-tiny and YOLOv3-tiny, and almost the same mean value of average precision as the YOLOv4-tiny. It is more suitable for real-time object detection, especially for developing on embedded devices. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Application Research of Chaotic Binary Particle Swarm Optimization Algorithm in Dynamic Spectrum Allocation

引用

Journal of Computers (Taiwan) 2020年第4期31卷 288-299页

作者： Teng, Zhi-Jun Xie, Lu-Ying Chen, Hao-Lei Zhang, Hua Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology China Ministry of Education[Northeast Electric Power University China Jilin 132012 China School of Electrical Engineering China Northeast Electric Power University China

Dynamic spectrum allocation (DSA) in cognitive radio system has become a hot topic to solve the spectrum scarcity. Particle swarm optimization (PSO) has shown great flexibility in solving the spectrum allocation problem, and many related studies have been proposed. However, there is still room for improvement in the problem that PSO will have a slow convergence rate in the DSA and the latter particle search is easy to fall into the local optimum. In this paper, a dynamic time-varying spectrum allocation scheme based on chaotic binary particle swarm optimization is proposed. The improved algorithm introduces the idea of chaotic map to optimize the initial population and the optimal position of each generation of particles, and utilizes the global ergodicity of chaotic map to overcome the shortcomings of the algorithm. Based on the graph theory model, a mathematical model of dimensionality reduction spectrum allocation is built to realize DSA for users. The experimental results show that the convergence time cost of the improved algorithm is low, and the higher network rewards can be obtained under different experiments, and the fast and efficient spectrum allocation is realized to satisfy the demands of cognitive radio communication. © 2020 Computer Society of the Republic of China. All rights reserved.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

A comparative thermodynamic analysis of Kalina and organic Rankine cycles for hot dry rock:a prospect study in the Gonghe Basin

引用

Frontiers in energy 2020年第4期14卷 889-900页

作者： Xuelin ZHANG Tong ZHANG Xiaodai XUE Yang SI Xuemin ZHANG Shengwei MEI State Key Laboratory of Control and Simulation of Power System and Generation Equipments Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Jingjing Energy Storage Co. Ltd.Changzhou 213200China School of QiDi(TUS)Renewable Energy Qinghai UniversityXining 810016China

Hot dry rock is a new type of geothermal resource which has a promising application prospect in *** paper conducted a comparative research on performance evaluation of two eligible bottoming cycles for a hot dry rock power plant in the Gonghe *** on the given heat production conditions,a Kalina cycle and three organic Rankine cycles were tested respectively with different ammonia-water mixtures of seven ammonia mass fractions and nine ecofriendly working *** results show that the optimal ammonia mass fraction is 82%for the proposed bottoming Kalina cycle in view of maximum net power *** analysis suggests that wet fluids should be supercritical while dry fluids should be saturated at the inlet of turbine,*** maximum net power output of the organic Rankine cycle with dry fluids expanding from saturated state is higher than that of the other organic Rankine cycle combinations,and is far higher than the maximum net power output in all tested Kalina cycle *** the given heat production conditions of hot dry rock resource in the Gonghe Basin,the saturated organic Rankine cycle with the dry fluid butane as working fluid generates the largest amount of net power.

关键词： hot dry rock Kalina cycle organic Rankine cycle thermodynamic analysis

来源：评论

学校读者我要写书评

暂无评论

Complementary Coordinated Dispatch of Multi-energy systems Considering power Flexibility Margin

Complementary Coordinated Dispatch of Multi-energy Systems C...

引用

2019 IEEE PES Innovative Smart Grid Technologies Asia, ISGT 2019

作者： Xiao, Bai Xiao, Zhiwen Yan, Gangui Jiang, Zhuo Wang, Maochun Yang, Hongzhi Dong, Ling Key Laboratory of Modern Power System Simulation and Control Renewable Energy Technology Northeast Electric Power University Jilin China School of Computer Science and Technology Beihua University Jilin China State Grid Qinghai Electric Power Company Xining China

ISBN: (纸本)9781728135205

In the light of wind and photovoltaic curtailment caused by the lack of flexibility in multi-energy power systems, a method for measuring the flexibility margin of power source is proposed. Aiming at the lowest cost of fuel and atmospheric emission control, a coordinated optimal dispatching model of wind, photovoltaic, hydropower and thermal was constructed. Flexibility balance constraints are introduced into the model, and the model is divided into three dispatching layers: non- water renewable energy, hydropower and thermal power. The net load is updated step by step. Heuristic algorithm is used to determine the thermal power unit combination and particle swarm optimization algorithm is improved to optimize the unit output. Taking a provincial power grid in China as an example, the calculation results show that the model and method can not only as far as possible utilize renewable energy, but also reduce system redundancy and environmental pollution. © 2019 IEEE.

关键词： Heuristic algorithms

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：