检索结果-内蒙古大学图书馆

IEEE Asia power and Energy Engineering Conference (APEEC)

作者： Guodong Huang Jiang Chang Zhi Cai Delin Wang Ruiwen Zhang Fangyu Wang Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology (China Electric Power Research Institute) Beijing China National Power Dispatching and Control Center Beijing China State Grid Beijing Electric Power Research Institute Beijing China

ISBN: (数字)9798331517540

ISBN: (纸本)9798331517557

With the deepening of the construction of the inter-provincial electricity spot market and its official operation, market risk assessment is becoming increasingly important. Based on the multi-level unified market structure, the differences between provincial and inter-provincial spot market are firstly analyzed. According to the operation characteristics and correlation characteristics of inter-provincial electricity spot market, the risk assessment index system is constructed from five aspects: market structure risk, market price risk, market member behavior risk, market operation efficiency risk, and market correlation risk, and the index weight is determined by using the analytic hierarchy process method and the improved entropy weight method, and the comprehensive calculation of market risk is carried out.. Finally, the evaluation and analysis of three typical scenarios in actual operation are carried out, and the examples show that the proposed evaluation method can accurately quantify the market risk and has good practicability.

关键词： Correlation Electricity Prevention and mitigation Process control Analytic hierarchy process Entropy power markets power system reliability Indexes Reliability

来源：评论

学校读者我要写书评

暂无评论

GRIDDPG: A Graph-Reinforced Intelligent Deep Policy Gradient Approach for Transferable power Grid Dispatch

GRIDDPG: A Graph-Reinforced Intelligent Deep Policy Gradient...

引用

Artificial Intelligence technology (ACAIT), Asian Conference on

作者： Nan Yang Liang Dong Zhejun Zhang Yupeng Huang Xinhang Li Yichen Wei Weitong Chen Xingwei Liu Lei Li Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology China Electric Power Research Institute Beijing China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

This paper proposes a novel deep reinforcement learning approach, named GRIDDPG (Graph-Reinforced Intelligent Dispatch with Deep Policy Gradient), for intra-day optimization dispatch in power grids. The proposed method embeds a double-layer intersecting Graph Neural Network (GNN) within the Deep Deterministic Policy Gradient (DDPG) framework, enabling the learning of power grid topology and operating state representations that inform the dispatch decision-making process. Comprehensive experiments are conducted on the SG-126 power grid simulator under three representative scenarios to evaluate the performance and generalization capability of GRIDDPG. The results demonstrate that GRIDDPG consistently outperforms the standalone DDPG algorithm in terms of grid operation security, operating cost reduction, renewable energy accommodation, and overall reward while ensuring the stability of the power grid. Furthermore, the study explores the potential of transfer learning between scenarios and finds that GRIDDPG exhibits a promising generalization capability.

关键词： Renewable energy sources Transfer learning Decision making power system stability Deep reinforcement learning power grids Graph neural networks Stability analysis Topology Security

来源：评论

学校读者我要写书评

暂无评论

Design of Flexible Ramping Ancillary Service Market with the Participation of Multiple Types of Entities in China

Design of Flexible Ramping Ancillary Service Market with the...

引用

IEEE Asia power and Energy Engineering Conference (APEEC)

作者： Yuxuan Li Zhi Cai Xiaojing Hu Liming Bo Xueting Cheng Xinyuan Liu Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology China Electric Power Research Institute Beijing China State Grid Shanxi Electric Power Supply Company Taiyuan China

ISBN: (数字)9798350373479

ISBN: (纸本)9798350373486

With the rising proportion of new energy, the existing market mechanism and ancillary service market are no longer able to meet the demand for ensuring supply and promoting consumption in the power system. In response to this issue, this article aims to design a flexible ramping ancillary service operation mechanism that can coordinate with the existing provincial electric energy market and ancillary service market in Shanxi Province, China, including demand analysis, performance evaluation, market pricing, assessment and settlement, in order to meet the urgent demand for the ramping capability of the power system.

关键词： Performance evaluation Electrical engineering Electricity Asia Pricing power systems Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Optimization Model for Ramping Ancillary Service Considering the Startup and Shutdown Status of Units

Optimization Model for Ramping Ancillary Service Considering...

引用

International Conference on power and Energy technology (ICPET)

作者： Zhi Cai Yuxuan Li Xiaojing Hu Liming Bo Xueting Cheng Xinyuan Liu Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology China Electric Power Research Institute Beijing China State Grid Shanxi Electric Power Supply Company Taiyuan China

ISBN: (数字)9798350375855

ISBN: (纸本)9798350375862

Flexible Ancillary Ramping Services (RAS) provides a solution to the insufficient system flexibility caused by the uncertainty of wind power. However, conventional flexible ramping ancillary services hardly provides upward and downward ramping capability at unit startup and shutdown and the upward and downward ramping capability during the startup and shutdown process. Taking into account the ramp rate constraints upon the unit in the output state and during the startup/shutdown process, as well as the ramping capability constraints upon the system due to net load fluctuations, a spot market clearing model that considers an improved flexible ramping product and wind curtailment penalty is proposed, and is verified through simulation case study.

关键词： Uncertainty Fluctuations Costs Optimization models systems operation Wind power generation Electricity supply industry Load modeling

来源：评论

学校读者我要写书评

暂无评论

Calculation Method of Available Transfer Capacity Based on Graph Convolutional Network 10

Calculation Method of Available Transfer Capacity Based on G...

引用

10th IEEE Data Driven Control and Learning systems Conference, DDCLS 2021

作者： Cai, Zhi Li, Yuxuan Dai, Sai Men, Deyue Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology China Electric Power Research Institute Beijing100192 China

ISBN: (纸本)9781665424233

Studying and evaluating the available transfer capacity (ATC) of transmission lines is of great significance when determining the reasonable operation mode of a power grid and optimizing the allocation of power grid resources. With the rapid development of deep learning technology, it is possible to quickly find the most ATC by mining historical data and prior knowledge without relying on physical model. Therefore, an ATC calculation method based on graph convolutional network (GCN) is proposed. The topology information between the nodes of a power grid is represented by adjacency matrix. The proposed algorithm can effectively mine the correlation between the nodal injection power, and map the complex non-linear relationship between ATC and power data with deep graph convolutional architecture. The simulation results show that the calculation accuracy of ATC based on GCN can meet the needs of practical application of power grid. © 2021 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

research and Application of Alarm Optimization Mechanism in power Grid Operation Monitoring 5

Research and Application of Alarm Optimization Mechanism in ...

引用

5th IEEE Advanced Information technology, Electronic and automation Control Conference, IAEAC 2021

作者： Feng, Chaohan Wang, Lulu Ye, Ruili Gu, Jingzi Xie, Lin Wang, Yan Feng, Qiong Cui, Can China Electric Power Research Institute Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology Beijing100192 China

The alarms of power grid control center is an important data basis for monitors to identify monitoring events, but a large number of invalid and redundant information seriously affects the analysis and judgment of anomalies or accidents, thus reducing the efficiency of power network monitoring and threatening the security of the power grid. In this paper, we use time-delay, decision tree and hash technology to filter the invalid alarms with frequent actions, automatically restore and repetition. The experimental results show that our alarms optimization scheme can improve the effectiveness of information and improve the level of power equipment monitoring and management. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Price Zone Partitioning Strategy for Cross-Regional Market Transaction 5

A Dynamic Price Zone Partitioning Strategy for Cross-Regiona...

引用

5th International Conference on Energy, Electrical and power Engineering, CEEPE 2022

作者： Cui, Hui Yang, Xiaonan Cheng, Dong Wang, Jianxiao Li, Jing Zhu, Junfei China Electric Power Research Institute Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology Beijing China North China Electric Power University School of Electrical & Electronic Engineering Beijing China State Grid Hunan Electric Power Company Changsha China

ISBN: (纸本)9781665479059

The reform of China's electricity market continues to deepen, the proportion of cross-regional transactions continues to increase, and the cross-regional power market needs to be further improved. Northern Europe has a relatively mature regional electricity price mechanism, which has great guiding significance for the construction of China's cross-regional and cross-provincial power market. This paper analyzes the applicability of the Nordic transnational electricity market clearing and congestion management model in China. The cross-regional market clearing method based on Locational Marginal Prices (LMP) and the flow-based (FB) model for cross-regional transmission capacity calculation are used for dynamic price zone partitioning and management. After considering the influence of geographical location and locational marginal electricity price, a k-means clustering model is used for price zone partitioning, and all transaction between price zones can be solved by FB model. A case study based on an IEEE 30-node system demonstrates the effectiveness of the proposed dynamic price zone partitioning strategy, which can better reflect the price signal and realize the optimal allocation of resources. © 2022 IEEE.

关键词： Economics Analytical models power engineering power system dynamics Europe Electricity supply industry Dynamic scheduling

来源：评论

学校读者我要写书评

暂无评论

Method for LSTM-Based Cascade Hydropower Plant Scheduling 33

Method for LSTM-Based Cascade Hydropower Plant Scheduling

引用

第33届中国控制与决策会议

作者： Zhi Cai Guofang Zhang Yi Lu Yuxuan Li Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology China Electric Power Research Institute State Grid Sichuan Electric Power Supply Company

ISBN: (纸本)9781665431293

With the increase of the number of cascade hydropower plants and the increase of the discrete number of state variables in the time period to obtain more high-precision solutions,the calculation time increases exponentially,which makes it difficult to optimize through physical ***,a data-driven cascade hydropower plant scheduling method with self-learning abilities is ***,perform cluster pre-processing of the historical dispatching data of hydropower plants in the scheduling scope with K-means algorithm;secondly,establish a deep learning model of cascade hydropower plant schedules based on long short-term memory(LSTM),and build the mapping model among system load,water regimen and hydropower plant schedule through historical data training,to make a decision,finally,continuously correct the model by accumulating the historical data,so that it has the ability of self-evolution and *** make case analysis based on the actual power grid data,and the calculation results show the effectiveness of the proposed method.

关键词： Cascade hydropower Generation schedule Deep learning Long short-term memory K-means cluster

来源：评论

学校读者我要写书评

暂无评论

Graphene-based dual-function acoustic transducers for machine learning-assisted human-robot interfaces

引用

InfoMat 2023年第2期5卷 66-79页

作者： Hao Sun Xin Gao Liang-Yan Guo Lu-Qi Tao Zi Hao Guo Yangshi Shao Tianrui Cui Yi Yang Xiong Pu Tian-Ling Ren Institute of Microelectronics and Beijing National Research Center for Information Science and Technology(BNRist) Tsinghua UniversityBeijingPeople's Republic of China CAS Center for Excellence in Nanoscience Beijing Key Laboratory of Micro-nano Energy and SensorBeijing Institute of Nanoenergy and NanosystemsChinese Academy of SciencesBeijingPeople's Republic of China State Key Laboratory of Power Transmission Equipment and System Security and New Technology School of Electrical EngineeringChongqing UniversityChongqingPeople's Republic of China School of Computer Science&Technology Beijing Institute of TechnologyBeijingPeople's Republic of China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijingPeople's Republic of China

Human–robot interface(HRI)electronics are critical for realizing robotic ***,we report graphene-based dual-function acoustic transducers for machine learning-assisted human–robot interfaces(GHRI).The GHRI functions both an artificial ear through the triboelectric acoustic sensing mechanism and an artificial mouth through the thermoacoustic sound emission *** success of the integrated device is also attributed to the multifunctional laser-induced graphene,as either triboelectric materials,electrodes,or thermoacoustic *** systematically optimizing the structure parameters,the GHRI achieves high sensitivity(4500 mV Pa^(–1))and operating durability(1000000 cycles and 60 days),capable of recognizing speech identities,emotions,content,and other information in the human *** the assistance of machine learning,30 speech categories are trained by a convolutional neural network,and the accuracy reaches 99.66%and 96.63%in training datasets and test ***,GHRI is used for artificial intelligence communication based on recognized speech *** work shows broad prospects for the development of robotic intelligence.

关键词： human-robot interface laser-induced graphene machine learning thermoacoustic triboelectric nanogenerator

来源：评论

学校读者我要写书评

暂无评论

Adaptive Heuristic Method Based on Reduced Costs and Physical Characteristics of power Grid

Adaptive Heuristic Method Based on Reduced Costs and Physica...

引用

IEEE Conference on Energy Internet and Energy system Integration (EI2)

作者： Shengnan Xu Qiang Ding Yanguang Chen Linghao Li Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology China Electric Power Research Institute Beijing China 5Paradigm Technology (Shenzhen) Co. Ltd. Shenzhen China

ISBN: (数字)9798331523527

ISBN: (纸本)9798331523534

In order to improve the efficiency of solving unit commitment problems, an adaptive heuristic method based on reduced costs and physical characteristics of the power grid is proposed to address the problem of large scale, complex constraints and variables, and difficulty in finding high-quality feasible solutions. Firstly, the physical characteristics of the power grid, the optimal solution to the relaxation problem, and the reduced costs of 0-1 variables for the power model are identified and obtained. Then, based on the model characteristics and relaxation information, accurate variable values are fixed and induced, and the number of fixed variables is adjusted according to the feasibility of constraints until all constraints are met. Finally, finding the optimal solution to the problem with fixed variables. The test results of the numerical examples show that the algorithm can quickly obtain high-quality feasible solutions to the original problem, effectively improving the efficiency of solving the unit commitment problem.

关键词： Costs Accuracy Heuristic algorithms Energy Internet system integration power grids Numerical models Mixed integer linear programming Object recognition

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：