检索结果-内蒙古大学图书馆

Application-oriented Model Management Method on dispatching and Control Cloud

Application-oriented Model Management Method on Dispatching ...

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

作者： Yupeng Huang Miao Wang Qiong Feng Yi Han Xiaolin Qi Zhijun Zhang Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology (China Electric Power Research Institute) Beijing China State Grid Tianjin Electric Power Company Tianjin China

ISBN: (数字)9781728152240

ISBN: (纸本)9781728152257

With the construction of the dispatching and control cloud platform, more and more dispatching applications need to rely on the model data of the cloud for function realization. The dispatching and control cloud uses the methods of unified modeling and integrated model maintenance to construct cloud models with unique coding, unique properties and unique parameters. In view of the differences between the storage form of the dispatching and control cloud model and the model form required for the dispatching applications, this paper proposes an application-oriented model management method on dispatching and control cloud, which can help the applications to define the model structure on demand, subscribe the cloud model data, save the historical model versions required for the application, and make cloud model support the dispatching applications.

关键词： Data models dispatching Metadata Analytical models Cloud computing Synchronization Tools

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Tie-line Scheduling Method

Data-Driven Tie-line Scheduling Method

引用

Data Driven Control and Learning systems (DDCLS)

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

ISBN: (数字)9781728159225

ISBN: (纸本)9781728159232

Tie-line scheduling in an interconnected power grid is difficult to perform optimization by establishing a unified physical model due to the different scheduling methods in different dispatching centers. It may cause repeated coordination and iteration in multi-level dispatching centers. Therefore, a data-driven tie-line scheduling method with self-learning ability is proposed. First, perform cluster pre-processing of historical dispatching data with K-means algorithm; secondly, establish a deep learning model of tie-line scheduling based on long short-term memory (LSTM), and build a mapping model among system load, clean energy output and tie-line schedule through historical data training; After that, the all above process is used as a foundation to do the tie-line scheduling; finally, continuously revise the model by accumulating historical data, so that it has the ability of self-evolution and self-learning. We make a case analysis based on the actual power grid data, and the calculation results show the effectiveness of the proposed method.

关键词： Data models Load modeling dispatching Power grids Deep learning Training Scheduling

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Spatiotemporal Deep Learning Predicting Residential Indoor Pm2.5 Concentration Using a Bayesian Neural Network Model

SSRN

引用

SSRN 2023年

作者： Dai, Hui Liu, Yumeng Wang, Jianghao Ren, Jun Gao, Yao Dong, Zhaomin Zhao, Bin Department of Building Science School of Architecture Tsinghua University Beijing100084 China Beijing Key Laboratory of Indoor Air Quality Evaluation and Control Tsinghua University Beijing100084 China School of Space and Environment Beihang University Beijing100191 China State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing100101 China Sustainable Urbanization Lab Department of Urban Studies and Planning Massachusetts Institute of Technology CambridgeMA02139 United States Shenzhen Institute of Building Research Co. Ltd China

Indoor PM2.5 pollution is one of the leading causes of death and disease worldwide. As monitoring indoor PM2.5 concentrations on a large scale is challenging, it is urgent to assess population-level exposure and related health risks to develop an easy-to-use and generalized model to predict indoor PM2.5 concentrations and spatiotemporal variations at the global level. Existing machine learning models of indoor PM2.5 are prone to deliver single-point predictions, and their input strategies are not widely applicable. Here, we developed a Bayesian neural network (BNN) model for predicting the distribution of indoor daily average PM2.5 concentration based on multiple data sources available from nationwide comprehensive sensor-monitoring records in China. The BNN model showed good performance with a 10-fold cross-validation R2 of 0.70, mean-absolute-error of 9.45 μg/m3, root-mean-square error of 13.3 μg/m3, and 95% prediction interval coverage of 85%. Our modeled population-weighted annual indoor PM2.5 concentration for China in 2019 was 22.8 μg/m3, far exceeding the WHO standard. This model can be applied to predict indoor PM2.5 concentrations on a large spatiotemporal scale, making it valuable for assessing and managing indoor air pollution-related health risks. © 2023, The Authors. All rights reserved.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

Cross-provincial Day-ahead to Intra-day Scheduling Method Considering Forecasting Uncertainty of New Energy

Cross-provincial Day-ahead to Intra-day Scheduling Method Co...

引用

IEEE International Conference on automation, Electronics and Electrical Engineering (AUTEEE)

作者： Zhi Cai Yuxuan Li Dan Xu Guofang Zhang Lun Tang Xiaming Guo Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology China Electric Power Research Institute Beijing China State Grid Sichuan Electric Power Supply Company Chengdu China

ISBN: (数字)9781728198279

ISBN: (纸本)9781728181585

There are generally large errors between forecast and actual values of new energy power in the dayahead stage, which may cause curtailment of wind power and photovoltaic power due to the insufficient reserve of provincial power grids in the intra-day stage. Therefore, multi-time scale multi-province coordinative day-ahead and intra-day scheduling model considering the uncertainty of new energy prediction is proposed in this paper: Considering the possible errors of new energy prediction in the day-ahead stage, a multi-provincial robust unit commitment model is established to provide sufficient reserves for new energy consumption; the tie-line scheduling and unit output in the intra-day stage according to ultra-short-term predicted data of new energy is adjusted to establish an intra-day scheduling model considering tie-line power flow control. The proposed model is applied to the actual calculation example in a certain region of China, the results of which show that the model can give play to the mutual aid of interconnected power grids and effectively improve the consumption level of new energy.

关键词： Predictive models Job shop scheduling Wind power generation Schedules Programming Power grids Energy consumption

来源：评论

学校读者我要写书评

暂无评论

Generation Schedule Considering Branch Security Check under New Energy Access

Generation Schedule Considering Branch Security Check under ...

引用

Sustainable Power and Energy Conference (iSPEC)

作者： Zhi Cai Qiang Ding Dan Xu Chi Zhang Yi Sun Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology China Electric Power Research Institute Beijing China State Grid Sichuan Electric Power Supply Company Chengdu China

ISBN: (数字)9781728191645

ISBN: (纸本)9781728191652

The uncertainty on new energy output, on the one hand, puts forward more reserve demand for the power generation schedule, on the other hand, increases the uncertainty of power flow in a security check because of new energy power deviation and reserve call. Therefore, firstly, the fuzzy chance constraints of reserve are classified as their equivalent forms according to the reliability distribution function of new energy prediction error, and the reserve needed for new energy prediction error is analyzed quantitatively Then, the limit scenario checking on the security constraints of the branch is introduced in accordance with the characteristics of the power flow fluctuation caused by the uncertainty of new energy. Secondly, the generation schedule model considering the uncertainty of new energy power is established. Finally, the calculation examples are analyzed based on the actual operation data of a province in China. The calculation results show the effectiveness of the proposed method.

关键词： Schedules Adaptation models Uncertainty Power grids Security Spinning Load flow

来源：评论

学校读者我要写书评

暂无评论

Multi-province Joint Dispatch Model Considering the Extreme Scenario Set of New Energy Power

Multi-province Joint Dispatch Model Considering the Extreme ...

引用

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

作者： Zhi Cai Guodong Huang Xiaming Guo Fuyao Deng Wei Liu Jinlong Wang Lun Tang Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology China Electric Power Research Institute Beijing China State Grid Sichuan Electric Power Supply Company Chengdu China

ISBN: (数字)9781728143033

ISBN: (纸本)9781728143040

At present, tie-line scheduling in China are mostly prepared based on the determined regional forecast power of new energy resources. In the case of big errors in the forecast of new energy resources, it may affect the ability of provinces or regions to consume and accommodate new energy resources. In view of this situation, we propose a multi-province joint hierarchical optimization dispatch model with stronger adaptability and robustness: the upper-level model calculates the multi-region unit commitment and tie-line schedule, and allows the power grid to keep enough reserves for new energy forecast errors by considering the extreme scenario of new energy power. The lower-level model establishes an economic dispatch model based on chance-constrained programming. The scheme can effectively restrain the influence of uncertain fluctuation of new energy output and improve the absorption capacity of new energy. Finally, an example analysis is carried out based on the actual operation data of a certain region in China, and the calculation results show the effectiveness of the proposed model.

关键词： Optimization Power grids Economics Predictive models Schedules Wind power generation Absorption

来源：评论

学校读者我要写书评

暂无评论

Design of Hydropower Dominated Provincial Electricity Spot Markets in China

Design of Hydropower Dominated Provincial Electricity Spot M...

引用

Power and Energy Engineering (ICPEE), International Conference on

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

ISBN: (数字)9781728191256

ISBN: (纸本)9781728191263

In the new round of China's electricity reform, the construction of electricity spot market will be fully implemented. However, the electricity market of some provinces is dominated by cascade hydropower, resulting in significant differences with those electricity markets in the United States and Europe. A provincial electricity spot market mechanism dominated by hydropower is designed accordingly. Firstly, based on the major market models abroad, the similarities and differences of Brazil and Norway hydropower dominated market models are analyzed in terms of electricity market reform, market trading mechanism and trans-regional resource allocation. Secondly, we analyzed the benefits brought by centralized market model to the operation safety, hydropower allocation optimization and connection with the current scheduling system. Moreover, it points out that the future electricity market should follow the model of “centralized spot market + medium and long-term difference contract”. The development of China's electricity spot market featuring a high proportion of hydropower is predicted according to three stages. Finally, the key technical requirements faced by future hydropower dominated electricity market construction are summarized.

关键词： Hydroelectric power generation Electricity supply industry Contracts Biological system modeling Power grids Europe Power supplies

来源：评论

学校读者我要写书评

暂无评论

Maintenance schedule of power transmission equipment based on SA and GSA

Maintenance schedule of power transmission equipment based o...

引用

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

作者： Z. Cai D. Men D. Xu G. Zhang Y. Dai Y. Lu China Electric Power Research Institute Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology Beijing China State Grid Sichuan Electric Power Supply Company Chengdu China

It is a multi-objective and multi-constraint, non-linear optimization problem that the maintenance scheduling of transmission equipment in interconnected large power grid needs to consider the guarantee of renewable energy transmission capability and the operational safety of regional power grids. Therefore, a method of maintenance scheduling of transmission equipment based on improved gravitational search algorithm (GSA) is proposed: one of the optimization objectives is to calculate the electric quantity of the abandoned renewable energy. In addition, considering the safety constraints of the operation of the interconnected power grid, the optimization model of the maintenance scheduling is established, and GSA method is used to solve the model. By introducing the idea of simulated annealing (SA) and using the Metropolis criterion to update the particle position according to the probability, the particle degradation in the GSA is reduced, and then the overall convergence and accuracy of the algorithm are improved. The annual maintenance scheduling of the actual power grid is verified as a calculating example.

关键词： simulated annealing search problems power grids power system interconnection power transmission lines maintenance engineering power transmission reliability

来源：评论

学校读者我要写书评

暂无评论

UHVDC Tie-line Scheduling Model Based on Conditional Value-at-Risk

UHVDC Tie-line Scheduling Model Based on Conditional Value-a...

引用

HVDC (HVDC), International Conference on

作者： Zhi Cai Xiaojing Hu Deyue Men Guofang Zhang Yi Sun Dawei Zhang Xiaming Guo Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology China Electric Power Research Institute Beijing China State Grid Sichuan Electric Power Supply Company Chengdu China

ISBN: (数字)9781728175935

ISBN: (纸本)9781728175942

There is a growing demand for trans-regional transmission of clean energy such as wind power and photovoltaic power through ultra-high voltage direct current (UHVDC) system. To solve the problem of difficulty in transmission of new energy through UHVDC due to random fluctuations, this paper puts forward a transmission scheme of using the supporting thermal power to smooth power fluctuation of new energy and realize bundled transmission, establishes an integrated tie-line scheduling model of wind power, photovoltaic power and thermal power transmission through UHVDC system, and introduces the conditional value-at-risk (CVaR) theory according to the concept of new energy transmission risk to quantify the new energy transmission risk, for analyzing the new energy transmission capacity of tie-line scheduling under different confidence levels and risks. The model is applied to a practical calculation example, and the calculation result shows the effectiveness of the proposed method.

关键词： Reactive power Wind power generation Photovoltaic systems dispatching Fluctuations Absorption Power transmission

来源：评论

学校读者我要写书评

暂无评论

Analysis and Outlook of Future Chinese Electricity Spot Market Model

Analysis and Outlook of Future Chinese Electricity Spot Mark...

引用

IEEE Asia Power and Energy Engineering Conference (APEEC)

作者： Zhi Cai Hui Cui Bin Han Guofang Zhang Yi Lu Yuhan Dai Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology China Electric Power Research Institute Beijing China State Grid Sichuan Electric Power Supply Company Chengdu China

ISBN: (数字)9781728167824

ISBN: (纸本)9781728167831

ZF [2015] No. 9 document issued by Chinese government indicates that the target market model in China in a new round of reform of the power system include centralized and decentralized market models. How to achieve the target model in a top-level design is an important issue in the construction of electricity market in China. Firstly, the differences and the similarities of these two models are analyzed based on foreign mainstream market models from four aspects: market decision making methods, market pricing methods, unit portfolios and auxiliary service transactions. Secondly, current situation of reform of electricity market in China is introduced. Based on grid structure and power supply structure in China, benefits of centralized market model in safe operation of grid, optimal allocation of resources and connection with existing dispatching system are analyzed; it is indicated that the proper Chinese electricity market model in the future is "centralized spot market + medium-term and long-term difference contract" model. The development of Chinese electricity spot market is forecast in three stages. Finally, the key technology demands in the construction of Chinese electricity market in the future are abstracted.

关键词：

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：