Time filter

Source Type

Yang S.,Hunan HDHL Electrical and Information Technology Co. | Kuang S.,Hunan HDHL Electrical and Information Technology Co. | Xu Z.,Hunan HDHL Electrical and Information Technology Co.
Diangong Jishu Xuebao/Transactions of China Electrotechnical Society | Year: 2013

As an important link, the original data analysis would improve the accuracy of short-term bus load forecasting a lot. Thus, a bad data processing strategy based on stratified analysis of characteristic matrix is presented. Firstly, the AFS clustering algorithm for dividing sample set optimal clustering structure is studied. The search interval of clustering number for per-unit curve sample set is calculated using AP(Affinity propagation) clustering algorithm, and the initialized matrix is obtained on the basis of the density index arranged according to the decreasing order. Then the optimal clustering results are finally achieved by effectiveness testing based on the Silhouette index. Referring to the characteristic curves, the horizontal and vertical eigenvectors reflecting properties of the load points are calculated, and the characteristic matrix is formed. By applying the discriminant criterion, the stratified analysis for the characteristic matrix of daily load curve is carried out, and thereafter the corresponding bad data processing strategies focusing on bus loads which have different variation of characteristics are established.Case study shows that the proposed method could improve the quality of raw data as well as the bus load forecasting accuracy effectively.


Mao T.,Hunan University | Yao J.,Hunan University | Kang T.,Hunan University | Deng D.,Hunan HDHL Electrical and Information Technology Co. | Zhao J.,Hunan HDHL Electrical and Information Technology Co.
Dianli Xitong Zidonghua/Automation of Electric Power Systems | Year: 2013

In light of massive information and heavy task of equipment overhaul, and heavy reliance on manpower and strong subjectivity in overhaul operation mode, grid overhaul scheduling combined with operation mode selection are comprehensively analyzed. The design and development of an intelligent overhaul and safety check management system for 110 kV distribution network are presented. By using TWaver and computer advanced technology, a complete set of modeling, management and evaluation system is formed, and the aim of grid data visualization, grid on-line monitoring and early warning is achieved. Based on genetic clustering algorithm, the overhaul scheduling intelligent compiling and operation mode assisted analysis of grid equipment are completed. The effectiveness of the system is demonstrated by introducing its system functions and application example. © State Grid Electric Power Research Institute Press.


Yao J.,Hunan University | Guan S.,Hunan University | Lu J.,Power Company of Hunan Province Test and Research Institute | Jiang Z.,Power Company of Hunan Province Test and Research Institute | And 3 more authors.
Dianwang Jishu/Power System Technology | Year: 2012

A method is proposed to identify zero resistance insulators under various pollution levels and humidity conditions by combining relative temperature distribution characteristics of insulator string with artificial neural network (ANN) model. The infrared image of suspension insulator string being operated in 110 kV transmission line is achieved by simulation tests and after the preprocessing of image denoising and segmentation the extracted characteristic parameters of relative temperature distribution in the region of insulator string are taken as temperature information characteristics to identify zero resistance insulator, and taking environmental relative humidity and equivalent salt deposit density as input vectors of identification model and regarding the state classification information that whether the actually measured insulation string contains zero resistance insulator as the output vector the optimized identification model is obtained by training and applied to the identification of zero resistance insulator. Testing results show that the zero resistance insulator identification by the proposed method is accurate, so it is available for reference to corrective maintenance and troubleshooting of porcelain insulation equipments for transmission lines.


Mao L.-F.,Hunan University | Yao J.-G.,Hunan University | Jin Y.-S.,Hunan University | Chen H.-L.,Hunan HDHL Electrical and Information Technology Co. | And 2 more authors.
Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | Year: 2010

For traditional combination methods of medium and long term power load forecasting, the weight coefficient is dependent on the prediction methods, so the model can not reflect the changes of load development. Therefore, a new combination model based on induced ordered weighted geometry averaging operator (IOWGA) and weighted Markov chain is proposed. According to the level of accuracy, this model assigns the weight to each individual method to achieve the correlation between weight coefficient and fitting accuracy in any time point. Since ordered weighted Markov chain has qualitatively forecasted the accuracy of each method of the target year, the weight coefficient can be determined for forecasting. Theoretical analysis shows that the new combination model fits the law of load development well and it helps to improve the forecasting accuracy with high practical value. © 2010 Chin. Soc. for Elec. Eng.


Xia J.-J.,Hunan University | Luo D.-S.,Hunan University | He H.-Y.,Hunan University | Hu Z.,Hunan HDHL Electrical and Information Technology Co. | Wu J.-F.,Hunan University
Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control | Year: 2011

For managing ancillary services effectively, a modeling method of visual workflow management is given for the electric power generation assessment system. With analysis of the characteristics of various types of ancillary services and their correlation and the work principle of the electric power generation assessment system, using visual technology and workflow technology in the field of computer, a modeling method of visual lightweight workflow management based on relational database is designed. Using this method, the workflow management of the electric power generation assessment system is modeled, and the implementation process is given. The results show that the modeling method of visual lightweight workflow management based on relational database is effective and practical. The efficiency and quality of ancillary services management can be improved by this model.


Sun Q.,Hunan University | Yao J.,Hunan University | Li X.,Hunan University | Kong Q.,Hunan HDHL Electrical and Information Technology Co. | And 3 more authors.
Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | Year: 2012

To establish the electrical railway traction load negative sequence source model suitable for negative sequence characteristics analysis and power flow calculation is extremely important. Negative sequence source modeling could be regarded as a load modeling problem, and a modeling method based on the classification and synthesis of negative sequence characteristics was proposed. The clustering tendency analysis was conducted on the sample set, with the measured response space of fundamental negative sequence current and the actual running state of locomotive as eigenvectors. On the premise of clustering possibility, the clustering validity function was used, aiming at obtaining the optimal classification result of the sample set. By means of mechanism analysis for the negative sequence characteristics of traction load, the model structure was determined, while the optimal model expression was achieved applying the method of stepwise multiple regression. Besides, the newly added sample was classified into the class within the minimum Euclidean distance from the clustering center, and the related model was tested. Case study shows that the negative sequence source model built is reasonable and effective. © 2012 Chin. Soc. for Elec. Eng.


Mao L.-F.,Hunan University | Yao J.-G.,Hunan University | Jin Y.-S.,Hunan HDHL Electrical and Information Technology Co. | Li W.-J.,Hunan HDHL Electrical and Information Technology Co. | And 2 more authors.
Dianwang Jishu/Power System Technology | Year: 2010

Historical load data is the basis of medium- and long-term load forecasting, thus the abnormal historical data and historical data missing seriously affect the accuracy and effectiveness of load forecasting. To remedy the insufficiency of traditional methods for abnormal data identification and data filling, a method for missing data filling, which is based on both T2 ellipse map to identify abnormal data and least square support vector machine (LSSVM), is proposed. The principal component of historical data is extracted by partial least square (PLS) to compute the accumulative contribution rate (ACR) of historical data to principal component and draw T2 ellipse, thereby the abnormal historical data that possesses too high contribution rate can be identified; the variation trend of historical data is fitted by LSSVM, thus the missing data can be filled. Results of calculation example show that the T2 ellipse map can effectively identify the abnormal samples in historical data and LSSVM possesses good data filling performance, therefore the proposed method is practicable.

Loading Hunan HDHL Electrical and Information Technology Co. collaborators
Loading Hunan HDHL Electrical and Information Technology Co. collaborators