Cheng Xueting

Diagnosis model of low voltage generation based on large data

Voltage is one of the measurement standard of power quality. The issue of low voltage in distribution network seriously affect the social economic development and peoples life. Consequently, it would optimize low voltage investment program, clear direction of low voltage investment and provide decision support for the management of low voltage. Canopy- Kmeans is one of the widely used classical partition clustering algorithm. Support vector machine is a kind of sorting algorithms that could take full advantage of limited learning sample to acquire generalization. Both Canopy-Kmeans and Support Vector Machine have better behavior and precision rate. However, the runtime and RAM would be the bottleneck in the case of large amount of data. The application of data mining algorithm based on big data is particularly important. This paper take advantage of distributed Kmeans and SVM algorithm to realize diagnosis model of cause of low voltage based on big data platform of Hadoop. Experiments have shown that this method has a higher accuracy and reliability compared to traditional Kmeans and SVM algorithm.

Detection and analysis of high voltage electrical equipment corona discharge based on ultraviolet imaging technology

The corona discharge phenomena of electrical equipment are generated with the increasing of insulation aging, electrical equipment, surface filth or atmospheric humidity. The corona discharge will cause the waste of power energy, radio interference, audible noise, insulation aging, and these defects are great threats to the safety and stability of electrical equipment. Using appropriate method to detect the operational state of electrical equipment is always significantly concerned by operation department. In this paper, the different corona discharge defect part of high voltage electrical equipment are summarized such as the grading ring, drop wire, jumper and over line, spacing rods, tube bus end and connecting joint. While the photon numbers of corona discharge under different defects are measured by the ultraviolet imager. The result shows that: the corona discharge characteristics of electrical equipment are different under the different defect type, and the photon number increases with the rising of the applied voltage. The detected photon number varies with different kinds of defects through applying same voltage. The ultraviolet imager shows the excellent performance in the detection of discharge defects and thus it can be prospectively used in the operation state detection of electrical equipment.

Evaluation and application of accommodation capability of wind power for grid

Accurately mastering the capability of wind power accommodation is conducive to construction planning of wind plant and provide auxiliary to dispatching decision in actual operation. Based on deep analysis of key factors influencing accommodation capability of wind power basic idea and method were proposed to manoeuvre wide and flexible adequacy resources involved in system regulation. Comprehensively considering technical characteristics of various power generations and such constrains as the balance of power and thermal loads and transfer capacity and taking the maximum accommodation capability of new energy as objective function, a model is built to analyze new energy accommodation capacity of power grid. Taking shanxi province in China, which is rich in new energy resources, as calculation example, the changes of new energy accommodation capability were simulated and analyzed under different scenes of introducing in different flexible resources.