Sun Caixin

RBF Neural Network and ANFIS-Based Short-Term Load Forecasting Approach in Real-Time Price Environment

With the appearance of electricity markets, the variation of the price of electricity will influence usage custom of electric energy. This will complicate short-term load forecasting and challenge the existing forecasting methods that are applied to a fixed-price environment. In regard to the influence of real-time electricity prices on short-term load, a model to forecast short-term load is established by combining the radial basis function (RBF) neural network with the adaptive neural fuzzy inference system (ANFIS). The model first makes use of the nonlinear approaching capacity of the RBF network to forecast the load on the prediction day with no account of the factor of electricity price, and then, based on the recent changes of the real-time price, it uses the ANFIS system to adjust the results of load forecasting obtained by RBF network. This system integration will improve forecasting accuracy and overcome the defects of the RBF network. As shown in this paper by the results of an example of factual forecasting, the model presented can work effectively.

Artificial Immune Network Classification Algorithm for Fault Diagnosis of Power Transformer

Dissolved gas analysis is an effective method for the early detection of incipient fault in power transformers. To improve the capability of interpreting the result of dissolved gas analysis, an artificial immune network classification algorithm (AINC), inspired by the natural immune system that is able to respond to an almost unlimited multitude of foreign pathogens, is proposed in this paper. The immune network system describes the complex interaction of antibodies and antigens in virtue of some immune mechanisms, such as immune learning, immune memory, etc. AINC mimics these adaptive learning and defense mechanisms to respond to fault samples of power transformers. Consequently, AINC can find a limited number of antibodies representing all fault samples distributing structures and features, which helps to realize dynamic classification. This proposed AINC algorithm has been tested by many real fault samples, and its results are compared with those of IEC ratio codes and artificial neural networks, which indicates that the proposed approach has remarkable diagnosis accuracy, and with it multiple incipient faults can be classified effectively

Application of Complex Wavelet Transform to Suppress White Noise in GIS UHF PD Signals

During online partial discharge (PD), ultra-high-frequency (UHF) detection of gas-insulated switchgear (GIS), obtaining acceptable levels of sensitivity, still continues to remain a very challenging task, primarily due to strong electromagnetic interference (including white-noise, random, discrete spectral, and stochastic pulses). As white-noise interference stands in the breach existing in GIS PD UHF detection inevitably, the available suppression methods are unsatisfactory. According to the feature of white noise, the Daubechies complex wavelet is constructed. Through the simple information (SI) and combined information (CI) of the complex wavelet transform (CWT), the denoising method of simulation signals and field signals of PD UHF is studied by the authors. In view of the estimation parameters, the results manifest that white-noise in GIS PD UHF signals can be suppressed effectively by the SI and CI of the CWT.

GIS partial discharge quantitative measurements using UHF microstrip antenna sensors

In view of the structure characteristic and operation performance of the field gas insulation switchgear (GIS), an external ultra high frequency (UHF) sensor, a novel microstrip antenna, is designed to detect UHF partial discharge (PD) signals for the field GIS. The microstrip antenna, which receives the UHF electromagnetic wave leaked from the GIS spacer, is just mounted on the GIS spacer, and has some effect to suppress the surrounding space electromagnetic interference. The analysis and on-site measurements manifest that the microstrip antenna working frequency bandwidth is 340 MHz to 440 MHz, which voltage standing-wave ratio (VSWR) is less than 2, the center frequency is 390 MHz, the relative bandwidth is 25.6% up to the wide bandwidth range, and its gain of the maximum radiation and reception directivity is covered 5.38 dBi. Based on the laboratory GIS simulation device measurements, the investigation of the relationship between UHF PD amplitude and apparent discharge quantity based on 1EC60270 is presented as linear curve. Meanwhile, comparison to the field 220 kV level GIS, the quantitative charge evaluated to about 40 pC by the UHF method could give a preliminary diagnosis for GIS insulation conditions. And the UHF measurement system is suited for GIS field partial discharge UHF on line detection and diagnosis.

DC flashover performance of iced insulators under pressure and pollution conditions

In an artificial climate chamber, DC flashover tests of insulator strings were performed under various ice, pressure, and pollution conditions. Based on these results, curves for the relationship between the DC flashover voltage of the insulator string and the pressure, the ice weight, and the pollution degree are given and analyzed. It is shown that, under the same ice weight and the same pressure, the DC flashover voltage of the precontaminated iced insulators is lower than that of clean insulators. The larger the pollution degree, the lower is the flashover voltage. Under the same pollution degree and the same pressure, the DC flashover voltage of the precontaminated iced insulators decreases as the atmospheric pressure decreases.<<ETX>>

The harmonic analysis method and its application in the on-line detection of electric equipment insulation

This paper describes the harmonic analysis method which can be used to measure the resistance current of the metal oxide arrester (MOA) and the dielectric loss of the capacitive apparatus. The theory of this method and the requirement to the hardware circuit are introduced also. The testing and the analysis of the theory show that this method is more accurate and sensitive than the routine compensation method for measuring higher order harmonic of the resistance current, and it can improve the stability and the precision for measuring tg/spl delta/. At last, the actual measuring results of using this method in substation are given also.

Experimental study on irreversible electrical breakdown of tumor cell under steep pulsed electric fields

Describes the dynamic changes of the SKOV3 cancer cell under steep pulsed electric fields (SPEFs, generated by the energy-controllable steep pulse apparatus for tumor treatment) using an inverted phase contrast microscope (IPCM) and finds that the cell was swollen in very short time. The study showed that the membrane of treated cell was destroyed under a scanning electron microscope (SEM), the nucleus was swollen and its karyotheca was not integrated under the transmission electron microscope (TEM). The mitochondria was also cavitated and swollen. It is clear that the SPEFs can result in irreversible electrical breakdown of the tumor cell. It may be a new therapy for tumor treatment.

GIS based distribution system spatial load forecasting and the optimal planning of substation location and capacity

The geographic information systems (GIS) platform is used in spatial load forecasting (SLF) and the mathematical models of the substation location and capacity optimisation problems are established in this paper. Based on the theory of network flow, a new multi-period optimal selecting algorithm of substation is proposed, which could determine the reasonable location, capacity and time that are put into the running of the substation. The real instance shows that this algorithm could solve the multi period optimal selecting problem of substations in distribution system planning (DSP) successfully, and has a practical value.

The research of local linear model of short term electrical load on multivariate time series

According to the idea of phase space reconstruction of scalar time series, phase space reconstruction of multivariate time series based on the short-term electric load is presented. The good time delay is chosen for each scalar time series by mutual information. The method to get the minimum embedding dimension is based on minimum forecasting errors. The choice of optimal neighbor points is presented in this paper according to Euclidean distance and degree of correlation between forecast point and its nearest neighboring points. Then one-rank local linear model based on multivariate time series is proposed. The daily load forecasting for a certain district in Chongqing is respectively carried out by the method presented in this paper. Through the analysis of the obtained forecasting results it is shown that the method presented in this paper is more accurate than that of scalar time series.

AC flashover performance and voltage correction of 27.5 and 110 kV iced composite insulator at 4000/spl sim/5500 m high altitude districts

Based on the test results carried out in the multi-function artificial climate chamber of Chongqing University (China) on two types of composite insulator, this paper discusses the effects of atmospheric pressures or altitudes, contamination level and ice amount secreted on the minimum AC flashover voltages of composite insulators, and analyzes the flashover performance of the composite insulator in icing, contaminating and low pressure conditions. The authors therefore put forward a correction method of flashover voltages.