Online power quality disturbance detection by support vector machine in smart meter

Abstract

Power quality assessment is an important performance measurement in smart grids. Utility companies are interested in power quality monitoring even in the low level distribution side such as smart meters. Addressing this issue, in this study, we propose segregation of the power disturbance from regular values using one-class support vector machine (OCSVM). To precisely detect the power disturbances of a voltage wave, some practical wavelet filters are applied. Considering the unlimited types of waveform abnormalities, OCSVM is picked as a semisupervised machine learning algorithm which needs to be trained solely on a relatively large sample of normal data. This model is able to automatically detect the existence of any types of disturbances in real time, even unknown types which are not available in the training time. In the case of existence, the disturbances are further classified into different types such as sag, swell, transients and unbalanced. Being light weighted and fast, the proposed technique can be integrated into smart grid devices such as smart meter in order to perform a real-time disturbance monitoring. The continuous monitoring of power quality in smart meters will give helpful insight for quality power transmission and management.

Harmonic Vector Error Analysis Based on Lagrange Interpolation

“…As in Section III, it is necessary to further study the final analysis error of each harmonic through the Fourier transform. Similar to linear interpolation, the error range of different interpolation positions is shown in equations ( 16) and (17). Since the single-point error is an absolute value, we must discuss it according to different situations.…”

“…Since the single-point error is an absolute value, we must discuss it according to different situations. Equation (17) shows that the error function is a cosine function, which is different from the error function in linear interpolation, which is a sine function. Therefore, because the true value = the observed value ± the error value, the discussion is divided into three situations.…”

“…Most of the harmonic calculations are based on the FFT algorithm. For example, in reference [17], because of the limitation of the FFT due to the fence effect and spectral leakage, the accuracy of the harmonic analysis is low; therefore, a characteristic harmonic analysis algorithm based on spectral refinement and interpolation was proposed. Reference [18] proposed a new method for the harmonic analysis of industrial power systems based on a windowed FFT with high accuracy, fast calculation speed and easy implementation.…”

Impedance Matching-Based Power Flow Analysis for UPQC in Three-Phase Four-Wire Systems

“…Nowadays, the three-phase four-wire (3P4W) power supply system has been widely used in low-voltage distribution networks (LVDNs) because of its more flexible voltage supply mode [1], that is, it can provide consumers with 220 V phase voltage and 380 V line voltage. However, due to issues such as the start-up of impact load equipment, the randomness of the grid-connected output power of renewable energy, and the short-circuit failure of power systems [2], the 3P4W distribution networks mainly face the problem of grid voltage fluctuations (i.e., sag/swell), which may cause data loss or even damage to critical loads [3], such as financial industry computers, network servers, etc.…”

Detection and Classification of Power Quality Disturbances in Power System Using Modified-Combination between the Stockwell Transform and Decision Tree Methods

“…In recent years, a number of other theories have been proven effective for detecting and classifying PQ disturbances in power systems introduced as combination methods of DWT and two types of machine learning-based algorithms [29], an improved method from the iterative adaptive kernel regression method [30], a method based on multi-resolution ST and DT [31], and the method based on image enhancement techniques and feature selection [32].…”