This paper presents the combination of advanced signal processing techniques and the machine intelligence approach to classify the power quality events. The Wavelet Transform (WT) and the S – Transform (ST) are utilized to extract the important useful features of the disturbance signal. The features extracted by using the above approaches are used to train a PNN classifier for automatic classif...

...............................................................................................................i

This article proposes a novel algorithm employing space vector ellipse (SVE) in complex plane to classify and visualize power quality disturbance-events (PQDEs). In the proposed method, at first, time-domain signal reference signal, which are separated by 90°, mapped 2D coordinates. Thus, tip of resultant rotating traces an ellipse, from three parameters, namely, semi-major axis, semi-minor axi...

unlike traditional power grids, smart grids have the advantage of bidirectional power flow and having distributed generations. distributed generation systems are usually supplied by renewable sources which can cause unpredicted voltage fluctuations as a result of being intermittent. while traditional compensating devices deal with the problem of voltage fluctuation and reduced power quality wit...

ac railway traction loads are usually huge single phase loads. as a result, a significant amount of negative sequence current (nsc) is injected into utility grid. moreover, harmonics and consumption ofreactive power are further power quality problems that the supply network is encountering. in this paper, acompensation strategy with the aid of railway power conditioner (rpc) is proposed to over...

this paper presents a novel method to calculate the reference source current and the referencecompensating current for shunt active power filters (sapfs). this method first calculates theamplitude and phase of the fundamental load current from a recursive algebraic approach blockbefore calculating the displacement power factor. next, the amplitude of the reference mains currentis computed with ...

This paper presents a wavelet transform and Support Vector Machine (SVM) based algorithm for classification of power quality (PQ) disturbances. The features extracted through the wavelet transform are trained by a SVM for classification of power quality disturbances. Five types of disturbances are considered for the classification problem. The simulation results reveal that the combination of w...

An system-level power management technique for massively distributed wireless microsensor networks is proposed. A power aware sensor node model is introduced which enables the embedded operating system to make transitions to different sleep states based on observed event statistics. The adaptive shutdown policy is based on a stochastic analysis and renders desired energy-quality scalability at ...