No abstract

No abstract

This paper presents a new concept based on wavelet design and machine learning applied to nonintrusive load monitoring. The wavelet coefficients of length-6 filter are determined using procrustes analysis and are used to construct new wavelets to match the load signals to be detected, unlike previous work which used previously designed wavelet functions that are special cases of Daubechies filters to suit other nonpower system applications such as communications and image processing. The results of applying the new concept to a test system consisting of four loads have shown that the newly designed wavelet can improve the prediction accuracy compared with that obtained using Daubechies filter of order three while keeping the prominent features of the pattern in the detail levels.Index Terms-Load signature, machine learning, nonintrusive load monitoring (NILM), wavelet design.

In this paper, the impact of plug-in electric vehicle (PEV) charging on distribution transformer overload and lossof-life (LOL) in the presence of rooftop solar photovoltaic (PV) is probabilistically quantified. The Monte Carlo (MC) method is used to address the uncertainties resulting from solar irradiance and temperature in case of solar PV and also to emulate the probabilistic aspect of PEV charging. Twenty scenarios of different penetration levels of solar PVs and PEVs are considered in this work. The results have shown significant reduction in percentage LOL due to solar PV contribution in the case of all-electric (AE) residential dwellings and hence the transformer replacement may be deferred by nearly 4 years, while it has a minor effect in the case of residential dwellings with gas heat and electric water heaters (WWH). Index Terms-Loss of life (LOL), Monte Carlo (MC) methods, rooftop solar photovoltaic (PV). 1949-3029

No abstract