Nonlinear Loads Model for Harmonics Flow Prediction, Using Multivariate Regression

Lamich, M.; Balcells, J.; Corbalan, Montserrat; Griful, Eulalia

doi:10.1109/tie.2017.2674596

Cited by 24 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their reliable and accurate predictions play an important role in maritime industry, such as economic investment, transportation planning, port planning and design, etc. In the literature [1], [2], [3], [4], many efforts have been recently devoted to effectively predict different types of time series. However, it is still generally difficult to model and predict such non-stationary time series using traditional mathematical methods, such as fuzzy theory [5], [6], Kalman filtering [7], Bayesian models [8], hybrid framework [9], autoregressive integrated moving average (ARIMA) [10] and their extensions.…”

Section: Introductionmentioning

confidence: 99%

Similarity Grouping-Guided Neural Network Modeling for Maritime Time Series Prediction

Liu

Zhao

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Reliable and accurate prediction of time series plays a crucial role in the maritime industry, such as economic investment, transportation planning, port planning, design, and so on. The dynamic growth of maritime time series has the predominantly complex, and nonlinear and non-stationary properties. To guarantee high-quality prediction performance, we propose to first adopt the empirical mode decomposition (EMD) and ensemble EMD (EEMD) methods to decompose the original time series into high-and low-frequency components. The low-frequency components can be easily predicted directly through traditional neural network (NN) methods. It is more difficult to predict high-frequency components due to their properties of weak mathematical regularity. To take advantage of the inherent self-similarities within high-frequency components, these components will be divided into several continuous small (overlapping) segments. The grouped segments with high similarities are then selected to form more proper training datasets for traditional NN methods. This regrouping strategy can assist in enhancing the prediction accuracy of high-frequency components. The final prediction result is obtained by integrating the predicted high-and low-frequency components. Our proposed three-step prediction frameworks benefit from the time series decomposition and similar segments grouping. The experiments on both port cargo throughput and vessel traffic flow have illustrated its superior performance in terms of prediction accuracy and robustness. INDEX TERMS Data prediction, neural network, similarity grouping, empirical mode decomposition (EMD), dynamic time warping (DTW).

show abstract

Section: Introductionmentioning

confidence: 99%

Similarity Grouping-Guided Neural Network Modeling for Maritime Time Series Prediction

Liu

Zhao

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Tables 1-4 present the measured and calculated electrical parameters according to the dependencies presented in Section 2 of the LED luminaires tested in the assumed range of voltage variations from 207 V to 253 V. The luminaires are supplied with non-deformed voltage. In the tables, 3% deviations were introduced (∆X Lim , ∆X LimB , ∆X LimT ) which are defined as follows: For the measurement data contained in Tables from 1 to 4, the reference value is the supply voltage value equal to 230 V. The introduced additional deviations described in Formulas (21), (22) and (23) allow to evaluate the effect of the RMS value of the supply voltage on the value of the distinctive electrical parameter. The coefficient defined as (22) shows the changes caused by the voltage drop below the reference value, and defined as (23) the changes caused by its increase, respectively.…”

Section: Studies Of the Influence Of Rms Value Of Supply Voltagementioning

confidence: 99%

“…For all tested luminaires, an increase in the RMS value of the supply voltage results in a reduction of the RMS value of the supply current and these changes are calculated at a level of a dozen or so percent from the relation (21). The values of deviations calculated from dependencies (22) and (23) prove that the luminaires are more sensitive in respect to the voltage deviation below the reference value of 230 V. The reactive power Q is more sensitive to the changes in the supply voltage and it varies from 35% to 44% for the luminaires tested. Similarly, the deformation power D is maintained, which varies from 14% to even 44%.…”

Section: Studies Of the Influence Of Rms Value Of Supply Voltagementioning

confidence: 99%

“…The paper will present the results of laboratory tests of typical road lighting luminaires made in LED technology supplied with distorted voltage with THD V coefficient values not exceeding the permissible value for low-voltage networks. In the literature [10,[21][22][23][24], this issue has not been comprehensively described. In addition, there are a number of publications presenting the results of the measurements and simulations concerning the emission of higher harmonics by lighting luminaires.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Electric Power Quantities of Road LED Luminaires under Sinusoidal and Non-Sinusoidal Conditions

Sikora

Markiewicz

2019

Energies

View full text Add to dashboard Cite

The paper presents the results of laboratory tests concerning the measurements of electrical parameters of road lighting luminaires. These measurements were focused on determining the dependence of the electrical parameters of the luminaires versus the changes of the RMS (Root Mean Square) value of the supply voltage and the level of disturbances in the supply voltage. The basic electrical parameters for light-emitting diode (LED) luminaires were analysed with the option of luminous flux adjustment if it existed. During the laboratory measurements, the luminaires were powered from the Agilent 6834B distorted voltage generator within the assumed acceptable range of the changes in the deformation level resulting from the applicable legal provisions for the reproduction of actual power supply conditions.

show abstract

“…The ever increasing use of distributed generation and power electronics-based non-linear loads leads to also increasing levels of harmonics distortion in the voltage waveform of the power system [1][2][3][4][5]. The harmonics distortion could cause serious power-quality problems, which result in economic losses such as increased energy losses, reduced lifetime of electrical equipment, and maloperation of protection devices to mention just a few [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Robust estimation of voltage harmonics in a single‐phase system

Reza¹,

Ciobotaru²,

Hossain

et al. 2019

IET Science, Measurement & Technology

View full text Add to dashboard Cite

Nonlinear Loads Model for Harmonics Flow Prediction, Using Multivariate Regression

Cited by 24 publications

References 14 publications

Similarity Grouping-Guided Neural Network Modeling for Maritime Time Series Prediction

Similarity Grouping-Guided Neural Network Modeling for Maritime Time Series Prediction

Analysis of Electric Power Quantities of Road LED Luminaires under Sinusoidal and Non-Sinusoidal Conditions

Robust estimation of voltage harmonics in a single‐phase system

Contact Info

Product

Resources

About