Search

Non-intrusive load monitoring (NILM) is an elegant solution for monitoring energy consumption. Essentially, it only requires a set of voltage and current sensors to be installed at the electrical entry point for load disaggregation. However, the main challenge of NILM is to accurately analyze the aggregate load data and determine the electrical consumption of each appliance. Recently, there have been some deep learning (DL) techniques proposed for NILM. These include deep convolutional neural networks (DCNNs), gated linear unit and residual network (GLU-Res), bidirectional long short-term memory (BLSTM), and autoencoder (AE). Generally, they can outperform some of the existing NILM models such as factorial hidden Markov model. Nevertheless, some of these DL methods cannot handle well on multi-state appliances, appliances with sparse patterns, and appliances with rapid changing patterns. This article proposes a new NILM model, which involves parallel convolution neural networks and BLSTM layers. Moreover, a feature extractor is proposed to unmask useful statistical features from aggregate signals to improve the learning capability of the network. The benchmark dataset REDD was used for testing the proposed method and the state-of-the-arts such as DCNN, GLU-Res, BLSTM, and AE. The results indicate that the proposed method can successfully outperform those methods. [ABSTRACT FROM AUTHOR]

This paper presents a review with a concise description and analysis of the fundamentals, characteristics, analytical details, merits, and drawbacks associated with existing methods in frequency and time domain for harmonic analysis in practical power networks. The description and analysis are centered on methods developed in the harmonic domain, hybrid frequency-time domain, and time domain, respectively. Validation of the reviewed methods for harmonic analysis, against one of the widely accepted digital simulators, such as EMTP, EMTDC, or MATLAB/SIMULINK, is reported in the cited individual contributions. [ABSTRACT FROM PUBLISHER]

This paper presents a time domain method to analyze the three phase rectifier with capacitor output filter. As demonstrated in the paper, the proposed method analytically evaluates harmonics, and obtains exact switching functions by iteratively solving for the switching instants. An analytical Jacobian of the mismatch equations is obtained to ensure a quadratic convergence rate for the iteration process. It is also demonstrated that a unified approach exists to analyze converters operating in the continuous conduction mode and discontinuous conduction mode. One potential application of the proposed model is to incorporate it into a harmonic power flow program to yield improved accuracy. [ABSTRACT FROM AUTHOR]

When a power-electronic converter is introduced into a linear network, voltage and current harmonics of differing orders become coupled (through the modulation effect of the converter). The interharmonic coupling introduced by the modulation effect of a converter may be mathematically represented through a frequency coupling matrix (FCM). Given that the source of the coupling is a modulation process, researchers have, in the past, focused on deriving the FCM in the frequency domain-a process that requires the truncation of the harmonic representation of signals. This paper presents an alternate approach to evaluate the FCM based on a time-domain derivation. In contrast to frequency-domain-based methods, it is shown that the time-domain approach avoids truncation. Furthermore, the time-domain approach does not require system linearization about an operating point; thus, the FCM is not limited by small-signal assumptions. [ABSTRACT FROM AUTHOR]

An iterative method based on a hybrid time/frequency-domain approach is proposed in this paper to solve for the steady state of a pulse width modulated voltage-source converter (VSC) with a dq-frame closed-loop controller. The method solves the linear controller equations in the frequency domain, while solving the VSC equations using time domain techniques. The model is validated against time domain simulation results. It is shown that the hybrid time/frequency-domain approach is both highly efficient and accurate, and it provides a viable alterative to brute-force time domain simulation for large signal harmonic analysis of the VSC. [ABSTRACT FROM AUTHOR]

When a realtime digital simulator, emulating a switched circuit such as a voltage source converter, is interfaced with a digital controller, the controller's firing signals may not be in synchronism with the simulation time step. Several methods to minimize the resulting inaccuracies have been proposed in the past. However, some of these approaches introduce unnecessary delays and/or generate artificial harmonics. In this paper, a method based on time averaging is presented. The algorithm is shown to be last, easy to implement in a programmable logic device, and highly accurate. The method is applied in a hardwarein-the-loop simulation, and the simulation results are compared with experimental results. [ABSTRACT FROM AUTHOR]