1. Introduction
The microgrid (MG) meets the exponential growth of load demand because of its reliable, secure, sustainable, and green energy supply [
1,
2]. This small-scale power supply network is constituted by several distributed energy resources (DERs), energy storage devices, communication facilities, and well-regulated loads [
3,
4,
5]. An MG is able to work in both an autonomous/islanded and grid-tied way. In the grid-tied operation, a portion of the load is driven by the primary AC grid, and in the islanded process, the main AC grid is disconnected from the microgrid and runs autonomously. As the MG shows dynamic (such as the mode of operation) characteristics and its system components show non-linear characteristics, it produces a negative influence on the system protection [
6]. Thus, the protection of the MG system is a considerable issue before facilitating this novel technology [
7,
8,
9,
10,
11].
The safe operation of the MG depends on the precise fault detection and classification (FDC) as the faults are unpredictable and random in nature and needs specialized technique to restore the faulty phases [
12,
13]. Furthermore, the protection method of the MG is not directly comparable to the conventional transmission line protection method due to its various modes of operation (autonomous or grid-tied), system arrangement (looped or radial), and types of DERs. An amount of short circuit faults like phase-to-phase (pp), phase-to-ground (PG), two PG (2PG), and three PG (3PG) [
14] occurs in the microgrid distribution line and develops an unbalanced current waveform in the MG premises. The precise and speedy FDC model serves as a strategy for the balanced behaviour of the MG system as it increases the chance of speedy restoration of the unhealthy phases from the MG model. The restoration of the damaged phases, in turn, enhances the quality level of electrical power and increases the transient response, as well as the system stability [
15,
16,
17].
Several fault prognosis and diagnosis models are considered to classify the faults in MG [
18,
19,
20,
21]. In [
22,
23], a protection plan of action based on communication was studied for the MG. This scheme keeps back-up security if the main protection scheme fails. A mathematical morphology based scheme was proposed in [
24] for a radial low voltage DC distribution network. An approach presented in [
25] used abc to dq transformation for the distributed generators’ (DGs) output to declare a fault type. Nonetheless, these schemes only consider the protection strategy for a particular operating mode or system topology. A phase angle and magnitude of positive and zero sequence voltage based fault characterization scheme was proposed in [
26]. Another MG protection plan of action based on harmonic current evaluation was introduced in [
27]. The mentioned approaches require setting an appropriate threshold value, which is challenging due to the dynamic behaviour of loads and variable fault impedances.
The neural network approaches are becoming popular among the fault prognosis methods where the fault features are required, which come from the line signals (current and voltage), for identifying a distinct fault class [
28]. Though the fault data are coming from the distribution line current or voltage waveforms, it is quite difficult to declare a fault class only using the raw signal data. In turn, the signal processing tools like wavelet transform [
29], S-transform [
30], or Hilbert–Huang transform [
31] are explored to reveal the relevant features from the distribution line waveforms that determine the behaviour of the line faults. Therefore, improving the accuracy of the neural network based FDC model has turned into one of the influential research platforms.
A decision tree (DT) based FDC scheme for the microgrid was presented in [
32] where the features were extracted by the discrete Fourier transform. A combined wavelet transform and DT was used to diagnose the MG faults [
3]. The wavelet transform (WT) can also be combined with the S-transform to detect the disturbance in grid-tied DG systems [
33]. Based on the extracted features by the Hilbert–Huang transform, a learning model including the naive classifier, SVM, and ELM has been used for declaring the type of faults [
6]. In [
34], the discrete wavelet transform (DWT) was combined with ELM for the detection, classification, and section identification of a microgrid. A semi-supervised model for FDC of the microgrid was presented in [
35]. A Taguchi based artificial neural network combined with DWT was presented in [
36]. These machine learning [
37,
38,
39] and neural network based approaches use a shallow architecture that limits the learning capability of the complex non-linear features of the MG. Due to the lack of hidden layers, these approaches cannot fuse the benefits of multiple features with perfection.
To address the aforementioned problems, this paper introduces a deep belief network (DBN) with multiple layers of hidden units that enables a way to improve the classification accuracy by learning the complex non-linear feature of the MG. Initially, the DBN was applied to diagnose the faults of aircraft engines. Thereafter, the research on gearboxes’, rolling-bearings’, and reciprocating compressor valves’ fault diagnosis grew rapidly [
40,
41,
42,
43]. The DBN is a stack of RBM, which makes the network deeper and enables the model to extract the features adaptively [
44,
45]. The DBN can handle non-linear data, which makes it to classify the faults more precisely in the microgrid domain.
The proposed network takes the three phase faulty voltage and current waveform data as an input to perform the fault diagnosis of the MG system. A DWT tool is used to extract the features from the raw signal samples. To increase the noise-immune performance of the DBN, an extension of this classifier with the dropout strategy is also proposed in this research. The dropout strategy significantly elevates the effectiveness of the proposed DBN against a level of considered noise.
The main findings of this article are as follows:
We design a novel network for distribution line FDC of MG based on the deep learning network together with the WT that enables the network to take out the relevant short circuit fault attribute from the faulted line signals effectively.
We develop a hierarchical generative model with multiple layers of RBM that restrains overfitting of the training dataset with a prominent unsupervised pre-trained process.
Both operating modes namely islanded and grid-connected/tied with two typologies (radial and loop) of MG are studied to measure the effectiveness of the proposed model.
The dropout strategy is integrated with the proposed network to establish the robust performance of the developed DBN model over the noisy environment.
The paper is arranged as follows.
Section 2 describes the design of the proposed generative model for the classification of MG faults with its required material.
Section 3 presents the performance analysis of the proposed DBN model. The paper is concluded in
Section 4.
3. Results and Discussion
This section illustrates the performance of the proposed fault detection and classification technique with different parameter variations. The fault current and voltage signals exposed dissimilar magnitudes in islanded mode and grid-connected mode. Thus, it was difficult to design a unified fault classification scheme. Therefore, the performance of the proposed model was individually analysed for different system topologies (radial or loop) and operating modes (grid-connected or islanded). The accuracy was evaluated by three aspects: (i) type of input signal, i.e., how the system performed with only the current or voltage waveform and with the voltage and current waveforms combined; (ii) sampling resolution, i.e., system accuracy evaluation with a variety of data acquirement rates; (iii) fault signal with noise present in it, i.e., the system performance with the noise present in the sampled signal. Additionally, a comparative analysis in terms of the accuracy of the existing and proposed FDC techniques was also carried out to show the superior short circuit fault classification performance of the proposed classifier.
3.1. Performance Assessment of the DBN Based FDC Scheme
In machine learning, to measure the validity of a learning model, a list of the data sample to test the model performance is used, which should be different from the training data [
50]. As a total of 1716 samples was made from the current and voltage waveforms for the individual datasets, it was first mixed and shuffled, and then, 30% of the data was randomly selected to test the effectiveness of the proposed model. The performance of the proposed DBN for Lines 1-3 was simulated with different system configurations and operating modes of MG and illustrated in
Figure 11 with the confusion matrix (CM) where the 11 different fault classer were inserted into the
x- and
y-axis in the form of an
matrix. The horizontal levels represent the actual class, whereas the vertical levels represent the predicted fault class. The confusion matrix also reports the count of true positives (TP), true negative (TN), false positives (FP), and false negatives (FN), which are defined as:
TP: A label is correctly predicted by the classifier, and it belongs to the original class.
TN: A label is correctly predicted by the classifier, and it does not belong to the original class.
FP: A label is predicted as positive by the classifier. but it does not belong to the original class.
FN: A label is predicted as negative by the classifier, but it belongs to the original class.
Primarily, from the CM, it was seen that most of the fault classes for all system configuration were classified correctly. The first accuracy measurement criterion from the confusion matrix was the average classification accuracy (AA) [
51] as stated in (18).
Here,
presents the total number of input data for the developed model, and
implies the number of correctly classified data. The proposed network could also show a similar performance for the rest of the distribution line. The average accuracy calculated for all of the distribution line is depicted in
Table 2. From the result, the highest accuracy of the proposed classifier was recorded as 99.70% for the grid-connected radial mode operation. For the other system configurations, the classifier performed better than 99.5%, which was in line with the expectation.
However, the average accuracy could not present the detailed result about the model performance. Thus, to investigate how the classifier behaved for individual fault classes, the classification performance was further assessed with the F1-score. The F1-score is a function of precision and recall/sensitivity, which is considered as perfect when its value is one and the worst if it is zero. The precision, which is known as the positive predictive value, can be defined as,
For a good classifier, the precision value should be one. From (19), if the FP increases, the precision value decreases, which is not expected for a good classifier. Another metric, recall, which is known as the true positive rate or the sensitivity of the classifier, can be defined as,
Like the precision, the recall value should be one for a good classifier. For this metric, if the FN increased, the recall value decreased, which was also not in line with the expectation. Therefore, another performance evaluation metric known as the F1-score was adopted, which takes both precision and recall into account. The higher F1 score of the proposed classifier for both voltage and current signals depicted in
Table 3 and
Table 4 showed that the classifier had less problems with the false positives and false negatives. Furthermore, from the classification accuracy (user accuracy) for each fault class, it could be concluded that the classifier had the ability to classify the faults with high accuracy.
3.2. Effect of Sampling Resolution and Signal Type
In the proposed FDC method, the three phase current and voltage waveforms were collected with a 20 kHz sampling resolution. In reality, the sampling frequency (SF) can be much less than 20 kHz because of the restrictions of the data collection apparatus. In some practical field scenarios, the FDC system needs to utilize current or voltage waveforms to perform the classification tasks due to the unavailability of both signals at the same time instance. Thus, the fault classification performance of the proposed classifier was examined with the variation of input signal type, as well as sampling rate. The SF utilized in this research were 2, 5, 10, 15, and 20 kHz, and the input signal types were the voltage waveform (Scheme-1) or current waveform (Scheme-2) and combined current and voltage waveform (Scheme-3). The classification results for an SF and a particular type of signal was done by performing the classification process five times. Thereafter, the mean value of the accuracies was determined to achieve the final results as shown in
Figure 12.
The increase in classification accuracy was expected as a higher SF carried more detailed fault information for a distinct short circuit fault class. Moreover, Scheme-3 offered the highest classification performance for all considered SF. At a smaller sampling rate, better classification performance was observed with the three phase current waveform than with the three phase voltage waveform. Furthermore, the FDC system performed better with the voltage signal information at a higher SF. At an SF range between 5 kHz and 10 kHz, Scheme-2 and Scheme-3 showed almost the same classification accuracy. This scenario was also expected, as the voltage waveform carried less low-frequency fault information than the current waveform for a distinct fault class. On the other side, the voltage waveform contained spare faulted transients, which were suitable to investigate the type of short circuit fault at the higher sampling rate. The above analysis explicated that the expected accuracy could not be accomplished with only the current or voltage waveform. If both waveforms were considered at a time, a higher fault classification performance could be accomplished within the considered frequency level as particular short circuit fault information for both the three phase current and voltage intents was used. From the aforementioned study, it was observed that the classification accuracy using only the current or voltage waveform was not satisfying; rather, their fusion offered more than a 99% classification accuracy at the large level of the considered frequency range, which validated the effectiveness of the proposed FDC model. The similar classification results could also be observed for the rest of the distribution line of the studied MG system.
3.3. Effect of Noise Present in the Measured Signal Data on the Classification Accuracy
In practice, the current or voltage waveforms are continuously subjected to statistical noises or uncertainties, which play an important role in degrading the overall performance of the MG fault diagnosis. Thus, the dropout strategy was added to the hidden layer of the RBM to confirm the performance [
52]. The fundamental idea of dropout is that it randomly sets the hidden nodes to zero at a certain probability to prevent overfitting of the model. That means some nodes present in the hidden layer do not engage in the training phase, and the weights will be reserved. The ignored nodes will be involved again in the next iteration. Thus, for each iteration process, the dropout strategy removes some random nodes of the hidden layer from the network. This process can effectively restrain the interdependence among the features and enhances the noise-immune classification performance. A comparison of the network structure with and without the dropout strategy is shown in
Figure 13.
To examine how the proposed model could show the result with noisy data, the system was run with a new sample dataset, which contained both signals (current and voltage). To validate the model performance with the noisy data, the white Gaussian noise of different signal-to-noise ratios (SNR) as per [
53] was added with 30% of the test data from the main dataset. Now, the proposed classifier was trained with the original data and tested with the contaminated data. The performance of the proposed classifier with the contaminated data is shown in
Figure 14. From the result, it was observed that the fault classification performance of the proposed FDC model with the dropout strategy was higher than the model without dropout. The classification performance without the dropout strategy was observed to decrease faster with the decrement of the SNR value for each mode of MG operation, as shown in
Figure 14. Finally, it was concluded that the classification accuracy against the noise guaranteed the robust performance of the proposed classifier.
3.4. Comparative Study
A comparison among the proposed model and several existing alternative fault diagnosis models is discussed in this section. In [
30], a discrete orthonormal S-transform based multi-kernel extreme learning machine (MKELM) was proposed and compared with KELM and SVM. The mentioned approaches use only the one cycle post fault current signal to declare a fault type that cannot confirm the accurate results at a lower SF, as discussed in
Section 3.2. However, comparing the proposed approach with the existing approaches is not fully consistent because of the following aspects. This research analysed the faults occurring in the considered MG for different topologies, i.e., looped or radial, operating modes, i.e., islanded or grid-tied, and for different distribution lines, separately. Therefore, the result analysis carried out in this study was much more challenging due to the diversity of the system parameters. Even though the results were not directly comparable, a comparison of the classification performance with the methods mentioned in [
30] is depicted in
Table 5. It was observed that the accuracy of the proposed approach was better than the other approaches. Again, the classification accuracy discussed in
Section 3.3 for the lower value of SNR proved the noise-immune performance of the proposed method. Additionally, the DBN based FDC scheme had a superior feature over the conventional and modern FDC techniques, as illustrated in
Table 6.