Islanding detection of synchronous distributed generators using data mining complex correlations

The Paradigm Revolution in the Distribution Grid: The Cutting-Edge and Enabling Technologies

“…The control actions are decided based on the operating states of the power system. A self-healing scheme based on operating state classification is proposed [38] Event detection AMI Random matrix theory [39] Anomaly detection and location AMI Spectral clustering [28] Phase identification of smart meters /customers AMI Online Sequence Extreme Learning Machine (OS-ELM) [40] Intrusion detection which is used to detect the attack in AMI AMI Wavelet transform [26] Load curve clustering algorithm AMI Multi-instance clustering algorithm [41] Consumer Segmentation AMI Euclidean distance-based anomaly detection schemes [42] Covert cyber deception assault-detection AMI Ensemble Classifier Bootstrap Aggregation [43] Intrusion detection AMI Data Mining of Code Repositories (DAMICORE) [44] Islanding detection of synchronous distributed generators Micro-PMU OPTICS [45] Segment data and finds the outliers in the segmented data Micro-PMU CNN [46], RNN [46] Power system transient disturbance classification Micro-PMU Multi-SVM [47] Data driven event classification Micro-PMU Multi-SVM and PCA [48] Disruptive event classification Micro-PMU Auto-encoder together with softmax classifier [48] Disruptive event classification Micro-PMU kernel Principle Component Analysis (kPCA) [49] Abnormal event detection Micro-PMU for distribution networks with DGs in [33]. The operating states of the system are determined based on the performance index, which is used as an indicator of system stability, reliability, and security.…”

Auto‐correlation‐based Islanding detection technique verified through hardware‐in‐loop testing

“…Therefore, the overall Islanding detection time from the inception of the Islanding event would be around 60 ms which is equivalent to three cycles. Table 7 shows the comparative assessment of the proposed scheme in terms of the percentage value of NDZ and detection time with the techniques based on ROCOF [11], oscillatory frequency [12], overvoltage/undervoltage (OV/UV), over frequency/under frequency (OF/UF) [13], inverse hyperbolic secant function (applied for acquired voltage signals) [16], time-frequency (TF) transform [17], wavelet transform (WT) [18][19][20], Hilbert-Hung transform (HT) [21], SVM [22,23], RVM [25], artificial neural network (ANN) [26,27], adaptive ensemble classifier (AEC) [28], Data mining [29,30], random forest (RF) [32], and principle component analysis (PCA) [24].…”

“…Furthermore, the hardware implementation of said techniques is also complex [17][18][19][20][21]. Subsequently, support vector machine (SVM), relevance vector machine (RVM), random forest, neural network, adaptive ensemble classifier, data mining, and principle component analysis-based approaches have been discussed in [22][23][24][25][26][27][28][29][30][31][32]. Even though these approaches give good results, the requirement of a vast number of input patterns for training, complexity in training procedure and large errors for unobserved pattern/dataset make the above techniques less popular.…”

New voltage feedback‐based islanding detection method for grid‐connected photovoltaic systems of microgrid with zero non‐detection zone

“…Recently, mathematical tools have been applied as the strong classifiers to categorise islanding and normal operational modes [15][16][17][18][19][20]. For instance, a decision tree-based intelligent relay has been recommended by Cui et al [15].…”