Electricity Pattern Analysis by Clustering Domestic Load Profiles Using Discrete Wavelet Transform

Abstract

Energy demand has grown explosively in recent years, leading to increased attention of energy efficiency (EE) research. Demand response (DR) programs were designed to help power management entities meet energy balance and change end-user electricity usage. Advanced real-time meters (RTM) collect a large amount of fine-granular electric consumption data, which contain valuable information. Understanding the energy consumption patterns for different end users can support demand side management (DSM). This study proposed clustering algorithms to segment consumers and obtain the representative load patterns based on diurnal load profiles. First, the proposed method uses discrete wavelet transform (DWT) to extract features from daily electricity consumption data. Second, the extracted features are reconstructed using a statistical method, combined with Pearson’s correlation coefficient and principal component analysis (PCA) for dimensionality reduction. Lastly, three clustering algorithms are employed to segment daily load curves and select the most appropriate algorithm. We experimented our method on the Manhattan dataset and the results indicated that clustering algorithms, combined with discrete wavelet transform, improve the clustering performance. Additionally, we discussed the clustering result and load pattern analysis of the dataset with respect to the electricity pattern.

Cross Domain Correlation Maximization for Enhancing the Target Recognition of SSVEP-Based Brain–Computer Interfaces

“…It is clear that the t-SNE (Chebyshev distance) points obtained by the eTransRCA form uniformly dispersed clusters and have minimal overlaps among them. In this study, four commonly used internal measures for the evaluation of clustering validity, i.e., the Calinski-Harabasz index (CHI), silhouette coefficient (SC), Davies-Bouldin index (DBI) [37], and separation (SP) [38] were calculated for each of the six different target recognition methods (see Tables III and IV). The results in Tables III and IV reveal that the proposed eTransRCA method has a better clustering capability than the other five control methods (for CHI, SC, and SP, where higher values indicate better performance, whereas for DBI, smaller values indicate better performance) for both the Benchmark dataset and BETA dataset.…”

ANN-Based Reliability Enhancement of SMPS Aluminum Electrolytic Capacitors in Cold Environments

“…This research suggests cluster algorithms that employ discrete wavelet transformation (DWT) to partition consumers according to their daily load patterns. The approach is deployed on the Manhattan dataset, demonstrating enhanced cluster efficiency and easing the analysis of electricity usage patterns [26].…”

Fuzzy C-means clustering based on micro-spatial analysis for electricity load profile characterization

“…To ensure the optimum number of clusters formed that is 5 clusters, then validation using silhouette algorithm is carried out using (8), the results of cluster validation are shown in the Figure 6. It shows the silhouette index for each sub-district.…”

“…Therefore, this research provides a novel approach in determining load profile characterization by performing a micro-spatial-based adaptive fuzzy (FCM) clustering technique to identify the pattern of load needs, types, and characteristics of the load C-means served by a smaller area (micro-spatial) [6]. The clustering method is needed so the physical areas can be grouped into some classes that consist of another similar characteristic areas [7], [8]. Fuzzy C-means clustering is one of the algorithms of clustering besides another algorithms which are hierarchical, K-means, and dynamic [9].…”

“…Fuzzy C-means clustering is one of the algorithms of clustering besides another algorithms which are hierarchical, K-means, and dynamic [9]. The well-known clustering method is K-means which basically uses iterative method for clustering [8], [10], [11] then the result can be used to analyze the power consumption behaviour [12]. If the clustering is done by considering each data as a separate cluster and then merging the similar ones, it is called hierarchical clustering as done in some literatures [10], [13], [14].…”