Load Pattern Clustering Research Articles

Incremental segmented slope residential load pattern clustering based on three-stage curve profiles

ABSTRACT This paper tackles high computational complexity in using Euclidean distance for residential load profiles (RLPs) similarity by proposing a three-stage incremental segmented slope clustering framework. The first two stages involve static clustering, where we obtain typical residential load profiles through piecewise slope clustering. In the third stage, dynamic clustering is performed based on the slope similarity of RLPs. This method enhances clustering performance and reduces computation cost, outperforming various benchmarks, with simulation results confirming the framework's effectiveness.

Meta-Heuristic Optimization Based Two-stage Residential Load Pattern Clustering Approach Considering Intracluster Compactness and Inter-cluster Separation

This article proposes a meta-heuristic optimization-based two-stage residential load pattern clustering (LPC) approach to address two main issues that exist in the most current LPC methods: 1) unreasonable typical load pattern (TLP) extraction; 2) a good clustering should achieve a good balance between the compactness and separation of the formed clusters. However, few clustering algorithms integrate both of these two aspects into the objective function of clustering for consideration. In the first stage, an adaptive density-based spatial clustering of applications with noise (DBSCAN) is proposed to automatically detect the uncommon load curves and obtain the TLP of each individual customer. In the second stage, LPC is formulated as an optimization problem in which clustering validity index (CVI) considering both compactness and separation is used as the objective function. Gravitational search algorithm (GSA) is adopted to solve this optimization problem. Four different CVIs are investigated to find the most appropriate one for LPC. A comparative case study using the real load data from 208 households from the U.K. verified the effectiveness of the proposed approach.

A comparative study of clustering techniques for electrical load pattern segmentation

Smart meters have been widely deployed in power networks since the last decade. This trend has resulted in an enormous volume of data being collected from the electricity customers. To gain benefits for various stakeholders in power systems, proper data mining techniques, such as clustering, need to be employed to extract the underlying patterns from energy consumptions. In this paper, a comparative study of different techniques for load pattern clustering is carried out. Different parameters of the methods that affect the clustering results are evaluated and the clustering algorithms are compared for two data sets. In addition, the two suitable and commonly used data size reduction techniques and feature definition/extraction methods for load pattern clustering are analysed. Furthermore, the existing studies on clustering of electricity customers are reviewed and the main results are highlighted. Finally, the future trends and major applications of clustering consumption patterns are outlined to inform industry practitioners and academic researchers to optimize smart meter operational use and effectiveness.

A Baseline Load Estimation Approach for Residential Customer based on Load Pattern Clustering

Demand response (DR) is a key technology enabling reliable and flexible power system operation more economically and environment-friendly than conventional manners from supply side. Customer baseline load (CBL) estimation is an important issue in the implementation of DR programs for assessing the performance of DR programs and designing economic compensation mechanisms. The accurate estimation of CBL is critical to the success of DR programs because it involves the interests of multi-stakeholders including utilities and customers. Motivated by the inaccuracy of existing CBL methods, this paper proposes a residential CBL estimation approach based on load pattern (LP) clustering to improve the accuracy of CBL estimation. First, an adaptive density-based spatial clustering of applications with noise (DBSCAN) algorithm is proposed to extract typical load patterns (TLPs) of each individual customer in order to avoid the adverse effects from aggregating many dissimilar LPs together as the real TLP. Second, K-means clustering is utilized to segment residential customers into several different clusters based on the similarity of LPs. Finally, CBLs for DR participants are estimated based on the actual load of non-participants at the same cluster during DR event periods. The proposed methods are compared with some traditional methods on a smart metering dataset from Ireland. The results show that the proposed methods have a better performance on accuracy than averaging and regression methods.

Two-Stage Load Pattern Clustering Using Fast Wavelet Transformation

Smart grids collect large volumes of smart meter data in the form of time series, or so-called load patterns. We outline the applications that benefit from analyzing this data (ranging from customer segmentation to operational system planning), and propose two-stage load pattern clustering. The first stage is performed per individual user and identifies the various typical daily power usage patterns (s)he exhibits. The second stage takes those typical user patterns as input to group users that are similar. To improve scalability, we use fast wavelet transformation (FWT) of the time series data, which reduces the dimensionality of the feature space where the clustering algorithm operates (i.e., from ${N}$ data points in the time domain to log ${N}$ ). Another qualitative benefit of FWT is that patterns that are identical in shape, but just differ in a (typically small) time shift still end up in the same cluster. Furthermore, we use ${g}$ -means instead of ${k}$ -means as the clustering algorithm. Our comprehensive set of experiments analyzes the impact of using FWT versus time-domain features, and ${g}$ - versus ${k}$ -means, to conclude that in terms of cluster quality metrics our system is comparable to state-of-the-art methods, while being more scalable (because of the dimensionality reduction).

Electrical Load Pattern Grouping Based on Centroid Model With Ant Colony Clustering

Load pattern clustering based on the shape of the electricity consumption is a key tool to provide enhanced knowledge on the nature of the consumption and assist meaningful customer partitioning. This paper presents new developments to group the load patterns using an initial set of centroids specified according to a user-defined centroid model. The original Electrical Pattern Ant Colony Clustering (EPACC) algorithm is illustrated, highlighting its characteristics and parameters, with centroids evolution during the iterative process until stabilization. The EPACC results are compared with those obtained from the classical k-means algorithm to group the representative load patterns taken from a set of non-residential customers in typical weekdays.

Residential Load Pattern Analysis for Smart Grid Applications Based on Audio Feature EEUPC

The smart grid is an important application field of the Internet of things. This paper presents a method of user electricity consumption pattern analysis for smart grid applications based on the audio feature EEUPC. A novel similarity function based on EEUPC is adapted to support clustering analysis of residential load patterns. The EEUPC similarity exploits features of peaks and valleys on curves instead of directly comparing values and obtains better performance for clustering analysis. Moreover, the proposed approach performs load pattern clustering, extracts a typical pattern for each cluster, and gives suggestions toward better power consumption for each typical pattern. Experimental results demonstrate that the EEUPC similarity is more consistent with human judgment than the Euclidean distance and higher clustering performance can be achieved for residential electric load data.

Day-ahead price forecasting in restructured power systems using artificial neural networks

Over the past 15 years most electricity supply companies around the world have been restructured from monopoly utilities to deregulated competitive electricity markets. Market participants in the restructured electricity markets find short-term electricity price forecasting (STPF) crucial in formulating their risk management strategies. They need to know future electricity prices as their profitability depends on them. This research project classifies and compares different techniques of electricity price forecasting in the literature and selects artificial neural networks (ANN) as a suitable method for price forecasting. To perform this task, market knowledge should be used to optimize the selection of input data for an electricity price forecasting tool. Then sensitivity analysis is used in this research to aid in the selection of the optimum inputs of the ANN and fuzzy c-mean (FCM) algorithm is used for daily load pattern clustering. Finally, ANN with a modified Levenberg–Marquardt (LM) learning algorithm are implemented for forecasting prices in Pennsylvania–New Jersey–Maryland (PJM) market. The forecasting results were compared with the previous works and showed that the results are reasonable and accurate.