Electric Load Pattern Classification for Demand-side Management Planning: A Hybrid Approach

Abstract

Smart Grids require a clear understanding of consumer demand patterns. Classification of consumers according to their demand pattern is required for the effective planning of tariffs, eligibility for demand-side management (DSM) programs, energy production and transmission, as well as for security purposes. We propose a framework for classification of consumer load patterns using a hybrid system with a parameter estimation model, a clustering model and an artificial neural network (ANN). The proposed model provides an effective unbiased classification method. The process starts with generating a training data set from existing consumers without a priori classification. The raw load data is processed through a parameter estimation model and a clustering algorithm to generate a training data set with distinct impartial classification clusters. The training data is fed to an ANN for learning. Once the load patterns are learned, the model can be used to further classify new consumers into a demand pattern. The ANN provides fast and accurate clustering performance without underlying assumptions about shape or class. An analysis of the optimal number of clusters is presented. Results indicate that clusters with distinguishable characteristics are achieved and we demonstrate how regulators can make use of this method in demand curtailment planning.

Smart Grids Data Analysis: A Systematic Mapping Study

“…The absolute majority of papers were focused on the evaluation of specific algorithms, not on scalability or Big Data concerns. However, when data streaming aspects are discussed, Apache Storm 1 / Spark 2 (2) and Massive Online Analysis (MOA) 3 were used. Massive Online Analysis (MOA) is an open source framework for large data streams analysis, project that is the complement of WEKA for Big Data analysis.…”

“…Massive Online Analysis (MOA) is an open source framework for large data streams analysis, project that is the complement of WEKA for Big Data analysis. [3], [40], [44], [49], [64], [67], [84], [94], [129], [153], [160], [204], [212], [214], [245]), fuzzy c-means clustering (7) ( [49], [64], [173], [204], [245], [265], [266]), Hierarchical Clustering (HAC) (7) ( [44], [56], [64], [94], [204], [212], [232]), Support Vector Machine (SVM) (6) [3], [112], [150], [204], [239], [250], Self-Organising Map (SOM) (4) [2], [64], [167], [212], Multi Layer Perceptron (MLP) ANN (3) [40], [150], [232], t-means clustering [183], k-Nearest Neighbour (kNN) [112], [204], Random Forest…”

Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs

“…Satish [1] uses a multi-ANN method to address the day-of-week problem, which affects most statistical methods. Buitrago [61] and also Abdulaal et al [62] propose a framework combining parameter estimation, clustering and ANNs to group load patterns. Lopez [63] uses self-organizing maps (SOM) for addressing the groupings of load patterns.…”

Short Term Residential Load Forecasting: An Improved Optimal Nonlinear Auto Regressive (NARX) Method with Exponential Weight Decay Function

“…The proposed regression and clustering stages proved more robust than conventional estimators. Authors in References [17,18] ensemble load patterns together by proposing a grouped framework of ANN, parameter estimation, and clustering. Currently, forecasting the load peak is also very critical since it effects significantly in the power system improvement and regional economic stability.…”

“…In case the energy of space and lead projectiles greater than step leader energy, their direction and position are updated using Equations (18) and (20). 10.…”