A Hybrid SOM and K-means Model for Time Series Energy Consumption Clustering

TL;DR

This paper presents a hybrid clustering approach combining Self-organizing maps and K-means to improve the analysis of monthly energy consumption patterns from smart meter data, enhancing interpretability and accuracy.

Contribution

The study introduces a novel hybrid method that leverages SOM for dimensionality reduction and K-means for clustering, specifically tailored for time series energy data.

Findings

Achieved a silhouette score of 66%, indicating strong clustering quality.

Effectively captured essential temporal patterns in energy consumption data.

Demonstrated improved clustering performance over traditional methods.

Abstract

Energy consumption analysis plays a pivotal role in addressing the challenges of sustainability and resource management. This paper introduces a novel approach to effectively cluster monthly energy consumption patterns by integrating two powerful techniques: Self-organizing maps and K-means clustering. The proposed method aims to exploit the benefits of both of these algorithms to enhance the accuracy and interpretability of clustering results for a dataset in which finding patterns is difficult. The main focus of this study is on a selection of time series energy consumption data from the Smart meters in London dataset. The data was preprocessed and reduced in dimensionality to capture essential temporal patterns while retaining their underlying structures. The SOM algorithm was utilized to extract the central representatives of the consumption patterns for each one of the houses over the course of each month, effectively reducing the dimensionality of the dataset and making it easier for analysis. Subsequently, the obtained SOM centroids were clustered using K-means, a popular centroid-based clustering technique. The experimental results demonstrated a significant silhouette score of 66%, indicating strong intra-cluster cohesion and inter-cluster separation which confirms the effectiveness of the proposed approach in the clustering task.