Document Type : Industry Article
Authors
1
Department of Information Technology Management,, Faculty of Management and Economics, Science and Research Branch, Islamic Azad University, Tehran, Iran
2
Department of Information Technology Management, Faculty of Management and Economics, Science and Research Branch, Islamic Azad University, Tehran, Iran
3
Department of Management,, Faculty of Management and Economics, Tarbiat Modares University, Tehran, Iran
4
Department of Power, Faculty of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran,
Abstract
Nowadays, demand response is recognized as an important element in the reliability of smart grid. Smart home energy management systems, which prioritize the start-up of electrical appliances according to the necessity of use and efficiency, play a vital role in the effectiveness of load response strategies in residential areas. Considering the sensor technologies, clarification on electricity consumption details helps to optimally monitor how the appliances are used. In this research, an unsupervised machine learning model was proposed for the clustering of home appliances to manage the bills of customers based on their inherent characteristics. Due to the small number of clusters, it becomes possible to manage electricity consumption. The hierarchical clustering method was used to classify appliances into three clusters. The first cluster is the appliances that are turned on at the discretion of the consumers immediately, the second cluster is the appliances that can be turned on according to the schedule and their usage can be postponed and the third cluster is appliances that are preferred by a limited number of consumers. The silhouette coefficient was developed as a measure of the hierarchical clustering model performance, where the average silhouette coefficient of 0.56 indicates the satisfaction of the model. Based on the results, it was found that the proposed clustering method can rationally classify different types of home appliances by selecting the appropriate characteristics since the appliances in a cluster are very similar to each other and can help users understand the operating conditions of the appliances.
Keywords
Main Subjects
)