Volume 3: Innovative Solutions for Energy Transitions: Part II

Office Appliance Category Classification Based on Non-Intrusive Load Monitoring Yu Wang, Jie Sun, Qie Sun , Ronald Wennersten

Abstract

Alongside the acceleration of building digitalization, making intelligent use of building energy consumption data attains more and more attention. As appliance-level energy consumption data is not generally available, the Non-Intrusive Load Monitoring (NILM) provides novel waysto disaggregate total energy consumption data into appliance-level while ensures privacy of customers. This work focuses on NILM algorithm that is applicable to common appliances and widespread smart metering infrastructure. The NILM energy consumption data of an office was collected with 1-min resolution and used for analysis. In the work, fuzzy c-means clustering NILM algorithm and inter-cluster entropy were used to classify and verify the categories of office appliances. The algorithm was proven to be able to disaggregate and classify office appliance energy consumption data with a satisfactory accuracy.

Keywords non-intrusive load monitoring, smart building, energy disaggregation, fuzzy c-means clustering