A Novel Method for Extracting Aging Load and Analyzing Load Characteristics in Residential Buildings
This study proposes a Hellinger distance algorithm for extracting the power features of aging load based on a non-intrusive load monitoring system (NILM). Hellinger distance algorithm is used to extract optimal features for load identification and the back-propagation artificial neural network (BP-ANN) is employed for the aging load detection. The proposed methods are used to analyze and identify the load characteristics and aging load in residential building. The result of aging load detection can provide the demand information for each load. The recognition result shows that the accuracy can be improved by using the proposed feature extraction method. In order to reduce the consumption of energy and send a real-time alarm of aging load to the user, the system provides the information of energy usage from the data analyses.
KeywordsNon-intrusive load monitoring system (NILM) aging load detection Hellinger distance back-propagation artificial neural network (BP-ANN)
Unable to display preview. Download preview PDF.
- 3.Chang, H.-H., Lian, K.-L., Su, Y.-C., Lee, W.-J.: Energy Spectrum-Based Wavelet Transform for Non-Intrusive Demand Monitoring and Load Identification. In: IEEE Industry Applications Society 48th Annual Meeting 2013 (IAS Annual Meeting 2013), Orlando, FL USA, October 6-11, pp. 1–9 (2013)Google Scholar
- 5.Chang, H.-H., Lin, L.-S., Chen, N., Lee, W.-J.: Particle Swarm Optimization Based Non-Intrusive Demand Monitoring and Load Identification in Smart Meters. In: IEEE Industry Applications Society 47th Annual Meeting 2012 (IAS Annual Meeting 2012), Las Vegas, NV USA, October 7-11, pp. 1–8 (2012)Google Scholar
- 7.Wang, Z., Zheng, G.: Residential Appliances Identification and Monitoring by a Nonintrusive Method. IEEE Transactions on Smart Grids 3(1) (March 2012)Google Scholar