Deep learning based non-intrusive load monitoring with low resolution data from smart meters

• DOI: 10.2478/caim-2022-0004
• Publication Date: 2022-10-12T14:21:38Z
• Authors: Marco Manolo Manca; Luca Massidda
• Keywords: Consumption; Smart meter

Abstract A detailed knowledge of the energy consumption and activation status electrical appliances in a house is beneficial for both user supplier, improving awareness allowing implementation management policies through demand response techniques. Monitoring individual certainly expensive difficult to implement technically on large scale, so non-intrusive monitoring techniques have been developed that allow be derived from sole measurement aggregate house. However, these methodologies often require additional hardware installed domestic system measure total with high temporal resolution. In this work we use deep learning method disaggregate low frequency signal generated directly by new generation smart meters deployed Italy, without need specific hardware. The performances obtained two reference datasets are promising demonstrate applicability proposed approach.