LIFTED: Household Appliance-level Load Dataset and Data Compression with Lossless Coding considering Precision
Lei Yan, Jiayu Han, Runnan Xu, Zuyi Li
Abstract
The issue of estimating the detailed appliance-level load consumption has received considerable attention. This paper first presents a Labelled hIgh Frequency daTaset for Electricity Disaggregation (LIFTED), which can be used for research on nonintrusive load monitoring (NILM). This dataset consists of one-week detailed appliance-level electricity usage information including voltage, current, active power, and reactive power for a single apartment in the United States, down-sampled at 50Hz. This paper also proposes an efficient Lossless Coding considering Precision (LCP) algorithm on data compression. This algorithm considers both the precision requirements of practical applications on load datasets and the unique characteristics of household appliance-level load datasets. The LCP algorithm is tested on the LIFTED and REDD dataset and the results demonstrate that LCP can achieve higher compression ratio compared to several existing algorithms.