Electricity usage profile disaggregation of hourly smart meter data

Research output: Contribution to conferencePoster

Abstract

This paper is motivated by the growing demand of disaggregating electricity consumption measured by smart meters, down to appliance level. The very low 15-min to 60- min granularity of energy measurements available for analysis, as is standard by the majority of nationwide smart metering programmes, is posing serious challenges. The non-intrusive load monitoring (NILM) solutions for these very low data rates cannot leverage on low (1-60sec) to high rates (in the order of kHz to MHz) NILM approaches, and so far have not received much attention in the literature. In this paper, we propose a novel electricity profile hourly disaggregation of energy consumed (kWh) based on K-nearest neighbours (K-NN), that relies on features such as statistical measures of the energy signal, time usage profile of appliances and reactive power consumption (if available). We propose relative standard deviation as a metric to assess the quality of each feature per appliance. For validation, three publicly accessible real-world datasets are used, namely the REDD, REFIT and AMPds (Version 2), for up to 3 months.

Conference

Conference4th International Workshop on Non-Intrusive Load Monitoring
CountryUnited States
CityAustin
Period7/03/188/03/18
Internet address

Fingerprint

Smart meters
Electricity
Electric power measurement
Monitoring
Reactive power
Electric power utilization

Keywords

  • smart meters
  • electricity consumption
  • energy signal

Cite this

Zhao, B., Stankovic, L., & Stankovic, V. (2018). Electricity usage profile disaggregation of hourly smart meter data. Poster session presented at 4th International Workshop on Non-Intrusive Load Monitoring, Austin, United States.
Zhao, Bochao ; Stankovic, Lina ; Stankovic, Vladimir. / Electricity usage profile disaggregation of hourly smart meter data. Poster session presented at 4th International Workshop on Non-Intrusive Load Monitoring, Austin, United States.4 p.
@conference{304418cdcf7e4a2582385852cc132239,
title = "Electricity usage profile disaggregation of hourly smart meter data",
abstract = "This paper is motivated by the growing demand of disaggregating electricity consumption measured by smart meters, down to appliance level. The very low 15-min to 60- min granularity of energy measurements available for analysis, as is standard by the majority of nationwide smart metering programmes, is posing serious challenges. The non-intrusive load monitoring (NILM) solutions for these very low data rates cannot leverage on low (1-60sec) to high rates (in the order of kHz to MHz) NILM approaches, and so far have not received much attention in the literature. In this paper, we propose a novel electricity profile hourly disaggregation of energy consumed (kWh) based on K-nearest neighbours (K-NN), that relies on features such as statistical measures of the energy signal, time usage profile of appliances and reactive power consumption (if available). We propose relative standard deviation as a metric to assess the quality of each feature per appliance. For validation, three publicly accessible real-world datasets are used, namely the REDD, REFIT and AMPds (Version 2), for up to 3 months.",
keywords = "smart meters, electricity consumption, energy signal",
author = "Bochao Zhao and Lina Stankovic and Vladimir Stankovic",
year = "2018",
month = "3",
day = "7",
language = "English",
note = "4th International Workshop on Non-Intrusive Load Monitoring ; Conference date: 07-03-2018 Through 08-03-2018",
url = "http://nilmworkshop.org/2018",

}

Zhao, B, Stankovic, L & Stankovic, V 2018, 'Electricity usage profile disaggregation of hourly smart meter data' 4th International Workshop on Non-Intrusive Load Monitoring, Austin, United States, 7/03/18 - 8/03/18, .

Electricity usage profile disaggregation of hourly smart meter data. / Zhao, Bochao; Stankovic, Lina; Stankovic, Vladimir.

2018. Poster session presented at 4th International Workshop on Non-Intrusive Load Monitoring, Austin, United States.

Research output: Contribution to conferencePoster

TY - CONF

T1 - Electricity usage profile disaggregation of hourly smart meter data

AU - Zhao, Bochao

AU - Stankovic, Lina

AU - Stankovic, Vladimir

PY - 2018/3/7

Y1 - 2018/3/7

N2 - This paper is motivated by the growing demand of disaggregating electricity consumption measured by smart meters, down to appliance level. The very low 15-min to 60- min granularity of energy measurements available for analysis, as is standard by the majority of nationwide smart metering programmes, is posing serious challenges. The non-intrusive load monitoring (NILM) solutions for these very low data rates cannot leverage on low (1-60sec) to high rates (in the order of kHz to MHz) NILM approaches, and so far have not received much attention in the literature. In this paper, we propose a novel electricity profile hourly disaggregation of energy consumed (kWh) based on K-nearest neighbours (K-NN), that relies on features such as statistical measures of the energy signal, time usage profile of appliances and reactive power consumption (if available). We propose relative standard deviation as a metric to assess the quality of each feature per appliance. For validation, three publicly accessible real-world datasets are used, namely the REDD, REFIT and AMPds (Version 2), for up to 3 months.

AB - This paper is motivated by the growing demand of disaggregating electricity consumption measured by smart meters, down to appliance level. The very low 15-min to 60- min granularity of energy measurements available for analysis, as is standard by the majority of nationwide smart metering programmes, is posing serious challenges. The non-intrusive load monitoring (NILM) solutions for these very low data rates cannot leverage on low (1-60sec) to high rates (in the order of kHz to MHz) NILM approaches, and so far have not received much attention in the literature. In this paper, we propose a novel electricity profile hourly disaggregation of energy consumed (kWh) based on K-nearest neighbours (K-NN), that relies on features such as statistical measures of the energy signal, time usage profile of appliances and reactive power consumption (if available). We propose relative standard deviation as a metric to assess the quality of each feature per appliance. For validation, three publicly accessible real-world datasets are used, namely the REDD, REFIT and AMPds (Version 2), for up to 3 months.

KW - smart meters

KW - electricity consumption

KW - energy signal

UR - http://nilmworkshop.org/2018/index.html

M3 - Poster

ER -

Zhao B, Stankovic L, Stankovic V. Electricity usage profile disaggregation of hourly smart meter data. 2018. Poster session presented at 4th International Workshop on Non-Intrusive Load Monitoring, Austin, United States.