SustData: A Public Dataset for ICT4S Electric Energy Research

Pereira, Lucas; Quintal, Filipe; Gonçalves, Rodolfo T.; Nunes, Nuno

doi:10.2991/ict4s-14.2014.44

Cited by 40 publications

(23 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, the GREEND data set [10] was released, which contains 1 second appliance data from nine houses in Italy and Austria. Most recently, the SustData data set [11] and DRED data set [12] have been released containing data from 50 and 1 home respectively. Table I summarises these data sets.…”

Section: Existing Data Setsmentioning

confidence: 99%

Dataport and NILMTK: A building data set designed for non-intrusive load monitoring

Parson

Fisher

Hersey

et al. 2015

2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

103

View full text Add to dashboard Cite

Abstract-Non-intrusive load monitoring (NILM), or energy disaggregation, is the process of using signal processing and machine learning to separate the energy consumption of a building into individual appliances. In recent years, a number of data sets have been released in order to evaluate such approaches, which contain both building-level and appliance-level energy data. However, these data sets typically cover less than 10 households due to the financial cost of such deployments, and are not released in a format which allows the data sets to be easily used by energy disaggregation researchers. To this end, the Dataport database was created by Pecan Street Inc, which contains 1 minute circuit-level and building-level electricity data from 722 households. Furthermore, the non-intrusive load monitoring toolkit (NILMTK) was released in 2014, which provides software infrastructure to support energy disaggregation research, such as data set parsers, benchmark disaggregation algorithms and accuracy metrics. This paper describes the release of a subset of the Dataport database in NILMTK format, containing one month of electricity data from 669 households. Through the release of this Dataport data in NILMTK format, we pose a challenge to the signal processing community to produce energy disaggregation algorithms which are both accurate and scalable.

show abstract

Section: Existing Data Setsmentioning

confidence: 99%

Dataport and NILMTK: A building data set designed for non-intrusive load monitoring

Parson

Fisher

Hersey

et al. 2015

2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

103

View full text Add to dashboard Cite

show abstract

“…To this end we extended an opensource Python package 3 that allows direct access to the raw measurements of each individual appliance being measured. More precisely, we changed the original scripts such that it was 1 LabJack, https://labjack.com/u6 2 Plugwise, https://plugwise.com 3 Plugwise Python, https://github.com/SevenW/Plugwise-2-py possible to capture plug-level measurements every two seconds instead of the default 10 seconds. The whole system is controlled by a netbook running Ubuntu 14, to which we added a web application to facilitate the configuration of the plugs during the deployment and maintenance phases and to provide the householders with a user interface where they can check the individual consumption of the monitored appliances.…”

Section: B Individual Appliance Consumptionmentioning

confidence: 99%

“…In order to measure the whole-house consumption data, we use the LabJack U6, a data acquisition board (DAQ) 1 , with 14 analog input ports and 16-bit resolution for a maximum sampling rate of 50 kHz. In the current version of SustDataED we are sampling current and voltage waveforms at 12.8 kHz and storing the resulting measurements in the bespoke SURF file format [2].…”

Section: A Whole-house Energy Consumptionmentioning

confidence: 99%

See 1 more Smart Citation

SustDataED: A Public Dataset for Electric Energy Disaggregation Research

Ribeiro¹,

Pereira²,

Quintal³

et al. 2016

Proceedings of ICT for Sustainability 2016

Self Cite

View full text Add to dashboard Cite

“…Figure 6) as an essential part of engaging with the ICT4S community to develop design projects and tools for smart cities (cf. [42]). …”

Section: Enabling Data Sharingmentioning

confidence: 99%

ICT for Sustainable Last-Mile Logistics: Data, People and Parcels

Bates¹,

Friday²,

Allen³

et al.

EPiC Series in Computing

View full text Add to dashboard Cite

In this paper we present a vision of how ICT can be leveraged to help combat the impact on pollution, congestion and carbon emissions contributed by the parcel delivery sector. This is timely given annual growth in parcel deliveries, especially same-day deliveries, and the need to inform initiatives to clean up our cities such as the sales ban on new petrol and diesel vehicles in the UK by 2040. Our insights are informed by research on parcel logistics in Central London, leveraging a data set of parcel manifests spanning 6 months. To understand the impact of growing e-commerce trends on parcel deliveries we provide a mixed methods case study leveraging data-driven analysis and qualitative fieldwork to demonstrate how ICT can uncover the impact of parcel deliveries on delivery drivers and their delivery rounds during seasonal deliveries (or "the silly season"). We finish by discussing key opportunities for intervention and further research in ICT4S and co-created Smart Cities, connecting our findings with existing research and data as a call to the ICT4S community to help tackle the growth in carbon emissions, pollution and congestion linked to parcel deliveries.

show abstract

SustData: A Public Dataset for ICT4S Electric Energy Research

Cited by 40 publications

References 15 publications

Dataport and NILMTK: A building data set designed for non-intrusive load monitoring

Dataport and NILMTK: A building data set designed for non-intrusive load monitoring

SustDataED: A Public Dataset for Electric Energy Disaggregation Research

ICT for Sustainable Last-Mile Logistics: Data, People and Parcels

Contact Info

Product

Resources

About