Role: Project Lead, Research Data Scientist (2017 - 2019)
The Big Data for Household Energy Insights project was housed at the Energy Research Centre at the University of Cape Town. The goals of the project were to provide strategic support and leadership to convene and mobilise key stakeholders towards building big data capabilities for domestic load research and to deliver technical data science and data stewardship activities in this regard.
The project has delivered South Africa’s first online, citeable datasets of Domestic Electrical Load (DEL) studies in South Africa. The published DEL datasets capture valuable household electricity consumption and survey data that covers over two decades of research gathered under the National Rationalised Specification Load Research Programme. Hosted securely at DataFirst, Africa’s only internationally accredited data archive, the datasets are now available to researchers for non-commercial use. The DEL datasets cover the period of major electrification in South Africa from 1994 to 2014 and span across five climatic zones, two time zones and various population groups. They are unique on the African continent and their release marks the pioneering step that key stakeholders - namely Eskom, a group of municipal stakeholders, the University of Cape Town, Stellenbosch University, professionals and specialists working in the load research space - have taken to advance and open data-driven energy research to a broader audience through digitisation and open data. Together with the five DEL datasets that have been published, the project has released two open source python packages to facilitate data access and processing.
Domestic Electrical Load Metering Data 1994-2014
Domestic Electrical Load Survey 1994-2014
Domestic Electrical Load Survey-Secure Data 1994-2014
Domestic Electrical Load Metering, Hourly Data 1994-2014
Domestic Electrical Load Survey - Key Variables 1994-2014
delretrieve: Data Retrieval for the DEL Study
delprocess: Data Processing of the DEL Study data
delarchetypes: Construct South African residential electricity consumer archetypes from the DEL Study data
- Toussaint, W. and Moodley, D. 2020. “Clustering Residential Electricity Consumption Data to Create Archetypes that Capture Household Behaviour in South Africa”. South African Computer Journal 32(2), 1–34. https://doi.org/10.18489/sacj.v32i2.845
- Toussaint, W. and Moodley, D. 2020. “Identifying optimal clustering structures for residential energy consumption patterns using competency questions.” In Conference of the South African Institute of Computer Scientists and Information Technologists 2020 (SAICSIT ‘20). Association for Computing Machinery, New York, NY, USA, 66–73. https://doi.org/10.1145/3410886.3410887
- Toussaint, W. and Moodley, D. 2020. “Using competency questions to select optimal clustering structures for residential energy consumption patterns.” ICLR 2020 Workshop on Machine Learning in Real Life. URL https://arxiv.org/abs/2006.00934
- Toussaint, W. and Moodley, D. 2019. “Comparison of Clustering Techniques for Residential Load Profiles in South Africa.” In Proceedings of the South African Forum for AI Research. URL http://ceur-ws.org/Vol-2540/FAIR2019_paper_55.pdf
- Toussaint, Wiebke. Evaluation of Clustering Techniques for Generating Household Energy Consumption Patterns in a Developing Country Context. 2019. URL http://hdl.handle.net/11427/30905
- Shedding light on residential energy consumer behaviour in South Africa, SAIEE Load Research Chapter Webinar (30 July 2019).
- Evaluation of clustering techniques for generating household energy consumption patterns in a developing country, eResearch Africa 2019, Cape Town, South Africa (18 April 2019).
- Building, managing and maintaining data and knowledge-sharing ecosystems for medium-sized research centres, SciDataCon-IDW 2018, Gaberone, Botswana (6 November 2018).
- Workshop on Domestic Load Research, Domestic Use of Energy Conference, Cape Town, South Africa (4 April 2018).