wiebket/delarchetypes

A pipeline to construct residential electricity consumer archetypes from the South African Domestic Electrical Load (DEL) database. # Clustering Residential Electricity Consumption Data in South Africa ## About This package is a pipeline that constructs South African residential electricity consumer archetypes from the South African Domestic Electric Load (DEL) database. This is the code repository for the following published research: 1. 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. [doi.org] 2. 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. [doi.org] 3. 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 [ceur-ws.org] 4. Toussaint, Wiebke. Evaluation of Clustering Techniques for Generating Household Energy Consumption Patterns in a Developing Country Context. 2019. URL [hdl.handle.net] **[Masters thesis with complete overview of experiments]** ### Data & Pre-Processing This code requires access to the DELMH and DELMSKV datasets from the NRS Load Research study. Data access can be requested from Data First at the University of Cape Town. The data descriptor for the dataset is available online. Two other packages have been released alongside this package for retrieving and processing data from the DEL database. ## Setup instructions Ensure that python 3 is installed on your computer. A simple way of getting it is to install it with Anaconda. Once python has been installed, the delarchetype package can be …