A South African Power Supply Reliability Dataset, Structured for Count Time Series and Machine Learning Applications

Recurring load-shedding and persistent power system disruptions in South Africa have intensified the need for reliable data-driven assessment of electricity supply dynamics. Addressing this challenge requires comprehensive and well-structured datasets that capture the key operational characteristics of the electricity system. This paper presents a dataset on load-shedding and power system operations in South Africa, developed to support time series modelling and electricity reliability studies. The dataset comprises hourly observations obtained from the Electricity Supply Commission (Eskom) data portal covering the period from July 2018 to June 2023. It contains key electricity system variables, including load-shedding frequency, contracted demand, dispatchable generation, thermal generation, renewable energy generation, electricity imports, and planned and unplanned capability loss factors. The response variable, load-shedding, was pre-processed (discretised) to construct structured data suitable for count time series and machine learning to analyse temporal patterns, seasonality, and electricity supply disruptions. In addition, selected variables were combined to provide comprehensive measures of planned and unplanned capability reductions within the electricity system. The dataset provides a valuable resource for load-shedding analysis, reliability assessment, forecasting, energy planning, and policy development in South Africa.