Global warming is a growing concern in every facet of life in recent years. Forecasts show a major shift in aerospace and agro processes in the foreseeable future due to the use of fossil fuels. This rapid climate change also caused by the corresponding need for energy will be exacerbated in the ecological spaces and processes on the African Continent, whose per capita electricity demand is well below the world average. The various energy options developed over the years have their individual merits and demerits as far as cost, efficiency, environmental degradation, and sustainability are concerned. Grid electricity, though environmentally friendly has issues of availability, accessibility and affordability. Hence a need to model grid demand and supply across Africa to meet benchmarked and set targets in line with national and regional economies’ decarbonization policies has arisen.

Profiling energy demand is crucial to energy transition for economies’ future, whether developed or developing, yet data and forecasts for Africa are yet very limited and at low spatial resolution to be used in energy modelling tools. It is clear in the literature that conventional and artificial intelligence (AI) models are widely used to forecast future energy needs and, in this project, will be used to estimate demand. Africa’s Energy industry has evolved over decades dynamically from crude means of power generation and supply to more advanced options available for adoption based on Load, availability, cost and sustainability of the environmental ambience thus shaping energy transition across the globe over time.

The Centre for Petroleum Energy Economics and Law (CPEEL) University of Ibadan in collaboration with PyPSA meets Africa proposes a machine learning solution to profiling electricity demand in African countries as a means to mitigate climate change. This requires a data-driven approach using machine learning as grid electricity has been seen as a hinged-on energy source availability cum dependencies, cost of transmission and distribution as against final consumer purchasing power, and global decarbonization drive/focus.

This study will adopt a mixed approach employing simulation and predictive algorithms on existing data which is to be statistically compared with real-time data. Furthermore, parameters to be adopted in the study entails Installed Capacity, Actual Generated Capacity, GDP Per Capita in PPP Annual Peak Load, Annual Base Load, Annual Electricity Consumption, Temperature and other Country Specific Variables includes (e.g. frequency of Grid Collapse) and foreign exchange rate. These parameters would be gathered over the past 10 years, while the model would allow for input from real-time data as the study is hinged on a time- series approach. Modelling and simulations would be done with the use of supervised machine learning processes.

Because darkness caused by incessant power outages has a particular environmental cost, this project will satisfy energy stakeholders’ desire for a data-driven grid demand model for economic prosperity and security. Furthermore, well-trained models would inform the true and optimal nature of grid demand and supply required for Africa’s energy transition. This would encourage energy optimization as related to both decarbonization and load cost energy system modelling