Increasing Clean Energy Access through AI
Globally, the number of people without access to electricity declined from 1.2 billion in 2010 to 759 million in 2019. Electrication through decentralized renewable-based solutions particularly gained momentum. The number of people connected to mini-grids has more than doubled between 2010 and 2019, growing from 5 to 11 million people.
Machine learning and articial intelligence have a strong use case in energy demand forecasting whereas solar energy production can be modeled for a given location using physics-based libraries such as PVLIB thus in this presentation Leroy will show how NeedEnergy has developed AI tools that allow Utilities, Energy Developers and Providers to identify opportunities in deploying distributed microgrids and Battery Energy Storage Systems in the area most needed to meet the demand as indicated by the need.
Leroy will present a case study on how NeedEnergy has used
- Weather variables in training its models to predict and forecast energy generation for microgrids in remote areas.
- Load Demand to train its Solar PV sizing tools, which bring insights and advice to utilities to respond to this demand with a combination of Solar PV and Battery Storage.
- Power trading data and volumes to predict day-ahead prices that will encourage energy developers to trade in these platforms especially in developing regions.
- Has been able to go beyond typical kWh/m² benchmarks and provide two linear models that can estimate residential electricity demand given a household’s monthly income and access to water.