Towards sustainable developing cities: A simplified forecasting model for sizing grid-tied PV using monthly electricity bills

Abstract

The recent reductions in PV costs and the convenient concurrence of insolation and schools' energy usage have resulted in increased interest in augmenting supply with solar PV to save on energy costs and unburden the grid in developing countries. However, optimal sizing of PV solutions requires a detailed analysis and hourly simulation to match demand, council tariff structures (incl. import vs. export rates) and geography. This complexity exposes already resource-constrained authorities to abuse by overzealous and unwitting suppliers, and currently impedes large-scale deployment of solar PV in a sunshiny cities depraved of its requisite energy. We present a novel approach to forecast schools' hourly demand using only monthly utility bills and a trained forecasting model. We also propose an iterative solar sizing technique to assess the economic viability of using PV at schools to support government and city council officials. The results show that the method is able to forecast annual energy usage and monthly demand to within 5% and 6% respectively, while accurately determining the potential return on investment.