An Economic Analysis of Energy Consumption at Student Residences in a South African-Based Academic Institution Using NARX Neural Network

One of the issues associated with supply electricity is its generation capacity, and this has led to prevalent power cuts high costs usage experienced in many developing nations, including South Africa. Historical research shown that annual rate increase for grown at an alarming since 2008 and, some years, as much 16%. The objectives study are estimate cost analysis twenty-nine residences University Johannesburg (UJ-Res) propose a model our university, well other African universities, become more energy-efficient. This was achieved by analyzing tariffs between 2015 2021. A forecast made period five years (2021 2026) using non-linear autoregressive exogenous neural network (NARX-NN) time-series model. From results obtained, better NARX-NN studied root mean squared error (RMSE) 2.47 × 105 determination coefficient (R2) 0.9661. projection result also shows energy consumed will projected year 2022 being peak estimated over ZAR 30 million (USD 2,076,268).