Estimation and Forecasting of Nigeria’s Residential, Commercial, and Industrial Electricity Demands
Energy demand forecasting has emerged as a crucial area of research, driven by the need for accurate predictions of future electricity consumption. This is critically essential for the effective planning and operation of electric power systems. Several studies have only forecasted what could be best...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11053813/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Energy demand forecasting has emerged as a crucial area of research, driven by the need for accurate predictions of future electricity consumption. This is critically essential for the effective planning and operation of electric power systems. Several studies have only forecasted what could be best termed as ‘suppressed electricity demand’ in Nigeria, given the non-consideration of basic unmet demand factors. Suppressed electric energy demand arises from inadequate energy access accounting for unmet electricity needs such as electricity capacity utilization, access rate, outages, and transmission and distribution (T&D) losses. These unmet electricity needs are considered sensitive determinants in achieving optimal planning and utilization of electricity in a developing economy like Nigeria. This study, therefore investigated and estimated these unmet basic electricity needs in deriving a potential electricity consumption and typical demand forecast for Nigeria in consideration of sustainability and full capacity utilization. It aimed at forecasting Nigeria’s potential electricity demand by analyzing the various electricity usage patterns in the country. It presented a methodological approach for estimating and forecasting the expected electricity demand in the nation by developing and examining economic and environmentally sustainable models with the incorporation of unmet electricity needs. These needs were analyzed using the developed models and sourced data to obtain advanced estimates of electricity consumption. A high-precision, long-term forecasting procedure was then implemented using these estimates. The implementation and simulation of the procedure was conducted with a Machine Learning/AI procedure (using Python) compatible with the Google Collaboratory tool. The obtained results were post processed using MS Excel. The results indicated that Nigeria’s potential electricity demand will be 69783.099, 80383.785 and 90984.472 GWh by 2030, 2040 and 2050, respectively. The forecast results were further validated with those obtained using stochastic/probabilistic extrapolation method. While the Python simulation indicated a lower average Mean Square Error (MSE) of 0.008%, the stochastic/probabilistic extrapolation procedure gave an MSE of 0.021%. With the forecasting results, decision-makers and policy-makers in Nigeria’s energy sector are armed with the right tool for effective and informed decision-making in electricity planning and management. The approach of this study to solving the national energy challenge is timely and aims to help navigate the complex challenges of making informed decisions in the sector, and establish future research avenues that may facilitate the effective integration of renewable energy into the national energy landscape. |
|---|---|
| ISSN: | 2169-3536 |