Research Article
Optimization of ANFIS Model for Improved Short-term Electrical Load Forecasting
Osita Omeje
,
Favour Edwards,
Linus Idoko*
Issue:
Volume 15, Issue 3, June 2026
Pages:
34-44
Received:
12 May 2026
Accepted:
25 May 2026
Published:
2 June 2026
Abstract: For power systems to be stable and reliable, an accurate prediction of electrical load demand is crucial. Electric utilities rely on short-term load forecasting to effectively manage the generation, transmission, and distribution of power to satisfy customer demand. Artificial Neuro-Fuzzy Inference System (ANFIS) is utilized in this work for short-term load forecasting due to its propensity to manage non-linear relationships and uncertainty. ANFIS method has been used in the past for short-term load forecasting, there are certain conditions and issues that need to be resolved. Data normalization, choice of optimization technique, and choice of membership function can greatly influence short-term load forecast using ANFIS. Thus, this paper explored the different choices available and recommended the best choices based on the results obtained. Hourly electrical load data from 24th November 2021 to 4th January 2022, sourced from University of Lagos Power Station, and relevant temperature data within the same range sourced from National Solar Irradiation Database (NSRDB) were used to train and test the various ANFIS architectures. Different ANFIS models, including different membership functions and sets of input data, were simulated on MATLAB, and the performance of the models was evaluated using standard matrices such as root mean square error (RMSE) and mean absolute percentage error (MAPE). The result of this study showed that the inclusion of temperature as an exogenous variable and the use of Gaussian membership function yielded a higher forecast accuracy with MAPE 0.05754% and RMSE 0.56614. This implies that using temperature as an input variable and Gaussian membership functions can improve forecasting accuracy.
Abstract: For power systems to be stable and reliable, an accurate prediction of electrical load demand is crucial. Electric utilities rely on short-term load forecasting to effectively manage the generation, transmission, and distribution of power to satisfy customer demand. Artificial Neuro-Fuzzy Inference System (ANFIS) is utilized in this work for short-...
Show More
Research Article
A Rural Security–Economic Stability Framework for Designing Hybrid Renewable Microgrids: A Representative Nigerian Case Study
Abdulhamid Musa*
Issue:
Volume 15, Issue 3, June 2026
Pages:
45-64
Received:
1 June 2026
Accepted:
10 June 2026
Published:
26 June 2026
DOI:
10.11648/j.epes.20261503.12
Downloads:
Views:
Abstract: Rural Nigerian communities face persistent electricity shortages, weak grid reach, diesel-price volatility, and limited productive-energy access. These conditions undermine household welfare, rural enterprise viability, health-service continuity, water supply, agro-processing, communication, and night-time security. Most hybrid renewable microgrid studies optimize levelized cost of energy (LCOE) or net present cost, while treating supply security, affordability under uncertainty, and socio-environmental performance as secondary outcomes. This paper develops a structured rural security–economic stability (RSES), framework for hybrid renewable microgrid planning. The framework contains five stages: resource profiling, load stratification, component sizing, multi-scenario optimization, and resilience stress-testing. A composite RSES index is introduced to combine reliability, autonomy, affordability, payback stability, renewable fraction, and avoided emissions into a single planner-facing score. The framework is applied to a synthetic but representative Northern Nigerian rural cluster of approximately 180 households and community services, with average demand of 410 kWh/day and peak demand of 68 kW. Four architectures are benchmarked: PV/Wind/Battery, PV/Diesel/Battery, PV/Wind/Hydrogen, and PV/Biomass/Battery. A reproducible custom hourly optimization model is used to simulate 8,760 hourly dispatch intervals. The PV/Biomass/Battery architecture achieved the strongest central performance, with LCOE of US$0.211/kWh, aggregate loss of power supply probability (LPSP) of 0.6%, renewable fraction of 94%, and RSES score of 0.80. The biomass result is reconciled through an explicit annual energy balance: the biomass generator supplies 23,900 kWh/year, consumes approximately 28.0 t/year of as-received residues, operates for 1,138 h/year, and uses only 4.8% of the assumed annual residue availability. The diesel-assisted design had competitive base-case cost but was most exposed to fuel-price shocks, while the hydrogen configuration achieved high reliability and renewable fraction but remained economically weak at the studied load scale. The results show that rural microgrid selection should be based not only on central LCOE but also on reliability, critical-load protection, payback stability, and shock-response bands.
Abstract: Rural Nigerian communities face persistent electricity shortages, weak grid reach, diesel-price volatility, and limited productive-energy access. These conditions undermine household welfare, rural enterprise viability, health-service continuity, water supply, agro-processing, communication, and night-time security. Most hybrid renewable microgrid ...
Show More
