Work

Investigating the Impact of Temperature on Daily Electric Load in Dry Season in Three Locations of Agbor, Asaba and Abraka, Delta State

Year: 2025
Type: article
Abstract: This study investigates temperature variations impact on daily electric load consumption during dry seasons using sophisticated forecasting models and empirical data analysis. The comprehensive dataset comprised 547 daily observations from three Delta State metropolitan cities—Agbor, Asaba, and Abraka—spanning 18 months (October 2022 to March 2024). The statistical analysis employed descriptive statistics, correlation analysis, regression modeling, and time-series decomposition, utilizing advanced techniques including Pearson correlation analysis, multiple linear regression, and machine learning models (LSTM, Random Forest, hybrid approaches). The analysis used R version 4.3.2, Python 3.9, TensorFlow 2.12, Scikit-learn, Prophet, and ARIMA models, featuring a novel hybrid LSTM-RF ensemble approach combining Long Short-Term Memory networks' sequential learning with Random Forest robustness. Results revealed strong positive correlation between ambient temperature and daily electric load demand (r = 0.847, p < 0.001). Dry season average daily load (2,847.3 MW) exceeded wet season levels (2,234.7 MW) by 27.4%. The hybrid LSTM-RF model achieved 94.2% forecasting accuracy with temperature variables versus 76.8% without temperature variables. Peak loads occurred during maximum daily temperatures (13:00-16:00), with temperature of 40.1 0C as the highest at an average of 81.2 MW per degree Celsius. The load-to-temperature ratio is comparatively constant throughout the day demonstrating temperature as a crucial predictor for electric load demand with significant implications for tropical region capacity planning and grid management.
Language: English
Open Access status: green
OpenAlex ID: W7118627136
FWCI:
Cites:
Cited by:
Related to: