Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Evaluating The Performance Of Supervised Multiple Linear Regression Machine Learning Algorithm In Predicting The Ampacity Of Overhead Transmission Lines

Domaine:

environment and energy

Type de record:

paper
Créateur:
KemHacBioRic
Éditeur:
Zenodo
Hôte:avatar
This study examines the overhead transmission line ampacity prediction performance of a supervised multiple linear regression machine learning algorithm integrated with the IEEE-738 heat balance equation, using ten years of historical data from the Nigerian Meteorological Agency (NiMet) and operational data from the Transmission Company of Nigeria (TCN) Afam network using a Python environment. Key meteorological factors included ambient temperature, wind velocity, solar radiation, and air pressure, while conductor properties such as emissivity and age were also considered. The aim was to evaluate the performance of supervised multiple regression algorithm to predict the dynamic amapcity of overhead transmission lines. This was achieved by first deriving the amapcity under different weather and line conditions, then deploying the algorithm for real-time dynamic line rating (DLR) prediction to determine its accuracy and speed based on the performance metrics. The IEEE-738 heat balance amapcity derivation results showed that the 450A-rated conductors had ampacitiy between 309A and 1406A (62% to 312% of the rated value) while the 630A-rated lines ranged from 380A to 1897A (60% to 301%), implying that depending on the weather conditions and other parameters, overhead transmission lines dynamic amapcity can increase up to 212% and decrease up to about 40% of the rated values of the lines' conductors. On the other hand, the prediction results of the Multiple Regression Machine Learning Algorithm showed a coefficient of determination 0.8912, a Standard Deviation of 0.0021, Root Mean Squared Error (RMSE) of 56.03, Mean Square Error (MSE) of 3139.32, and Mean Absolute Error (MAE) of 39.64 within a computing time of 0.9 second. While the prediction speed is very good, it is recommended that other supervised machine learning algorithms should be deployed with the same data to compare their prediction accuracy.

Visit

doi.org

Licenses

info:eu-repo/semantics/openAccessCreative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similaires

IMPLEMENTATION OF MACHINE LEARNING FOR PREDICTING MAIZE CROP YIELDS USING MULTIPLE LINEAR REGRESSION AND BACKWARD ELIMINATIONdavidsalako/supervised-learning-linear-regressionPredicting Sales Volume Using Multiple Linear RegressionEVALUATING THE PERFORMANCE OF MACHINE LEARNING ALGORITHMS FOR PREDICTING METEOROLOGICAL PARAMETERSPERFORMANCE OF MULTIPLE LINEAR REGRESSION AND AUTOREGRESSIVE INTEGRATED MOVING AVERAGE MODELS IN PREDICTING ANNUAL TEMPERATURES OF OGUN STATE, NIGERIAMuhavii/LINEAR-REGRESSION-MACHINE-LEARNING-MODEL

IMPLEMENTATION OF MACHINE LEARNING FOR PREDICTING MAIZE CROP YIELDS USING MULTIPLE LINEAR REGRESSION AND BACKWARD ELIMINATION

Predicting maize crop yields especially in maize production is paramount in order to alleviate pover

davidsalako/supervised-learning-linear-regression

A Supervised Learning Linear Regression Solution in Python 3. Cars4U Project - Supervised Learning L

Predicting Sales Volume Using Multiple Linear Regression

The process of sales forecasting is of strategic importance in industrial enterprises, and is also a

EVALUATING THE PERFORMANCE OF MACHINE LEARNING ALGORITHMS FOR PREDICTING METEOROLOGICAL PARAMETERS

Artificial learning techniques are currently used for weather and climate forecasting, etc. In this

PERFORMANCE OF MULTIPLE LINEAR REGRESSION AND AUTOREGRESSIVE INTEGRATED MOVING AVERAGE MODELS IN PREDICTING ANNUAL TEMPERATURES OF OGUN STATE, NIGERIA

The performance of Autoregressive Moving Average and Multiple Linear Regression Models in predicting

Muhavii/LINEAR-REGRESSION-MACHINE-LEARNING-MODEL

Kiswahili hate, non-hate speech model illustrating the linear regression algorithm (supervised learn