Emerging Technologies for Developing Countries. Second EAI International Conference, AFRICATEK 2018, Cotonou, Benin, May 29–30, 2018, Proceedings

Research Article

A Predictive Model for Automatic Generation Control in Smart Grids Using Artificial Neural Networks

Download
369 downloads
  • @INPROCEEDINGS{10.1007/978-3-030-05198-3_5,
        author={Chika Yinka-Banjo and Ogban-Asuquo Ugot},
        title={A Predictive Model for Automatic Generation Control in Smart Grids Using Artificial Neural Networks},
        proceedings={Emerging Technologies for Developing Countries. Second EAI International Conference, AFRICATEK 2018, Cotonou, Benin, May 29--30, 2018, Proceedings},
        proceedings_a={AFRICATEK},
        year={2018},
        month={12},
        keywords={Smart grid Artificial intelligence Artificial neural networks Deep learning},
        doi={10.1007/978-3-030-05198-3_5}
    }
    
  • Chika Yinka-Banjo
    Ogban-Asuquo Ugot
    Year: 2018
    A Predictive Model for Automatic Generation Control in Smart Grids Using Artificial Neural Networks
    AFRICATEK
    Springer
    DOI: 10.1007/978-3-030-05198-3_5
Chika Yinka-Banjo1,*, Ogban-Asuquo Ugot1
  • 1: University of Lagos
*Contact email: cyinkabanjo@unilag.edu.ng

Abstract

This paper presents a predictive model that estimates the load for an Automatic Generation Control (AGC) system. We start by laying the foundation for our system by discussing the AGC, and the benefits of embedding it in a smart power grid. The AGC as a system is discussed with a keen focus on the mathematical relationship between the load on the system and the frequency deviation. Our predictive model is a deep neural network trained on a multivariate time series dataset for energy consumption collected over 47 months. The results show that it is possible to predict to a high accuracy, the total load on the power system within the next minute. The goal of the predictive model is predicated upon the notion that the ability to forecast the future load on the system results in the ability to estimate the frequency deviation as well, and thus giving the AGC the ability to forecast risks such as a system overload.