Machine learning for energy cost modelling in wastewater treatment plants

Understanding the energy cost structure of wastewater treatment plants is a relevant topic for plant managers due to the high energy costs and significant saving potentials. Currently, energy cost models are generally generated using logarithmic, exponential or linear functions that could produce not accurate results when the relationship between variables is highly complex and non-linear. In order to overcome this issue, this paper proposes a new methodology based on machine-learning algorithms that perform better with complex datasets. In this paper, machine learning was used to generate high-performing energy cost models for wastewater treatment plants, using a database of 317 wastewater treatment plants located in north-west Europe. The most important variables in energy cost modelling were identified and for the first time, the energy price was used as model parameter and its importance evaluated.