# Establishment and analysis of online energy baseline for water purification plants: A case study in Kaohsiung city, Taiwan

## TL;DR

This study establishes an online energy baseline model for water purification plants in Kaohsiung, Taiwan, using AI to improve energy efficiency and comparison across facilities.

## Contribution

The study introduces an AI-based energy baseline modeling system for water purification plants using multiple machine learning methods and operational data.

## Key findings

- Kaohsiung's average energy use for water purification is lower than the global average.
- The most energy-intensive plant uses eight times more energy than the least.
- AI models outperformed traditional regression in predicting energy baselines.

## Abstract

Water and energy are closely linked and are crucial for national security and economic development. Most water providers prioritise the stability of water supply and aim to reduce energy consumption under the premise of a stable supply. The average energy required to supply water in Taiwan in one of the lowest worldwide. In the Kaohsiung area, the average energy used by a water purification plant to provide 1 m3 of water is 0.32 kWh/m3, lower than the world average of 0.37 kWh/m3. However, the most energy-consuming plant (Weng Park water purification plant) uses eight times as much energy as the least energy-consuming plant (Pingding water purification plant). Most studies focus on the energy required to provide 1 m3 of water. This study combined attributes of four plants, such as the amount of energy consumed, quantity of water supplied, purified, and collected, and weather data. These data were used to model energy baselines for water providers. Artificial intelligence was imported into Microsoft Azure machine learning to train the model, which was verified using another Kaohsiung plant and one overseas to establish an online energy baseline modelling system that can be applied in various water purification plants.

•This study used the factory energy baseline to represent the energy baseline of water supply companies.•Artificial intelligence was imported into Microsoft Azure machine learning to train the model.•Unlike studies using only regression, this study uses AI methods with various parameters affecting energy consumption.•Used Linear, Neural Network, and Support Vector Regression to collect annual data from water purification plants.

This study used the factory energy baseline to represent the energy baseline of water supply companies.

Artificial intelligence was imported into Microsoft Azure machine learning to train the model.

Unlike studies using only regression, this study uses AI methods with various parameters affecting energy consumption.

Used Linear, Neural Network, and Support Vector Regression to collect annual data from water purification plants.