Application of LSTM Networks for Water Demand Prediction in Optimal Pump Control
Open Access
Abstract
Every morning, water suppliers need to define their pump schedules for the next 24 h for drinking water production. Plans must be designed in such a way that drinking water is always available and the amount of unused drinking water pumped into the network is reduced. Therefore, operators must accurately estimate the next day’s water consumption profile. In real-life applications with standard consumption profiles, some expert system or vector autoregressive models are used. Still, in recent years, significant improvements for time series prediction have been achieved through special deep learning algorithms called long short-term memory (LSTM) networks. This paper investigates the applicability of LSTM models for water demand prediction and optimal pump control and compares LSTMs against other methods currently used by water suppliers. It is shown that LSTMs outperform other methods since they can easily integrate additional information like the day of the week or national holidays. Furthermore, the online- and transfer-learning capabilities of the LSTMs are investigated. It is shown that LSTMs only need a couple of days of training data to achieve reasonable results. As the focus of the paper is on the real-world application of LSTMs, data from two different water distribution plants are used for benchmarking. Finally, it is shown that the LSTMs significantly outperform the system currently in operation.Keywords
This publication has 33 references indexed in Scilit:
- ARIMA-M: A New Model for Daily Water Consumption Prediction Based on the Autoregressive Integrated Moving Average Model and the Markov Chain Error CorrectionWater, 2020
- Machine Learning and Data Analytic Techniques in Digital Water Metering: A ReviewWater, 2020
- A Short-Term Data Based Water Consumption Prediction ApproachEnergies, 2019
- Short-term water demand forecasting using machine learning techniquesJournal of Hydroinformatics, 2018
- Short-term demand forecast using a bank of neural network models trained using genetic algorithms for the optimal management of drinking water networksJournal of Hydroinformatics, 2016
- Short-term forecasting of hourly water consumption by using automatic metering readers dataProcedia Engineering, 2015
- Comparison of Multivariate Regression and Artificial Neural Networks for Peak Urban Water-Demand Forecasting: Evaluation of Different ANN Learning AlgorithmsJournal of Hydrologic Engineering, 2010
- Predictive models for forecasting hourly urban water demandJournal of Hydrology, 2010
- Short‐term municipal water demand forecastingHydrological Processes, 2005
- Applying knowledge discovery to predict water-supply consumptionIEEE Expert, 1997