Most water utilities have to handle a substantial number of customer complaints every year. Traditionally, complaints are handled by skilled staff who know how to identify primary issues, classify complaints, find solutions, and communicate with customers. The effort associated with complaint processing is often great, depending on the number of customers served by a water utility. However, the rise of natural language processing (NLP), enabled by deep learning, and especially the use of deep recurrent and convolutional neural networks, has created new opportunities for comprehending and interpreting text complaints. As such, we aim to investigate the value of the use of NLP for processing customer complaints. Through a case study about the Water Utility Groningen in the Netherlands, we demonstrate that NLP can parse language structures and extract intents and sentiments from customer complaints. As a result, this study represents a critical and fundamental step toward fully automating consumer complaint processing for water utilities.

Open water systems such as irrigation canals are used to transport and deliver water from the source to the user.Water loss in these systems by seepage, leakage, evaporation, or unknown water offtakes can be large. If this loss is unknown to the model used, it will not be considered by the controller and create a real system model mismatch. This mismatch will affect the water level directly and create an offset from the reference set point of the water level. A control configuration for open water canals, model predictive control (MPC) based on moving horizon estimation (MHE-MPC), to deal with offset problems resulting from real system-model mismatch is described in this paper. MHE uses the past predictions of the model and the past measurements of the system to estimate unknown disturbances and systematically removes the offset in the controlled water level. This control configuration is numerically tested on an accurate hydrodynamic model of the Control Algorithms Test Canal of the Technical University of Catalonia (UPC-PAC). The results presented in this paper show that MHE-MPC can realize offset-free control and the results are better than those of the well-known disturbance modelling offset-free control scheme.