Edevar Luvizotto

Hybrid regression model for near real-time urban water demand forecasting

The most important factor in planning and operating water distribution systems is satisfying consumer demand. This means continuously providing users with quality water in adequate volumes at reasonable pressure, thus ensuring reliable water distribution. In recent years, the application of statistical, machine learning, and artificial intelligence methodologies has been fostered for water demand forecasting. However, there is still room for improvement; and new challenges regarding on-line predictive models for water demand have appeared. This work proposes applying support vector regression, as one of the currently better machine learning options for short-term water demand forecasting, to build a base prediction. On this model, a Fourier time series process is built to improve the base prediction. This addition produces a tool able to eliminate many of the errors and much of the bias inherent in a fixed regression structure when responding to new incoming time series data. The final hybrid process is validated using demand data from a water utility in Franca, Brazil. Our model, being a near real-time model for water demand, may be directly exploited in water management decision-making processes.

Social Network Community Detection for DMA Creation: Criteria Analysis through Multilevel Optimization

Management of large water distribution systems can be improved by dividing their networks into so-called district metered areas (DMAs). However, such divisions must be based on appropriated technical criteria. Considering the importance of deeply understanding the relationship between DMA creation and these criteria, this work proposes a performance analysis of DMA generation that takes into account such indicators as resilience index, demand similarity, pressure uniformity, water age (and thus water quality), solution implantation costs, and electrical consumption. To cope with the complexity of the problem, suitable mathematical techniques are proposed in this paper. We use a social community detection technique to define the sectors, and then a multilevel particle swarm optimization approach is applied to find the optimal placement and operating point of the necessary devices. The results obtained by implementing the methodology in a real water supply network show its validity and the meaningful influence on the final result of, especially, elevation and pipe length.

Hybrid SOM+k-Means clustering to improve planning, operation and management in water distribution systems

Abstract With the advance of new technologies and emergence of the concept of the smart city, there has been a dramatic increase in available information. Water distribution systems (WDSs) in which databases can be updated every few minutes are no exception. Suitable techniques to evaluate available information and produce optimized responses are necessary for planning, operation, and management. This can help identify critical characteristics, such as leakage patterns, pipes to be replaced, and other features. This paper presents a clustering method based on self-organizing maps coupled with k-means algorithms to achieve groups that can be easily labeled and used for WDS decision-making. Three case-studies are presented, namely a classification of Brazilian cities in terms of their water utilities; district metered area creation to improve pressure control; and transient pressure signal analysis to identify burst pipes. In the three cases, this hybrid technique produces excellent results.

Calibration Model for Water Distribution Network Using Pressures Estimated by Artificial Neural Networks

The success of hydraulic simulation models of water distribution networks is associated with the ability of these models to represent real systems accurately. To achieve this, the calibration phase is essential. Current calibration methods are based on minimizing the error between measured and simulated values of pressure and flow. This minimization is based on a search of parameter values to be calibrated, including pipe roughness, nodal demand, and leakage flow. The resulting hydraulic problem contains several variables. In addition, a limited set of known monitored pressure and flow values creates an indeterminate problem with more variables than equations. Seeking to address the lack of monitored data for the calibration of Water Distribution Networks (WDNs), this paper uses a meta-model based on an Artificial Neural Network (ANN) to estimate pressure on all nodes of a network. The calibration of pipe roughness applies a metaheuristic search method called Particle Swarm Optimization (PSO) to minimize the objective function represented by the difference between simulated and forecasted pressure values. The proposed method is evaluated at steady state and over an extended period for a real District Metering Area (DMA), named Campos do Conde II, and the hypothetical network named C-town, which is used as a benchmark for calibration studies.

Leakage Control and Energy Recovery Using Variable Speed Pumps as Turbines

AbstractOne of the primary concerns in water supply systems is pressure control. High pressure increases both leakage and the risk of pipes bursting, while low pressure can reduce the water supplie...

PSO Applied to Reduce the Cost of Energy in Water Supply Networks

The growth of urban population and subsequent expansion of the cities impose difficulties of gather a reliable water supply systems that attend the fluctuations of demand throughout the day, and their operation with appropriate hydraulic and operational parameters. The search of better routines for water pumping stations with both starting and stopping of pumps or use of variable speed devices has become increasingly common, and the motivation of this search is found in the need for energy saving. But the task is arduous and becomes fertile field for the application of modern techniques and robust optimization. Noteworthy are currently those that seek their inspiration in nature systems, such as Particle Swarm Optimization, which is based on intelligence of groups, such as schools of fish or swarms of bee. By this way, the present work aims to contribute to the topic, developing a hybrid algorithm (simulator-optimizer) for determination of optimized routines for pumping station i.e., routines that seek the best operational routine for an extended period of 24 hours.

Correlation Analysis of Water Demand and Predictive Variables for Short-Term Forecasting Models

Operational and economic aspects of water distribution make water demand forecasting paramount for water distribution systems (WDSs) management. However, water demand introduces high levels of uncertainty in WDS hydraulic models. As a result, there is growing interest in developing accurate methodologies for water demand forecasting. Several mathematical models can serve this purpose. One crucial aspect is the use of suitable predictive variables. The most used predictive variables involve weather and social aspects. To improve the interrelation knowledge between water demand and various predictive variables, this study applies three algorithms, namely, classical Principal Component Analysis (PCA) and machine learning powerful algorithms such as Self-Organizing Maps (SOMs) and Random Forest (RF). We show that these last algorithms help corroborate the results found by PCA, while they are able to unveil hidden features for PCA, due to their ability to cope with nonlinearities. This paper presents a correlation study of three district metered areas (DMAs) from Franca, a Brazilian city, exploring weather and social variables to improve the knowledge of residential demand for water. For the three DMAs, temperature, relative humidity, and hour of the day appear to be the most important predictive variables to build an accurate regression model.