Embracing Analytics in the Drinking Water Industry / Juneseok Lee.

Format:

Book

Author/Creator:

Lee, Juneseok, author.

Contributor:

Keck, Jonathan, editor.

Language:

English

Subjects (All):

Water--Analysis.

Water.

Physical Description:

1 online resource (xiv, 423 pages)

Edition:

1st ed.

Place of Publication:

IWA Publishing 2022

London : IWA Publishing, 2022.

Language Note:

English.

Summary:

Analytics can support numerous aspects of water industry planning, management, and operations. Given this wide range of touchpoints and applications, it is becoming increasingly imperative that the championship and capability of broad-based analytics needs to be developed and practically integrated to address the current and transitional challenges facing the drinking water industry. Analytics will contribute substantially to future efforts to provide innovative solutions that make the water industry more sustainable and resilient. The purpose of this book is to introduce analytics to practicing water engineers so they can deploy the covered subjects, approaches, and detailed techniques in their daily operations, management, and decision-making processes. Also, undergraduate students as well as early graduate students who are in the water concentrations will be exposed to established analytical techniques, along with many methods that are currently considered to be new or emerging/maturing. This book covers a broad spectrum of water industry analytics topics in an easy-to-follow manner. The overall background and contexts are motivated by (and directly drawn from) actual water utility projects that the authors have worked on numerous recent years. The authors strongly believe that the water industry should embrace and integrate data-driven fundamentals and methods into their daily operations and decision-making process(es) to replace established rule-of-thumb and weak heuristic approaches and an analytics viewpoint, approach, and culture is key to this industry transformation.

Contents:

Intro

Cover

Contents

Preface

Chapter 1: Introduction

1.1 WHAT IS ANALYTICS?

1.2 HOW CAN ANALYTICS HELP THE WATER INDUSTRY?

1.3 EFFECTIVE UTILITY MANAGEMENT

1.3.1 Foundational element #1 - attributes of effectively managed water sector utilities

1.3.2 Foundational element #2 - keys to management success

1.3.2.1 Leadership

1.3.2.2 Strategic business planning

1.3.2.3 Organizational approaches

1.3.2.4 Measurement

1.3.2.5 Continual improvement management framework

1.3.3 Foundational element #3 - water utility measures

1.3.4 Foundational element #4 - water utility management resources

1.4 EFFECTIVE UTILITY MANAGEMENT (EUM) AND WATER ANALYTICS

1.4.1 Supply and demand management

1.4.2 Enterprise asset management

1.4.3 Distribution system modeling

1.4.4 Long-range planning

1.4.5 Systems optimization

1.5 RECOMMENDATIONS

1.5.1 Analytics leadership

1.5.2 Cultural importance

1.5.3 Capacity planning

1.5.4 Systems and structure

1.5.5 Tools and technology

1.5.6 Professional development and collaborative research

1.6 A CLEAR FUTURE FOR ANALYTICS

1.7 ROADMAP OF THE BOOK

1.7.1 Planning section

1.7.2 Operations section

1.7.3 Management section

REFERENCES

Part I: Planning

Chapter 2: Water demand analysis | regression

LEARNING OBJECTIVES

2.1 INTRODUCTION

2.2 PRINCIPLES OF REGRESSION

2.2.1 What is regression?

2.2.2 Basic regression equation - water demand and lot size example

2.2.3 OLS assumptions

2.2.3.1 Assuming linearity

2.2.3.2 Assuming independence between explanatory variables (multicollinearity)

2.2.3.3 Independent observations

2.2.3.4 Several assumptions dealing with error term

2.2.4 Panel data regression

2.2.5 Multiple regression

2.2.5.1 Problem 1

2.2.5.2 Brief suggested solutions

2.3 MODEL SPECIFICATION.

2.3.1 Water use relationships

2.3.2 Data exploration

2.3.2.1 Data collection

2.3.2.2 Data time series length

2.3.2.3 Data management and cleaning

2.3.2.4 Descriptive statistics and visualizations

2.3.3 Level of aggregation

2.3.4 Data range and variation

2.3.5 Misspecification

2.3.5.1 Problem 2

2.4 ESTIMATING PARAMETERS

2.4.1 Panel regression - pooled, fixed effects, and random effects

2.4.2 Estimation example walk-through problem in R

2.5 INTERPRETATION

2.5.1 Regression example - forecasting

2.5.2 Regression example - metering impacts

2.5.3 Presentation of results

2.5.3.1 Problem 3

2.5.3.2 Brief suggested answer

2.6 CONCLUSION

Chapter 3: Water demand forecasting - machine learning

3.1 INTRODUCTION

3.2 DATA

3.2.1 Data collection

3.2.2 Data cleaning

3.2.3 Feature engineering

3.2.4 Feature selection

3.2.5 Data transformations

3.3 MODEL BUILDING

3.3.1 Model selection

3.3.2 Hyperparameter optimization

3.3.3 Training, validation, and testing

3.4 MODEL EVALUATION

3.4.1 Model accuracy

3.4.2 Model interpretability

3.5 MODEL DEPLOYMENT

3.6 TOOLS AND SOFTWARE

3.6.1 Prerequisites

3.6.2 Useful tools, packages, and APIs

3.7 PRACTICAL EXAMPLES

3.7.1 Installation

3.7.2 Example 1: A simple model for demand forecasting

3.7.3 Installing and loading R packages

3.7.4 Get and preprocess the data

3.7.5 Model training and testing

3.7.6 Questions

3.7.7 PDP and ICE plots

3.8 CONCLUSION

Chapter 4: Water demand forecasting | time series data

4.1 INTRODUCTION

4.2 TIME SERIES DATA ANALYSIS

4.2.1 ARIMA model

4.2.2 SARIMA model

4.2.3 Creating ARIMA/SARIMA models using econometric toolbox

4.2.4 Forecasting

4.2.5 Limitations.

4.3 MACHINE LEARNING TIME SERIES

4.3.1 Machine learning

4.3.1.1 Artificial neural network

4.3.1.2 Support vector machine

4.3.1.3 Forecasting

4.3.2 Practice problems

4.4 DEEP LEARNING TIME SERIES

4.4.1 Deep learning models

4.4.1.1 Convolutional neural network

4.4.1.2 Recurrent neural network

4.4.2 Practice problems

4.5 OTHER POPULAR ML TECHNIQUES

4.5.1 Ensemble learning

4.5.1.1 Water end use dataset

4.5.1.2 Bootstrapping

4.5.1.3 Bagging

4.5.1.4 Random forest

Chapter 5: Use of cost-benefit analysis (CBA) in water infrastructure

5.1 INTRODUCTION

5.2 CONTRIBUTION OF CBA TO WATER POLICYMAKING

5.2.1 Imperatives of water scarcity: demand management or supply enhancement?

5.2.2 CBA as a decision-making tool

5.2.3 Policy background

5.3 CBA METHODS

5.3.1 Building a spreadsheet of the CBA model

5.3.2 Identifying and measuring the benefits

5.3.3 Identifying and measuring the costs

5.3.4 Time horizon and discount and interest rates

5.4 CBA IN PRACTICE

5.4.1 CBA of reservoir construction

5.4.2 CBA of rainwater harvesting systems (RWHS)

5.5 CONCLUSION

Part II: Operations

Chapter 6: Water quality modeling and analysis

6.1 INTRODUCTION

6.2 EPANET AND EPANET-MSX SOFTWARE

6.3 CREATING AN EPANET NETWORK FILE

6.4 MODELING WATER AGE AND SINGLE-SPECIES WATER QUALITY ON EPANET

6.5 MODELING MULTIPLE SPECIES USING EPANET-MSX

6.6 RUNNING EPANET-MSX SOFTWARE AND CALIBRATING RESULTS TO SAMPLED DATA

6.7 MODEL STATISTICAL VERIFICATION

6.8 CONCLUSION

Chapter 7: Calibration and uncertainty analysis of hydraulic models

7.1 INTRODUCTION

7.2 UNCERTAIN PARAMETERS IN PIPE NETWORK ANALYSIS

7.2.1 Pipe roughness coefficients

7.2.2 Nodal demands.

7.2.3 Pipe diameters

7.2.4 Leakage parameters

7.2.5 Boundary conditions, tanks, valves and pump characteristics

7.3 REVIEW ON CALIBRATION STEPS

7.3.1 Identifying the intended use of the model

7.3.2 Determining initial estimation of model parameters

7.3.3 Collecting calibration data

7.3.4 Evaluating model results

7.3.5 Performing macro-level calibration

7.3.6 Performing sensitivity analysis

7.3.7 Micro-calibration

7.4 AUTOMATIC CALIBRATION

7.4.1 Conceptual framework

7.4.2 Dynamic link for the simulation-optimization model

7.4.3 Mathematical statement of the problem

7.4.3.1 Actual decision variables

7.4.3.2 Objective function

7.4.3.3 Constraints

7.5 EXAMPLE 7.1: CALIBRATION OF ANYTOWN MODIFIED NETWORK

7.5.1 Optimization model: genetic algorithm

7.5.2 Optimization model setting

7.5.3 Model execution and results

7.6 PARAMETER UNCERTAINTY ANALYSIS IN PIPE NETWORK MODELING

7.6.1 Does UA search for the most pessimistic combination of parameters?

7.6.2 Approaches for parameter UA

7.6.3 Interval analysis (IA) for parameter UA

7.6.3.1 Impact Table Method

7.7 EXAMPLE 7.2: INTERVAL ANALYSIS FOR THE ATM NETWORK

7.7.1 Producing the impact table

7.7.2 Calculating the extreme pressure heads

7.8 CONCLUSION

Chapter 8: Optimal pump operation

8.1 INTRODUCTION

8.2 A BRIEF REVIEW ON PUMP PERFORMANCE

8.2.1 Head-flow characteristics

8.2.2 Power-flow characteristics

8.2.3 Efficiency-flow characteristics

8.2.4 NPSH-flow characteristics

8.2.5 System's curve and pump duty-point

8.2.6 Affinity laws for rotational speed

8.2.6.1 Example 8.1

8.3 MAIN CONSIDERATIONS FOR OPTIMAL PUMP OPERATION

8.3.1 BEP and minimum efficiency

8.3.2 Pump discharge range

8.3.3 Pump speed

8.3.4 Pump switches and daily working hours.

8.4 PUMP OPERATION CONTROL

8.4.1 Change in system curve

8.4.2 Change in characteristic curve

8.5 OPTIMAL PUMP SCHEDULING

8.5.1 Simulation-optimization approach

8.5.2 Optimization objectives

8.5.3 Pump scheduling approaches: CSP vs. VSP

8.5.4 Example 8.2 - CSP approach

8.5.4.1 Objective function

8.5.4.2 Decision variables and decision vector

8.5.4.3 Constraints

8.5.4.4 Constraint handling

8.5.4.5 GA settings and execution

8.5.4.6 Results

8.5.4.7 Challenges and opportunities

8.5.5 Example 8.3 - VSP approach

8.5.5.1 Objective function

8.5.5.2 Decision vector

8.5.5.3 Constraints

8.5.5.4 Model execution and results

8.5.5.5 Challenges and opportunities

8.6 VSP SCHEDULING

EWQMS APPROACH

8.6.1 EWQMS for ATM network - A single objective optimization approach

8.6.1.1 Example 8.4A

8.6.1.2 Example 8.4B: VSP scheduling with WAM constraint

8.6.1.3 Example 8.4C: VSP scheduling for WAM minimization

8.6.2 EWQMS for ATM network - A multi-objective optimization approach

8.6.2.1 General concept of multi-objective optimization

8.6.2.2 Example 8.5: VSP scheduling for energy cost vs WAM minimization

8.7 CONCLUSION

Chapter 9: Hydraulic transients in pipe systems

9.1 INTRODUCTION

9.2 NUMERICAL METHOD CONSIDERING INITIAL AND BOUNDARY CONDITIONS

9.2.1 Reservoir

9.2.2 Junctions

9.2.3 Discretization error

9.2.4 Truncation error

9.2.5 Consistency

9.2.6 Convergence

9.2.7 Stability

9.2.8 CFL (Courant Friedrich Lewy) stability condition

9.2.9 Example

9.2.9.1 Given

9.2.9.2 Find

9.2.9.3 Solution

9.3 OTHER PHENOMENON OF INTERESTS | CAVITATION AND COLUMN SEPARATION

9.3.1 Discrete vapor cavity model (DVCM)

9.3.2 Short term pressure peaks following cavity collapse.

9.4 TRANSIENT SIMULATIONS IN WATER DISTRIBUTION NETWORKS: TSNet.

Notes:

CC BY-NC-ND

Description based on online resource; title from PDF title page (IWA Publishing, viewed March 25, 2023).

Description based on publisher supplied metadata and other sources.

OCLC:

1348377808

Publisher Number:

https://doi.org/10.2166/9781789062380