Content uploaded by Lakshmi Kanthan Narayanan
Author content
All content in this area was uploaded by Lakshmi Kanthan Narayanan on Aug 06, 2021
Content may be subject to copyright.
IoT-based water demand forecasting and distribution
design for smart city
Lakshmi Kanthan Narayanan and Suresh Sankaranarayanan
ABSTRACT
The percentage of fresh water resource availability in the world is diminishing every year. According
to a world economic forum survey, the increase in water demand will result in high scarcity globally
in the next two decades. The eradication of the water demand increase and reducing the losses
during the transportation of water is challenging. Thus accordingly, an Internet of Things (IoT)-based
architecture integrated with Fog for underground water distribution system has been proposed.
Towards designing an IoT water distribution architecture for a smart city, we need to first forecast the
water demand for consumers. Hence, accordingly, water demand forecasting has been carried out
on a daily basis for a period of three months as a case study using autoregressive integrated moving
average (ARIMA) and regression analysis. Based on water demand forecasting analysis, a water
distribution design for an IoT-based architecture has been carried out using hydraulic engineering
design for proper distribution of water with minimal losses which would result in the development of
a smart water distribution system (SWDS). This has been carried out using EPANET.
Lakshmi Kanthan Narayanan
Suresh Sankaranarayanan (corresponding
author)
SRM Institute of Science and Technology,
Kattankulathur,
Chennai, Tamilnadu 603203
India
E-mail: sureshs3@srmist.edu.in
Key words |ARIMA, EPANET, Fog, IoT, SWDS
INTRODUCTION
The International Water Association (IWA) states that water
loss management has achieved increased attention. The rec-
ommendations of IWA have proposed new methods for
modelling leakage detection and loss management com-
ponents (Gupta et al. ).
The common problem that occurs during the transpor-
tation of water from the source via underground pipes to
consumers is transportation loss. The losses are mainly
due to the fittings of the pipe network, leakages, breaks
and cracks in the pipe, overflow in the main tanks/sub-
tanks, pressure loss and obstruction due to sediments or
blocks in pipes.
The construction of smart water distribution system
(SWDS) architecture for a smart city is done with storage
reservoirs, booster pumping stations, fire hydrants and consu-
mer service lines and redundancy of the network is provided
via smart water grids and loops (Bibri &Krogstie ). In the
past, the water distribution models used fuzzy-based
decisions in the estimation of flow rate (Zischg et al. ).
The impact of Cloud computing has played a vital role in
bringing the concept of Internet of Things (IoT) into reality.
But at the same time, Cloud computing cannot be integrated
into all the IoT-based systems. The data acquired from the
sensors need to be processed in real time for providing
quick control action for the industrial IoT devices. Fog com-
puting has achieved many more advantages over Cloud
computing, such as low latency, less computational delay
and less bandwidth operation (Bonomi et al. ;Veerama-
nikandan & Sankaranarayanan ).
Thus, accordingly, an IoT-based underground water dis-
tribution architecture integrated with Fog computing and
Cloud has been proposed (Narayanan & Sankaranarayanan
) where the real-time processing happens at the Edge,
also called Fog computing, based on the sensor data
1411 © IWA Publishing 2020 Journal of Water and Climate Change |11.4 |2020
doi: 10.2166/wcc.2019.019
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
captured from underground pipes for control action at the
substation. The Cloud is responsible for storing all historical
information and other pertinent information for Big Data
analyses.
Towards designing such an IoT-based underground water
distribution architecture for a smart city with minimal trans-
portation losses, we first need to understand and study
consumer behaviour towards water consumption based on
the historical data available. Thus, the water demand predic-
tion was made for daily consumption over a three-month
period as a case study using autoregressive integrated
moving average (ARIMA) and linear regression with com-
parative analysis. Based on the demand prediction, an
effective and efficient water distribution system has been
designed on the basis of day-wise water demand prediction,
which will resolve issues related towater distribution. Figure 1
shows a sample water distribution system (www.epa.gov).
The main contributions of the paper are as follows.
(1) Statistical analysis of water consumption data and
demand forecasting using ARIMA and regression.
(2) Comparative analysis on statistical model towards
demand forecasting.
(3) Designing of water distribution in IoT-based water
distribution architecture using EPANET-based on the
demand forecasting.
The remaining section of the paper is organized as
follows. The next section presents a complete literature
survey on various technologies adapted in water distribution
and demand forecasting methods. This is followed by a sec-
tion discussing in detail the construction of IoT-based WDS
design with the integration of Fog and Cloud computing
along with demand forecasting-based WDN construction.
The statistical methods adopted for the demand forecasting
are presented in the next section. Then a section deals with
the comparative analysis between ARIMA and linear
regression and water distribution design based on the fore-
cast using EPANET. The final section presents the
conclusions and future work.
LITERATURE REVIEW
Much research has been carried out on designing an IoT-
based WDS using sensors in order to monitor the supply
Figure 1 |Water distribution system (courtesy of United States Environmental Protection Agency).
1412 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution design for smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
and quality of water. This WDS will display real-time water
consumed by customers (Perera et al. ).
For a block of apartments, the WDS is built with a series
of interconnected sensors, which are deployed in the pipe
network in order to measure the flow and consumption in
the system. The consumed data are sent to the Cloud
which will perform the task of intimating the customer
regarding their consumption (Amatulla et al. ).
Research has been carried out in constructing an effec-
tive distribution system for rural distribution networks
with a combination of ultrasonic and conductivity sensors
for assessing the water level and quality of water in the dis-
tribution tanks, respectively. In this system, the measured
data are sent to a mobile-based application for further
assessment (Chanda et al. ).
An IoT-based distribution prototype was designed by
Amatulla (Amatulla et al. ) for smart cities. This
system is purely a microprocessor-based monitoring system
where the periodically monitored data are transmitted
through Wi-Fi to the web-based system which is remotely
located (Varma et al.). Ultrasonic sensors are also
used in the water management system (WMS) for identifying
the level of water in the tanks (Candelieri & Archetti ).
Similarly, in the WDS, the sensors are also deployed in
the external pipes that connects the apartment or commu-
nity in order to monitor the amount of water distributed to
each individual household. These data are transmitted
through Wi-Fi to the Cloud platform for further analysis
and graphical report generation (Laspidou et al. ).
The above-discussed water distribution systems are only
IoT-based monitoring systems in which no intelligence and
control automation is involved.
The following paragraphs will discuss in detail research
work that has been carried out by employing machine learn-
ing (ML) and deep learning (DL).
The usage of time series analysis plays a vital role in fore-
casting and prediction. Data clustering is executed by using
time series analysis. Support vector machine regression is
implemented over hourly water consumption data observed
from test-bed setup. This characterization pattern method is
validated over the urban demand of the water distribution net-
work (WDN) of the city of Milan (Gwaivangmin & Jiya ).
Feature extraction of water demand pattern is done by
the construction of Kohonen self-organizing maps. This
analysis is purely dependent upon consumers’bills. This
characterization enables autonomous classification on the
basis of consumption of water by the consumers. This con-
sumption pattern analysis was carried out with the
consumers of the Greek island of Skiathos (Herrera et al.
).
An artificial neural network is deployed over a distri-
bution and control design based on the supervisory
control. This system is designed on the basis of a case
study done in Nigeria. The ultimate aim of this system is
to provide an optimal solution towards WDN in order to
solve the issues that arise due to water scarcity (Chen &
Boccelli ).
Water consumption and demand forecasting of a resi-
dential tower in Korea was used as a case study analysis.
The average consumption over the period of 2012 to 2014
was carried out and used as a training input for the predic-
tion model. This resulted in the construction of a decision-
making model for water distribution (Rinaudo ).
Environmental variables such as humidity, rainfall,
temperature, and atmospheric pressure were left out by
implementing multiple kernel regression algorithms for
daily water demand prediction in order to improve the accu-
racy and computational efficiency of the system which
resulted in the design of a decision-making system for a
smart city (Herrera et al. ).
A computational frame for the analysis of water demand
in urban areas is implemented by using a machine learning
approach called regression analysis. It is implemented in
two stages. The first stage is clustering of consumption
data on the basis of consumption pattern or behaviour.
A time series forecasting framework was implemented
for statistical forecasting of short-term water demands
using fixed seasonal autoregressive model and adaptive sea-
sonal autoregressive model for predicting real demand of
consumers in a real-world scenario using prototype models
(Candelieri & Archetti ).
Multivariate statistical modelling and microcomponent
modelling are the two adaptive techniques that were utilized
in long-term forecasting of water demand prediction
(Laspidou et al. ).
From the above examples, there were some develop-
ments and research pertaining to an IoT-based monitoring
system for water distribution without integration of Fog
1413 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution design for smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
and intelligence. Also, those systems were not designed for
an underground water distribution system for a smart city.
In addition, regarding water demand forecasting, long-
term predictions were done based on water consumption
data collected from various sources like data source organiz-
ations, water meters or from test-bed setup.
In none of these systems discussed above, had water
demand forecasting been carried out on a daily basis for a
short term based on available daily water consumption his-
toric data. In addition, water demand forecasting was not
integrated with water distribution system design for an effi-
cient and optimal distribution of water to the consumers
in a smart city concept without wastage of water.
Accordingly, we will be discussing in the forthcoming
sections, the proposal of an IoT-based water distribution
architecture integrated with Fog and Cloud, followed by
water demand forecasting and water distribution design in
detail.
IOT-BASED WATER DISTRIBUTION ARCHITECTURE
In the real-world scenario, there are many independent
systems which are used for demand prediction, water distri-
bution automation, monitoring the distribution, estimation
of supply, quality evaluation, etc. However, all these systems
are independently designed for specific applications.
In India, currently, there are no concrete systems in
practice since they are more than 100 years old. There are
only a few systems in practice in order to perform under-
ground pipe monitoring such as in oil refineries, mines, etc.
Taking these points into consideration and with the
advent of IoT and Fog computing, an IoT-based water distri-
bution architecture integrated with Fog and Cloud is
proposed (Narayanan & Sankaranarayanan ) with the
ultimate aim of providing cost-effective, highly reliable archi-
tecture for water distribution and underground pipe health
monitoring based on the predicted water demand and deter-
mined hydraulic parameters. There are various variable
components, such as climate, season, rainfall, family type,
which can have a huge impact on the decision-making
system in the determination of consumer demand. The fol-
lowing are the essential goals that need to be satisfied for
a water distribution system:
(1) The water distribution system (WDS) should understand
the consumer demands and hydraulic parameters which
are dependent on geographical topology.
(2) The WMS should be aware of the basics of supply
requirements as well as demand. It should also investi-
gate the purpose of the application.
(3) The WMS should be thoroughly trained with the intake
structure, source of supply and also WDN (WDN)
structure.
(4) The WDS should be fed with complete information
about the material types and controlling mechanism
used in the system.
Figure 2 illustrates an IoT-based architecture for water
distribution and underground pipe health monitoring
system. Figure 3 shows a sample community-based WDS.
Water distribution system
Based on the IoT-based architecture for a WDS, the design
of the water distribution system is important and a key
task in distribution of water to consumers. This design in
the architecture is based on demand prediction which is
based on historical data of water consumption and, accord-
ingly, supply of water will be initiated by the local SCADA
engineer from the substation.
Hence, predicting the water demand for consumers
with regards to water distribution design, we need to look
into methodologies pertaining to water demand prediction
based on historical water consumption data which are
discussed below.
WATER DEMAND FORECASTING
The water demand forecast is performed using statistical
models of forecasting algorithms, namely, ARIMA and linear
regression. For the prediction of water demand and analysis,
a dataset of day-to-day water consumption of people residing
in the city of Austin (Texas, USA) is taken into account.
The dataset contains the aggregated reading of water
consumption on a daily basis. The dataset also consists of
two maximum consumptions, namely, Peak-1 and Peak-2
consumption during peak hours of the day. The dataset
1414 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution design for smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
detailed account is provided by US government data (www.
data.gov). The dataset contains eight years and three
months of readings from 1 January 2010 to 31 March
2018. Figure 4 illustrates the consumption of water by the
people of Austin over the period January 2010 to March
2018.
We will now discuss in detail the methodology of the
two algorithms –ARIMA and linear regression –regarding
prediction and analysis on historical water consumption
data over a period of eight years.
ARIMA for demand prediction
An ARIMA algorithm has the ultimate aim of performing
statistical analysis of seasonal data regarding data arrange-
ment based on the time pattern globally known as time
Figure 2 |IoT-based architecture for WDS and underground pipe health monitoring (Narayanan & Sankaranarayanan 2019).
Figure 3 |A community-based WDS (courtesy of Prince Mohammad Bin Fahd University) (www.pmu.edu).
1415 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution design for smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
series analysis. This analysis is done to determine the trend
of data, seasonality of occurrences, moving average and to
evaluate the algorithmic performance on the basis of deter-
mining and analysing error.
Box and Jenkins performed a wide range of analysis
using ARIMA. There are three phases that are involved in
the Box–Jenkins analysis model (Tom et al.).
Phase-I: data identification
The primary and initial step of the Box–Jenkins model is
preparation of data. In this phase, the data are transformed
in order to make the data series stationary and to stabilize
the variance.
Model selection is the continuous process of this phase
in which the partial autocorrelation function (PACF) and
ACF are carried out in order to find the optimal model.
Phase-II: estimation of parameters and testing
In this phase, the parameters are estimated in all the poss-
ible models and the best-fit model is chosen on the basis
of optimal criteria. This step is followed by diagnostics,
where the residuals are diagnosed by portmanteau test and
PACF/ACF is also verified. The residuals are verified
whether it is a white noise or not. If the residuals are
found to be white noise, then Phase III is carried out, else
the procedures in Phase I are repeated.
Phase-III: data forecasting
In this phase, the data is being forecasted. In the procedure of
time series analysis, the pattern is decomposed into simpler
form or should be divided into sub-patterns. The data is
assumed as a function of seasonality, error and trend cycle.
Phase-IV: data decomposition modelling
In time series analysis, data are always defined as a function
of error, trend cycle and seasonality component which is
expressed as:
Zt¼f(St,Et,Tt) (1)
In general, the additive form of decomposition is deter-
mined by computing the sum of all the components. The
additive form is represented as:
Zt¼StþEtþTt(2)
This decomposition is applicable only if the seasonal
functions maintain a constant pattern, i.e., no rapid decrease
Figure 4 |Aggregate consumption of the city of Austin over a period of eight years.
1416 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution design for smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
or increase in functional component over a period of time.
Here, the water consumption is a seasonal dependent func-
tion where the consumption rate varies with respect to
seasons of a year. Hence, the decomposition is multiplica-
tive in nature.
ZT¼STEtTt(3)
This is further transformed into additive model by taking
the log of the series in order to derive the additive relation-
ship from the multiplicative relationship.
logZt¼logStlogEtlogTt(4)
Smoothing of data is done to obtain trend-cycle by redu-
cing the random variations. The simple way of smoothing
the time series is moving average (MA). The expression of
MA is as follows:
Tt¼1
KX
m
j¼m
Ztþj, where m¼(Kþ1)
2(5)
Here, MA is determined as first order of k, where kis an
integer. It is suitable for calculating an odd number of obser-
vations. For computing MA for six-month observations, the
following equations are derived.
Example of 2 ×6MA:
T2:5¼(Z1þZ2þZ3þZ4þZ5þZ6)
6(6)
T3:5¼(Z2þZ3þZ4þZ5þZ6þZ7)
6(7)
On averaging these two 6 MA smoothers:
T0
3¼(T2:5þT3:5)
2(8)
T0
3¼(Zþ2Z2þ2Z3þ2Z4þ2Z5þ2Z6þ2Z7)
12 (9)
Figure 5 illustrates the 7 MA, i.e., 7 day moving average
applied over the water consumption dataset in order to ana-
lyze the trend for the next 7 days and how it is used in the
process of decomposition. This is beneficial for water
demand prediction on a daily basis over a three-month
period.
Figure 6 describes the trend and seasonality pattern. A
good prediction or data forecasting model will have resi-
dues or forecast errors as described in the following
equation:
Zt¼etþC(10)
Statonarity testing
Dickey–Fuller testing is widely used in practice to test the
stationarity in time series data (Figure 7). It is highly essen-
tial to satisfy the unit root testing method. The primary step
is estimation of the regression model.
Zt¼∅Zt1þb1Zt1þb2Zt2þ...þbpZtp(11)
where ∅value is 4.68, which means Z
t
is stationary. Hence,
Z
t
0is denoted as differential series of Z
t
–Z
t-1
.
Figure 5 |Seven days MA for the 2018 dataset.
1417 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution design for smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
Figure 6 |The decomposition of time series: (a) trend, (b) seasonality, (c) error component.
1418 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution design for smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
Prediction/forecasting
In order to perform prediction, this model used the seasonal
ARIMA: (SARIMA) as
SARIMA ¼(p,d,q)(P,D,Q)S(12)
where sis no. of periods per season, pis order of auto-
regression (AR), dis degree of data differencing (I) invoked
and q is order of moving average (MA).
The general ARIMA (1, 1, 1) (1, 1, 1)
12
model is
expressed as follows:
(1 ∅1B12)(1 ∅1B12 )(1 B)(1 B12)Zt
¼(1 θ1B)(1 θ1B12)et(13)
Here Bis the lag factor, the values of ∅1,θ1are par-
ameters of autoregressive and moving average and used
for forecasting. These steps are applied to the daily water
consumption dataset for a period of eight years in order to
predict their consumption pattern. This work aims to predict
the water demand on a daily basis for the next three months.
The demand forecast analysis and accuracy is discussed in
the Results and discussion section.
Least square linear regression
Linear regression is a statistical model which is used to derive
the relationship between two variables and also helps to
determine the impact of one variable over the other. Here,
the water consumption is one variable, which is impacted
by the change in date/month of year. The regression model
is expressed in terms of association between variables X
and Y. The algorithmic representation of this association is
expressed in terms of a straight line as follows:
Y¼aþbX (14)
Here, ais the intercept of Y and bis the slope of the line.
If the line is a fair line which intercepts the variables X and
Y, and also if the line obtained is a fairly flat line, then the
slope will be small and also the rise of the line obtained will
be smaller than the run. The expression to determine slope is:
slope of line ¼rise
run (15)
slope ¼b¼rise
run ¼Y2Y1
X2X1
(16)
Forecasting through least square regression lines
In the water demand forecasting model, the X axis is
assumed as an independent variable called date and the
consumption variable is assumed as Y. In this dataset,
there is no implication to say that Yis the resultant of X.
The following expression is used to determine the
regression line:
^
Y¼aþbX (17)
Figure 7 |Stationarity testing using Dickey–Fuller test.
1419 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution designfor smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
Here, Xis the observed value of independent variable
called date and ^
Yis the dependent variable of Y called
consumption.
The least square criterion is determined through the fol-
lowing algebraic equation. Here, consider there are ‘n’
observed points for both X and Y variables with a range
from 1 to n. Then for the ‘i’observations, the difference or
deviation between the predicted and observed value can
be formulated as:
ei¼Yi^
Yi(18)
Figure 8 |Decomposition of linear regression: (a) trend, (b) plot of residual water usage, (c) normalized residuals, (d) error plot vs residuals. (Continued.)
1420 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution designfor smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
In order to determine the best-fit points to the demand
prediction curve, the positive and the negative errors get
cancelled and the error ∑e
i
¼0.
Figure 8 shows the decomposition of linear regression
on water consumption dataset illustrating the trend, residual
water usage, normalized residuals and plot of error versus
residual.
Figure 9 shows the best fit regression line for water
demand prediction on a daily basis for the period of three
months which is January–March 2018. The result is 0.2698
which shows that it is a good fit. Best fit should lie between
0 and 1 (www.ncss.com).
RESULTS AND DISCUSSION
Based on ARIMA and least square linear regression method
applied for demand forecasting on water consumption dataset,
this section discusses demand forecast result analysis in terms
of error rate accuracy. Based on the demand forecast, the
WDS will be designed for IoT architecture using EPANET.
Measurement of forecast accuracy
The statistical estimation method of determining error is dis-
cussed previously in detail. The following algebraic
Figure 8 |Continued.
Figure 9 |Best fit curve of linear regression.
1421 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution designfor smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
expression is used in this error calculation which plays an
important role in determining the efficiency of the forecast
model. Figure 10 and Table 1 show the statistical forecast
using the LSLR model. Figure 11 and Table 2 show the
statistical forecast using ARIMA model:
et¼OtFt(19)
where O
t
is the actual consumption and F
t
is the forecasted
demand.
Mean error
ME ¼1
nX
n
i¼1
et(20)
Mean absolute error
MAE ¼1
nX
n
i¼1jetj(21)
Table 1 |Forecast for three months using LSLR
Date 2018 Consumed ( y) 2018 Actual predicted (P) (P-Y)/Y ¼error Mod (2018 error) Percentage error Actual error (Y-P) 2018 Sqr. error
1-Jan 13,953.60 13,247.67 0.05 0.95 94.94 705.93 498,343.99
2-Jan 13,861.20 13,204.14 0.05 0.95 95.26 657.06 431,732.93
3-Jan 15,435.60 13,936.75 0.10 0.90 90.29 1,498.85 2,246,555.86
–– – – – – – –
29-Mar 14,768.40 13,583.30 0.08 0.92 91.98 1,185.10 1,404,471.19
30-Mar 13,683.60 13,077.66 0.04 0.96 95.57 605.94 367,165.20
31-Mar 13,449.60 12,968.19 0.04 0.96 96.42 481.41 231,752.04
Total 87.62% 9.47 ×10
5
Figure 10 |Prediction vs consumption using LSLR model.
1422 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution designfor smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
The percentile error PAE is calculated as follows, in
which the relative measures are frequently used:
PE ¼YtFt
Yt
×100 (22)
Mean absolute percentage error
(MAPE)¼1
nX
n
t¼1jPetj(23)
Mean absolute square error
MASE ¼1
nX
n
i¼1jetj
!
2
(24)
Root mean square error
RMSE ¼ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi
MASE
p(25)
Figure 11 |Prediction vs consumption using ARIMA.
Table 2 |Forecast for three months using ARIMA
Date 2018 Consumed (y) 2018 Actual predicted (P) (P-Y)/Y ¼error Mod (2018 error) Percentage error Actual error (Y-P) 2018 Sqr. error
1-Jan 13,953.60 13,172.44 0.06 0.94 94.40 781.16 610,205.31
2-Jan 13,861.20 13,513.51 0.03 0.97 97.49 347.69 120,891.50
3-Jan 15,435.60 13,604.39 0.12 0.88 88.14 1,831.21 3,353,314.18
–– – – – – – –
29-Mar 14,768.40 13,888.32 0.06 0.94 94.04 880.08 774,542.09
30-Mar 13,683.60 14,186.21 0.04 0.04 3.67 502.61 252,616.78
31-Mar 13,449.60 13,941.76 0.04 0.04 3.66 492.16 242,222.18
Total 52.45% 1.08 ×10
6
Table 3 |Comparison of forecast errors for three months
Error ARIMA LSLR
MAPE 52.45% 88.09%
MASE 1.08 ×10
6
9.47 ×10
5
RMSE 1.03 ×10
3
9.73 ×10
2
1423 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution designfor smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
The forecast calculation accuracy between the two
statistical models ARIMA and LSLR is compared and dis-
played in Table 3. From the comparative analysis it is
evident that error in terms of MASE and RMSE is higher
for ARIMA compared to LSLR in terms of predicted and
actual value towards demand prediction. However, in
regard to prediction accuracy, the ARIMA model forecast
accuracy is better than the LSLR forecast model where
MAPE is higher for LSLR as compared to ARIMA, as
shown in Table 3. That is, higher MAPE signifies that
percentage error is greater for LSLR which results in
low accuracy as compared to ARIMA where MAPE is
less. From the statistical analysis it is also found that in
spite of the demand prediction, consumption is at quite
a high rate. It is not necessary that the consumption is
entirely utilized by the consumers. The consumption
reading is inclusive of losses due to pipe breakages,
joint materials and gate valves, ageing of WDN, etc., natu-
ral causes and theft of water. In order to minimize the
losses, a highly efficient WDN is required. The following
section discusses in detail the design of the WDN and
simulating the hydraulic behaviour as a pre-requisite for
IoT-based WDS.
Design of WDN using EPANET
Based on the demand prediction made using the ARIMA
model for the first season (January–March) of 2019, the
WDN is constructed on the basis of the following assump-
tions (Table 4).
Table 4 |WDN design assumptions
S. no. Name of parameter Description
1 No. of distribution points 50
2 Material of pipe PVC
3 No. of junctions 26
4 Diameter of pipe 100 mm
5 Length b/w each junction 500 m
6 Roughness coefficient 140
7 Calculation method Hazen–Williams formula
Figure 12 |Season-1 forecast for three months of the year 2019 (January 2019–March 2019).
1424 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution designfor smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
The formula for calculating head loss occurring in pipe
is determined using the Hazen–Williams formula as follows:
h100ft ¼0:002083 100
c
1:852
Lq1:852
d4:8655
h
(26)
where h
100
ft is friction head loss inside pipe per 100 feet, Lis
length of pipe in feet, cis Hazen–Williams friction constant,
qis volume of flow in gallons per minute, d
h
is hydraulic
diameter inside the pipe.
Thedateof17January2019predicteddatais
taken for pipe network simulation. The water distribution
on that particular date is taken as the average
quantity for 24 hours’distribution and it is illustrated in
Figure 12.
The WDN network is constructed as per the details
furnished below. EPANET network design consists of 50
distribution mains supplied by 1 reservoir.
•The average demand and the maximum demand for Jan-
uary 2019 is computed as 12,625 million gallons (MG) as
per the prediction for 17 January 2019. 1,286 MG is the
maximum requirement in the three months’predicted
analysis (January 2019–March 2019).
•The maximum demand is for a postal zone and it is
assumed as 50 supplier tanks connected through 25
junctions.
•The variable length of PVC for the upper networks is 500
and the bottom network is 1,000 m.
•The diameter of the pipe is 100 mm.
•The base demand of each node is distributed equally
across the 25 junctions.
•The base water level in the supply reservoir is assumed as
the quantity of water required as per the prediction made
by analysis.
Table 5 illustrates how the water demand for 17 January
2019 is assumed to be supplied and simulated along with the
peak and normal duration supply.
The construction of the WDN and the hourly flow of
water in the WDN is illustrated in the following figures.
From Figures 13–15, it is understood that the simulation
of WDN is done using EPANET. This simulation helps in
determining the hydraulic parameters such as flow
volume, pressure, head-loss, etc. at each and every junction
and node of the WDN. It is also helpful in predetermining
the hydraulic nature of WDN for the already existing
water distribution system. It is helpful in the design of a
new hydraulic distribution system as well as being useful in
determining the performance of the existing or already con-
structed WDN. EPANET analysis, as shown in Figures 14
and 15,describestheflow of water in the WDN in the
course of time. It helps the SCADA engineer to map the
flow in the pipeline. It also illustrates how data prediction
can be integrated with the WDN design, which is done
with the ultimate aim of reducing losses in water distribution.
This analysis also helps to determine the exact flow including
the losses that happen during the transmission in order to
match the supply as per requirement.
Table 5 |Hourly supply of water on 17 January 2019
EPANET supply 17 January 2019 (in
hrs) Supply (MG)
Multiplier
factor
0 375 0.2
1 350 0.06
2 450 0.02
3 550 0.03
4 575 0.06
5 775 0.13
6 1,000 0.9
7 1,400 1.68
8 1,600 1.35
9 1,400 1.35
10 300 0.67
11 300 0.56
12 250 1
13 200 2.56
14 200 3.56
15 200 2.81
16 200 1.24
17 300 0.75
18 500 0.9
19 400 1.75
20 300 1.25
21 300 1.25
22 400 0.34
23 300 0.34
Total predicted ¼12,624.72 Total supplied
12,625
1425 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution designfor smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
CONCLUSION AND FUTURE WORK
To conclude, an IoT-based architecture integrated with Fog
for an underground WDS has been proposed. In addition to
proposing an IoT-based architecture for WDS, water
demand forecasting has been done for water distribution
design. The water demand forecast has been carried out
on a daily basis for a period of three months using
ARIMA and regression analysis.
Based on water demand forecasting analysis, water dis-
tribution design for an IoT-based architecture has been
carried out using hydraulic engineering design for proper
Figure 13 |WDN design using EPANET.
Figure 14 |Water flow during final distribution stage on 17 January 2019 at node 25 during 0.45 hrs.
1426 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution designfor smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
distribution of water with minimal losses which would result
in the development of a smart water distribution system
(SWDS). This has been carried out using EPANET.
In future, the system can extend to predicting water
demand using LSTM which is an extension of recurrent
neural networks and be similarly extended for water distri-
bution design for varying types of consumers. Also, the
system can be incorporated with intelligence for an under-
ground pipe health monitoring system using intelligent
agents for immediate action from SCADA engineers.
REFERENCES
Amatulla, P. H., Navnath, B. P., Yogesh, B. P. & Ashwini, Z. S.
IoT based water management system for smart city.
International Journal of Advanced Research Ideas and
Innovation in Technology 3(2), 379–383. https://www.ijariit.
com/manuscripts/v3i2/V3I2-1252.pdf
Bibri, S. E. & Krogstie, J. Smart sustainable cities of the
future: an extensive interdisciplinary literature review.
Sustainable Cities and Society 31, 183–212. https://doi.org/
10.1016/j.scs.2017.02.016.
Bonomi, F., Milito, R., Natarajan, P. & Zhu, J. Fog
computing: a platform for internet of things and analytics. In:
Big Data and Internet of Things: A Roadmap for Smart
Environments (N. Bessis & C. Dobre, eds). Springer,
Switzerland, pp. 169–186. https://doi.org/10.1007/978-3-
319-05029-4_7.
Candelieri, A. & Archetti, F. Identifying typical urban water
demand patterns for a reliable short-term forecasting –the ice
water project approach. In: Procedia Engineering,
Proceedings of 16th Conference on Water Distribution System
Analysis, Bari, Italy, 89, 1004–1012. https://doi.org/10.1016/
j.proeng.2014.11.218.
Chanda, R., Prabaharan, S. R. S. & Muthulakshmi, S. IoT
based water management, IEEE Xplore. In: International
Conference on NextGen Electronic Technologies: Silicon to
Software, Chennai, India. https://ieeexplore.ieee.org/
abstract/document/8067943/similar#similar
Chen, J. & Boccelli, D. L. Demand forecasting for water
distribution systems. In: Procedia Engineering, Proceedings of
12th International Conference on Computing and Control for
the Water Industry, Perugia, Italy, 70, 339–342. https://doi.
org/10.1016/j.proeng.2014.02.038.
Gupta, A. D., Bokde, N. & Kulat, K. D. Hybrid leakage
management for water network using psf algorithm and soft
computing techniques.Water Resources Management 32 (3),
1133–1151. https://doi.org/10.1007/s11269-017-1859-3.
Gwaivangmin, B. I. & Jiya, J. D. Water demand prediction
using artificial neural network for supervisory control.
Nigerian Journal of Technology (NIJOTECH) 36 (1), 148–154.
http://dx.doi.org/10.4314/njt.v36i1.19.
Herrera, M., Izquierdo, R., Perez-Garcia, D. & Ayala-Cabrera,
D. On-line learning of predictive kernel models for
urban water demand in a smart city.In:Procedia
Engineering, Proceedings of 12th International Conference
on Computing and Control for the Water Industry, Perugia,
Italy, 70, 791–799. https://doi.org/10.1016/j.proeng.2014.
02.086.
https://www.epa.gov/dwsixyearreview/drinking-water-
distribution-systems.
https://www.ncss.com.
https://www.pmu.edu.sa/Academics/Design_Water_Supply_
Facility_Khobar_Residential_Complex.aspx.
Figure 15 |Water flow in WDN for 24 hrs.
1427 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution designfor smart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
Laspidou, C., Papageorgiou, E., Kokkinos, K., Sahu, S., Gupta, A. &
Tassiulas, L. Exploring patterns in water consumption by
clustering.In:Proceedia Engineering, Proceedings of 13th
Computer Control for Water Industry Conference, Leicester,
UK, 119, pp. 1439–1446. https://doi.org/10.1016/j.proeng.
2015.08.1004.
Narayanan, L. K. & Sankaranarayanan, S. IoT based smart
water distribution management and underground pipe health
monitoring system for smart city. In: IEEE Sponsored 2019
5th International Conference for Convergence in Technology
(In press).
Perera, C., Qin, Y., Estrella, J. C., Marganiec, S. R. & Vasilkos,
A. V. Fog computing for sustainable smart cities: a
survey.ACM Computing Surveys 50 (3), 1–39. http://delivery.
acm.org/10.1145/3060000/3057266/a32-perera.pdf?
ip=103.4.223.69& id=3057266&acc=ACTIVE%
20SERVICE&key=045416EF4DDA69D9%
2EA1D9F3C769B82345%2E4D4702B0C3E38B35%
2E4D4702B0C3E38B35&__acm__=1556078150_f57b96df7
ab5f648ea15d0f91354d036.
Rinaudo, J. D. Long-term water demand forecasting.
In: Understanding and Managing Urban Water in Transition
(Q. Grafton, K. A. Danielle, C. Nauges, J.-D. Renaudo & N.
W. W. Chan, eds). Springer, Dordrecht, pp. 239–268. https://
doi.org/10.1007/978-94-017-9801-3_11.
Tom, R. J., Sankaranarayanan, S. & Rodrigues, J. P. C. Smart
energy management and demand reduction by consumers
and utilities in an IoT fog based power distribution system.
IEEE Internet of Things Journal X(X), 1–8. 10.1109/JIOT.
2019.2894326.
Varma, S. K., Hemalatha, I. & Kishore, R. A smart water
management system for rural area water tanks. Journal of
Chemical and Pharmaceutical Sciences 10 (10), 29–33.
Retrieved from https://www.jchps.com/specialissues/2016%
20SPECIAL%20ISSUE%2010/07%20JCP.pdf
Veeramanikandan, M. & Sankaranarayanan, S. Publish/
subscribe based multi-tier based computational model in
internet of things for latency reduction.Journal of Parallel
and Distributed Computing 127,18–27. https://doi.org/10.
1016/j.jpdc.2019.01.004.
Zischg, J., Rauch, W. & Sitzenfrei, R. Morphogenesis of urban
water distribution networks: a spatiotemporal planning
approach for cost-efficient and reliable supply.Entropy
20 (9), 1–22. https://doi.org/10.3390/e20090708.
First received 28 January 2019; accepted in revised form 10 June 2019. Available online 18 July 2019
1428 L. K. Narayanan & S. Sankaranarayanan |IoT-based water demand forecasting and distribution design forsmart city Journal of Water and Climate Change |11.4 |2020
Downloaded from http://iwaponline.com/jwcc/article-pdf/11/4/1411/829970/jwc0111411.pdf
by guest
on 06 August 2021
