Professional Documents
Culture Documents
Zoning Irrigation
Zoning Irrigation
a r t i c l e i n f o a b s t r a c t
Article history: Information and communication technologies play an important role in reforming traditional agriculture
Received 29 February 2020 as well as agricultural development. In this context and to benefit from these technologies, a new irri-
Received in revised form gation strategy is proposed in this paper. A zoning irrigation system based on Internet of Things (IoT) is
28 March 2021
developed and tested, where the main objectives are the optimization of plant growing conditions and
Accepted 2 April 2021
Available online 6 April 2021
the reduction of water use and energy consumption. The proposed system based on a Wireless Sensors
Network (WSN) was installed in different considered zones of a greenhouse. This network sends the data
Handling editor: Dr. Govindan Kannan from the plant environment, such as soil humidity and temperature to a server (Raspberry pi) by means
of radio-frequency (RF) communication. To control the irrigation, a fuzzy logic controller (FLC) processes
Keywords: these data and makes an intelligent and optimal decision. The developed system can monitor and control
Fuzzy control the irrigation in the greenhouse from anywhere and at any time by using a Human Man Interface (HMI)
HMI developed under Node-RED of IBM. The proposed system was applied to irrigate tomato plants in a real
Node-RED server environment. Comparison of the irrigation performance with three other irrigation techniques shows
IoT
that the amount of water and the consumption of energy by adopting the proposed method decreased
WSN
significantly.
Zoning irrigation
© 2021 Elsevier Ltd. All rights reserved.
https://doi.org/10.1016/j.jclepro.2021.127001
0959-6526/© 2021 Elsevier Ltd. All rights reserved.
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
majority of these countries suffer from a water shortage, they have protocols have been applied in order to make the IoT transactions,
to adapt rational management of the water resources and adopt which have been validated to ensure security in the cloud. Tradi-
intelligent irrigation techniques (Doungmanee, 2016; Johansson tional blacklisting methods for intrusion detection in IoT devices
et al., 2016; Morison et al., 2008; Velasco-Mun ~ oz et al., 2018). are no longer effective due to the emergence of novel attacks from
Over the last 20 years, fuzzy logic (FL) has attracted considerable adversaries. To address this problem, a lot of works based on the
attention in agriculture and it has also helped farmers to make the different machine and deep learning algorithms for intrusion
right choices and decisions for their crops (Papageorgiou et al., detection have been proposed in the literature (Stergiou et al.,
2016). Application of FL in irrigation systems is more attractive to 2021; Sunitha Krishnan and Thampi, 2020; Tahsien et al., 2020).
most researchers because this kind of controller does not require an IoT has certainly changed the way of living, working, thinking,
exact estimation or an exact model of the system that often could feeling and behaving, and has contributed to solving many prob-
be confusing and require significant and impressive assets (Bahat lems in different sectors (Tzounis et al., 2017). Therefore, it has been
et al., 2000). In this context, several studies have been proposed applied in agriculture to help the farmers. A greenhouse farm su-
to take advantage of the efficiency of FL technique. Gao et al. have pervision and automatic irrigation system based on IoT has shown
proposed an intelligent irrigation system based on WSN and fuzzy its ability on tracking plant water requirements, alerting the irri-
control (Gao et al., 2013). The test results compared to the pro- gation unit, and supplying farm information in real time (Benyezza
portionaleintegralederivative (PID) controller show that the FLC is et al., 2018a; Nawandar and Satpute, 2019). An intelligent IoT irri-
more suitable for greenhouse irrigation control. Touati et al. have gation management system has been proposed to minimize water
developed a smart irrigation system, where a FLC is used to control consumption and the working time needed for irrigation (Difallah
the irrigation and the tests give good results comparing to the et al., 2018). A combination of intelligent automated irrigation
traditional feedback system (Touati et al., 2013). Li et al. have pro- system based on IoT, K-Nearest Neighbor (KNN) and classification
posed a real-time irrigation decision support system based on a machine learning algorithm has been proposed to analyze sensors’
fuzzy technique and a dedicated software was developed in this information for soil water irrigation (Shekhar et al., 2017). A Cuckoo
study for alfalfa irrigation management. The system provided the search algorithm based on the ThingSpeak cloud has been devel-
irrigation timing and amounts needed for the alfalfa irrigated sys- oped to allow the allocation of water for farming in any condition,
tem to operate efficiently. The test in Zhuozhou, in Hebei Province as well as the selection of appropriate crops for specific land
of China, has shown that this system of support for irrigation de- (Pathak et al., 2019). ThingSpeak has been also used to control the
cisions is very promising for alfalfa irrigation and harvesting (Li irrigation and monitor the different water parameters by using a
et al., 2019). FL has been proposed to control irrigation in many smartphone or a PC from anywhere and at any time in order to
other studies, where the results show that the proposed system is monitor the orchid greenhouse climate and the growth status of
effective in irrigating agriculture fields by considering the avail- Phalaenopsis (Jiang et al., 2016). A smart system based on IoT and
ability of water, its saving, and soil field moisture conditions image processing has been built, where the authors have expected
(Carrasquilla-Batista and Chaco n-Rodr; Ibrahim, 2018; Izzuddin that this system will contribute successfully to upgrading Phalae-
et al., 2018; Kia et al., 2009; Krishnan et al., 2020; Ponnusamy nopsis’ farming methods in the future (Liao et al., 2017). Several
et al., 2017; Villarrubia et al., 2017). Other researchers have used studies have been proposed to monitor and control the irrigation
FL to control the greenhouse climate according to the different using android applications based on Arduino microcontroller in
greenhouse parameters like temperature and humidity (Azaza which the main objective is saving water (Lorvanleuang et al., 2018;
et al., 2016; Ben Ali et al., 2016; Benyezza et al, 2018b, 2019; Permale et al., 2017; Raut et al., 2018; Rawal, 2017; Seenu et al.,
Revathi and Sivakumaran, 2016). Their results confirm the effec- 2018).
tiveness of the FLC in achieving favorable climate conditions, as WSN systems have been widely used in agriculture over the last
well as significant energy saving. FL has been proposed as a solution decade. This technology has provided an important support for
in other fields. Marzbanrad et al. have developed a FLC to increase accurate resource management, irrigation optimization, fertilizer
vehicle stability and ensure the prevention of vehicle rollover use, disease monitoring or prevention, and prediction of appro-
during maneuvers (Marzbanrad et al., 2015). Montazeri-Gh et al. priate timing of harvest (Wark et al., 2007). Thus, a lot of research
have proposed a power control algorithm for hybrid electric vehi- projects have been realized. A novel algorithm based on Machine
cles based on FLC to minimize fuel consumption and the exhaust Learning techniques and WSN has been proposed to predict soil
emissions such as CO, HC, and NOx (Montazeri-Gh and Mahmoodi- moisture and to make effective irrigation decisions (Goap et al.,
K, 2016). Bouhedda et al. succeeded to set up an intersection traffic 2018). A monitoring and management system of potato crops has
light control system based on FL by using a programmable logic been proposed based on WSN using low-power sensor nodes
controller (PLC) (Bouhedda et al., 2021). (Shinghal Kshitij, 2010). WSN has been used to monitor soil mois-
IoT is one of the most revolutionary technologies in modern ture for establishing an autonomous irrigation management system
wireless communications. IoT is a set of interconnected objects that (Dong et al., 2013). A Smart Watering System (SWS) based on an
are able to collect and transfer data. The major challenges IoT faces, android application using a fuzzy approach has been proposed to
are security, the limited calculation and the storage capacity of take an intelligent decision and a blockchain in order to enhance
sensing devices (Deng et al., 2020; Gupta and Quamara, 2020; Shah the security of all data and communications (Munir et al., 2019). A
et al., 2021). Gupta and Quamara have presented a survey on the low-cost WSN-based decision support system and FL have been
historical background and architecture of IoT, the main categories of developed to help and support the farmers in irrigation manage-
challenges, and existing solutions (Gupta and Quamara, 2020). ment, reducing the waste of irrigated water, and improving the
Some of the related IoT infrastructure protocols and open-source exploitation of the water resource (Mannini and Genovesi, 2013).
platforms and frameworks were also addressed by the authors. Nikolidakis et al. proposed a new routing protocol to increase the
Cloud computing is commonly adopted as a foundation technology energy efficiency of WSN using an electronic embedded circuit for
to operate gathered data (Deng et al., 2020). Al-Qerem et al. have automated irrigation system (Nikolidakis et al., 2015).
used cloud computing to process the transaction of data provided This work aims to develop a smart and low-cost irrigation sys-
by sensing devices (Al-Qerem et al., 2020). The authors have tem based on zoning in order to minimize the use of water as well
introduced IoT transactions using cooperative concurrency control as the consumption of energy. Data on soil and environmental
in the fog-cloud environment. Augmented partial validation conditions (temperature and moisture) are collected and
2
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
transmitted to a base station (server) using a WSN based on RF The field area: irrigate a small area is not the same as a huge
communication. Once these data are collected and stored in a area.
server, the right necessary time for irrigation in each zone is Sensor range: the area covered by the sensor (in a huge area, a
calculated using a FLC. An HMI based on IoT and Node-RED of IBM is single sensor is not enough).
developed to monitor the collected data from the different The non-linearity of the soil.
considered zones. The presented system is evaluated by making Water flow: the water flow rate is affected by pipe length and
comparisons with three other irrigation systems. the distance to the water source especially in a huge area.
The paper is arranged in three main sections, the proposed The plant type: the same system can be applied to any type of
system with different hardware and software tools is presented in plant.
Sections II and III respectively. The results of the proposed system
are presented in Section IV. Finally, in Section V the conclusions are More details about the tools used to set up the proposed system
drawn. are given in the sections below.
The block diagram of the proposed irrigation system is shown in This section describes the three layers of the proposed system
Fig. 1. It is composed of three main parts: processing, cloud, and that have been adopted:
communication part. The agricultural field was divided into mul-
tiple zones (Fig. 2) according to its size and the area that can be a) Processing layer: contains the FLC.
covered by the soil moisture sensor. A node contains a sensor (soil b) Cloud layer: a server for hosting data and the controller.
moisture sensor) and actuator (solenoid valve) which were placed c) Communication layer: for transferring data between the
in each zone. Since the temperature affects the soil by making it different parts of the system by means of serial, RF communi-
dried when it increases, a temperature sensor was used to measure cation and Internet using a WSN architecture.
the inside temperature of the greenhouse (Feng and Liu, 2015; Sen
and Ozturk, 2017). The measured data are sent to a collector node
(Sink) via RF communication and then transmitted to a processing
unit (Raspberry pi 3). A FLC was developed and hosted on the 3.1. Fuzzy controller structure
server, in order to control the optimal necessary irrigation time for
each zone. The server sends an ON/OFF command to the corre- FL, formalized by Lofti Zadeh in 1965, is an extension of Boolean
sponding valve according to the time calculated by the FLC. The logic. It is a generalization of the classical set theory which, by
valve location of each zone is illustrated in Fig. 2. The cloud layer virtue of its digital dimension, opposes the principles of modal
allows the user to monitor and control the irrigation by using a PC, logic. It has the benefit of introducing the principle of confidence to
smartphone, or any adequate terminal from anywhere and at any check a condition, allowing it to be in a state other than true or
time over the Internet. The system is a mix of drip and furrow false. FL gives significant flexibility and enables rules to be
irrigation. The irrigation flow supplied by the pump is conveyed expressed in natural language (Hooda and Raich, 2016). Four main
inside a flexible hose unrolled between the crop rows of each zone parts can be distinguished constituting the structure of a FLC as
in furrows separated by 10e20 cm depending on the type of soil illustrated in Fig. 3 (Ross, 2016).
(Fig. 2). The sheath has branches that guide the flow of water within
each furrow. a) Fuzzification: This part translates quantitative numerical
The implementation of the proposed system is done by taking data from a sensor into qualitative linguistic variables
into account the following constraints: through a membership function. Various types of functions
3
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
can be seen in the literature, the most commonly used are Because the soil environment has large inertia, non-linearity,
trapezoidal, triangular and Gaussian. and strong coupling with different environmental parameters, it
b) Rule base: We consider inference rules as a collection of is difficult to set up an exact and precise mathematical model for
several rules linking the system’s fuzzy inputs variables to its the soil and consequently to make a precise decision to control the
fuzzy outputs. These rules are represented as “IF-THEN” irrigation using traditional control methods (Cepeda et al., 2011;
rules: Zhang et al., 1996). FL is a better approach for decision making
IF condition 1 AND/OR condition 2 (and/or …) THEN action problems (Munir et al., 2019) because it has the ability to mimic
on the outputs. human beings in reasoning (Zadeh, 1988), flexibility, and aptitude
c) Inference engine: The inference block is the core of a FLC, it to deal with nonlinearities and uncertainties systems (Azaza et al.,
is capable of simulating human reasoning and inducing FLC 2016; Danish and Onder, 2020; Fedor and Perdukova , 2017; Liu
action using fuzzy involvement and inference rules in FL. The et al., 2014; Mei et al., 2001). The FLC was adopted as a solution
numerical processing of inference rules allows the control- to deal with the non-linearity of the soil related to the environ-
ler’s linguistic fuzzy output to be obtained, which can be mental parameters and the irrigation control. The FLC allows to
accomplished using a variety of methods, including: Mam- combine between multiple sources of information in the field and
dani, Sugeno and Larsen (Mamdani and Assilian, 1975). makes an intelligent decision to control the irrigation. The FLC does
d) Defuzzification: This step allows merging the different not need any mathematical modeling of the system. It only requires
commands generated by the inference engine to give only expertise and a proper configuration of the various components of
one output and transform this qualitative linguistic variable the fuzzy structure, where the non-linearity conditions are effi-
into quantitative numerical data. The most common defuz- ciently handled with the linguistics variables and the set of rules.
zification methods are: center of gravity (COG) and mean of The FLC (Fig. 4) calculates the irrigation time (Irr_t) of each zone
maximum (MOM) (Ross, 2016). according to greenhouse temperature (Temp) and the difference
between the setpoint and the current soil moisture (Err_M). To
implement the FLC, a python code is written according to the
adopted structure of the fuzzy system.
For the membership functions, each input and output has five
Fig. 3. Internal structure of a FLC. Fig. 4. Inputs and output of the adopted FLC.
4
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
Cold ‘C’, Medium ‘M’, Hot ‘H’, Very Hot ‘VH’}, the second input Rule Temp Err Irr_t
(Err_M) was described also by five fuzzy {Zero ‘Z’, Small ‘S’, Medium 1 M S VSh
‘M’, Big ‘B’, Very Big ‘VB’} and for the output (Irr_t), five linguistic 2 H S Sh
values are considered {Very Short ‘VSh’, Short ‘Sh’, Medium ‘M’, 3 C M M
Long ‘L’, Very Long ‘VL’}. Fig. 5 gives more details about the used 4 VC B M
5 VH VB VL
membership functions and the universe of discourse.
… … … …
Soil moisture is water that is contained in the ground and is
influenced by precipitation, soil temperature, and more. The
interaction between the soil moisture and these factors was taken
b) The number of membership functions for each variable.
into consideration and applied in the fuzzy rules, where 25 rules
c) The adopted rules.
based on Mamdani inference were used to manage the controller.
The relationship between inputs and outputs was described by “IF-
These choices were made optimally based on expert knowledge
THEN” rules extracted from experiences and expert knowledge.
and experimental tests.
Some of these rules are given in Table 1. These rules allow to pro-
vide intelligent decisions to control the irrigation according to soil
and environmental state. 3.2. Node-RED server
The combination of the FLC with the zoning strategy can be
considered as the optimization algorithm for water and energy This server is an open-source server developed by IBM in 2013
saving. The optimization algorithm was integrated into the FLC to connect the Internet to hardware devices, APIs as well as online
through the right choice of three important parameters: services. It is a simple wiring of nodes or predefined code blocks to
perform tasks. Node-RED is based on JavaScript, one of the most
a) The type of membership functions of inputs and output. widely used and easy to learn programming languages. The run-
time is built on Node.js as a flow-based development tool, taking
full advantage of its event-driven and non-blocking model. The
generated flows are saved in JSON, which enables them to be
shared, imported, and exported to the real world (Rogers and
Stanford-Clark, 2018).
Node-RED offers a variety of pre-installed nodes that can be
used. Also, it is possible to create new personalized nodes, speci-
fications, and functionality. These nodes are composed of an HTML
and a JavaScript files. The HTML file indicates how the node should
appear and how many inputs/outputs should be used. The Java-
Script file determines the functionality of the node (Popov, 2016;
Rogers and Stanford-Clark, 2018).
Fig. 6 shows some modules (set of nodes) available in Node-RED,
such as:
a) Receiving data block: It is the part responsible for reading the node’s inputs are the argument for the python script and the
data provided by the sink node and the guideline instructions script’s final result is sent to the node’s output.
(plant type) established by the user through the HMI. The in-
ternal architecture of this block is illustrated in Fig. 8, where it One instance of data can easily be sent directly to the output
contains: through the command “print”, but it becomes more complicated
“serial in” node: to read data sent by the Sink from a local when there are two or more variables. In this case, the position of
serial port (COM12 in our case). each variable must be specified. Another problem is string con-
“button” node: to select the plant type. version, an everlasting computer science problem. To avoid all
“functions” node: to store the data, provided by the sink, and these problems, the data are formatted using “json” format, which
the plant conditions (reference values). is a collection of name/value pairs separated by a comma. This
format is supported by all modern languages (C, Cþþ, JavaScript,
All of these received data are concatenated in a single vector in a Python, etc.) (Lindsay Bassett, 2015).
global variable to allow their transition to the processing block. The output of “pythonshell in” provides a frame of data which
consists of several variables (temperature, soil_m zone1, irriga-
b) Data processing block: This block (Fig. 9) allows the analysis tion_time zone1, etc.) of type “string”, These variables must be
and processing of the data transmitted through the sink node separated for individual display and command transmission to the
with taking into account the plant conditions. The “pythonshell Sink. For this purpose, the node “json” is used. This latter allows
in” node is used to run the python script of the FLC where the converting between “json” string and object type. The “json”
6
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
function must be followed by several functions to get values indicate valve state ON/OFF) and text (for displaying irriga-
separately like: Soil_m Zone1, Soil_m Zone1, Temperature, etc. tion time).
d) Sending commands block: The “serial out” node (Fig. 11)
c) Displaying data block: This block (Fig. 10) is used to display transmits FLC decision commands from the server to the
the data outputs, which are the irrigation time and the state sink.
of the actuators. It enables the use of different dashboard
nodes, such as gauge or chart, to monitor the irrigation sys-
tem from anywhere and at any time (for the soil moisture of
the different zones and the greenhouse temperature), led (to 3.3. Communication
Fig. 10. Some Node-RED flows for displaying data. Fig. 11. Serial out node.
7
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
300 GHz. Due to their property to penetrate items and travel To measure the temperature, the DHT22 sensor is used (Fig. 13c).
lengthy distances, they are used in wireless communication It is a low-cost digital temperature and humidity sensor. A capac-
(Dowla, 2004). The main advantages of using wireless communi- itive moisture sensor and a thermistor are used to measure
cation are the ease of deployment, self-organization, and reduced respectively moisture and temperature of the air around the pin,
wiring, which significantly reduces the cost of installation and and a digital signal, containing the measured values, is transmitted
maintenance in large areas. to the data pin.
The communication between the collector node and the
different zones is established using RF communication. Each node
4. Tests, results and discussion
starts a communication with the sink node on a certain frequency,
called channel, by sending a data packet containing the current soil
The proposed system was implemented and tested in a real field
moisture. After the entire packet has been transmitted, the receiver
of six square meters to irrigate tomato crops during eight days;
sends an acknowledge packet to the transmitter containing the
from 28 July to 04 August 2019. The considered area was divided
irrigation command sent by the server based on the FLC.
into two zones. Each one included a wireless node with a solenoid
valve and a soil moisture sensor (Fig. 13 a, Fig. 13b). A third sensor
3.4. Components of the wireless node node was also installed to measure the ambient temperature
(Fig. 13c). Raspberry Pi was used and served as a server and HMI
Fig. 12 depicts the node installed in each zone, which is made up host (Fig. 13d).
of five major components, namely: Batteries were used to power the wireless nodes. These nodes
are mainly composed of a microcontroller and an ultra-low power
a) Nano Arduino: It is the node’s heart; its role is to store and consumption transmission module, the nRF24L01þ. Data process-
execute a program for data acquisition from sensors, com- ing is done on the server, which is advantageous for saving energy
mand transmission to actuators, and data transmission or in the nodes and keeping power consumption low where the role of
data reception from the server (Fig. 12a). nodes is reduced practically to just sending and receiving data. By
b) nRF24L01 þ module: It is the element used for RF adopting this way, the battery life can be extended from several
communication to send and receive data (Fig. 12b). It is a weeks to months.
Nordic Semiconductor chip RF Transceiver Integrated Circuit An approximative study according to the node consumption and
(IC). It operates in the license-free 2.4 GHz ISM band the communication protocol has shown that the node batterie has
(ISMeIndustrial, Scientific and Medical) with 250 kbps, 1 to be replaced every eight months if an AA NiMH (Nickel Metal
Mbps and 2 Mbps data rate support. It is connectable with Hydride) cell with 2400 mAh is used. The batteries can be replaced
SPI and has a wide range of very interesting features such as and recharged manually. If the proposed irrigation method is
low power modes, multiple channels, switching and cali- applied outside a greenhouse (open field) and in sunny areas, a
bration of frequency (Michael, 2017). This module is used not better solution would be to replace the battery with solar power
only because of its low cost, but also because it is relatively modules.
easy to use for short or long-range communications. The considered variables in the greenhouse have slow dy-
c) Soil moisture sensor YL-69 (hygrometer): It is used to namics. For this reason and to save energy consumption, the
measure the humidity of the soil (Fig. 12c). duration of each cycle, was fixed to one second, which is more than
d) Battery: It is used to provide energy to the node (Fig. 12d). enough time to read data from all the nodes by the sink. Table 2
e) Valve: It is used to control the water circulation (Fig. 12e). illustrates the complexity analysis of the proposed approach
8
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
Table 2 (Fig. 14) during one week is shown in Fig. 15. These findings, as
Complexity analysis of the proposed method. expected, show that the FLC controlled effectively the soil moisture,
Processor RAM Execution time Average CPU usage which had been successfully stabilized between 400% and 500%,
which corresponds to the ideal condition for the considered plant
1.2 GHz 64-bit quad core 1 G0 1015(s) 60%
ARM Cortex-A53 (Mattoo, 2017).
Fig. 16 shows the used components for the HMI dashboard
corresponding to the blocks shown in Fig. 10. The user can monitor
which depends on the used hardware platform (Raspberry pi), the the different parameters of each zone like temperature (Temp) and
efficiency of the compiler, the operating system, the programming its variation using a graph, soil moisture (Soil_MZ1 and Soil_MZ2),
skills, the size of the inputs and more: valve state (valve 1 and valve 2), and irrigation time (irri_time_Z1
and irri_time_Z2) from a local HMI or by using the cloud over the
The execution time: It is the time it takes the Raspberry Pi to run Internet.
the FLC script to determine the irrigation time for two regions, For another plant, exactly the same system can be used. Just the
which is equivalent to 1015 s (real time decision). soil moisture reference should be set according to the corre-
Average CPU usage: The whole system (FLC and Node-RED sponding plant through the HMI (Fig. 17). The user needs just to
server) occupies 60% of Raspberry’s CPU. It was calculated us- select the considered plant (pepper, cucumber, eggplant, etc.), and
ing the “cpu node” which allows monitoring the CPU usage in the system reacts according to the selected plant reference set
Node-RED. which, according to expert knowledge, is already incorporated into
the system.
The evaluation of soil moisture corresponding to the two zones By default, the Node-RED editor is not secured, anyone who can
with the FLC under different temperatures of the environment access its IP address can access the editor and deploy changes. For
this reason, it must be secured in order to safeguard the system and
prevent outsiders from accessing it. Three preventive measures
were adopted to ensure security:
9
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
Fig. 15. Soil moisture variation in each zone during one week using the FLC.
10
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
Table 3
Although we are convinced that the proposed system is efficient
Water use and operating duration of actuators for eight days.
and provides an improvement on water and energy saving
Methods Consumed water (L) Duration of actuators’ functioning compared to the other existing irrigation strategies, it is very
1st method 64 01h31mn00s difficult to give an exact percentage improvement in this manu-
2nd method 57 01h18mn45s script because it needs a comparison on several scales and each
3rd method 72 01h40mn15s scheme has its advantages and limitations, however:
Proposed method 46 01h03mn52s
11
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
Table 4
Relative difference of water and energy cost of the three methods compared to the proposed solution during four months.
Methods Relative difference of water cost Relative difference of energy cost Total
Table 5
System components cost.
Raspberry pi 3 Arduino nano nRF24L01 þ module Soil moisture sensor Temperature sensor Valve Node-RED server Total cost in 200 m2
Price (US $) 45,30 2,71 2,99 1,61 4,29 3,50 Open source 276.49
5. Conclusion
Table 6
Comparative between the proposed solution with the traditional irrigation strategies.
comparison Proposed method Drip irrigation Furrow irrigation Sprinkler irrigation Flood irrigation
criteria
Water & Energy Very high (especially in huge area) High, compared to furrow and flood Low Low to medium Very low
saving
Irrigation Control Intelligent control (very precise) Manually Not possible Manually Not possible
Installation Cost Lowest operational and labor (based on Low initial and operational as Lowest initial High initial and Lowest initial
wireless communication) compares to sprinkler High operational operational High operational
and labor and labor
Monitoring Based on WSN and IoT Based on labor locally Based on labor Based on labor Based on labor
locally locally locally
Maintenance Low cost (due to using WSN and IoT) Need regular maintenance High operational Need regular /
and labor maintenance
Labor Cost Very low (replaced by WSN and IoT) Moderate High Moderate High
Disease and pest can be monitored through the HMI by adding Relatively less High Medium Very high
problems sensors
Efficiency of High High Minimum Moderate Minimum
fertilize use
12
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
Table 7
Comparative between the proposed solution with some new previous proposed strategies.
Krishnan Temperature, humidity, soil FL implemented in Arduino GSM/GPRS -Local LCD display - High water & energy saving
et al. moisture, water level, rain & -Notification through mobile compared to drip & manual flood
(2020) LDR phone irrigation
- Remote monitoring
- Low manual labor cost
- Solar power
Villarrubia Humidity, soil moisture, FL Wi-Fi, GPRS, Android application (TV - Low-cost system
et al. temperature, light, water Implemented in mc ATmega328p with ethernet & platform, mobile phone) - Water saving
(2017) level & oxygen PANGEA multi-agent systems RF - WSN based
- Remote monitoring
- Storage database
Touati Soil moisture, temperature, FL implemented in mc Xbee, GSM/ PC (LabView) - Solar power
et al. solar radiation & water flow Atmega32 GPRS - High water saves
(2013) - Remote monitoring
- Low-cost, efficient & easy to
implement
Shekhar Temperature & soil moisture machine learning algorithm K-NN SPI & Webpage - Remote monitoring
et al. deployed in Raspberry ethernet - Soil quality predicting
(2017)
Goap et al. Soil temperature, soil support vector regression model and k- Xbee, SPI Webpage - Predict the irrigation requirements
(2018) moisture, air temperature & means clustering algorithm implemented & Wi-Fi with high accuracy
humidity in the server - Centralized database
- WSN based
- Remote monitoring
- Web service for online weather
data collection
- Cost effective
- Water saving
Munir Light, soil moisture, camera, Decision support system based on FL Wi-Fi & Android phone application - Remote monitoring
et al. temperature & humidity implemented in the server Bluetooth - Secure communication
(2019) - Optimize energy consumption
- Decentralized database
Proposed Temperature & soil moisture FL implemented in the server RF, SPI Node-RED - High water & energy saving
Method & Wi-Fi Server (access through the web compared to (Gao et al., 2013) &
without need to install any (Harish Kumar, 2017)
applications) - Zoning based irrigation
- High precision (zoning þ FLC)
- Remote access (through Node-RED
server)
- Server implementation (not limited
to mc memory)
- WSAN based
- Cloud storage
- Low-cost system
- Modular
- Easy installation
Intelligent control using FL. Healthcare: WSNs can be implanted in humans and send real-
Real time monitoring using IoT and WSN. time data to a server, where it can be processed and analyzed.
Money saving by minimizing the consumption of water and The newly developed HMI allows doctors to keep track of their
energy. patients’ health outside of the hospital and improve risk man-
Farmer efforts Reducing. agement. The proposed system can also be used in health care to
Easy installation with the ability to add and adopt a modular connect medical equipment to the cloud, allowing for better
node if more zones are required. monitoring and maintenance.
More sensors or actuators can be easily added to the adopted Traffic management: The proposed system can be used to
system’s architecture through easy adaptation of the nodes. monitor intersections (via WSN and IoT) and intelligently con-
Using of low-cost hardware especially in terms of IoT and trol traffic lights (via the FLC).
communication. Industry 4.0: The Node-RED server can be used to develop HMIs
Valid for many types of plants. that enable users, from any location and at any time, to monitor
and control their processes and improve security and optimize
As perspectives to this work, it is planned to improve and bring processes and workflows.
more affinity by securing data transfer between the fields and the
server using new cryptography techniques. It is also interesting to
create a database system from the collected data that can be used
for analysis, prediction and more. CRediT authorship contribution statement
Furthermore, the solution adopted can be adapted for other
applications like: Hamza Benyezza: Methodology, Software, Validation, Investi-
gation, Writing e original draft, Writing e review & editing.
Mounir Bouhedda: Conceptualization, Validation, Resources,
13
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
Writing e original draft, Writing e review & editing, Supervision, Doungmanee, P., 2016. The nexus of agricultural water use and economic devel-
opment level. Kasetsart J. Soc. Sci. 37 (1), 38e45. https://doi.org/10.1016/
Project administration. Samia Rebouh: Validation, Writing e
j.kjss.2016.01.008.
original draft, Writing e review & editing. Dowla, F.U., 2004. Handbook of RF and Wireless Technologies. Newnes.
Fedor, P., Perdukova , D., 2017. Use of fuzzy logic for design and control of nonlinear
MIMO systems. In: Modern Fuzzy Control Systems and its Applications. InTech.
Declaration of competing interest https://doi.org/10.5772/68050.
Feng, H., Liu, Y., 2015. Combined effects of precipitation and air temperature on soil
The authors declare that they have no known competing moisture in different land covers in a humid basin. J. Hydrol. 531 (3),
1129e1140. https://doi.org/10.1016/J.JHYDROL.2015.11.016.
financial interests or personal relationships that could have Gao, Liai, Zang, Mang, Chen, G., 2013. An intelligent irrigation system based on
appeared to influence the work reported in this paper. wireless sensor network and fuzzy control. J. Netw. 8, 1080e1087. https://
doi.org/10.4304/jnw.8.5.1080-1087.
Goap, A., Sharma, D., Shukla, A.K., Rama Krishna, C., 2018. An IoT based smart
Acknowledgment irrigation management system using Machine learning and open source tech-
nologies. Comput. Electron. Agric. 155, 41e49. https://doi.org/10.1016/
This work is supported by the Directorate General for Scientific j.compag.2018.09.040.
Gupta, B.B., Quamara, M., 2020. An overview of Internet of Things (IoT): architec-
Research and Technological Development (DGRSDT) of the Algerian tural aspects, challenges, and protocols. Concurr. Comput. 32, 1e24. https://
Ministry of Higher Education and Scientific Research (MESRS). doi.org/10.1002/cpe.4946.
Harish Kumar, B., 2017. WSN based automatic irrigation and security system using
Raspberry pi board. In: 2017 International Conference on Current Trends in
References Computer, Electrical, Electronics and Communication (CTCEEC). IEEE,
pp. 1097e1103. https://doi.org/10.1109/CTCEEC.2017.8455140.
ADE, 2020. ADE, Algerian of Waters. https://www.ade.dz/. accessed 8.27.20. Hooda, D.S., Raich, V., 2016. Fuzzy Logic Models and Fuzzy Control : an Introduction.
Al-Qerem, A., Alauthman, M., Almomani, A., Gupta, B.B., 2020. IoT transaction Alpha Science International.
processing through cooperative concurrency control on fogecloud computing Ibrahim, F.S., 2018. Smart irrigation system using a fuzzy logic method. Int. J. Eng.
environment. Soft Comput 24, 5695e5711. https://doi.org/10.1007/s00500-019- Res. Technol. 11 (9), 1417e1436.
04220-y. Izzuddin, T.A., Johari, M.A., Rashid, M.Z.A., Jali, M.H., 2018. Smart irrigation using
Azaza, M., Tanougast, C., Fabrizio, E., Mami, A., 2016. Smart greenhouse fuzzy logic fuzzy logic method. ARPN J. Eng. Appl. Sci. 13 (2), 517e522.
based control system enhanced with wireless data monitoring. ISA Trans. 61, Jiang, J.A., Wang, C.H., Liao, M.S., Zheng, X.Y., Liu, J.H., Chuang, C.L., Hung, C.L.,
297e307. https://doi.org/10.1016/j.isatra.2015.12.006. Chen, C.P., 2016. A wireless sensor network-based monitoring system with
Bahat, M., Inbar, G., Yaniv, O., Schneider, M., 2000. A fuzzy irrigation controller dynamic convergecast tree algorithm for precision cultivation management in
system. Eng. Appl. Artif. Intell. 13 (2), 137e145. https://doi.org/10.1016/S0952- orchid greenhouses. Precis. Agric. 17, 766e785. https://doi.org/10.1007/s11119-
1976(99)00053-6. 016-9448-7.
Ben Ali, R., Aridhi, E., Abbes, M., Mami, A., 2016. Fuzzy logic controller of temper- Johansson, E.L., Fader, M., Seaquist, J.W., Nicholas, K.A., 2016. Green and blue water
ature and humidity inside an agricultural greenhouse. IREC 2016 - 7th Int. demand from large-scale land acquisitions in Africa. Proc. Natl. Acad. Sci. U.S.A.
Renew. Energy Congr. 1e6. https://doi.org/10.1109/IREC.2016.7478929. 113 (41), 11471e11476. https://doi.org/10.1073/pnas.1524741113.
Benyezza, H., Bouhedda, M., Djellout, K., Saidi, A., 2018a. Smart irrigation system Khanna, A., Kaur, S., 2019. Evolution of Internet of Things (IoT) and its significant
based Thingspeak and Arduino. In: 2018 International Conference on Applied impact in the field of precision agriculture. Comput. Electron. Agric. 157,
Smart Systems (ICASS). IEEE, pp. 1e4. https://doi.org/10.1109/ 218e231. https://doi.org/10.1016/j.compag.2018.12.039.
ICASS.2018.8651993. Kia, P.J., Far, A.T., Omid, M., Alimardani, R., Naderloo, L., 2009. Intelligent control
Benyezza, H., Bouhedda, M., Faci, N., Aissani, M., Rebouh, S., 2019. Greenhouse based fuzzy logic for automation of greenhouse irrigation system and evalua-
monitoring and fuzzy control system based on WSAN and IoT. 3rd. Int. Conf. tion in relation to conventional systems. World Appl. Sci. J. 6 (1), 16e23.
Appl. Autom. Ind. Diagnostics 1e5. https://doi.org/10.1109/ Krishnan, R.S., Julie, E.G., Robinson, Y.H., Raja, S., Kumar, R., Thong, P.H., Son, L.H.,
ICAAID.2019.8934984. 2020. Fuzzy logic based smart irrigation system using Internet of Things.
Benyezza, H., Bouhedda, M., Zerhouni, M.C., Boudjemaa, M., Abu Dura, S., 2018b. J. Clean. Prod. 252, 119902. https://doi.org/10.1016/j.jclepro.2019.119902.
Fuzzy greenhouse temperature and humidity control based on Arduino. In: Kumar, N., Poonia, V., Gupta, B.B., Goyal, M.K., 2021. A novel framework for risk
2018 International Conference on Applied Smart Systems (ICASS). IEEE, pp. 1e6. assessment and resilience of critical infrastructure towards climate change.
https://doi.org/10.1109/ICASS.2018.8652017. Technol. Forecast. Soc. Change 165 (C), 120532. https://doi.org/10.1016/
Bonanomi, G., D’Ascoli, R., Antignani, V., Capodilupo, M., Cozzolino, L., Marzaioli, R., j.techfore.2020.120532.
Puopolo, G., Rutigliano, F.A., Scelza, R., Scotti, R., Rao, M.A., Zoina, A., 2011. Li, M., Sui, R., Meng, Y., Yan, H., 2019. A real-time fuzzy decision support system for
Assessing soil quality under intensive cultivation and tree orchards in Southern alfalfa irrigation. Comput. Electron. Agric. 163 https://doi.org/10.1016/
Italy. Appl. Soil Ecol. 47, 184e194. https://doi.org/10.1016/j.apsoil.2010.12.007. j.compag.2019.104870.
Bouhedda, M., Benyezza, H., Toumi, Y., Rebouh, S., 2021. Fuzzy traffic lights Liao, M.-S., Chen, S.-F., Chou, C.-Y., Chen, H.-Y., Yeh, S.-H., Chang, Y.-C., Jiang, J.-A.,
controller based on PLC. In: Lecture Notes in Networks and Systems. Springer 2017. On precisely relating the growth of Phalaenopsis leaves to greenhouse
Science and Business Media Deutschland GmbH, pp. 447e456. https://doi.org/ environmental factors by using an IoT-based monitoring system. Comput.
10.1007/978-3-030-63846-7_42. Electron. Agric. 136, 125e139. https://doi.org/10.1016/J.COMPAG.2017.03.003.
Carrasquilla-Batista, A., Chaco n-Rodríguez, A., 2017. Proposal of a fuzzy logic Lindsay Bassett, 2015. Introduction to JavaScript Object Notation: A To-The-Point
controller for the improvement of irrigation scheduling decision-making in Guide to JSON. O’Reilly Media.
greenhouse horticulture. In: 2017 1st Conference on IEEE PhD Research in Liu, Z., Wang, F., Zhang, Y., Chen, X., Chen, C.L.P., 2014. Adaptive fuzzy output-
Microelectronics and Electronics Latin America, PRIME-LA 2017. Institute of feedback controller design for nonlinear systems via backstepping and small-
Electrical and Electronics Engineers Inc. https://doi.org/10.1109/PRIME- gain approach. IEEE Trans. Cybern. 44 (10), 1714e1725. https://doi.org/
LA.2017.7899172. 10.1109/TCYB.2013.2292702.
Cepeda, P., Ponce, P., Romero, D., Molina, A., 2011. Fuzzy C-means clustering tech- Lorvanleuang, S., Zhao, Y., Lorvanleuang, S., Zhao, Y., 2018. Automatic irrigation
nique applied for modeling parameters of an intelligent greenhouse open system using android. OALib 5 (4), 1e7. https://doi.org/10.4236/oalib.1104503.
control system. In: 2011 IEEE Electronics, Robotics and Automotive Mechanics Mamdani, E.H., Assilian, S., 1975. An experiment in linguistic synthesis with a fuzzy
Conference. IEEE, pp. 283e288. https://doi.org/10.1109/CERMA.2011.52. logic controller. Int. J. Man Mach. Stud. 7 (1), 1e13. https://doi.org/10.1016/
Clemmens, A.J., Dedrick, A.R., 1994. Irrigation Techniques and Evaluations. Springer, S0020-7373(75)80002-2.
Berlin, Heidelberg, pp. 64e103. https://doi.org/10.1007/978-3-642-78562-7_4. Mannini, P., Genovesi, R., 2013. IRRINET : large scale DSS application for on-farm
Danish, E., Onder, M., 2020. Application of fuzzy logic for predicting of mine fire in irrigation scheduling Atmosphere System: applications and Challenges IRRI-
underground coal mine. Saf. Health Work. 11 (3), 322e334. https://doi.org/ NET : large scale DSS application for on-farm irrigation scheduling. Procedia
10.1016/j.shaw.2020.06.005. Environ. Sci. 19, 823e829. https://doi.org/10.1016/j.proenv.2013.06.091.
de Fraiture, C., Wichelns, D., 2010. Satisfying future water demands for agriculture. Marzbanrad, J., Soleimani, G., Mahmoodi-K, M., Rabiee, A.H., 2015. Development of
Agric. Water Manag. 97 (4), 502e511. https://doi.org/10.1016/ fuzzy anti-roll bar controller for improving vehicle stability. J. Vibroeng. 17 (7),
j.agwat.2009.08.008. 3856e3864.
Deng, H., Qin, Z., Sha, L., Yin, H., 2020. A flexible privacy-preserving data sharing Mattoo, A., 2017. Achieving Sustainable Cultivation of Tomatoes, Achieving Sus-
scheme in cloud-assisted IoT. IEEE Internet Things J 7 (12), 11601e11611. https:// tainable Cultivation of Tomatoes. Burleigh Dodds Science Publishing. https://
doi.org/10.1109/JIOT.2020.2999350. doi.org/10.4324/9781351114158.
Difallah, W., Benahmed, K., Bounnama, F., Draoui, B., Saaidi, A., 2018. Intelligent Mei, F., Man, Z., Nguyen, T., 2001. Fuzzy modelling and tracking control of nonlinear
irrigation management system. Int. J. Adv. Comput. Sci. Appl. 9 (9), 429e433. systems. Math. Comput. Model. 33 (6e7), 759e770. https://doi.org/10.1016/
Dong, X., Vuran, M.C., Irmak, S., 2013. Autonomous precision agriculture through S0895-7177(00)00278-8.
integration of wireless underground sensor networks with center pivot irri- Michael, W., 2017. Using the NRF24L01 2.4GHz RF Control Module with the Arduino.
gation systems. Ad Hoc Netw. 11 (7), 1975e1987. https://doi.org/10.1016/ Molden, D., 2007. Water for Food Water for Life: A Comprehensive Assessment of
J.ADHOC.2012.06.012. Water Management in Agriculture. Francis and Taylor. https://doi.org/10.4324/
14
H. Benyezza, M. Bouhedda and S. Rebouh Journal of Cleaner Production 302 (2021) 127001
9781849773799. Sen, C., Ozturk, O., 2017. The relationship between soil moisture and temperature
Montazeri-Gh, M., Mahmoodi-K, M., 2016. Optimized predictive energy manage- vegetation on Kirklareli city Luleburgaz District A natural pasture vegetation.
ment of plug-in hybrid electric vehicle based on traffic condition. J. Clean. Prod. Int. J. Environ. Agric. Res. 3 (3), 21e29.
139, 935e948. https://doi.org/10.1016/j.jclepro.2016.07.203. Shah, J.L., Bhat, H.F., Khan, A.I., 2021. Integration of cloud and IoT for smart e-
Morison, J.I.L., Baker, N.R., Mullineaux, P.M., Davies, W.J., 2008. Improving water use healthcare. In: Healthcare Paradigms in the Internet of Things Ecosystem.
in crop production. Philos. Trans. R. Soc. B Biol. Sci. 363 (1491), 639e658. Elsevier, pp. 101e136. https://doi.org/10.1016/b978-0-12-819664-9.00006-5.
https://doi.org/10.1098/rstb.2007.2175. Shekhar, Y., Dagur, E., Mishra, S., Tom, R.J., Veeramanikandan, M.,
Munir, M.S., Bajwa, I.S., Cheema, S.M., 2019. An intelligent and secure smart wa- Sankaranarayanan, S., 2017. Intelligent IoT based automated irrigation system.
tering system using fuzzy logic and blockchain. Comput. Electr. Eng. 77, Int. J. Appl. Eng. Res. 12 (18), 7306e7320.
109e119. https://doi.org/10.1016/j.compeleceng.2019.05.006. Shinghal Kshitij, A.N., 2010. Wireless sensor networks in agriculture: for potato
Munir, M.S., Bajwa, I.S., Naeem, M.A., Ramzan, B., 2018. Design and implementation farming. Int. J. Eng. Sci. Technol. 2, 3955e3963.
of an IoT system for smart energy consumption and smart irrigation in tunnel Singh, A., 2019. Environmental problems of salinization and poor drainage in irri-
farming. Energies 11 (12). https://doi.org/10.3390/en11123427. gated areas: management through the mathematical models. J. Clean. Prod.
Nawandar, N.K., Satpute, V.R., 2019. IoT based low cost and intelligent module for 206, 572e579. https://doi.org/10.1016/j.jclepro.2018.09.211.
smart irrigation system. Comput. Electron. Agric. 162, 979e990. https://doi.org/ Stergiou, C.L., Psannis, K.E., Gupta, B.B., 2021. IoT-based Big data secure management
10.1016/j.compag.2019.05.027. in the fog over a 6G wireless network. IEEE Internet Things J 8 (7), 5164e5171.
Nikolidakis, S.A., Kandris, D., Vergados, D.D., Douligeris, C., 2015. Energy efficient https://doi.org/10.1109/jiot.2020.3033131.
automated control of irrigation in agriculture by using wireless sensor net- Sunitha Krishnan, K.S., Thampi, S.M., 2020. Deep learning approaches for IoT se-
works. Comput. Electron. Agric. 113, 154e163. https://doi.org/10.1016/ curity in the Big data era. In: Combating Security Challenges in the Age of Big
j.compag.2015.02.004. Data. Springer, pp. 105e135. https://doi.org/10.1007/978-3-030-35642-2_6.
Nikzad, A., Chahartaghi, M., Ahmadi, M.H., 2019. Technical, economic, and envi- Tahsien, S.M., Karimipour, H., Spachos, P., 2020. Machine learning based solutions
ronmental modeling of solar water pump for irrigation of rice in Mazandaran for security of Internet of Things (IoT): a survey. J. Netw. Comput. Appl. 161,
province in Iran: a case study. J. Clean. Prod. 239, 118007. https://doi.org/ 102630. https://doi.org/10.1016/j.jnca.2020.102630.
10.1016/j.jclepro.2019.118007. Touati, F., Al-Hitmi, M., Benhmed, K., Tabish, R., 2013. A fuzzy logic based irrigation
Papageorgiou, E.I., Kokkinos, K., Dikopoulou, Z., 2016. Fuzzy Sets in Agriculture. system enhanced with wireless data logging applied to the state of Qatar.
Fuzzy Logic in Its 50th Year. Springer, Cham, pp. 211e233. Comput. Electron. Agric. 98, 233e241. https://doi.org/10.1016/
Pathak, A., AmazUddin, M., Abedin, M.J., Andersson, K., Mustafa, R., Hossain, M.S., j.compag.2013.08.018.
2019. IoT based smart system to support agricultural parameters: a case study. Tzounis, A., Katsoulas, N., Bartzanas, T., Kittas, C., 2017. Internet of Things in agri-
Procedia Comput. Sci. 155, 648e653. https://doi.org/10.1016/ culture, recent advances and future challenges. Biosyst. Eng. 164, 31e48.
J.PROCS.2019.08.092. https://doi.org/10.1016/j.biosystemseng.2017.09.007.
Permale, H.K., Masturah, M.T., Abdullah, A.H., 2017. Automatic irrigation monitoring Velasco-Mun ~ oz, J.F., Aznar-S
anchez, J.A., Belmonte-Uren ~ a, L.J., Roma
n-Sanchez, I.M.,
system using android based application. J. Telecommun. Electron. Comput. Eng. 2018. Sustainable water use in agriculture: a review of worldwide research.
10. Sustainability 10 (4), 1e18. https://doi.org/10.3390/su10041084.
Ponnusamy, R., Rajaprakash, S., Jaichandran, R., 2017. Fuzzy logic controller for Villarrubia, G., De Paz, J.F., De La Iglesia, D.H., Bajo, J., 2017. Combining multi-agent
effective irrigation based on field soil moisture and availability of water. J. Adv. systems and wireless sensor networks for monitoring crop irrigation. Sensors
Res. Dyn. Contr. Syst. 9 (1). 17 (8). https://doi.org/10.3390/s17081775.
Popov, D., 2016. Little Node-RED Book: Getting Started with Node-RED. Scribbles Wark, T., Corke, P., Sikka, P., Klingbeil, L., Guo, Y., Crossman, C., Valencia, P., Swain, D.,
and Snaps. Bishop-Hurley, G., 2007. Transforming agriculture through pervasive wireless
Raut, R., Varma, H., Mulla, C., Pawar, V.R., 2018. Soil monitoring, fertigation, and sensor networks. IEEE Pervasive Comput 6 (2), 50e57. https://doi.org/10.1109/
irrigation system using IoT for agricultural application. In: Lecture Notes in MPRV.2007.47.
Networks and Systems: Intelligent Communication and Computational Tech- Yavuz, D., Kara, M., Suheri, S., 2012. Comparison of different irrigation methods in
nologies. Springer, pp. 67e73. https://doi.org/10.1007/978-981-10-5523-2_7. terms of water use and yield in potato farming. J. Selcuk Univ. Nat. Appl. Sci. 1
Rawal, S., 2017. IOT based smart irrigation system. Int. J. Comput. Appl. 159 (8), (2), 1e12.
7e11. https://doi.org/10.5120/ijca2017913001. Zadeh, L.A., 1988. Fuzzy logic. Computer 21, 83e93. https://doi.org/10.1109/2.53.
Revathi, S., Sivakumaran, N., 2016. Fuzzy based temperature control of greenhouse. Zhang, F., Guo, S., Zhang, C., Guo, P., 2019. An interval multiobjective approach
In: IFAC-Papers OnLine. Elsevier B.V., pp. 549e554. https://doi.org/10.1016/ considering irrigation canal system conditions for managing irrigation water.
j.ifacol.2016.03.112 J. Clean. Prod. 211, 293e302. https://doi.org/10.1016/j.jclepro.2018.11.111.
Rogers, L., Stanford-Clark, A., 2018. Wiring the IoT : Connecting Hardware with Zhang, N., Wang, M., Wang, N., 2002. Precision agricultureda worldwide overview.
Raspberry Pi. Node-Red, and MQTT. Comput. Electron. Agric. 36 (2e3), 113e132. https://doi.org/10.1016/S0168-
Ross, T.J., 2016. Fuzzy Logic with Engineering Applications. Wiley. 1699(02)00096-0.
SADEG, 2020. SADEG | Algerian Gas and Electricity Distribution Company. https:// Zhang, Q., Wu, C.H., Tilt, K., 1996. Application of fuzzy logic in an irrigation control
www.sadeg.dz/. accessed 8.27.20. system. Proc. IEEE Int. Conf. Ind. Technol. 593e597. https://doi.org/10.1109/
Seenu, N., Jeevanath, V.S., Mohan, M., 2018. Android based intelligent irrigation icit.1996.601660.
system. Int. J. Pure Appl. Math. 119 (7), 67e71.
15