A PROJECT REPORT
On
IOT Based Garbage Monitoring System Using Arduino
By
[Link] (Reg. No.: RA1611005010246)
[Link] (Reg. No.: RA1611005010086)
Under the guidance of
Dr. [Link], M.E., Ph.D
Associate Professor, EEE
FACULTY OF ENGINEERING AND TECHNOLOGY
SRM Nagar, Kattankulathur- 603 203
Kancheepuram Dist
APRIL 2019
ii
BONAFIDE CERTIFICATE
Certified that this project report titled “IOT Based Garbage Monitoring System
Using Arduino” is the bonafide work of [Link] (Reg. No.:RA1611005010246) and
[Link] (Reg. No.:RA1611005010086) who carried out the project work under my
supervision. Certified further, that to the best of my knowledge the work reported herein
does not form part of any other project report or dissertation on the basis of which a
degree or award was conferred on an earlier occasion on this or any other candidate.
Signature of the Guide Signature of the HOD
Dr. [Link], M.E., Ph.D Dr. [Link] KUMAR, M.E., Ph.D
Associate Professor, EEE Professor and Head
Department of EEE Department of EEE
SRM IST SRM IST
Internal Examiner External Examiner
Date:
ACKNOWLEDEMENT
iii
I would like to express my gratitude to our respected Director
(E&T),[Link] for their encouragement towards our growth
and activities.
I extend my sincere gratitude to Professor and Head of EEE Department, Dr.
[Link] KUMAR,SRM University, Kattankulathur for his commendable support and
encouragement towards the completion of project with perfection.
I owe my deep sense of gratitude to my Project Coordinators,
[Link] and [Link], Assistant Professors having extended their
fullest support in completing the project work.
I whole heartily thank to my guide, Mr. [Link] Associate Professor,
Department of Electrical and Electronics Engineering for standing by my side during the
hard days and being my Guide for this project.
I also heartily thank to, Mr. [Link] Assistant professor, Department
of Electrical and Electronics Engineering for helping me and extending his support for
this project.
Last but not the least; I would like to thank my Parents and Friends for the
supports, concerns and prayers, which were a major factor in the completion of this
project.
As everything begins and ends with God, I conclude this acknowledgement by
thanking God for everything.
(GURRAM V ANILKUMAR)
iv
ABSTRACT
We are living in an age where tasks and systems are fusing together with the power of
IOT to have a more efficient system of working and to execute jobs quickly! With all the
power at our finger tips this is what we have come up with.
The Internet of Things (IoT) shall be able to incorporate transparently and seamlessly a
large number of different systems, while providing data for millions of people to use and
capitalize. Building a general architecture for the IoT is hence a very complex task,
mainly because of the extremely large variety of devices, link layer technologies, and
services that may be involved in such a system.
One of the main concerns with our environment has been solid waste management which
impacts the health and environment of our society. The detection, monitoring and
management of wastes is one of the primary problems of the present era. The traditional
way of manually monitoring the wastes in waste bins is a cumbersome process and
utilizes more human effort, time and cost which can easily be avoided with our present
technologies. This is our solution, a method in which waste management is automated.
This is our IoT Garbage Monitoring system, an innovative way that will help to keep the
cities clean and healthy.
v
TABLE OF CONTENTS
CHAPTER TITLE PAGE
ABSTRACT iv
LIST OF TABLES vii
LIST OF FIGURES viii
1 INTRODUCTION 1
2 HARDWARE REQUIREMENTS 5
2.1 Arduino UNO 5
2.2 HC-SR04 Ultrasonic Sensor 6
2.2.1 HC-SR04 Sensor Features 6
2.3 GSM Module 7
2.4 8
2.5 9
2.6 9
2.6.1 Case study 1 10
2.6.2 Case study 2 10
3 DESIGN AND MODELLING 12
4 IMPLEMENTATION 18
4.1 Hardware Implementation 18
4.2 Software Implementation 21
5 SYSTEM TESTING 25
6 CONCLUSION 29
LIST OF TABLES
TABLE TITLE PAGE
1 Specification of Arduino 10
2 Pin number and their function 11
LIST OF FIGURES
vi
FIGURE TITLE PAGE
1 Flow Chart of Project 7
2 Arduino Uno Board 7
3 HC-SR04 Ultrasonic Sensor 8
4 GSM Module 14
5 Project Diagram 19
6 Circuit Diagram 19
CHAPTER 1
INTRODUCTION
We are living in an age where tasks and systems are fusing together with the power of
IOT to have a more efficient system of working and to execute jobs quickly! With all the
power at our finger tips this is what we have come up with. The Internet of Things (IoT)
shall be able to incorporate transparently and seamlessly a large number of different
vii
systems, while providing data for millions of people to use and capitalize. Building a
general architecture for the IoT is hence a very complex task, mainly because of the
extremely large variety of devices, link layer technologies, and services that may be
involved in such a system. One of the main concerns with our environment has been solid
waste management which impacts the health and environment of our society. The
detection, monitoring and management of wastes is one of the primary problems of the
present era. The traditional way of manually monitoring the wastes in waste bins is a
cumbersome process and utilizes more human effort, time and cost which can easily be
avoided with our present technologies. This is our solution, a method in which waste
management is automated. This is our IoT Garbage Monitoring system, an innovative
way that will help to keep the cities clean and healthy.
1.1 The Problem
Nowadays, there are tons of flats and apartments which have been built in the rapid
urbanization area. This is due to high housing demands which have been drastically risen
as a result of migration from villages to cities to find work. In order to accommodate the
growing population in the urban area, the government has also constructed more
apartment complexes. There are several issues faced by the residents of the flats. One of
them is disposal of solid waste. Unlike private houses, the residents of all the apartments
use a common dustbin, which tends to fill up very quickly. This overflowing of garbage is
a sanitary issue which might cause diseases like cholera and dengue. Moreover it is a
waste of fuel to travel around a complex or an area to find that some of the garbage are
filled and some are not. Also, on rare days, problems might arise that there is so much
garbage that the truck doesn’t have enough capacity. The idea struck us when we
observed that the garbage truck use to go around the town to collect solid waste twice a
day. Although this system was thorough it was very inefficient. For example let's say
street A is a busy street and we see that the garbage fills up really fast whereas maybe
street B even after two days the bin isn't even half full. This example is something that
actually happens thus it lead us to the ''Eureka'' moment!
viii
What our system does is it gives a real time indicator of the garbage level in a trashcan at
any given time. Using that data we can then optimize waste collection routes and
ultimately reduce fuel consumption. It allows trash collectors to plan their daily/weekly
pick up schedule. An Ultrasonic Sensor is used for detecting whether the trash can is
filled with garbage or not. Here Ultrasonic Sensor is installed at the top of Trash Can and
will measure the distance of garbage from the top of Trash can and we can set a threshold
value according to the size of trash can. If the distance will be less than this threshold
value, means that the Trash can is full of garbage and we will print the message “Basket
is Full” on the message and if the distance will be more than this threshold value, then we
will print the distance remaining for the garbage vat to be full.
CHAPTER 2
HARDWARE REQUIREMENTS
ix
We will need the following hardware to accomplish our project. 1. HC-SR04 ultrasonic
sensor. 2. Arduino Uno. 3. GSM module 4. Connecting wires.
2.1 ARDUINO UNO
Arduino is an open-source platform used for building electronics projects. Arduino
consists of both a physical programmable circuit board (often referred to as a
microcontroller) and a piece of software, or IDE (Integrated Development Environment)
that runs on your computer, used to write and upload computer code to the physical
board.
The Arduino platform has become quite popular with people just starting out with
electronics, and for good reason. Unlike most previous programmable circuit boards, the
Arduino does not need a separate piece of hardware (called a programmer) in order to
load new code onto the board – you can simply use a USB cable. Additionally, the
Arduino IDE uses a simplified version of C++, making it easier to learn to program.
Finally, Arduino provides a standard form factor that breaks out the functions of the
micro-controller into a more accessible package. The Arduino is a microcontroller board
based on the ATmega8. It has 14 digital -input/output pins (of which 6 can be used as
PWM outputs), 6 analog inputs, a16 MHz ceramic resonator, a USB connection, a power
jack, an ICSP header, and a reset button. It contains everything needed to support the
microcontroller; simply connect it to a computer with a USB cable or power it with a
ACto-DC adapter or battery to get started .The Uno differs from all preceding boards in
that it does not use the FTDI USB-to-serial driver chip. Instead, it features the
Atmega16U2 (Atmega8U2 up to version R2) programmed as a USB-to-serial
converter .Revision 2 of the Uno board has a resistor pulling the 8U2HWB line to ground,
making it easier to put into DFU mode. Revision of the board has the following new
features:
Pin out: added SDA and SCL pins that are near to the AREF pin and two other new pins
placed near to the RESET pin, the IOREF that allow the shields to adapt to the voltage
provided from the board. In future, shields will be compatible with both the board that
uses the AVR, which operates with 5V and with the Arduino Due that operates with
3.3V. The second one is a not connected pin that is reserved for future purposes.
Stronger RESET circuit.
AT mega 16U2 replace the 8U2.
x
"Uno" means one in Italian and is named to mark the upcoming release of Arduino 1.0.
The Uno and version 1.0 will be the reference versions of Arduino, moving forward. The
Uno is the latest in a series of USB Arduino boards, and the reference model for the
Arduino platform.
Parameters For Arduino UNO Description
Microcontroller ATmega328
Operating Voltage 5V
Input Voltage (recommended) 7-12V
Input Voltage (limits) 6-20V
Digital I/O Pins 14
Analog Input Pins 6
DC Current per I/O Pin 40mA
DC Current for 3.3V Pin 50mA
Flash Memory 32KB(ATmega328) of which 0.5KB used
by bootloader
SRAM 2KB (ATmega328)
EEPROM 1KB (ATmega328)
Clock Speed 16MHz
Length 68.6mm
Width 53.4mm
Weight 53g
xi
Table 1 : Specifications of Arduino
2.2 HC-SR04 ULTRASONIC SENSOR
HC-SR04 is an ultrasonic sensor which is used for measuring the distance between the
top of the lid to the top of the garbage.
PIN NUMBER PIN NAME DESCRIPTION
1. VCC The Vcc pin powers the sensor, typically with
+5V
2. Trigger Trigger pin is an Input pin. This pin has to be kept
high for 10us to initialize measurement by
sending US wave.
3. Echo Echo pin is an Output pin. This pin goes high for
a period of time which will be equal to the time
taken for the US wave to return back to the
sensor.
4. GND This pin is connected to the Ground of the system.
Table 2: Pin Number and Function of Ultrasonic sensor
2.2.1 HC-SR04 SENSOR FEATURES
Operating voltage: +5V
Theoretical Measuring Distance: 2cm to 450cm
Accuracy: 3mm
Measuring angle covered : <15 degrees
Operating Current: <15ma
Operating Frequency: 40Hz
2.2.2 ULTRASONIC SENSOR WORKING
xii
The HC-SR04 Ultrasonic (US) sensor is a 4 pin module, whose pin names are Vcc,
Trigger, Echo and Ground respectively. This sensor is a very popular sensor used in many
applications where measuring distance or sensing objects are required. The module has
two eyes like projects in the front which forms the Ultrasonic transmitter and Receiver.
The sensor works with the simple high school formula that
Distance = Speed × Time
The Ultrasonic transmitter transmits an ultrasonic wave, this wave travels in air and when
it gets objected by any material it gets reflected back toward the sensor this reflected
wave is observed by the Ultrasonic receiver module. Now, to calculate the distance using
the above formulae, we should know the Speed and time. Since we are using the
Ultrasonic wave we know the universal speed of US wave at room conditions which is
330m/s. The circuitry inbuilt on the module will calculate the time taken for the US wave
to come back and turns on the echo pin high for that same particular amount of time, this
way we can also know the time taken. Now simply calculate the distance using a
microcontroller or microprocessor.
2.3 GSM MODULE
GSM/GPRS module is used to establish communication between a computer and a
GSMGPRS system. Global System for Mobile communication (GSM) is an architecture
used for mobile communication in most of the countries. Global Packet Radio Service
(GPRS) is an extension of GSM that enables higher data transmission rate. GSM/GPRS
module consists of a GSM/GPRS modem assembled together with power supply circuit
and communication interfaces (like RS-232, USB, etc) for computer. GSM/GPRS
xiii
MODEM is a class of wireless MODEM devices that are designed for communication of
a computer with the GSM and GPRS network. It requires a SIM (Subscriber Identity
Module) card just like mobile phones to activate communication with the network. Also
they have IMEI (International Mobile Equipment Identity) number similar to mobile
phones for their identification. A GSM/GPRS MODEM can perform the following
operations:
1. Receive, send or delete SMS messages in a SIM.
2. Read, add, search phonebook entries of the SIM.
3. Make, Receive, or reject a voice call. The MODEM needs AT commands, for
interacting with processor or controller, which are communicated through serial
communication. These commands are sent by the controller/processor. The MODEM
sends back a result after it receives a command. Different AT commands supported by the
MODEM can be sent by the processor/controller/computer to interact with the GSM and
GPRS cellular network.
A GSM modem is a wireless modem that works with a GSM wireless network. A
wireless modem behaves like a dial-up modem. The main difference between them is that
a dial-up modem sends and receives data through a fixed telephone line while a wireless
modem sends and receives data through radio waves.
A GSM modem can be an external device or a PC Card / PCMCIA Card. Typically, an
external PC Card / PCMCIA Card is designed for use with a laptop computer. It should
be inserted into one of the PC Card / PCMCIA Card slots of a laptop computer. Like a
GSM mobile phone, a GSM modem requires a SIM card from a wireless carrier in order
to operate. A SIM card contains the following information:
Subscriber telephone number (MSISDN)
International subscriber number (IMSI, International Mobile Subscriber Identity)
State of the SIM card
Service code (operator)
Authentication key
PIN (Personal Identification Code)
xiv
PUK (Personal Unlock Code) Computers use AT commands to control modems. Both
GSM modems and dial-up modems support a common set of standard AT commands. In
addition to the standard AT commands, GSM modems support an extended set of AT
commands. These extended AT commands are defined in the GSM standards. With the
extended AT commands, the following operations can be performed:
Reading, writing and deleting SMS messages.
Sending SMS messages.
Monitoring the signal strength.
Monitoring the charging status and charge level of the battery.
Reading, writing and searching phone book entries.
2.4 NodeMCU
xv
CHAPTER 3
DESIGN AND MODELLING
In this section we design structure of the system before implementation of [Link] use
advanced microcontroller called Arduino (ATmega8). It has in built with many
components like analog to digital converter, clock of 16 MHz, shift registers. In this
project we put the ultrasonic sensor on top of the garbage bin/ dump. The output of the
ultrasonic sensor is processed by the Arduino and the output is then sent to the GSM
module which sends a text message to the concerned person. We have a threshold value
of [Link] means that if the distance of the sensor from the top of the garbage is less
than 5cm, the output will come with a message that the basket is full. Also, a buzzer will
ring if output is less than 5cm.
xvi
CHAPTER 4
IMPLEMENTATION
4.1 Hardware Implementation
Connections of the ultrasonic sensor with the Arduino are very simple. Connect
the VCC and the ground of the ultrasonic sensor to the 5V and the ground of the Arduino.
Then connect the TRIG and ECHO pin of ultrasonic sensor to the pin 11 and 12 of the
Arduino respectively(you can use any other pin as well).Connect the RX pin of the
arduino with the TX pin of the GSM module and the TX pin of the arduino with the RX
pin of the GSM module. Connect the GND of the arduino to the ground of the module.
Also, the GSM module needs an external 12v supply.
Figure 4: Circuit Diagram
4.2 SOFTWARE IMPLEMENTATION
4.2.1 ARDUINO IDE
The open-source Arduino Software (IDE) makes it easy to write code and upload
it to the board. It runs on Windows, Mac OS X, and Linux. The environment is written in
Java and based on Processing and other open-source software. This software can be used
with any Arduino board. The Arduino development environment contains a text editor for
writing code, a message area, a text console, a toolbar with buttons for common
functions, and a series of menus. It connects to the Arduino hardware to upload programs
and communicate with them. Software written using Arduino are called sketches. These
sketches are written in the text editor. Sketches are saved with the file extension .ino. It
has features for cutting/pasting and for searching/replacing text. The message area gives
feedback while saving and exporting and also displays errors. The console displays text
output by the Arduino environment including complete error messages and other
xvii
information. The bottom right-hand corner of the window displays the current board and
serial port. The toolbar buttons allow you to verify and upload programs, create, open,
and save sketches, and open the serial monitor.
4.2.2 Source Code
#include <SoftwareSerial.h>
SoftwareSerial BT(0, 1); //TX, RX respetively
#include <LiquidCrystal.h>
LiquidCrystal lcd(12, 11, 5, 4, 3, 2);
int trigpin = 10; // Initializing Ultrasonic's Trigger pin
int echopin = 9; // Initializing Ultrasonic's Echo pin
int distance = 0;
int duration = 0;
int button = 13;
int rled = 6;
int yled = 7;
int gled = 8;
void setup()
[Link](9600);
[Link](9600);
pinMode(trigpin,OUTPUT);
pinMode(echopin,INPUT);
xviii
pinMode(button,INPUT); //limit switch to check the garbage can is open or close
digitalWrite(button, HIGH);
pinMode(rled,OUTPUT); //90%
pinMode(yled,OUTPUT); //50% to 90%
pinMode(gled,OUTPUT); //less than 50%
digitalWrite(rled,HIGH);
digitalWrite(yled,HIGH);
digitalWrite(gled,HIGH);
[Link](16, 2);
[Link](0, 0);
[Link](" Smart Garbage ");
[Link](0, 1);
[Link](" Monitoring ");
delay(2000);
[Link]();
void loop()
[Link]();
delay(500);
digitalWrite(trigpin,LOW);
xix
delayMicroseconds(5);
digitalWrite(trigpin,HIGH);
delayMicroseconds(5);
digitalWrite(trigpin,LOW);
duration = pulseIn (echopin,HIGH);
distance= duration/29/2;
[Link]("Distance: ");
[Link](distance);
[Link](" cm");
[Link](" \t");
[Link](0, 0);
[Link]("Distance: ");
[Link](distance);
[Link](" cm");
if(digitalRead(button)==1)
{
[Link]("Please close the garbage can");
[Link](0, 1);
[Link]("Close garbagecan");
digitalWrite(rled,LOW);
delay(800);
digitalWrite(rled,HIGH);
delay(50);
}
xx
else if((distance<=10) && (digitalRead(button)==0))
{
[Link]("Garbage level: Full");
[Link](0, 1);
[Link]("Level: ");
[Link]("90 %");
digitalWrite(rled,LOW);
delay(800);
digitalWrite(rled,HIGH);
delay(50);
}
else if((distance<=25) && (distance>10) && (digitalRead(button)==0))
{
[Link]("Garbage level: Half-filled");
[Link](0, 1);
[Link]("Level: ");
[Link]("50 %");
digitalWrite(yled,LOW);
delay(800);
digitalWrite(yled,HIGH);
delay(50);
}
else if((distance>25) && (digitalRead(button)==0))
{
xxi
[Link]("Garbage level: Empty");
[Link](0, 1);
[Link]("Level: ");
[Link]("10 %");
digitalWrite(gled,LOW);
delay(800);
digitalWrite(gled,HIGH);
delay(50);
}
[Link](" ");
delay(2000);
}
xxii
CHAPTER 5
IDENTIFICATION OF NEURAL ARCHITECTURE FOR ELD
PROBLEM
In chapter 4, LM algorithm is identified to be most suitable for off-line training of
NN for ELD problems. In this chapter, the single layer and multilayer architectures are
chosen for investigation. The chosen architectures are trained with LM algorithm. The
NN models are compared in terms of compactness and complexity. The results are
validated extensively for IEEE 26 BUS systems. The suitable neural architecture is
identified.
5.1 COMPARISON OF NEURAL ARCHITECTURES FOR ON-LINE
ECONOMIC LOAD DISPATCH PROBLEM
The popular single layer and multilayer feed-forward architecture are designed for
on-line economic load dispatch problem. The IEEE 26 Bus system is considered for
investigation. There are totally six generators. Around 120 data sets are obtained using
Lambda iteration method for various load demands (100 for training and 20 for testing).
The input to NN Model is power demand (P D). The outputs are the real power generation
of six generators (PG1, PG2, PG3, PG4, PG5, PG6), loss (PL), cost (C).The activation function for
hidden and output layers is chosen as tan-sigmoid and pure linear function respectively.
For comparison, both the NN architectures are trained with the same input/output data
using the Levenberg-Marquardt algorithm for the target accuracy of 1×10-7. The structure
obtained for single layer and multilayer feed-forward is 1-68-8 and 1-15-15-8
respectively. The designed two architectures are used to solve economic load dispatch
problem. The performance of both the architectures is compared in terms of accuracy and
compactness.
The designed SLFF-NN model and MLFF-NN model are compared in terms of
accuracy. 20 data sets are used for testing the SLFF-NN and MLFF-NN. The sample
results for loss and cost along with error curve for both the architectures are presented in
Figure (5.1) and Figure (5.2) respectively. From the results obtained, it is found that the
outputs obtained from multilayer architecture are found to closely match with the
conventional method as compared to SLFF-NN architecture. The average error for single
and multi layer architecture is consolidated and presented in Table (5.1). From the Table
xxiii
(5.1), it is observed that the average error for multi layer is lesser as compared to the
single layer architecture. This is due to the high degree of non-linear mapping capability
of the multilayered structure.
(a) (b)
Figure 5.1 Power Loss (a) SLFF-NN (b) MLFF-NN
(c) (d)
Figure 5.2 Cost($/Hr) (c) SLFF-NN (d) MLFF-NN
Table 5.1 Average Error for SLFF-NN and MLFF-NN
Outputs %Average Error Outputs %Average Error
Single Single
Multi layer Multi layer
layer layer
xxiv
PG1 -0.0169 0.008662 PG5 -0.0598 -0.01938
PG2 0.0127 0.001407 PG6 -0.0142 -0.00373
PG3 -0.0481 -0.03735 PL -0.124 -0.11677
PG4 -0.0418 -0.00842 Cost 0.233 -0.00829
The performance of SLFF-NN and MLFF-NN is compared in terms of structural
compactness and computational complexity which assumes importance for real time on-
line economic load dispatch problem. The number of parameters for the feed-forward
architecture can be calculated using the formula (5.1). As SLFF-NN is a special case of
MLFF-NN with one hidden layer, the same formula (5.1) suits both type of FF-NN.
M m -1 m M m
S S S
m=1 m=1
PMLFF = weights biases 5.1
The number of parameters and neurons required for SLFF-NN and MLFF-NN are
presented in Table 2. In terms of compactness, multilayer network requires lesser number
of neurons as compared to single layer network. The total number of parameters required
for multilayer feed-forward architecture is lesser as compared to single layer architecture.
Table 5.2 Performance Comparison of NN Models in terms of complexity
NN FF-NN Computational Complexity
Architecture Architecture No. of No. of
Neurons Parameters
SLFF 1-68-8 76 688
MLFF 1-15-15-8 38 398
The Multilayer feed-forward architecture is approximately 2 times more compact
as compared to single layer architecture. The multilayer feed-forward neural Network
model provides the required accuracy with lesser number of neurons/parameters as
xxv
compared to single layer feed-forward neural network. Thus multilayer architecture is
more compact and gives required accuracy. Hence it is concluded that the MLFF-NN is
found to be more suitable for on-line Load dispatch.
This project carries out a new type of investigation on the neural architectures for
on-line load dispatch which is the major contribution of this paper. The popular SLFF-
NN and MLFF-NN architecture are considered for investigation. The two architectures
are trained with same input/output data using LM algorithm for the same target accuracy.
The results are validated for IEEE 26 bus system. From the results obtained, the MLFF-
NN is found to result in the most compact architecture with much lesser number of
neurons/parameters as compared to SLFF-NN. Thus it is concluded that the MLFF-NN is
compact, accurate and suitable for on-line economic Load Dispatch problem.
The Multilayer feed-forward architecture is approximately 2 times more compact
as compared to single layer architecture. The multilayer feed-forward neural Network
model provides the required accuracy with lesser number of neurons/parameters as
compared to single layer feed-forward neural network. Thus multilayer architecture is
more compact and gives required accuracy. Hence it is concluded that the MLFF-NN is
found to be more suitable for on-line Load dispatch.
xxvi
CHAPTER 6
CONCLUSIONS
Economic load dispatch (ELD) is an important function in power system planning
and Operation. The conventional Lambda iteration method is computationally rigorous
and time consuming and may not suitable for on-line applications. Thus NN provides an
alternate solution for ELD problems. Many papers on NN based ELD are reported in
literature and it is currently under active area of research.
The major issues in NN based ELD are the NN model used for ELD should be
simple, structurally compact and computationally less complex, accurate. This in turn to
an extent depends on the type of neural architectures and learning algorithms. Three types
of learning algorithms namely BPM, VLR, LM and two types of neural architectures
namely SLFF-NN and MLFF-NN are considered for investigation. Various architectures
and learning algorithms are used to solve ELD problems. The results are extensively
validated on IEEE 26 BUS system. From the investigation, it is identified that the LM
algorithm is suitable for off-line training of NN for ELD problems. The MLFF-NN is
identified to be suitable architecture for ELD problems.
REFERENCES
1. Modern Power System Analysis by DP kothari and I J Nagrath.
2. A. J. Wood and B. F. Wollenberg, Power Generation, Operation and Control. New
York: Wiley, 1996.
3. Shoults RR, Mead MM. Optimal estimation of piece-wise linear incremental cost
curves for EDC. IEEE Trans Power Appar Syst 1984;PAS-103:1432–8.
4. Lin CE, Viviani GL. Hierarchical economic dispatch for piecewise quadratic cost
functions. IEEE Trans Power Appar Syst 1984;PAS-103:1170–5.
5. [Link], Y.T. Cha, and J.H. Park, “Short-term load forecasting using an artificial
neural network. “IEEE Trans. Power Syst., vol.7, no.1, pp.124-132, Feb.1992.
6. Short-term load forecast of a low load factor power system for optimization of
merit order dispatch using adaptive learning algorithm by [Link],
[Link].
xxvii
7. C.N. Lu, [Link] and [Link]: "Neural Network Based Short Term Load
Forecasting", IEEE Transactions on Power Systems, Vol.8 No.1, pp. 336-342,
1993.
8. J. H. Park, Y. S. Kim, I. K. Eom, K.Y. Lee, “Economic load dispatch for piecewise
quadratic cost function using Hopfield neural network,” IEEE Trans. on Power
Systems, pp. 1030-1038, vol.8, no.3, 1993.
9. C.T. Su & C.T. Lin , “New approach with a Hopfield Modeling Framework to
Economic Disptch,” IEEE Trans. on Power Systems, vol.16, no.1, Feb. 2001
10. N Chakraborty, S. Chakraborty & P. K. Mukherjee, “Adaptive ANN Applied to
Optimize Economy in Generation System with Transmission Loss,” IE(I) Journal-
EL, pp.212-219, vol. 77, 1997
11. M.R. Gent and J.W. Lamont, “Minimum Emission Dispatch”, IEEE Trans. on
Power App. and Syst., [Link]-90, Nov./Dec. 1972, pp. 2650- 2660.
