CHAPTER 1

1.1. INTRODUCTION
Electrical load forecasting is very important for utilities and power system operators to
meet the load plus the energy lost in power systems. Therefore, many operating decisions such as
economic allocation of generation, security analysis and maintenance planning are based on load
forecasts. The load forecasts are typically programmed from a few minutes to an hour ahead or
as much as 20 years into the future. Electrical load forecasting is divided into four types: long
term, medium term, short term and very short term. The short-term load forecasting is a
prediction of load from 1 hour to 1 week.

In this paper, the problem of load forecasting is constrained to short term load forecasting
and is expressed as fuzzy linear estimation problem. Different membership functions, for load
parameters are used namely triangular membership and trapezoidal functions. The main
objective is to minimize the error between the actual load value and forecasted value of the
available data points. Short term load forecasting is an integral part of power system operation
and is used to predict load demand up to a week ahead so that day to day operation of a power
system can be efficiently planned and the operating cost can be minimized. Though Load
forecasting is not an easy task to perform. The load on buyer side is complex. Also there are
numerous significant externally affecting variables that should be taken into account such as
weather, time economic situation and random disturbance.

The prime duty of any utility is to provide reliable power to customers. Customer load
demand in electric distribution systems is subject to change because human activities follow
daily, weekly, and monthly cycles. The estimation of future active loads at various load buses
ahead of actual load occurrence is known as load forecasting. If it is done inappropriately, then
the direct effect is on the planning for the future load. Also the result is the difference of the load
that will develop from the planning done for the same, and eventually the entire planning process
is at risk. As the utility supply and consumer demand is fluctuating and the change in weather
conditions, energy prices increases by a factor of ten or more during peak load, load forecasting
is vitally important for utilities.
 In this study MATLAB program is used for load forecast using fuzzy logic. A
formulation of Fuzzy Logic System (FLS) used to construct nonparametric models of nonlinear
processes, given only input– output data.
 ABSTRACT

Load forecasting is an important component for power system energy management

system. Precise load forecasting helps the electric utility to make unit commitment decisions,
reduces spinning reserve capacity and schedule device maintenance plan properly. It also reduces
the generation cost and increases reliability of power systems. In this work, a fuzzy logic
approach for short term load forecasting is attempted. Time, temperature and similar previous
day load are used as the independent variables for short term load forecasting. Based on the time,
temperature and similar previous day load, fuzzy rule base are prepared using Mamdani
implication, which are eventually used for the short term load forecasting. MATLAB
SIMULINK software is used here in this work for system designing and simulation. For the short
term load forecasting, load data from the 132kv sub-station, Indapur (load control center) is
considered.
 LITERATURE REVIEW

In this paper[1],the main objective is to minimize the error between the actual load value
and forecasted load value of the available data points. Fuzzy model are developed for crisp load
power with fuzzy load parameters and for fuzzy load power with fuzzy load parameters. The
fuzzy parameters are obtained for the model. These parameters are used to predict the load as
fuzzy function for 24 hours ahead. Data has been used for PSTCL, 220 KV SUB-STATION
V.P.O.Pakhowal Dist Ludhiana, Punjab

In this paper [2], In this work, a fuzzy logic approach for short term load forecasting is
attempted. Time, temperature and similar previous day load are used as the independent
variables for short term load forecasting. Based on these variables, fuzzy rule base are prepared
using Mamdani implication, which are eventually used for the short term load forecasting.
MATLAB SIMULINK software is used in this work for system designing and simulation. For
the short term load forecasting, load data from specific area load control center is considered.
The work load forecasting is done with an error varies between +12.14% to -9.48 %.

very close values to the actual data and are the alternative way for short-term
load forecasting in Turkey
In this paper [4] neural networks and combined Fuzzy Logic, for long term
load forecasting is proposed. In this paper the This paper [3], shows that fuzzy
logic can give good results in very large test data sets for 1 year. Besides, for
countries with large areas, the temperature data taken from only one point would
lead to increase the forecasting errors. Therefore, the average of temperature for six
cities having the maximum power consumption is weighted average. The mean
absolute percentage errors of the fuzzy logic and ANFIS models in terms of
prediction accuracy are obtained as 2.1 and 1.85, respectively. The results show
that the proposed fuzzy logic and ANFIS models are capable of load forecasting
efficiently and produce relationship between the humidity, temperature and load is
identified with a case study for a particular region in Oman. The output load
obtained is corrected using a correction factor from neural networks, which
depends on the previous set of loads, number of customers etc. The data is taken
for the three years and the results are obtained for the fourth year. It is further
validate using the actual data from an electrical company.
In this paper [5] The aim of this paper is to review and classify short term
electric load forecasting methods. have discussed the review of STLF. The earliest
survey for load forecasting was carried out by Matthewman and Nicholson (1968) .
After Moghram and Rahman (1989) who has done a review of load foresting
techniques.Many new techniques have introduced. Hasham and Mohammad
(2002) has given an excellent survey and comparison of different load forecasting
methods.
1.2 Objectives :-

The main objectives of this study are to:-

i.)The main objective is to minimize the error between the actual load value and Forecasted
value of the available data points.

ii.) Design of fuzzy logic system for short term electric load forecasting.

iii) For proper planning of power system.

iv) For proper planning of transmission & distribution planning.

v) For proper power system operation, financing, man power development,

grid formation, energy sales.

 CHAPTER 2

Load Forecasting

2.1.Load Forecasting:-

Accurate models for electric power load forecasting are essential to the
operation and planning of a utility company. Load forecasting helps an electric
utility to make important decisions including decisions on purchasing and
generating electric power, load switching, and infrastructure development. Load
forecasts are extremely important for energy suppliers, ISOs, financial institutions,
and other participants in electric energy generation, transmission, distribution, and
markets. Load forecasts can be divided into three categories: short-term fore-casts
which are usually from one hour to one week, medium forecasts which are usually
from a week to a year , and long-term forecasts which are longer than a year. The
forecast for different time horizons are important for different operations within a
utility company. The natures of these forecasts are different as well. For example,
for a particular region, it is possible to predict the next day load with an accuracy
of approximately 1-3%. However, it is impossible to predict the next year peak
load with the similar accuracy since accurate long-term weather forecasts are not
available. For the next year peak forecast, it is possible to provide the probability
distribution of the load based on historical weather observations. It is also possible,
according to the industry practice, to predict the so-called weather normalized load,
which would take place for average annual peak weather conditions or worse than
average peak weather conditions for a given area. Weather normalized load is
the load calculated for the so-called normal weather conditions which are the
average of the weather characteristics for the peak historical loads over a certain
period of time. The duration of this period varies from one utility to another. Most
companies take the last 25-30 years of data.

Load forecasting has always been important for planning and operational
decision conducted by utility companies. However, with the deregulation of the
energy industries, load forecasting is even more important. With supply and
demand fluctuating and the changes of weather conditions and energy prices
increasing by a factor of ten or more during peak situations, load forecasting is
vitally important for utilities. Short-term load forecasting can help to estimate load
flows and to make decision that can prevent overloading. Timely implementations
of such decisions lead to the improvement of network reliability and to the reduced
occurrences of equipment failures and blackouts. Load forecasting is also
important for contract evaluations and evaluations of various sophisticated
financial products on energy pricing offered by the market. In the deregulated
economy, decisions on capital expenditures based on long-term forecasting are also
more important than in a non-deregulated economy when rate increases could be
justified by capital expenditure projects. Most forecasting methods use statistical
techniques or artificial intelligence algorithms such as regression, neural networks,
fuzzy logic, and expert systems. Two of the methods, so-called end-use and
econometric approach are broadly used for medium- and long-term forecasting.
variety of methods, which include the so-called similar day approach, various
regression models, time series, neural networks, statistical learn-ing algorithms,
fuzzy logic, and expert systems, have been developed for short-term forecasting.
As we see, a large variety of mathematical methods and ideas have been used for
load forecasting. The development and improvements of appropriate mathematical
tools will lead to the development of more accurate load forecasting techniques.
The accuracy of load forecast in depends not only on the load forecasting
techniques, but also on the accuracy of forecasted weather scenarios. Weather
forecasting is an important topic which is outside of the scope of this chapter. We
simply mention significant progress in the development of computerized weather
forecasting systems, including the scale Model MM5 developed and supported by
a consortium of universities

The load forecasting is totally based on time and hence classified under three categories :-

1. Short term load forecasting:-

2. Medium term load forecasting

3. Long term load forecasting

2.1.1 Short term load forecasting:-

Short-term load forecasting methods Short-term load forecasting draws much attention. A
variety of methods using statistical techniques or artificial intelligence algorithms, which include
regression models, time series, neural networks, statistical learning algorithms, fuzzy logic, or
expert systems, have been developed for short-term forecasting .These methods all have been
succeeded in short-term load forecasting problems. The success of a forecasting technique
depends not only on the approach but also on the quality of input data which could contain
proper patterns representing the system dynamics. In general, the load presents two distinct
patterns: weekday and weekend load patterns. Weekday patterns include Tuesday through Friday
and weekend patterns include Sunday through Monday. In addition, holiday patterns are different
from non-holiday patterns. A large variety of statistical and artificial intelligence techniques have
been developed for short-term load forecasting

2.1.2.Medium- and long-term load forecasting:-

The end-use modeling, econometric modeling, and their combinations are the most often
used methods for medium- and long-term load forecasting. Descriptions of appliances used by
customers, the sizes of the houses, the age of equipment, technology changes, customer behavior,
and population dynamics are usually included in the statistical and simulation models based on
the so-called end-use approach. In addition, economic factors such as per capita incomes,
employment levels, and electricity prices are included in econometric models. These models are
often used in combination with the end-use approach.
Long-term forecasts include the forecasts on the population changes, economic
development, industrial construction, and technology development. End-use models. The end-
use approach directly estimates energy consumption by using extensive information on end use
and end users, such as appliances, the customer use, their age, sizes of houses, and so on.
Statistical information about customers along with dynamics of change is the basis for the
forecast. End-use models focus on the various uses of electricity in the residential, commercial,
and industrial sector. These models are based on the principle that electricity demand is derived
from customer’s demand of light, cooling, heating, refrigeration, etc. Thus end-use models
explain energy demand as a function of the number of appliances in the market ideally this
approach is very accurate. However, it is sensitive to the amount and quality of end-use data. For
example, in this method the distribution of equipment age is important for particular types of
appliances.
End-use forecast requires less historical data but more information about customers and
their equipment.Econometric models. The econometric approach combines economic theory and
statistical techniques for forecasting electricity demand. The approach estimates the relationships
between energy consumption (dependent variables) and factors influencing consumption. The
relationships are estimated by the least-squares method or time series methods.One of the options
in this framework is to aggregate the econometric approach, when consumption in different
sectors (residential, commercial, industrial, etc.) is calculated as a function of weather, economic
and other variables, and then estimates are assembled using recent historical data. Integration of
the econometric approach into the end-use approach introduces behavioral components into the
end-use equations.

2.2. Load Forecasting Techniques

A. Multiple Regression Method

B. Exponential Smoothing

C. Iterative Reweighted Least Square

D. Adaptive Load Forecasting

E. Stochastic Time Series

F. Armax Model

G. Similar Day Look Up Approach

H. Statically Robust Method

I. Delpha Technique

J. End Use Analysis

K. Fuzzy Logic

L. Artificial Neural Network

M. Support Vector Machine

N. Expert System

O. Econometric Method

A. MULTIPLE REGRESSION METHOD

Multiple regression (Matthew man 1968) [25] uses a dependent variable to determine
independent variable through modeling. The load should found in terms of independent as well
as dependent variables, the model uses the form as equation-1

Y=o+1x1+2x2+……….+kXk…….(1)

Where y is the load,

x1, x2 & xk are the affecting factors

o,1 & k are the regression parameters with respect to x1,x2& xk

And  is an error term

This method is very sensitive to temperature variation and a small change may give a
considerable change in forecast. A change in temperature is directly responsible for load
variation; the calculation and simulation for those of the Bangladesh power system in done by
Nahid-Al-Masood et al with a linear regression model. Where the system has energy limitations
and seasonal forecast is efficiently possible through regression based model has discussed.

B. Exponential Smoothing

This method uses data of the energy consumption in history and based on time series
(Christiaanse 1971). Smoothing method smoothed the data for estimates. Following types of
exponential smoothing is used presently [34]

 First order exponential smoothing

 Second order exponential smoothing
 Higher order exponential smoothing
 Holt-Winters mechanism

C. ITERATIVE REWEIGHTED LEAST SQUARE

The method uses an operator to control one variable at a time [8] The starting point finds through
an operator. The method takes an autocorrelation function as well as a partial autocorrelation
function to find a model of load dynamics. A three way optimal model is identified; weighting
function, tuning constant and weighted sum of the squared residuals. Consider a linear equation-
2 for parameter estimation:

Y = X+……(2)

Where

Y is vector of observations of n×1 matrix

X is a coefficient of n × p matrix

 is unknown parameter of p × 1 matrix

 is random error of m × 1 matrix

Mbamalu and El-Hawar proposed an interactive approach employing least-squares and the IRLS
procedure for estimating the parameters of a seasonal multiplicative autoregressive model. The
large scale nonlinear load forecasting is possible through least squares with support vector.

d.Adoptive Load Forecasting

Adoptive load forecasting is based on continuous correction of data. It can be used as an online
software system for utilities to control the flow of power which uses the Kalman filter theory
with current prediction error and the current weather data acquisition programs to estimate the
next state vector.

e. stochastic time series

Time series method has been the most popular method although it has several drawbacks such as
complex to use, require more time and historical data for prediction but in today’s most complex
system and system of fast development in the context of energy generation and demand method
has difficulty to predict however it has been used for STLF [ 36, 8] . The remaining models of
time series uses are:

1. Autoregressive (AR) model

2. Autoregressive moving-average (ARMA) model

3. Autoregressive integrated moving-average (ARIMA) model

f.Similar Day Look Approach

Similar day look up approach uses the historical data of a few years back which has similar
weather conditions, similar days in week, similar regional activities. Now a day’s forecast
through similar day look up approach uses a combination of several days through linearly or
through regression [43]. The technique has its own limitations as the demographic situation for
similar day may get changed and it will deflect our forecast from accuracy.

g. Fuzzy Logic

The fuzzy logic method for load forecasting has accuracy and less time required for computation.
Fuzzy method needs no of mathematical models for mapping between input & output. It uses the
For precise output & unknown dynamic system; which is possible in fuzzy logic through
centroid defuzzification [ 13]. Fuzzy logic has an excellent capacity to draw similarities from the
same data [40]. Liu et al. (1996) [41] saw that fuzzy system is capable of drawing similarities
from a large amount of data which may define as,

Vk=(Lk-Lk-1)/T

Ak=(Vk-Vk-1)/T

Where

Vk= First order difference

Ak =Second order differences

There have been two stage always have been include; training and online forecast work . During
the training session measured data of previous load are used to train the system with selection of
variables in linguistic form where the fuzzification is processed are forecast is done through
approximation and then defuzzification is carried out to show the output. The block diagram
shows in its processing system:
The input variables are all those which ultimately affect electricity consumption are as day’s
maximum temperature, day’s minimum temperature, working day, holidays, day’s capacity etc. .
The fuzzy logic approach is very adoptive and may use with other methods and may mix with
geometric techniques like Euclidean norms

H. ARTIFICIAL NEURAL NETWORK

In a neural network, the basic element is the neuron. The neurons get information from a
source and combine and perform an operation with them and produce results [8]. The artificial
neural network was starting development in mid 1980s; these are still in very early stage
although we find an extraordinary perforation from the system based on pattern recognition
observed from past event and estimations the values for prediction in future. ANN is capable to
approximate any function numerically for required accuracy and is data driven method which
provide facility to the user that tentative model. Liu et al.uses a fully connected feed forward
type neural network where Damborg et al wrote neural network offers potential to overcome
reliance on the functional form of a load forecasting model. Daniel Ortiz-Arroyo et al.gives
accurate load forecasting with ANN with analyzing the problem and choosing an appropriate
domain. K. Liu et al gives the comparative study of methods of load forecasting specially ANN.
Hesham K. Alfares et al gives an excellent comparative study on ANN models and previous
work on it. D.C. Park et al gives ANN model for electrical load forecasting. Paras Mandal et al
gave a several hours ahead load forecasting model using ANN. Y. Rui et al gave a review on
comparative models on ANN. Guoqiang Zhang et al shown a state of art load forecasting using
ANN. G.A. Adepoju et al gave application of ANN for load forecasting in the Nigerian power
system. Sanjib Mishra and SK Patraforecast electrical load using neural network and hybrid it
with an artificial immune system. Load forecasting with ANN is closer to real load but at peaks
the errors are more; at these peaks the reduction in error is possible using rough set conception.

I. KNOWLEDGE BASED EXPERT SYSTEM

Expert systems are the result of advancement in Artificial Intelligence in last two decades. It is a
software program which acts as an expert system. The program has the ability to reason, explain
and expand new information. The model for load forecasting is created using knowledge from
experts. Above is called an acquisition module component of expert systems.

Rahman et al (1991) gives the rule based algorithm which consists of functions
developed for electrical load forecasting based on the relation between weather and prevailing
daily and hourly load shapes; this happens in the rule base form of IF-THEN. The work is
performed offline and dependent on operator experience and observation. A decision making
model for combination of short term load forecasting is given by Kang Chongqing et al (2012)
which is a key feature of expert systems.

J.ECONOMETRIC METHOD

The method is a combination of trend analysis and end use analysis which uses mathematics,
economics & statistics for electrical load forecasting. The econometric method makes changes
possible in relation of input and output. It uses the complex equations for creating relation
between input and output for load forecasting the method has a great advantage that it can predict
the load for different segments like residential, commercial or industrial sector which ultimately
reduce the error in overall forecasting. Present agencies of government mostly believe and apply
this method for load prediction; figure-2 gives brief information about the residential segment
with influencing factor: Residential forecasts are influenced by six factors: per capita income,
population, residential electric prices, residential gas prices, household types, and efficiencies.
The uncertainty of load forecasting concerning with market price and power system reliability is
given by Kang Chongqing et al

K. Evolutionary Algorithms & Hybrid Techniques

Evolutionary Algorithms are the powerful, fast, ease adoptive and heuristic approaches to solve
the problems of forecasting and perform efficient forecasting. The methods are based on
biological genetic of living organism.

CHAPTER 3
FUZZY LOGIC

3.1.1. Fuzzy Logic

Fuzzy logic is a logic having many values, approximate reasoning and have a vague
boundary. The variables in fuzzy logic system may have any value in between 0 and 1 and hence
this type of logic system is able to address the values of the variables (called linguistic variables)
those lie between completely truths and completely false. Each linguistic variable is described by
a membership function which has a certain degree of membership at a particular instance. The
human knowledge is incorporated in fuzzy rules. The fuzzy inference system formulates suitable
rules and based on these rules the decisions are made. This whole process of decision making is
mainly the combination of concepts of fuzzy set theory, fuzzy IF-THEN rules and fuzzy
reasoning. The fuzzy inference system makes use of the IF-THEN statements and with the help
of connectors present (such as OR and AND), necessary decision rules are constructed. The
fuzzy rule base is the part responsible for storing all the rules of the system and hence it can also
be called as the knowledge base of the fuzzy system.

Fuzzy inference system is responsible for necessary decision making for producing a
required output. The fuzzy control systems are rule-based systems in which a set of fuzzy rules
represent a control decision mechanism for adjusting the effects of certain system stimuli. The
rule base reflects the human expert knowledge, expressed as linguistic variables, while the
membership functions represent expert interpretation of those variables. Fuzzy logic is a
generalization of the usual Boolean logic used for digital circuit design. An input under Boolean
logic takes on a truth value of “0” or “1”.

Under fuzzy logic an input has associated with it a certain qualitative ranges. For instance
a transformer load may be “low”, “medium” and “high”. Fuzzy logic allows one to (logically)
deduce outputs from fuzzy inputs. In this sense fuzzy logic is one of a number of techniques for
mapping inputs to outputs (i.e. curve fitting). Among the advantages of fuzzy logic are the
absence of a need for a mathematical model mapping inputs to outputs and the absence of a need
for precise (or even noise free) inputs. With such generic conditioning rules, properly designed
fuzzy logic systems can be very robust when used for forecasting. Of course in many situations
an exact output (e.g. the precise 12PM load) is needed. After the logical processing of fuzzy
inputs, a “defuzzification” process can be used to produce such precise outputs describe
applications of fuzzy logic to electric load forecasting.

3.1.2. BLOCKS DIAGRAM AND FLOW CHART:

The significance of this search is present short term load forecasting for a day ahead by
taking into considerations time and weather parameters such as temperature. The classification of
the load data is done using fuzzy set techniques. Figure 5.1 shows the basic block diagram of the
proposed work. The inputs to the fuzzy set based classifier i.e. hourly data of forecasted
temperature and time are given to the fuzzy inference system through fuzzification block. The
fuzzy inference block is the heart of the system as it processes the input data and gives output as
the forecasted load. The inference system accomplishes the task of forecasting by the used of the
fuzzy rule based prepared by the forecaster. The accuracy of the forecast depends on the
experience of the forecaster, the rules prepared by the forecaster and the number of rules
prepared. After, the inference system gives output; the defuzzification block converts the
fuzzified output to the crisp output which can be further displayed on a graph known as the load
curve.
Firstly, the historical data are examined and the maximum and the minimum range of
different parameters are obtained. These ranges are used in the process of the Fuzzification of
different parameters such as time and temperature. After the fuzzification is done, based on the
different parameter of load forecasting rule are prepared. This rules are the heart of the fuzzy
system, so utmost care should be taken to prepare these rules. Once, the rules are prepared
forecast the load of the desired hour.
Figure 3.2 shows the flow chat of STLF using fuzzy logic. The output obtained is
compared with the actual load and the error in load forecasting is used to improve the rule base
for future forecast. This improvement in rule of fuzzy logic
Increases the accuracy of the load forecasting
Figure 3.1.2. Fuzzy logic methodology for short term load forecasting.
3.2 Fuzzy sets

In classical, or crisp, sets the transition for an element in the universe between
membership and non membership in a given set is abrupt and well-defined (said to be ‘‘crisp’’).
For an element in a universe that contains fuzzy sets, this transition can be gradual. This
transition among various degrees of membership can be thought of as conforming to the fact that
the boundaries of the fuzzy sets are vague and ambiguous. Hence, membership of an element
from the universe in this set is measured by a function that attempts to describe vagueness and
ambiguity. A fuzzy set, then, is a set containing elements that have varying degrees of
membership in the set. This idea is in contrast with classical, or crisp, sets because members of a
crisp set would not be members unless their membership was full, or complete, in that set (i.e.,
their membership is assigned a value of 1). Elements in a fuzzy set, because their membership
need not be complete, can also be members of other fuzzy sets on the same universe. Elements of
a fuzzy set are mapped to a universe of membership values using a function-theoretic form

3.2.1.Membership function

Membership function since all information contained in a fuzzy set is described by its
membership function; it is useful to develop a lexicon of terms to describe various special
features of this function. For purposes of simplicity, the functions shown in the following figures
will all be continuous, but the terms apply equally for both discrete and continuous fuzzy sets.

3.2.2.Fuzzification

Fuzzification is the process of making a crisp quantity fuzzy. We do this by simply recognizing
that many of the quantities that we consider to be crisp and deterministic are actually not
deterministic at all: They carry considerable uncertainty. If the form of uncertainty happens to
arise because of imprecision, ambiguity, or vagueness, then the variable is probably fuzzy and
can be represented by a membership function. In the real world, hardware such as a digital
voltmeter generates crisp data, but these data are subject to experimental error. Fuzzification is
the process of converting crisp numerical values into the degrees of membership related to the
corresponding fuzzy sets. A membership function (MF) will accept as its argument a crisp value
and return the degree to which that value belongs to the fuzzy set the MF represent.
3.2.3. Defuzzification

Defuzzification as mentioned in the introduction, there may be situations where the output of a
fuzzy process needs to be a single scalar quantity as opposed to a fuzzy set. Defuzzification is the
conversion of a fuzzy quantity to a precise quantity, just as fuzzification is the conversion of a
precise quantity to a fuzzy quantity. The output of a fuzzy process can be the logical union of
two or more fuzzy membership functions defined on the universe of discourse of the output
variable.

3.2.4.. Methods of defuzzification:

One of the more common types of defuzzification technique is the maximum defuzzification
techniques. These select the output with the highest membership function they include:

 First of maximum
 Middle of maximum
 Last of maximum
 Mean of maxima
 Random choice of maximum

3.2.5. Fuzzy rule base

The first inference method, due to mamdani and assilian, is the most common in practice and in
the literature. To begin the general illustration of this idea, we consider a simple two-rule system
where each rule comprises two antecedents and one consequent. This is analogous to a dual-
input and single-output fuzzy system. The graphical procedures illustrated here can be easily
extended and will hold for fuzzy rule-bases (or fuzzy systems) with any number of antecedents
(inputs) and consequents (outputs). The mamdani method has several variations. There are
different t-norms to use for the connectives of the antecedents, different aggregation operators
for the rules, and numerous defuzzification methods that could be used [13]. In the field of
artificial intelligence (machine intelligence) there are various ways to represent knowledge.
Perhaps the most common way to represent human knowledge is to form it into natural language
expressions of the type. IF premise (antecedent), THEN conclusion (consequent)
3.3. FUZZY LOGIC TOOLBOX

Fuzzy logic in Matlab can be dealt very easily due to the existing new Fuzzy Logic Toolbox.

This provides a complete set of functions to design an implement various fuzzy logic processes.

The major fuzzy logic operations include:

 Fuzzification,
 Defuzzification,
 Fuzzy Inference.

These all are performed by means of various functions and even can be implemented using the
Graphical User Interface

The Toolbox provides three categories of tools

 Command line functions

 Graphical interactive tools
 Simulink blocks and examples

3.3.1. Member functions

There are number of membership functions have been proposed in the past few
year‟s namely triangular membership functions and trapezoidal membership
functions. A more exact fuzzy expert system is acquired by separating the region
into intervals. The intervals for the time have been divided into eight membership
functions and intervals of temperature have been divided into four triangular
membership functions. The intervals for the forecasted load output has divided into
eight triangular membership function as very low, low, sub normal, moderate
normal, normal, above normal, high and very high.
3.3.1. Input variable membership functions
To express fuzzy information, the information space is divided into several subspaces, which
have overlapped segments. They are named according to its natural characters.

The Time, Temperature, Weather condition are clustering into some longer periods compared to
hourly variables. The triangle membership functions are applied to express these variables
clustering groups.

The load fluctuation is heavy in hourly variables and has the highest relativity. In this project the
highest points of the load curve as the highest points of the membership functions.

3.3.2. Output variables membership functions

In the general state, membership functions are selected from the optional and fixed form in
certain. The region of output membership functions is confirmed in of the mahapareshan 132 kv
Indapur load data.
3.3.3. Application example analysis
The actual electric load from an Indapur is taken as an example to show the validity of this
method.

3.4. Input variables membership functions

 Time variable

 Temperature variable

 Weather condition variable

3.4.1. Time variables

According to our input variables we have take time from all days of week. The load is varies
with respect to temperature an d weather conditions. In Time membership functions are plotted
between Night - Rearly morning-Morning-noon-After noon-evening-Overnight. Range of this
variable is [0 24].

Parameters ranges are as:

Night : [0 3 5]

Rearly morning : [4.5 6 7]

Morning : [6.5 9 11.5]

Noon : [11 12.75 15.5]

Afternoon : [15 16 18]

Evening : [17.5 19 20.5]

Over-Night : [20 22 24]

Figure.3.4.1- Time variables
3.4.2. Temperature variables

According to our input variables we have temperature for whole week. According to temperature
our load becomes vary with respect to hour of whole day. In temperature membership functions
are plotted between very low-low-medium-medium to high-high-very high. Range of this
variable is [5 - 50] in centigrade.

Parameters ranges are as:

Very low : [5 7 12]

Low : [10 14 18]

Medium : [16 22 27]

Medium to high : [25 31 36]

High : [35 39 44]

Very high : [42 46 50]

Figure3.4.2-Temperature variables
3.4.3. Weather condition variables

According to our input variables we have variable as season viz. winter& fall, spring, summer,
rainy, winter. This season our load becomes vary. In season membership functions are also
plotted between winter& fall -spring- summer-rainy- winter. Range of this variable is [1 365].

Parameters ranges are as:

winter& fall : [0 25 50]

Spring : [45 90 110]

Summer : [100 150 220]

Rainy : [190 240 310]

Winter : [300 335 365]

Figure3.4.3-weather condition variables

3.5. Fuzzy rules

The forecasting values are on the base of fuzzy relationship synthesize rules and input variables
membership functions. The rules take a role to link input variables with output variables.

3.5.1. Output variables membership functions

. Range of this variable is [0 50] in MW.

Parameters ranges are as:

Very low : [0 8 16]

Low : [14 22 26]

Medium : [24 30 37]

High : [36 41 44]

Very High : [42 46 50]

 Fig.3.5.1.Load variables

3.6.Calculation Table
 1 FEB 2017
Time Season Temperature Load Load % APE
Forecasted Actual
2:00 AM WINTER 12 20.4 21 2.8
5:00 AM WINTER 11 30.5 28 -8.92
8:00 AM WINTER 18 30.4 31 1.93
11:00 AM WINTER 22 25 27 7.40
2:00 PM WINTER 26.5 40 37 -8.10
5:00 PM WINTER 24 40.2 38 -5.78
8:00 PM WINTER 20 25 29 13.79
11:00 PM WINTER 15 20.4 22 7.27

2 FEB 2017
Time Season Temperature Load Load % APE
Forecasted Actual
2:00 AM WINTER 13 20.4 20 -2
5:00 AM WINTER 14 30.5 29 -5.17
8:00 AM WINTER 19 30.4 31 1.93
11:00 AM WINTER 24 25 24 -4.16
2:00 PM WINTER 29 40 39 -2.56
5:00 PM WINTER 26 40.2 42 4.28
8:00 PM WINTER 21 25 27 7.40
11:00 PM WINTER 17 20.4 23 11.30

3 FEB 2017
Time Season Temperature Load Load % APE
Forecasted Actual
2:00 AM WINTER 17 20.2 19 -6.31
5:00 AM WINTER 18 25 24 -4.16
8:00 AM WINTER 21 25 27 7.40
11:00 AM WINTER 29 27.5 27 -1.85
2:00 PM WINTER 32 37 39 5.12
5:00 PM WINTER 31 40.2 39 -3.07
8:00 PM WINTER 26 25 29 13.79
11:00 PM WINTER 19 20.4 21 2.85
 4 FEB 2017
Time Season Temperature Load Load % APE
Forecasted Actual
2:00 AM WINTER 13 20.4 22 7.27
5:00 AM WINTER 13 30.5 29 -5.17
8:00 AM WINTER 18 30.4 29 -4.82
11:00 AM WINTER 22 25 28 10.71
2:00 PM WINTER 25 40 38 -5.26
5:00 PM WINTER 24 40.2 37 -8.64
8:00 PM WINTER 20 25 36 30.55
11:00 PM WINTER 17 20.4 23 11.30

5 FEB 2017
Time Season Temperature Load Load % APE
Forecasted Actual
2:00 AM WINTER 13 20.5 20 -2.5
5:00 AM WINTER 14 25 26 3.84
8:00 AM WINTER 19 30.4 30 -1.33
11:00 AM WINTER 24 30.5 31 1.61
2:00 PM WINTER 26 25 27 8
5:00 PM WINTER 24 40.2 40 -0.5
8:00 PM WINTER 21 25 24 -4.16
11:00 PM WINTER 19 20.4 21 2.85

6 FEB 2017
Time Season Temperature Load Load % APE
Forecasted Actual
2:00 AM WINTER 13 20.5 20 -2.5
5:00 AM WINTER 15 25 24 -4.16
8:00 AM WINTER 19 30.4 30 -1.33
11:00 AM WINTER 25 25 23 -8.69
2:00 PM WINTER 27 40.2 39 -3.07
5:00 PM WINTER 25 40.2 41 1.95
8:00 PM WINTER 22 25 26 3.84
11:00 PM WINTER 20 20.2 20 -1

7 FEB 2017
Time Season Temperature Load Load % APE
Forecasted Actual
2:00 AM WINTER 14 20.4 20 -2
5:00 AM WINTER 17 25 24 -4.16
8:00 AM WINTER 21 30.4 30 -1.33
11:00 AM WINTER 26 25 24 -4.16
2:00 PM WINTER 28 40.1 40 -0.25
5:00 PM WINTER 24 40.2 39 -3.07
8:00 PM WINTER 22 25 26 3.84
11:00 PM WINTER 21 20.2 21 3.80

8 FEB 2017
Time Season Temperature Load Load % APE
Forecasted Actual
2:00 AM WINTER 15 20.4 20 -2
5:00 AM WINTER 16 25 25 0
8:00 AM WINTER 22 30.4 30 -1.33
11:00 AM WINTER 28 25 24 -4.15
2:00 PM WINTER 29 40.1 39 -2.82
5:00 PM WINTER 27 25 24 -4.16
8:00 PM WINTER 24 30.4 31 1.93
11:00 PM WINTER 22 25 23 -8.79
% APE =

│ Pactual Load – PForecasted Load│ × 100

Pactual Load

5.6. RESULT

5.6.1. Input/output Rules

Sr.No. Inputs Output
Time Temprature Weather condition
1 Night Very low Winter & fall Medium
2 Rearly morning Very low Winter & fall Medium
3 Morning Low Winter & fall Medium
4 Noon Medium Winter & fall High
5 After noon Medium Winter & fall High
6 Evening Low Winter & fall Medium
7 Over night Low Winter & fall Low
8 Night Low spring Low
9 Rearly morning Low Spring Low
10 Morning Low Spring Medium
11 Noon Medium Spring Medium
12 After noon M to High Spring High
13 Evening Medium Spring High
14 Evening Low Spring Medium
15 Over night Low Spring Low
16 Over night Very Low spring Very low
17 Night Low Winter & fall Low
 CHAPTER 4

CONCLUSION

The important characteristic of the proposed methodology is the expansion of fuzzy logic
approach to solve the forecasting problem with ambiguity of data such as temperature day types
and load pattern etc. In this thesis the study shows that the fuzzy approach gives the better
forecasting performance but it has easy process to deal with forecasting. . In this paper, short
term load forecasting using fuzzy is formulated and solved. The forecasted results are obtained
and presented using data from MSETCL 132kV Sub-Station Indapur.
 REFERENCES

[1] Jagbir Kaur, Dr. Yadwinder Singh Brar,” Short Term Load Forecasting using Fuzzy Logic
of 220kV Transmission Line” , International Journal of Engineering Research &
Technology(IJERT),Vol. 3 Issue 9, September- 2014.

[2] A. Taifour Ali, Eisa B. M. Tayeb, Zaria M. Shamseldin, ’’Short Term Electrical Load
Forecasting Using Fuzzy Logic,” International Journal Of Advancement In Engineering
Technology, Management and Applied Science (IJAETMAS)” Volume 03 - Issue 11 || November
– 2016.

[3] Hasan Hu¨seyin Cevik Mehmet Cunkas,” Short-term load forecasting using fuzzy logic” and
ANFIS, Published online: 4 January 2015.

[4] Swaroop R, Member IAENG Hussein Ali Al Abdulqader, “Load Forecasting for Power
System Planning using Fuzzy-Neural Networks”, Proceedings of the World Congress on
Engineering and Computer Science ,Published on October 24-26, 2012.

[5] Manish Shah, Rahul Agrawal, “A Review On Classical And Modern Techniques with
Decision Making Tools For Load Forecasting,” International Journal of Emerging Trends in
Development, Issue 3, Vol.6 November 2013.

[6] Priti Gohil, Monika Gupta, “Short term load forecasting using fuzzy logic Short term
loadforecasting using fuzzy logic”.

[7]Load data is collected from the 132kv sub-station, Indapur (load control center)

[8]Temperature data is collected from website www.accuweather.com