You are on page 1of 7

CHAPTER 1

INTRODUCTION

1
1. Introduction
1.1 Introduction

Voltage stability analysis is concerned with the ability of assessing the power system
to maintain acceptable voltages at all system buses under normal conditions and after
being subjected to disturbances. Several works have been conducted previously for the
prediction of voltage stability and proximity to collapse conditions based on conventional
techniques, using sensitivity indices and based on continuation methods. Continuation
method based voltage stability analysis techniques are fairly accurate but hampered by
the fact of taking longer computational time being based on repetitive power flow. For
online voltage stability, index suits well, if it is accurate indicator of voltage stability
margin and can be calculated fast. Some of the works focus on static voltage stability
analysis using such instability measuringindicators as that of the popular L-index. This
index gives sufficiently accurate as well as practical means of the assessment, and can
express the stability analysis in simple and operator friendly way.

Application of Back proportional neural network (BPNN) to the above-mentioned


problem has attained increasing importance mainly due to the efficiency of present day
computers. Moreover real-time use of conventional methods in an energy management
center can be difficult due to their significant large computational times. One of the main
features, which can be attributed to BPNN, is its ability to learn nonlinear problem offline
with selective training, which can lead to sufficiently accurate online response. BPNN
approach to voltage stability assessment and improvement has been proposed. The ability
of BPNN to understand and properly classify such a problem of highly non-linear
relationship has been established in most of them and the significant consideration is that
once trained effectively BPNN can classify new data much faster than it would be
possible with analytical model.

2
1.2 Stability analysis of power system
1.2.1 Power System Stability

Power systems stability may be broadly defined as that property of a power


system that enables it to remain in a state operating equilibrium under normal operating
conditions and to regain an acceptable state of equilibrium after being subject to a
disturbance. Power system is voltage stable if voltage after a disturbance is close to
voltage at normal operating condition. A power system becomes unstable when voltages
uncontrollably decrease due to outage of equipment (generator, line, transformer, bus bar,
etc.), increment of load, decrement of production and/or weakening of voltage control.

Power system stability is defined as characteristics for a power system to remain


in state of equilibrium after a disturbance. Traditionally, the stability problem has been
the rotor angle stability, i.e. maintaining synchronous operation. Instability may also
occur without loss of synchronism, in which case the concern is the control and stability
voltage.

1.2.2 Voltage Stability

The voltage stability is the ability of a power system tomaintain steady acceptable
voltage at all buses in the system at normaloperating condition and after being subjected
to a disturbance. Power systemis voltage stable if voltage after a disturbance is close to
voltage at normaloperating condition. A power system becomes unstable when
voltagesuncontrollably decrease due to outage of equipment (generator, line,transformer,
bus bar, etc.), increment of load, decrement of production and/orweakening of voltage
control.

Voltage control and stability problems are not new to the electric utility industry
but are now receiving special attention in many systems. Once associated primarily with
week systems and long lines, voltage problems are now also a source of concern in highly
developed networks as a result of heavier loadings. In recent years, voltage has been
responsible for several major network collapses.

3
Modern electric power system is a complex network of synchronous generators,
transmission lines and loads. The characteristics of the system vary with changes in load
and generation schedules. Electric utilities first grew as isolated systems, and then
gradually neighboring utilities began to join highly interconnected systems. The overall
reliability has improved through interconnection but disturbances in such system
propagate through, leading to system instability and possible blackouts.

1.2.3 Voltage Instability

Voltage instability stems from the load dynamics to restore power consumption
beyond the capability of the combined transmission and generation system. Power
systems stability may be broadly defined as that property of a power system that As a
consequence, the terms “voltage instability” and “voltage collapse” are appearing more
frequently in the literature and discussion of system planning and operation. A system
enters a state of voltage instability when a disturbance, increase in load demand, or
change in system condition cause a progressive and uncontrollable decline in voltage.
“Voltage instability” is the inability of power system to meet the demand for reactive
power.

1.2.4 Voltage Collapse

“Voltage collapse” is the process by which the sequence of events accompanying


voltage instability leads to a unacceptable voltage profile in a significant part of the
power system. This condition results from reactive losses significantly exceeding the
reactive resources available to supply them. Circuits loaded above surge impedance
loadings and reduced output of shunt capacitors as voltages decline can lead to
accelerating voltage drops. Voltage collapse can look like both a steady-state problem
with time to react and a problem where no effective operator intervention is possible. It is
very hard to predict the area that will be affected or electrically isolated from the grid.

When a power system is subjected to a sudden increase of reactive power


demand, the additional demand is met by reactive power reverses carried by the
generators and compensators. Generally there are sufficient reserves and the system settle

4
to a stable voltage level. However, it is possible, because of a events and system
conditions, causing a major breakdown of part or all of the system.

1.2.5 Causes of Voltage Instability

The following are the causes of voltage instability:

 The load on transmission line is too high.

 The voltage sources are too far from the load centers.

 The source voltages are too low.

 There is insufficient load reactive compensation.

Voltage stability analysis of radial distribution networks, as they experiencing


distinct change from a low to high load level every day, under certain critical loading
conditions, the distribution system experience voltage collapse. Brownell and Clarke [20]
have reported that voltage collapse. A new voltage stability index [21] is proposed for
radial distribution networks. It is shown that the node, at which the value of voltage
stability index is minimum, is more sensitive to voltage collapse.

1.3 Back Propagation

A BackPropagation network consists of at least three layers of units: an input


layer, at least one intermediate hidden layer, and an output layer (see Figure 1). In
contrast to the IAC and Hopfield networks, connection weights in a Back Propagation
network are one way. Typically, units are connected in a feed-forward fashion with input
units fully connected to units in the hidden layer and hidden units fully connected to units
in the output layer. When a BackPropagation network is cycled, an input pattern is
propagated forward to the output units through the intervening input-to-hidden and
hidden-to-output weights.

We can interpret the output of a BackPropagation network as a classification


decision.We could have instead used a BackPropagation network to make gang
classification judgments (Jets OR Sharks) based on the characteristics of the gang

5
members. A key difference between the BackPropagation and IAC approaches is
learning. IAC networks have fixed weights, which means that for the Jets and Sharks
problem, all of the knowledge about the gang members has to be hard-wired into the
network. BackPropagation networks are not limited in this way because they can adapt
their weights to acquire new knowledge. In this chapter, we will explore how
BackPropagation networks learn by example, and can be used to make predictions.

With BackPropagation networks, learning occurs during a training phase in which


each input pattern in a training set is applied to the input units and then propagated
forward. The pattern of activation arriving at the output layer is then compared with the
correct (associated) output pattern to calculate an error signal. The error signal for each
such target output pattern is then Back Propagated from the outputs to the inputs in order
to appropriately adjust the weights in each layer of the network. After a BackPropagation
network has learned the correct classification for a set of inputs, it can be tested on a
second set of inputs to see how well it classifies untrained patterns. Thus, an important
consideration in applying BackPropagation learning is how well the network generalizes.

6
1.4 Organization of the thesis

The objective of this work is to investigate the voltage stability assessment based on BP
Neural Network.

Chapter 1 has presented the introduction to the power system stability, voltage
stability, voltage collapse.

Chapter 2 presents the complete description of the Voltage stability.

Chapter 3 presents the load flow technique used for Neuton Rapson Method
Chapter 4 presents the complete description of the artificial neural network
Chapter 5 Brief introduction of back propagation neural network,
Implementation of back propagation neural network.

Chapter 6 presents case studies of different three layer BP neural networks.

You might also like