Conference PaperPDF Available

An Expert System for Site Selection of Thermal Power Plants

Authors:
  • Manotr Techlabs Private Limited

Abstract

Energy,known as Strategic Commodity, is critical and any uncertainty about its supply can threaten the functioning of the economy. Thermal power plants are base load plants which meets three-fourth of the total power requirement.Selection of site for thermal power plant is vital for its overall efficiency during its entire period of operation. This paper proposes an expert system for site selection of thermal power plants. We use Flex Expert System Shell in which production rules are framed based on regulatory criteria. The system analyses the proposed site based on criteria laid down by governing bodies and decides its suitability for commissioning the plant. The system automates the decision making process, thereby eliminating the human intervention. The expert system also provides suggestions to the user on latest technologies for optimal utilization of resources.
Journal of Basic and Applied Engineering Research
Print ISSN: 2350-0077; Online ISSN: 2350-0255; Volume 1, Number 8; October, 2014 pp. 36-40
© Krishi Sanskriti Publications
http://www.krishisanskriti.org/jbaer.html
An Expert System for Site Selection of
Thermal Power Plants
K. Sambasivarao
1
, D. Kavin Raj
2
, Deepika Dua
3
1
M.Tech (AI & ANN), University of Petroleum & Energy Studies, Dehradun
Abstract: Energy, known as Strategic Commodity, is critical and
any uncertainty about its supply can threaten the functioning of
the economy. Thermal power plants are base load plants which
meets three-fourth of the total power requirement. Selection of
site for thermal power plant is vital for its overall efficiency
during its entire period of operation. This paper proposes an
expert system for site selection of thermal power plants. We use
Flex Expert System Shell in which production rules are framed
based on regulatory criteria. The system analyses the proposed
site based on criteria laid down by governing bodies and decides
its suitability for commissioning the plant. The system automates
the decision making process, thereby eliminating the human
intervention. The expert system also provides suggestions to the
user on latest technologies for optimal utilization of resources.
Keywords: Thermal Power Plant, Site Selection, Expert Sys-tem,
Flex, Decision Support System
1.
INTRODUCTION
Considering the uncertain economic conditions of state
electricity boards (SEBs), the power market dynamics, the
fundamental changes in the attitudes, aspirations and needs of
the consumers along with the strong growth of political role
and interventions in the power sector, increase in demand and
fill the demand and supply gap, currently characterizing the
power production plants depending on site selection, it can be
said that the need for expert systems method of strategic
planning was never so acute as now. The power sector is an
integral part of the country
s economic growth and sustainable
development. The Power sector in India has an installed
capacity of 2, 34, 60194 Mega Watt (MW) as of 31st Jan,
2014 recording an increase of 14% over that of March
2013[1]. Thermal power plants accounted for an
overwhelming 66% of the total installed capacity in the
country, with an installed capacity of 1, 60, 483.99 MW. Total
Aggregate Technical and Commercial losses stands at an
average of 28%. In order to overcome the ATC losses, the
government introduced Restructured Accelerated Power
Development Reforms Program (R-APDRP). Demand supply
gap between electricity generation and demand touched 8% in
April 2013 according to the Central Electricity Authority
(CEA). Although the usage of renewable energy have been
increasing in the past couple of years, thermal power plants
with bulk capacities continues to be the potential solution to
meet the increased demand due to its viability and availability
of fuel. Inorder to meet the demand and increase the power
production, Ministry of Power (MoP) took initiative to
develop Ultra Mega Power Projects (UMPPs). These are very
large sized projects, each project approximately taking inputs
as Rs. 260 billions, 4000 MW and 2500 acres of land,
adopting supercritical technology with a view to achieve
higher levels of fuel efficiency, which results in fuel saving
and lower green-house gas emissions[2].
Improving energy efficiency is one of the most desirable
options for bridging the gap between demand and supply.
Unlike other power plants, thermal power plants need a large
amount of land as it requires large machineries to generate
bulk amount of power. The disposal of the increasing amounts
of solid waste from coal-fired thermal power plants is
becoming a serious concern to the environmentalists. Since
selection of a plant site has a significant influence on the
design, construction and operating costs of a power plant, it
has to be conducted in a precise manner taking into
consideration of all factors which will have a profound impact
on its operation. Inorder to boost the power production in the
country, Electricity Act 2003 made generation free from
licensing, but so far sixty five clearances are made mandatory
like Environmental, Pollution, and Forest etc. Land acquisition
has a major role to play besides selecting a particular place for
project.
Expert Systems are intelligent systems that encapsulate
specialized knowledge about a particular domain of expertise
and are capable of making intelligent decisions within that
domain. Any area in which human experts solve problems is a
potential area for the use of expert systems. Expert Systems
successfully tackled the complex problems of various areas
include medical diagnosis, geological exploration, fault
diagnosis in electronic equipment. In this paper, Rule Based
Expert System is used to make Intelligent Decisions for the
site selection of Thermal Power Plants.
The organization of the paper is as follows. Section 2
discusses the previous contributions towards the site selection
An Expert System for Site Selection of Thermal Power Plants 37
Journal of Basic and Applied Engineering Research (JBAER)
Print ISSN: 2350-0077; Online ISSN: 2350-0255; Volume 1, Number 8; October, 2014
of Thermal Power Plant. Section 3 introduces the criteria
considered for the Site Selection. FLEX Expert System Shell
is introduced in Section 4. The Methodology and Decision tree
are presented in Section 5. Section 6 shows the Results and
Discussion. Finally, the paper is concluded in Section 7.
2.
RELATED WORK
There are a couple of works, which are involved in the
evaluation of potential sites for commissioning thermal power
plants. A Decision Support System for thermal power plant
siting(SDSS) aids decision makers to make individual decision
and multiple decision on the site alternatives, in the stage of
preliminary feasibility study. The SDSS frames the knowledge
in the knowledge base by means of 500 rules and outputs the
decision results based on user inputs [3]. Geospatial in-
formation (GIS) is used in evaluation of potential site for coal-
based thermal power plants. Multi-spectral satellite data and
other related data were used to create a database, which then
suitably combined with regulatory conditions to rank the sites
based on a Site Suitability Index (SSI)[4]. Researchers have
also tried using geospatial data along with collateral data on
geology, topography, hydrology, meteorology and other
regulatory considerations in identifying potential sites for pit-
head coal-based thermal power stations. The sites were then
ranked using an SSI and decisions are made according to that
[5].
3.
SITE SELECTION CRITERIA
Selecting a proper site for a thermal power plant is vital for its
long term efficiency and a lot many factors come into play
when deciding where to install the plant. Of course it may not
be possible to get everything which is desirable at a single
place but still the location should contain an optimum mix of
the requirements for the settings to be feasible for long term
economic justification of the plant. In general, both the
construction and operation of a power plant requires the
existence of some conditions such as water resources and
stable soil type. Still there are other criteria that although not
required for the power plant, yet should be considered because
they will be affected by either the construction or operation of
the plants such as population and protected areas. The
following list covers most of the factors that should be studied
and considered in selection of proper sites for power plant
construction:
1. Supply of Fuel
2. Geology and Soil Type
3. Availability of Water
4. Availability of Land
5. Transportation Facilities
6. Nearness to Load Centers
7. Distance from Populated Areas
A. Guidelines of Ministry of Environment and Forests
Ministry of Environment Forest (MoEF) has laid down some
regulations for Site Selection of Coal based Thermal Power
Plants [6]. Those are as follows:
1. Locations of thermal power stations are avoided within
25 km of the outer periphery of the following:
2. Metropolitan cities
3. National park and wildlife sanctuaries
4. Ecologically sensitive areas like tropical forest,
biosphere reserve, important lake and coastal areas rich
in coral formation
5. The sites should be chosen in such a way that chimneys
of the power plants does not fall within the approach
funnel of the runway of the nearest airport
6. Those sites should be chosen which are at least 500 m
away from the flood plain of river system
7. Location of the sites are avoided in the vicinity (say 10
km) of places of archaeological, historical,
cultural/religious/tourist importance and defense
installations
B. Guidelines of Central Electrical Authority
Forest or prime agriculture lands are avoided for setting up of
thermal power houses or ash disposal.
1. Choice of location is based on the following [7] : -
Nearness to coal source
o Accessibility by road and rail
o Availability of land, water and coal for the final
installation capacity
o Coal transportation logistics
o Power evacuation facilities
o Availability of construction material, power and
water
o Preliminary environmental feasibility including re-
habilitation and resettlement requirements, if any
2. Land requirement for large capacity power plant is about
0:2km
2
per 100 MW for the main power house only
excluding land for water reservoir (required if any).
3. The land for housing is taken as 0:4km
2
per project.
4. Land requirement for ash pond is about 0:2km
2
per 100
MW considering 50% of ash utilization. Land for ash
pond is considered near the main plant area (say 5 to 10
38 K. Sambasivarao, D. Kavin Raj, Deepika Dua
Journal of Basic and Applied Engineering Research (JBAER)
Print ISSN: 2350-0077; Online ISSN: 2350-0255; Volume 1, Number 8; October, 2014
km away). In case of non-availability of low lying ash
pond area at one place, the possibility of having two
areas in close proximity is considered.
5. Water requirement is about 40 cusecs per 1000 MW.
6. First priority is given to the sites those are free from
forest, habitation and irrigated/agricultural land. Second
priority is given to those sites that are barren, i.e.,
wasteland, intermixed with any other land type, which
amounts to 20% of the total land identified for the
purpose.
7. Location of thermal power station is avoided in the coal-
bearing area.
8. Coal transportation is preferred by dedicated marry-go-
round (MGR) rail system. The availability of corridor for
the MGR need to be addressed while selecting the sites.
4.
EXPERT SYSTEMS
Expert Systems (ES) are intelligent systems that emulate the
behavior of a human expert as he attempts to solve some
complex problem in a particular domain [8]. Expert Systems is
historically considered as a branch of Artificial Intelligence,
which is an Intelligent Computer program that uses knowledge
and Inference procedures to solve problems that are difficult
enough to require significant human expertise for their
solutions. Expert Systems use knowledge rather than data for
controlling the solution process. Knowledge is separated from
the control program. So, knowledge can be constantly refined
and updated without actually affecting the software. The most
popular expert systems are rule-based systems. Rules can
represent relations, recommendations, directives, strategies
and heuristics. A rule-based expert system consists of five
components - the knowledge base, the database, the inference
engine, the explanation facilities, and the user interface. The
knowledge base contains the domain knowledge useful for
problem solving. The knowledge is represented as a set of
rules in the form of IF (condition) THEN (action) structure
[9]. When the condition part of a rule is satisfied, the rule is
said to fire and the action part is executed. The inference
engine carries out the reasoning whereby the expert system
reaches a solution. The inference engine links the rules given
in the knowledge base with facts provided in the database and
uses two main strategies to operate - the forward chaining
strategy and the backward chaining strategy.
A. Flex
An Expert System Shell can be considered as an Expert
System with the knowledge removed. Therefore, all the user
has to do is to add the knowledge in the form of rules and
provide relevant data to solve a problem[10]. Many Expert
Systems are now developed on personal computers using
shells. This can eliminate the need for the programmer and
also reduce the role of the knowledge engineer. Expert System
Shells offer a dramatic reduction in the development time of
Expert Systems.
FLEX is an Expert System Shell which is implemented in
Prolog. It uses Knowledge Specification Language (KSL)
looks much more like Standard English than a programming
language. FLEX contains many constructs ideal for building
knowledge based systems such as frames, instances, rules,
relations, groups, questions, answers, demons, actions,
functions etc. FLEX can compile both FLEX and Prolog files.
5.
METHODOLOGY
Expert System for Site Selection is developed by using FLEX
Expert System Shell. All set of information affecting the
selection of site is framed as production rules and fed into the
system. The rule only which is relevant to the current context
can be applied at a time. The development of Site Selection
Expert System has three main phases - Knowledge
Acquisition, Knowledge Organization and Knowledge
Representation.
All the information such as Regulations laid down by Ministry
of Environment Forest, Regulations laid down by Central
Electrical Authority, Environmental Impact Assessment Re-
ports of various existing plants, Reports by Central Electrical
Authority about Land Requirement Water Requirement,
Coastal Regulation Zone Notification from Ministry of
Environment Forest for Coastal Power Plants, National
Rehabilitation Resettlement Policy from Ministry of Rural
Development and advanced technologies recommended for
optimization of available resources are gathered as a part of
Knowledge Acquisition.
The knowledge acquired from the domain expert and various
sources should be organized well in the knowledge base for
fast and accurate responses. The knowledge collected from
different sources is of different forms. All the knowledge
collected in various forms is encoded into production rules.
All the knowledge collected from various sources is organized
into five modules. The first two modules are of strictly
exclusionary criteria whereas the remaining three modules are
of details regarding fuel and water availability and
accessibility of site. Knowledge is primarily represented in the
form of IF ! THEN rules. The if part of the rule is also called
as antecedent which contains the condition and the then part is
called as consequent consisting of conclusions, which the rule
will execute when it is selected and fired.
All the relevant rules are grouped in a rule group and all sets
of rules are contained in the ruleset. Action, which acts as the
main program for the system prompts the user window in
which the end user enters the facts in response to questions
and invoke the ruleset which contains relevant rule groupings
for the current context.
An Expert System for Site Selection of Thermal Power Plants
Journal of Basic and Applied Engineering Research (JBAER)
Print ISSN: 2350-
0077; Online ISSN: 2350
Forward chaining method of inference is
system which reasons with facts and
knowledge
comes up with accurate solution. The
expert
able to explain its line of reasoning to the
user
inherent characteristics.
Fig. 1. Decision Tree for assessing site
suitability
A. Decision Tree
A decision tree is a way of relating a
output using a series of rules arranged in a
tree
shows the decision tree for assessing
site
location might be ruled out as
completely
suitable with some general suggestions. In
some
be rejected without performing all the tests.
site passes through all phases of site
selection
be selected. The suggestions regarding the
latest
to be used for the optimal utilization of
resources
efficiency are included at the end of
accessibility
details regarding the clearances to be
obtained
included at the end.
6.
RESULTS AND DISCUSSION
The details about the location being
considered
from the user and will be stored in the wor
king
the inference engine matches the data with
the
of the rules and the corresponding rules
will
system will ask the questions only which
are
decision making. Finally, it will give
the
output, whether the site is selected or
not.
An Expert System for Site Selection of Thermal Power Plants
Journal of Basic and Applied Engineering Research (JBAER)
0077; Online ISSN: 2350
-0255;
Volume 1, Number 8; October, 2014
applied for the
knowledge
available and
expert
system is also
user
as part of its
suitability
series
of inputs to an
tree
structure. Fig.1
site
suitability. A
completely
unsuitable or
some
cases site can
If the proposed
selection
criteria, it will
latest
technologies
resources
and better
accessibility
details. The
obtained
are also
considered
will be taken
king
memory. Then
the
condition part
will
be fired. The
are
necessary for
the
corresponding
not.
If the site is
selected, it will give details
regarding
to setup the plant including
suggestions
latest technologies for optimal
utilization
also to improve overall plant
efficiency.
the reasons to the user for
rejection.
window after passing through all
shown in the above Fig. 2.
Fig. 2. Graphical
User
7.
CONCLUSION
Expert System for site selection
of
Flex expert system shell has
been
acquired from various sources
of
regarding regulations for setting
land criteria, type of fuel sources
,
the power plants follow in the
current
accessibility details to the plant
,
advanced technologies to build a
base. Acquired knowledge is
organized
easing faster access of the
knowledge
to give solutions. Knowledge is
represented
production rules and is compared
with
to arrive to a solution using
forward
technique. Flex has proved to be a
useful
expert system for complex
problems.
tested and validated for all
possible
given by the user.
8.
FUTURE WORK
Expert System developed for site
plants using Flex Expert System
Shell
of uncertainty at various stages of
of uncertainty was not able to be
solved
to its inherent inability in handling
in developing the system. The
work
39
Volume 1, Number 8; October, 2014
regarding
the clearances necessary
suggestions
to the user on the
utilization
of the resources and
efficiency.
Otherwise, it will give
rejection.
The sample output
the phases of selection is
User
Interface
thermal power plants using
been
developed. Knowledge
of
books, journals, websites
up power plant, minimum
,
and unit capacities which
current
industrial scenario,
,
and recommendations of
comprehensive knowledge
organized
into modules for
knowledge
by the control procedure
represented
in the form of
with
facts given by the user
forward
chaining inference
useful
tool in developing an
problems.
The System has been
possible
combinations of the facts
selection of thermal power
Shell
represents some point
site
selection process. Issue
solved
by expert system due
uncertain information used
work
can be extended with
40 K. Sambasivarao, D. Kavin Raj, Deepika Dua
Journal of Basic and Applied Engineering Research (JBAER)
Print ISSN: 2350-0077; Online ISSN: 2350-0255; Volume 1, Number 8; October, 2014
fuzzy logic which solves the problem of uncertainty,
amicably. The project can be extended further to suggest the
complete design of the power plant by including the
knowledge of the design criteria followed for the
commissioning of the power plant into the knowledge base of
the system.
REFERENCES
[1] http://www.cea.nic.in/installedcapacity.html.
[2] Power Line, Vol.18, No.5, Jan 2014.
[3] Wang Guangsheng, Hu Zhaoguang, and Wang Pingyang,
Decision Sup-port System for Thermal Power plant Siting,
Proceedings on Computer, Communication, Control and Power
Engineering, IEEE TENCON, 1993.
[4] S.Kaliraj, V.K.Malar, Geospatial Analysis to assess the potential
site for coal based thermal power station in Gujarat, India,
Advances in Applied Science Research, Vol.3, No.3, pp
no.1554-1562, 2012
[5] Dr.A.K.Samantaray, N.P.Singh, T.K.Mukherjee, Evaluation of
potential pit-head sites for coal-based thermal power stations
based on site-suitability index(SSI) using geospatial
information, Map Asia Conference, Paper No: AD 103, 2004.
[6] Guidelines of Ministry of Environment and Forests(MoEF),
Government of India, for site selection of coal-based thermal
power stations.
[7] Guidelines of Central Electrical Authority(CEA), Government
of India, for site selection of coal-based thermal power stations.
[8] Chukwuchekwa Ulumma Joy, Chukwuchekwa Nkwachukwu,
Prediction of the suitability of locations for Wind Farms using
Flex Expert System, Academic Research International, Vol.1,
Issue.1, July 2011.
[9] Dan.W.Patterson, Introduction to Artificial Intelligence and
Expert Systems, 3rd Edition, Prentice Hall India, 2012.
[10] Michael Negnevitsky, Artificial Intelligence: A Guide to
Intelligent Systems, 2nd Edition, Addison-Wesley, 2005.
Article
Full-text available
This paper proposes a blend of three techniques to select COVID-19 testing centers. The objective of the paper is to identify a suitable location to establish new COVID-19 testing centers. Establishment of the testing center in the needy locations will be beneficial to both public and government officials. Selection of the wrong location may lead to lose both health and wealth. In this paper, location selection is modelled as a decision-making problem. The paper uses Fuzzy Analytic Hierarchy Process (AHP) technique to generate the criteria weights, Monkey Search Algorithm to optimize the weights and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method to rank the different locations. To illustrate the applicability of the proposed technique, a state named Tamil Nadu, located in India is taken for a case study. The proposed structured algorithmic steps were applied for the input data obtained from the government of India website, and the results were analyzed and validated using the government of India website. The ranks assigned by the proposed technique to different locations are in aligning with the number of patients and death rate
Article
Full-text available
Wind-generated electricity has the ability to provide electricity to homes and businesses without causing air pollution or depleting non-renewable resources, unlike electricity generated by coal, natural gas, and oil (fossil fuels). Wind farm developments are mostly not common with the local populations and as a result, many factors have to be taken into consideration before such development can take place. This paper presents a Forward Chaining Flex knowledge-base for locating Wind Farms. Such factors as energy production, visual and sound impact for the local community, the number of wildlife species in the area and their population sizes, a geological survey to determine ground stability and a hydrological survey to show the effect of the development on local rivers and water sources, are arranged in a decision tree and consequently built into a knowledge-based system using the Flex expert system shell. Sample outputs from the developed Flex expert system show that a location might be ruled out as 'completely unsuitable', 'ideal' or a 'second best' choice.
Article
Full-text available
The advanced space technology known as Remote sensing and GIS is a perfect tool for Geo Spatial applications in science and engineering. In the present study, identification of suitable site for Thermal Power Plant along the mining area in Rajpardi district of Gujarat, India is one of the evidence of Geospatial technology for mankind development. Multi-spectral satellite data and collateral data of geology, geomorphology, topography, settlement and transport, forest cover, hydrology and climate were used to generate the integrated thematic database in GIS platform for selecting the suitable site for Thermal Power Station (TPS) construction. Selection of site for TPS was based on four primary criteria, such as land, water, coal mine and environment, and two secondary criteria, namely settlement and accessibility to the site. A Site-Suitability Index (SSI) is processed the multi spatial parameters according to the regulatory guidelines of MoEF (Ministry of Environment and Forest) and CEA (central Electricity Authority). Each class in spatial layers is assigned with weighed value 1 to 10 based on the relative importance to suitability. The sum of Weightage of spatial layers using weighted overlay analysis, the result have been classified as high, medium, low and not suitable .
Article
A textbook for upper division undergraduate and first year graduate courses. Assumes basic computer science courses and a general maturity in mathematics.
Conference Paper
On the basis of new technologies such as fuzzy sets, analytic hierarchy process and expert systems etc., a practical decision support system for thermal power plant siting (SDSS) has been set up and is presented in this paper. SDSS, as displayed on the PC screen, consists of ten parts: introduction, system maintenance, individual decision, clear database, consultation, auxiliary operation, multiple decision, sensitivity analysis, graph system and exit. SDSS can help decision makers to make individual decisions and multiple decisions on the site alternatives, in the preliminary feasibility study stage for thermal power plant siting, then it outputs the decision results and their certainty factors. SDSS not only can explain its reasoning process, decision results and rules in detail but also provide some expert conclusions in special fields for users. Guided by the domain experts SDSS can modify or enlarge its knowledge base easily. Through changing the weights of the criteria SDSS can do a sensitivity analysis on any site alternative if the users want. SDSS has good flexibility and can be used as a frame structure to form the expert systems in other fields. The man-machine interface in SDSS is clear and audio-visual, the decision results can be shown in all kinds of displays. SDSS can be applied to the other domains and the designing institutes throughout the country. Application of SDSS to the site selection of Wu Shashan, Ying Longshan, Qiang Jiao along the Zhe Jiang coast obtained a good result