=Paper=
{{Paper
|id=None
|storemode=property
|title=Applying Soft Computing to Estimation of Resources' Price in Oil and Gas Industry
|pdfUrl=https://ceur-ws.org/Vol-841/submission_34.pdf
|volume=Vol-841
|dblpUrl=https://dblp.org/rec/conf/maics/MirseidovaIA12
}}
==Applying Soft Computing to Estimation of Resources' Price in Oil and Gas Industry==
https://ceur-ws.org/Vol-841/submission_34.pdf
Applying Soft Computing to Estimation of Resources’ Price in
Oil and Gas Industry
Sholpan Mirseidova, Atsushi Inoue, Lyazzat Atymtayeva
Kazakh-British Technical University
Tole bi st., 59
Almaty, Kazakhstan
s.mirseidova@gmail.com
situation of project. That’s why it will be very convenient
Abstract to use Fuzzy Logic methodology of Soft Computing to
make certain calculations in order to estimate the total
The oil and gas industry is highly risky capital-intensive profit of the project and remove the uncertainty of non
field of business. Many companies are working hard to clear boundaries of oil price.
perform projects on a global scale in order to get, produce
In the direction of application of fuzzy logic to similar
and deliver their final products. No matter the economic
conditions, it is vital for organizations to efficiently manage
economic problems, the following research was made: the
their capitals projects, which facilitates to control problem of developing automated system of technical –
expenditure, handle priorities and mineral resources, and economic estimation in oil and gas fields was considered
make assets productive as quickly as possible. It is also by Yu.G. Bogatkina [2], and The Fuzzy Logic Framework
critical to efficiently and safely maintain and improve these was build on investigation of risk-based inspection
assets. Probably the most volatile item of the project cost in planning of oil and gas pipes [3]. The first one describes
oil and gas industry is the market price of resources or economic estimation of oil and gas investment projects
assets. Both sides (stakeholders) seek for efficient witnesses’ necessity of taking into account a great number
profitable price for selling and buying final product. This of uncertainty factors. Uncertainty factors influence on
paper provides the description of application developed for investment project can bring about unexpected negative
fair oil price estimation using Fuzzy Sets and Logic results for the projects, which were initially recognized
approach of Soft Computing and FRIL inference language economically expedient for investments. Negative
with its environment installed on UNIX virtual machine. scenarios of development, which were not taken into
consideration in investment projects, can occur and prevent
Introduction realization of investment project. Especially important is
accounting of information uncertainty, which directly
Managing the complexity and profit of major projects in depends on mathematical apparatus choice, defined by
today’s oil and gas landscape has never been more critical. mathematical theory, and provides for formalization of
Against the backdrop of a decline in both global economic uncertainty, appearing during control over investment
conditions and corporate revenues, stakeholders are flows. The second framework emphasizes attention on
demanding improved return on investment (ROI), reduced important feature of plant operation – availability of a
risk and exposure and greater transparency. Since capital considerable amount of information as qualitative and
construction projects in the upstream oil and gas industry imprecise knowledge. Risk-based inspection schedule was
comprise a significant percentage of company spend, there developed for oil and gas topside equipment with
must be a particular focus on predictability, transparency supporting fuzzy logic models.
and reliability, including estimation of profit, controlling No study was made in Kazakhstan connected with
and reducing the costs associated with these projects. The problems of uncertainty in oil prices and project costs in
best opportunity to make a positive impact on the life cycle terms of the principles of fuzzy logic, which could give a
of capital project in this industry is during early planning, more complete picture of price changes and their influence
even before the capital outlay occurs. In order to control on the general economic situation in the country, which
planning it is useful to develop an integrated cost allows forecasting of rising inflation and determining the
management function that aligns all cost-related processes most optimal range of prices taking into account various
and functions and incorporates data developed or economic factors.
maintained in other processes. Emphasis should be placed
on budget control, approved corporate budget changes and Problem Solving
project management internal budget transfers.[1] As the
prices of oil and gas fluctuate every day this is the most The given application offers solution to the problem of
difficult part of budget control, because even slight the project profit estimation considering the price of oil as a
changes in the value has a huge impact on overall financial fuzzy set. Such types of applications are developed for
project managers in oil and gas industry to make [5] in 1965 as an extension of the classical notion of set. In
evaluation of project profit for the future decision. Also all classical set theory, the membership of elements in a set is
investors and financial institutions of this industry could be assessed in binary terms according to a bivalent condition
interested in using the given tool. — particular element either belongs or does not belong to
The total profit of the project could be generally the set (crisp set). In opposite, fuzzy set theory allows the
expressed as follows: gradual assessment of the membership of elements in a set.
According to the definition, a fuzzy subset of a set U is
P= Oil_price * Supply_scope defined by means of a membership function µ : U → [0, 1].
And a membership of an element x in (crisp) set U is
According to the research [4] there are three main determined by an indicator (characteristic) function µ : U
standards for the formation of market prices for → {0, 1}[6].
Kazakhstan's oil exports: prices of Brent dtd type of oil, Using fuzzy sets in estimation of oil price gives
Urals (REBKO) and a mixture of CPC. The prices are opportunity to remove straight principles of crisp sets. For
usually published by Platts organization (see table 1). The example, in the case of crisp sets we should take only three
price of Kazakhstan’s oil is calculated according to the exact numbers for oil price and market differential and
formula: calculate assessment for the worst, standard, and the best
cases. In opposite, with the help of fuzzy sets it is possible
Price=Brent_Price (or Urals_Price) +/- to take into account the variation of price in time, in other
Market_Differential words statistical or historical changes. Another significance
of fuzzy sets is in possibility to manage uncertainty. It
Key benchmarks ($/bbl) means that we can more precisely define which numbers
Data code Change Assessment Change that represent the price of oil can be called normal or
Dubai (SEP) PCAAT00 -1.47 110.10-110.12 -1.47 higher/lower than that and with which membership degree.
Dubai (OCT) PCAAU00 -1.57 110.28-110.30 -1.57 Concerning all of conditions described above three
Dubai (NOV) PCAAV00 -1.54 110.48-110.50 -1.54 universal sets can be defined:
MEC (SEP) AAWSA00 -1.47 110.10-110.12 -1.47
MEC (OCT) AAWSB00 -1.57 110.28-110.30 -1.57 UX1 = [80, 140] – price of Brent dtd.
MEC (NOV) AAWSC00 -1.54 110.48-110.50 -1.54 UX2 = [-5, 5] – market differential
Brent/Dubai AAJMS00 -0.30 5.76-5.78 -0.30
UY = [50, 160] – oil price
Brent (Dated) PCAAS00 -0.95 116.84-116.85 -0.95
The approximate values of borders of sets are taken from
Dated North AAOFD00 -0.95 116.84-116.85 -0.95
statistical values of mentioned parameters for the previous
Sea Light
year [6] (see fig.2 for the set of Brent dtd. price). So there
Brent (AUG) PCAAP00 -1.32 116.46-116.48 -1.32
are 2 Inputs and 1 Output in the system.
Brent (SEP) PCAAQ00 -1.21 115.66-115.68 -1.21
Also fuzzy sets on inputs X1 and X2 and output Y were
Brent (OCT) PCAAR00 -1.22 115.60-115.62 -1.22 created with membership values as follows:
Sulfur De- AAUXL00 0.40
escalator Fuzzy sets on X1(for the price of Brent dtd. see fig.1):
WTI (AUG) PCACG00 -1.35 94.94-94.96 -1.35
WTI (SEP) PCACH00 -1.38 95.41-95.43 -1.38 ‘less than usual’ = {1/80, 0.8/90, 0.7/100, 0.5/110, 0.2/113,
WTI (OCT) AAGIT00 -1.40 95.87-95.89 -1.40 0.1/115, 0/118, 0/120, 0/130, 0/140}
ACM AUG)* AAQHN00 -1.10 107.59-107.61 -1.10
ACM (SEP)* AAQHO00 -1.38 107.61-107.63 -1.38 ‘more than usual’ = {0/80, 0/90, 0/100,
ACM AAQHP00 -1.40 107.87-107.89 -1.40 0/110,0.2/113,0.4/115,0.5/118,0.7/120,0.9/130, 1/140}
(OCT)*
Table 1: Prices of key benchmarks (Source: Platts)
Usually traders make an agreement for the value of
market differential. Market price construction for
Kazakhstani oil depends on CIF August’s (CIF stands for
cost, insurance, freight) market differential.
The main idea is to consider these two parameters (the
price of Brent dtd. oil and market differential) as fuzzy
sets, because the former changes every day, and the second
Figure 1: Fuzzy sets for the price of Brent dtd.
is a result of contract between traders.
The research is based on the theory of fuzzy sets and
logic. Fuzzy sets were initially offered by Lotfi A. Zadeh The given sets were constructed following principle: as
the price for Brent dtd. has changed between 80 and 140
(according to statistics [7] and fig.2), then element 80 Fuzzy sets on Y (for the resulting value of oil price
belongs to the set ‘less than usual’ with higher membership see fig.4):
which equal s to 1 than 140 belongs to this set
(membership equals to 0), and the rest members own ‘cheap’={1/50, 0.9/60, 0.8/70, 0.7/80, 0.6/90, 0.4/100,
steadily decreasing membership degrees. Similarly the set 0.2/110,0/115, 0/120,0/140,0/160}
‘more than usual’ can be explained.
‘normal’={0/50, 0/60, 0.1/70, 0.3/80, 0.5/90, 0.7/100,
($/barrel) 0.9/110, 1/115, 0.5/120, 0/140,0/160}
‘expensive’={0/50, 0/60, 0/70, 0/80, 0/90, 0/100,0/110,
0/115, 0.7/120, 0.9/140, 1/160}
Figure 4: Fuzzy sets for the resulting value of oil price
Figure 2: Dated Brent (Source: Platts) There are 4 “IF-THEN” rules in the system.
Fuzzy sets on X2 (for the value of market differential RULE 1: IF X1 is ‘less than usual’ AND X2 is ‘significantly
see fig.3) low’ THEN Y is ‘cheap’
‘significantly high’={1/-5, 0.8/-4, 0.5/-3, 0.2/-2, 0/-1, 0/0, RULE 2: IF X1 is ‘less than usual’ AND X2 is ‘significantly
0.1/0.1, 0.2/1, 0.4/2, 0.6/3, 0.9/4, 1/5} high’ THEN Y is ‘normal’
‘significantly low’={0/-5, 0.2/-4, 0.4/-3,0.7/-2, 0.8/-1, 1/0, RULE 3: IF X1 is ‘more than usual’ AND X2 is
0.9/0.1, 0.8/1, 0.6/2, 0.3/3, 0.1/4, 0/5} ‘significantly low’ THEN Y is ‘normal’
RULE 4: IF X1 is ‘more than usual’ AND X2 is
‘significantly high’ THEN Y is ‘expensive’
These rules express the direct dependency
(proportionality) between two parameters – the price of
Brent dtd. and market differential – and oil price according
to the formula above.
Figure 3: Fuzzy sets for the value of market differential Development Technologies
The most frequently used market differentials vary The given application was developed using FRIL. With
from -5 to 5 as was mentioned in the list of universal sets the help of FRIL method of inference number of cases can
for three parameters. The higher the value of market be calculated.
differential (without sign) the more significant influence it FRIL was initially an acronym for "Fuzzy Relational
has to the final price of resource, so that the members -5 Inference Language", which was the predecessor of the
and 5 have the highest membership degree in the set current FRIL language, which was developed in the late
‘significantly high’. Other members of this universal set, 1970's following Jim Baldwin's work on fuzzy relations.
which are close to 0, have higher degree in the set FRIL is an uncertainty logic programming language
‘significantly low’ respectively. which not only comprises Prolog as one part of the
Finally, the resulting universal set for oil price was language, but also allows working with probabilistic
divided into three approximate subsets: cheap, normal or uncertainties and fuzzy sets as well.
optimal, and expensive. The membership degrees of the The theory of mass assignments developed by J.F.
elements were assigned following the same principle Baldwin in the Artificial Intelligence group of the
described above. Department became a foundation to FRIL language. A
fuzzy set is defined as a possibility distribution which is prices. Moreover, the quality of exported oil (density,
equivalent to a family of probability distributions. FRIL content of sulfur and wax, etc.), maintenance of quality,
supports both continuous and discrete fuzzy sets. stable production and supply, and the cost of oil production
FRIL gives opportunity to express uncertainty in data, in a particular region have an impact on market price [4].
facts and rules with the help of fuzzy sets and support Yet another example, oil price in Kazakhstan also
pairs. There are three special types of uncertainty rule depends on dollar variation. So, additional fuzzy set
besides the Prolog rule. They are: the basic rule, the representing the value of dollar in Kazakhstani tenge can
extended rule, and the evidential logic rule. The second, be added and application will calculate it without any
extended, rule is widely used for causal net type problems. In addition, the application can be easily
applications, and the evidential logic rule is appropriate to customized to calculate the price of gas and prices of other
case-based and analogical reasoning. Every rule can have mineral resources.
related conditional support pairs, and the method of
inference from these rules is based on Jeffrey's rule which Appendix
is connected with the theorem of total probability. Fuzzy
sets can be used to represent semantic terms in FRIL Source Code
clauses. In addition, a process of partial matching of fuzzy
terms like this, which is called semantic unification, gives %% oil-price.frl
support for FRIL goals [8], [9]. %% NOTE: we use FRIL method of inference
%% (different from Mamudani, Sugeno,etc.)
Analysis of Results % estimate the price of oil depending on Brent dtd. and
market differential
For instance, if the price of Brent dtd equals to 120 % INPUTS: price of Brent, market differential
(which belong to the set ‘more than usual’) and CIF % OUTPUT: oil price
market differential is -3 the application outputs
defuzzyfied value equal to 116.199. If we apply initially %% universe of diccourse
described formula to this data, we will get 120 – 3 = 117.
So, the result, which was received by fuzzy sets set (dom-brent 80 140)
application, is close to the output of calculations following set (dom-market_dif -5 5)
formula. However, there is a difference in 1 dollar per set (dom-oil_price 50 160)
barrel that can considerably affect the final project cost.
More results for the values of the Brent dtd. price and %% fuzzy sets on Brent dtd.
market differential from different sets are listed in
appendix below. (less_than_usual [80:1 90:0.8 100:0.7 110:0.5 113:0.2
The application gives the fair price to the sellers’ side, 115:0.1 118:0 120:0 130:0 140:0] dom-brent)
so that the price by contract, that is lower than this, is not
profitable, and the price that higher than this, is not (more_than_usual [80:0 90:0 100:0 110:0 113:0.2
competitive on the market. On the other side, buyer takes 115:0.4 118:0.5 120:0.7 130:0.9 140:1] dom-brent)
the reasonable price for the product, which correspond
reality with taking into account situation in the market. %% fuzzy sets on market differential
Finally, the project profit can be obtained by
multiplication of output value to whatever value of the (significantly_high [-5:1 -4:0.8 -3:0.5 -2:0.2 -1:0 0:0
supply scope following the volume in the contract. 0.1:0.1 1:0.2 2:0.4 3:0.6 4:0.9 5:1] dom-market_dif)
Conclusion (significantly_low [-5:0 -4:0.2 -3:0.4 -2:0.7 -1:0.8 0:1
0.1:0.9 1:0.8 2:0.6 3:0.3 4:0.1 5:0 ] dom-market_dif)
As a result let us notice that Fuzzy Sets and Logic can be
successfully applied to estimate project profit by assuming %% fuzzy sets on oil price
several parameters as fuzzy sets, constructing those sets
and applying fuzzy logic to them in order to reduce (cheap [50:1 60:0.9 70:0.8 80:0.7 90:0.6 100:0.4
uncertainty. There are still many opportunities to improve 110:0.2 115:0 120:0 140:0 160:0] dom-oil_price)
the precision of calculations.
The market price of Kazakhstani oil depends on several (normal [50:0 60:0 70:0.1 80:0.3 90:0.5 100:0.7
fundamental factors, which can be divided into fixed and 110:0.9 115:1 120:0.5 140:0 160:0] dom-oil_price)
variable. Variable factors, such as the level of
consumption of petroleum and petroleum products in a (expensive [50:0 60:0 70:0 80:0 90:0 100:0 110:0
specific period of time, the amount of energy resource 115:0 120:0.7 140:0.9 160:1] dom-oil_price)
available on the market, conditions of delivery, the number
of traders, significantly affect on the fluctuation of oil %% Fuzzy Associative Matrix (FAM)
%
% b\d | L | H | no (more) solutions
% --------------
% L |C|N| yes
% M |N|E|
% Fril >?((simulation-v 90 -1))
%% fuzzy rules based on FAM Price of Brent: 90 , Market differetial: -1
((price cheap) ((price 74.128)) : (1 1)
(brent less_than_usual)(market_dif Fuzzy set [49.989:0 50:1 90:0.744 110:0.488 115:0.36
significantly_low)) 160.007:0.36 160.011:0] defuzzifies to 74.128 over
sub-domain (50 115)
((price normal)
(brent less_than_usual)(market_dif no (more) solutions
significantly_high))
yes
((price normal)
(brent more_than_usual)(market_dif Fril >?((simulation-v 140 5))
significantly_low)) Price of Brent: 140 , Market differetial: 5
((price expensive) ((price 142.216)) : (1 1)
(brent more_than_usual)(market_dif Fuzzy set [115:0 120:0.7 140:0.9 160:1 160.011:0]
significantly_high)) defuzzifies to 142.216 over sub-domain (115 160)
no (more) solutions
((simulation-v B D) yes
(addcl ((brent B)))
(addcl ((market_dif D))) References
(p 'Price of Brent:' B ', ' 'Market differetial:'
D)(pp) 1. Ernst & Young. 2011 Capital projects life cycle
(qsv ((price X))) management. Oil and Gas., pp. 1,6. EYG No.
(delcl ((brent B))) DW0085 1103-1237776
(delcl ((market_dif D)))) 2. "APPLICATION OF THEORY OF FUZZY SET
IN AUTOMATED SYSTEM OF TECHNICAL-
%% eof %% ECONOMIC ESTIMATION OF OIL AND GAS
FIELDS." by Yu.G. Bogatkina,, Institute of Oil
Execution Results and Gas Problems of the Russian Academy of
Sciences, 2010
Fril >?((simulation-v 80 1)) 3. Risk-based Inspection Planning of Oil and Gas
Price of Brent: 80 , Market differetial: 1 Pipes – The Fuzzy Logic Framework in
EXPLORATION & PRODUCTION – Oil and
((price 76.9223)) : (1 1) Gas review Volume 8 Issue 2, p. 26-27.
Fuzzy set [49.9978:0 50:0.8 60:0.8 70:0.82 4. RFCA RATINNGS Rating Agency. Almaty,
71.6666:0.826667 90:0.68 110:0.36 115:0.2 ] 2010. АНАЛИЗ НЕФТЕДОБЫВАЮЩЕЙ
defuzzifies to 76.9223 over sub-domain (50 140) ОТРАСЛИ РК., pp. 32-37
5. L. A. Zadeh, 1965, "Fuzzy sets". Information and
no (more) solutions Control 8 (3) 338–353.
6. Page Ranking Refinement Using Fuzzy Sets and
yes Logic., Inoue A., Laughlin A., Olson J., Simpson
D., 2011, Eastern Washington University, USA
Fril >?((simulation-v 120 -3)) 7. platts.com Value 32, Issue 134, July 11, 2011.
Price of Brent: 120 , Market differetial: -3 Crude Oil Marketwire., pp. 1-13
8. Fril Systems Ltd (1999). Fril - Online Reference
((price 116.199)) : (1 1) Manual - Preliminary Version (incomplete).
Fuzzy set [115:0.65 119.545:0.872727 120:0.86 Retrieved October 20, 2005.
140:0.72 160:0.72 160.011:0] defuzzifies to 116.199 9. Pilsworth, B. W. (n.d.). The Programming
over sub-domain (60 160) Language Fril. Retrieved October 18, 2005