Page 570 -

550 CHAPTER 13 DECISION ANALYSIS

MANAGEMENT SCIENCE IN ACTION

Controlling Particulate Emissions at Ohio Edison Company
hio Edison Company is an operating company These revenue requirements represented the
O of FirstEnergy Corporation. Ohio Edison and monies that would have to be collected from the
its subsidiary, Pennsylvania Power Company, pro- utility’s customers to recover costs resulting from
vide electrical service to more than one million the choice made. A decision tree was constructed
customers in central and northeastern Ohio and to represent the particulate control decision and
western Pennsylvania. Most of this electricity is gen- its uncertainties and costs. A decision node was
erated by coal-fired power plants. To meet evolving used to represent the two choices possible: fabric
air quality standards, Ohio Edison conducted a deci- filters or electrostatic precipitators. Chance nodes
sion analysis to help them select the best particulate were used to represent the uncertainties involved.
control equipment for three of its coal-fired generat- Costs associated with the decision model were
ing units. obtained from engineering calculations or esti-
Preliminary studies narrowed the particulate mates. Probabilities for the chance nodes were
control equipment choice to a decision between obtained from existing data or the subjective
fabric filters and electrostatic precipitators. The assessments of knowledgeable persons.
decision was affected by a number of uncertain- The result of the decision analysis led Ohio Edi-
ties: the uncertainty concerning the way air quality son to select the electrostatic precipitator technol-
regulations might be interpreted, the uncertainty ogy for the three generating units. Had the decision
concerning sulfur content requirements for the analysis not been performed, the particulate
coal to be burned and the uncertainty concerning control decision would have favoured the fabric
construction costs, among others. Because of filter equipment. Decision analysis offered a means
the complexity of the problem, the uncertain for effectively analyzing the uncertainties involved
events involved and the importance of the choice, in the decision and led to a decision that yielded
a comprehensive decision analysis was con- both lower expected revenue requirements and
ducted. lower risk.
The choice was based on minimizing the
Based on information provided by Thomas J. Madden and M.S. Hyrnick
annual revenue requirements for the three large
of Ohio Edison Company, Akron, Ohio.
generating units over their remaining lifetime.

where

EVPI ¼ expected value of perfect information
EVwPI ¼ expected value with perfect information about the states of nature
EVwoPI ¼ expected value without perfect information about the states of nature

Note the role of the absolute value in Equation (13.5). For minimization problems
the expected value with perfect information is always less than or equal to the
For practise in determining
the expected value of expected value without perfect information. In this case, EVPI is the magnitude of
perfect information, try the difference between EVwPI and EVwoPI, or the absolute value of the difference
Problem 9. as shown in Equation (13.5).

Copyright 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s). Editorial review has
deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.