Document Type

Article

Publication Version

Accepted Manuscript

Publication Date

11-2011

Journal or Book Title

Energy Systems

Volume

2

Issue

3-4

First Page

209

Last Page

242

DOI

10.1007/s12667-011-0042-9

Abstract

We formulate a generation expansion planning problem to determine the type and quantity of power plants to be constructed over each year of an extended planning horizon, considering uncertainty regarding future demand and fuel prices. Our model is expressed as a two-stage stochastic mixed-integer program, which we use to compute solutions independently minimizing the expected cost and the Conditional Value-at-Risk; i.e., the risk of significantly larger-than-expected operational costs. We introduce stochastic process models to capture demand and fuel price uncertainty, which are in turn used to generate trees that accurately represent the uncertainty space. Using a realistic problem instance based on theMidwest US, we explore two fundamental, unexplored issues that arise when solving any stochastic generation expansion model. First, we introduce and discuss the use of an algorithm for computing confidence intervals on obtained solution costs, to account for the fact that a finite sample of scenarios was used to obtain a particular solution. Second, we analyze the nature of solutions obtained under different parameterizations of this method, to assess whether the recommended solutions themselves are invariant to changes in costs. The issues are critical for decision makers who seek truly robust recommendations for generation expansion planning.

Comments

This is a manuscript of an article from Energy Systems 2 (2011): 209. The final publication is available at Springer via http://dx.doi.org/ 10.1007/s 12667-011-0042-9. Posted with permission.

Copyright Owner

Springer-Verlag

Language

en

File Format

application/pdf

Published Version

Share

COinS