Doctoral Dissertations

Alternative Title

Modeling hourly electricity prices: a structural time series approach incorporating modified Generalized Autoregressive Conditionally Heteroskedasticity innovations

Abstract

"The main objective of this research is to develop time series based procedures for modeling day-ahead and real-time hourly electricity prices. Such empirical processes exhibit features that make the direct application of standard time series models infeasible. Four years of hourly day-ahead and real-time electricity price data from the region supplied by the American Electric Power (AEP) company through the PJM Regional Transmission Organization (RTO) and one half years of real-time electricity prices from the MISO RTO are utilized as an empirical basis for developing such procedures. The price data show several features, such as irregular seasonal behavior, weekly and daily cycles, as well as sensitivity to oil price fluctuations, making it unsuitable for modeling using techniques that assume stationarity. A structural time series approach is adopted to remove the non-stationary behavior in the daily aggregate of both real-time and day-ahead series. The residual hourly price series, obtained by subtracting the predicted daily averages, show seasonal and daily fluctuations in unconditional volatility. It is shown how a scaling mechanism can be utilized to remove long-term fluctuations in the variance of residual hourly real-time price due to economic conditions and demand. The resulting scaled residual real-time hourly price series is modeled using several GARCH type models that not only account for conditional heteroskedasticity, but also allow for cyclical changes in the unconditional variance. The adjusted residual hourly day-ahead price series is modeled using spline functions to estimate the daily cycles that change across seasons. The problems posed by this data are of a sufficiently general nature such that this research are can be looked upon as providing a new paradigm for modeling high-frequency data with non-stationary and cyclical features that change over time"--Abstract, page iii.

Advisor(s)

Samaranayake, V. A.

Committee Member(s)

Adekpedjou, Akim
Gelles, Gregory M.
Wen, Xuerong
Bohner, Martin, 1966-

Department(s)

Mathematics and Statistics

Degree Name

Ph. D. in Mathematics

Publisher

Missouri University of Science and Technology

Publication Date

Fall 2011

Pagination

xv, 144 pages

Note about bibliography

Includes bibliographical references (pages 140-143).

Rights

© 2011 Edirisinghe Mudiyanselage Asitha Edirisinghe, All rights reserved.

Document Type

Dissertation - Restricted Access

File Type

text

Language

English

Library of Congress Subject Headings

Electricity -- Prices -- Econometric models
GARCH model
Time-series analysis

Thesis Number

T 9894

Print OCLC #

795129257

Electronic OCLC #

909288755

Link to Catalog Record

Electronic access to the full-text of this document is restricted to Missouri S&T users. Otherwise, request this publication directly from Missouri S&T Library or contact your local library.

http://laurel.lso.missouri.edu/record=b8623053~S5

Share

 
COinS