Disaggregating Time Series Data for Energy Consumption by Aggregate and Individual Customer

DISAGGREGATING TIME SERIES DATA FOR ENERGY CONSUMPTION BY AGGREGATE AND INDIVIDUAL CUSTOMER Steven R. Vitullo, B.S., M.S. Marquette University, 2011 This dissertation generalizes the problem of disaggregating time series data and describes the disaggregation problem as a mathematical inverse problem that breaks up aggregated (measured) time series data that is accumulated over an interval and estimates its component parts. We describe five different algorithms for disaggregating time series data: the Naive, Time Series Reconstruction (TSR), Piecewise Linear Optimization (PLO), Time Series Reconstruction with Resampling (RS), and Interpolation (INT). The TSR uses least squares and domain knowledge of underlying correlated variables to generate underlying estimates and handles arbitrarily aggregated time steps and non-uniformly aggregated time steps. The PLO performs an adjustment on underlying estimates so the sum of the underlying estimated data values within an interval are equal to the aggregated data value. The RS repeatedly samples a subset of our data, and the fifth algorithm uses an interpolation to estimate underlying estimated data values. Several methods of combining these algorithms, taken from the forecasting domain, are applied to improve the accuracy of the disaggregated time series data. We evaluate our component and ensemble algorithms in three different applications: disaggregating aggregated (monthly) gas consumption into disaggregated (daily) gas consumption from natural gas regional areas (operating areas), disaggregating United States Gross Domestic Product (GDP) from yearly GDP to quarterly GDP, and forecasting when a truck should fill a customer’s heating oil tank. We show our five algorithms successfully used to disaggregate historical natural gas consumption and GDP, and we show combinations of these algorithms can improve further the magnitude and variability of the natural gas consumption or GDP series. We demonstrate that the PLO algorithm is the best of the Naive, TSR, and PLO algorithms when disaggregating GDP series. Finally, ex-post results using the Naive, TSR, PLO, RS, INT, and the ensemble algorithms when applied to forecast heating oil deliveries are shown. Results show the Equal Weight (EW) combination of the Naive, TSR, PLO, RS, and INT algorithms outperforms the forecasting system Company YOU used before approaching the GasDay laboratory at Marquette University, and comes close, but does not outperform existing techniques the GasDay laboratory has implemented to forecast heating oil deliveries.

[1]  Fred L. Collopy,et al.  Error Measures for Generalizing About Forecasting Methods: Empirical Comparisons , 1992 .

[2]  J. Wilcox.  Disaggregating Data Using Related Series , 1983 .

[3]  Wolfgang Müller,et al.  Autoregressive Approaches to Disaggregation of Time Series Data , 1971 .

[4]  Eric Ghysels,et al.  Can we improve the perceived quality of economic forecasts , 2001 .

[5]  Peter R. Winters,et al.  Forecasting Sales by Exponentially Weighted Moving Averages , 1960 .

[6]  J. Edward Jackson,et al.  A User's Guide to Principal Components. , 1991 .

[7]  George F. Corliss,et al.  Exploiting Domain Knowledge to Forecast Heating Oil Consumption , 2011 .

[8]  H. Theil,et al.  Economic Forecasts and Policy. , 1959 .

[9]  Anthony E. Bopp,et al.  On Combining Forecasts: Some Extensions and Results , 1985 .

[10]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[11]  Mohamed Alosh,et al.  A dynamic linear model approach for disaggregating time series data , 1989 .

[12]  H. White.  A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for Heteroskedasticity , 1980 .

[13]  J. Scott Armstrong,et al.  Forecasting by Extrapolation: Conclusions from 25 Years of Research , 2001 .

[14]  George F. Corliss,et al.  Mathematical Models for Natural Gas Forecasting , 2009 .

[15]  E. F. Sánchez-Úbeda,et al.  Modeling and forecasting industrial end-use natural gas consumption☆ , 2007 .

[16]  J. G. Smith,et al.  Meeting Seasonal Peak Demands for Natural Gas , 1971 .

[17]  C. Sims.  MACROECONOMICS AND REALITY , 1977 .

[18]  Franz C. Palm,et al.  Linear regression using both temporally aggregated and temporally disaggregated data , 1982 .

[19]  Leonard J. Tashman,et al.  Out-of-sample tests of forecasting accuracy: an analysis and review , 2000 .

[20]  Tsuginosuke Sakauchi,et al.  Applying Bayesian Forecasting to Predict New Customers' Heating Oil Demand , 2011 .

[21]  Adrian E. Raftery,et al.  Weather Forecasting with Ensemble Methods , 2005, Science.

[22]  A. A. Weiss,et al.  Semiparametric estimates of the relation between weather and electricity sales , 1986 .

[23]  Steven R. Vitullo.  Disaggregating Interval Time-Series Data Applied to Natural Gas Flow Estimation , 2007 .

[24]  Enrique de Alba,et al.  Disaggregation and Forecasting: A Bayesian Analysis , 1988 .

[25]  J. Scott Armstrong,et al.  On the Selection of Error Measures for Comparisons Among Forecasting Methods , 2005 .

[26]  D. Smith,et al.  Combination of forecasts in electricity demand prediction , 1989 .

[27]  Marek Brabec,et al.  A statistical model for the estimation of natural gas consumption , 2008 .

[28]  J. Dickinson.  Some Comments on the Combination of Forecasts , 1975 .

[29]  F. K. Lyness.  Gas Demand Forecasting , 1984 .

[30]  R. Buizza,et al.  Neural Network Load Forecasting with Weather Ensemble Predictions , 2002, IEEE Power Engineering Review.

[31]  R. Suganya,et al.  Data Mining Concepts and Techniques , 2010 .

[32]  Roy Batchelor,et al.  Forecaster diversity and the benefits of combining forecasts , 1995 .

[33]  Steven R. Vitullo,et al.  Detrending Daily Natural Gas Demand Data Using Domain Knowledge , 2010 .

[34]  G. Peter Zhang,et al.  Neural Networks in Business Forecasting , 2003 .

[35]  Daniel O. Stram,et al.  Disaggregation of Time Series Models , 1990 .

[36]  D. G. Baker.  Effect of Observation Time on Mean Temperature Estimation , 1975 .

[37]  Wai-Sum Chan,et al.  Disaggregation of annual time‐series data to quarterly figures: A comparative study , 1993 .

[38]  J. Boot,et al.  Further Methods of Derivation of Quarterly Figures from Annual Data , 1967 .

[39]  T. Hesterberg,et al.  A regression-based approach to short-term system load forecasting , 1989, Conference Papers Power Industry Computer Application Conference.

[40]  Reuven R. Levary,et al.  A Natural Gas Flow Model under Uncertainty in Demand , 1980, Oper. Res..

[41]  Stephen M. Stigler,et al.  The History of Statistics: The Measurement of Uncertainty before 1900 , 1986 .

[42]  J. M. Bates,et al.  The Combination of Forecasts , 1969 .

[43]  J. Stock,et al.  Forecasting Using Principal Components From a Large Number of Predictors , 2002 .

[44]  Víctor M. Guerrero,et al.  Temporal disaggregation of time series : an ARIMA-based approach , 1990 .

[45]  R. Engle,et al.  Modelling peak electricity demand , 1992 .

[46]  F. K. Lyness.  Consistent Forecasting of Severe Winter Gas Demand , 1981 .

[47]  J. Scott Armstrong,et al.  Combining forecasts: The end of the beginning or the beginning of the end? , 1989 .

[48]  Victor Ginsburgh,et al.  A further note on the derivation of quarterly figures consistent with annual data , 1973 .

[49]  J. Edward Jackson,et al.  A User's Guide to Principal Components. , 1991 .

[50]  G. Chow,et al.  Best Linear Unbiased Interpolation, Distribution, and Extrapolation of Time Series by Related Series , 1971 .

[51]  T. Funabashi,et al.  One-Hour-Ahead Load Forecasting Using Neural Networks , 2002 .

[52]  Robert V. Brill,et al.  Applied Statistics and Probability for Engineers , 2004, Technometrics.

[53]  N. S. Barnett,et al.  Private communication , 1969 .

[54]  G. C. Tiao,et al.  An introduction to multiple time series analysis. , 1993, Medical care.

[55]  D. Stram,et al.  A METHODOLOGICAL NOTE ON THE DISAGGREGATION OF TIME SERIES TOTALS , 1986 .

[56]  W. Patterson,et al.  Energy forecasting , 1977, Nature.

[57]  Douglas C. Montgomery,et al.  Applied Statistics and Probability for Engineers, Third edition , 1994 .

[58]  Carlos E. Pedreira,et al.  Neural networks for short-term load forecasting: a review and evaluation , 2001 .