Applied Stochastic Models in Business and Industry

Migon, Helio S.; Alves, Larissa C.

2013 Applied Stochastic Models in Business and Industry

doi: 10.1002/asmb.1990

This paper introduces electricity load curve models for short‐term forecasting purposes. A broad class of multivariate dynamic regression models is proposed to model hourly electricity load. Alternative forecasting models, special cases of our general model, include separate time series regressions for each hour and week day. All the models developed include components that represent trends, seasons at different levels (yearly, weekly, etc.), dummies to take into account weekends/holidays and other special days, and short‐term dynamics and weather regression effects, discussing the necessity of nonlinx ear functions for cooling effects. Our developments explore the facilities of dynamic linear models such as the use of discount factors, subjective intervention, variance learning and smoothing/filtering. The elicitation of the load curve is considered in the context of subjective intervention analysis, which is especially useful to take into account the adjustments for daylight savings time. The theme of combination of probabilistic forecasting is also briefly addressed. Copyright © 2013 John Wiley & Sons, Ltd.

Gutiérrez‐Peña, E.; Mendoza, M.

2013 Applied Stochastic Models in Business and Industry

doi: 10.1002/asmb.1964

Palma, Wilfredo

2013 Applied Stochastic Models in Business and Industry

doi: 10.1002/asmb.1965

2013 Applied Stochastic Models in Business and Industry

doi: 10.1002/asmb.1993

Hosking, J.R.M.; Natarajan, R.; Ghosh, S.; Subramanian, S.; Zhang, X.

2013 Applied Stochastic Models in Business and Industry

doi: 10.1002/asmb.1987

We propose a model of the daily load curve for residential electricity usage, including in particular the effects of dynamic price incentives on the demand response, a topic of considerable interest in the emerging Smart Grid. The model is based on a time series and stochastic regression framework in which the observed daily load curve is represented in terms of a set of periodic smoothing‐spline basis functions, with the basis function coefficients evolving according to a linear Gaussian state‐space model that incorporates level shifts, day of the week and holiday adjustments, and weather effects, as well as the dynamic price‐incentive effects mentioned earlier. Model parameters are estimated from observational time‐series data using maximum‐likelihood methods, with the computations being efficiently carried out using Kalman filtering recursions. The resulting fitted model can be used for short‐term load forecasting by providing a forward sequence of price‐incentive signals and weather projections over the forecast period. This proposed modeling and forecasting methodology have many advantages over competing methods in the literature, including the ability to model intraday load‐substitution effects that are induced by the specified dynamic pricing schedules, the ability to use fine‐grained (5–15 min interval) observational data without greatly increasing the computational cost of the estimation and forecasting procedures, the ability to use informative prior distributions for any model parameters that cannot be reliably estimated from the available observational data, and the ability to update model forecasts based on the latest sequence of partial observational data without having to store the entire time‐series history. Copyright © 2013 John Wiley & Sons, Ltd.

Espasa, Antoni; Durban, Maria

2013 Applied Stochastic Models in Business and Industry

doi: 10.1002/asmb.1975

Aung, Zeyar

2013 Applied Stochastic Models in Business and Industry

doi: 10.1002/asmb.1979

Hosking, J. R. M.; Natarajan, Ramesh; Ghosh, Soumyadip; Subramanian, Shivaram; Zhang, Xiaoxuan

2013 Applied Stochastic Models in Business and Industry

doi: 10.1002/asmb.1992

Göb, Rainer; Lurz, Kristina; Pievatolo, Antonio

2013 Applied Stochastic Models in Business and Industry

doi: 10.1002/asmb.2008

In the past, studies in short‐term electrical load forecasting have been rather sceptical on the use of meteorological covariates like temperature for short‐term forecasting purposes. The main reasons were time delays in data provision and the poor precision of meteorological forecasts. Both arguments have lost their impact, as new recent studies have shown. We explore the use of meteorological covariates in short‐term load forecasting based on the rather new method of exponential smoothing with covariates (ESCov). The existing ESCov model is refined by including multiple seasonalities. The method is empirically explored in the hourly prediction of the electrical consumption of customers from provinces of an Italian region. Copyright © 2013 John Wiley & Sons, Ltd.

Pilar MuñOz, M.

2013 Applied Stochastic Models in Business and Industry

doi: 10.1002/asmb.1999