Short-term load forecasting is an essential instrument in power system planning, operation, and control. Many operating decisions are based on load forecasts, such as dispatch scheduling of generating capacity, reliability analysis, and maintenance planning for the generators. Overestimation of electricity demand will cause a conservative operation, which leads to the start-up of too many units or excessive energy purchase, thereby supplying an unnecessary level of reserve. On the other hand, underestimation may result in a risky operation, with insufficient preparation of spinning reserve, causing the system to operate in a vulnerable region to the disturbance. In this paper, semi-parametric additive models are proposed to estimate the relationships between demand and the driver variables. Specifically, the inputs for these models are calendar variables, lagged actual demand observations, and historical and forecast temperature traces for one or more sites in the target power system. In addition to point forecasts, prediction intervals are also estimated using a modified bootstrap method suitable for the complex seasonality seen in electricity demand data. The proposed methodology has been used to forecast the half-hourly electricity demand for up to seven days ahead for power systems in the Australian National Electricity Market. The performance of the methodology is validated via out-of-sample experiments with real data from the power system, as well as through on-site implementation by the system operator.
Short-Term Load Forecasting Based on a Semi-Parametric Additive Model
Published 2012 in IEEE Transactions on Power Systems
ABSTRACT
PUBLICATION RECORD
- Publication year
2012
- Venue
IEEE Transactions on Power Systems
- Publication date
2012-02-01
- Fields of study
Engineering, Environmental Science, Economics
- Identifiers
- External record
- Source metadata
Semantic Scholar
CITATION MAP
EXTRACTION MAP
CLAIMS
CONCEPTS
- australian national electricity market
The Australian power system context in which the forecasting method is evaluated and implemented.
Aliases: NEM
- calendar variables
Date- and time-based inputs such as season, day, or other calendar indicators used as predictors.
Aliases: calendar features
- complex seasonality
Strong recurring temporal patterns in electricity demand that vary across multiple time scales.
- historical and forecast temperature traces
Observed and predicted temperature time series from one or more sites used as weather inputs.
Aliases: temperature traces
- lagged actual demand observations
Past observed electricity demand values used as autoregressive predictors.
Aliases: lagged demand
- modified bootstrap method
A resampling procedure adapted to generate uncertainty estimates under the seasonal structure of electricity demand.
Aliases: bootstrap method
- on-site implementation
Deployment of the forecasting approach in an operational system environment.
- out-of-sample experiments
Evaluations performed on data not used for model fitting to test generalization.
- prediction intervals
A range estimate intended to contain future electricity demand with a specified level of uncertainty.
- semi-parametric additive model
An additive statistical model that combines parametric and nonparametric components to relate demand to driver variables.
Aliases: semi-parametric additive models
- short-term load forecasting
The task of predicting near-future electricity demand over horizons from hours to days.
Aliases: load forecasting
REFERENCES
Showing 1-32 of 32 references · Page 1 of 1