Forecasting electricity consumption by aggregating specialized experts
From MaRDI portal
Abstract: We consider the setting of sequential prediction of arbitrary sequences based on specialized experts. We first provide a review of the relevant literature and present two theoretical contributions: a general analysis of the specialist aggregation rule of Freund et al. (1997) and an adaptation of fixed-share rules of Herbster and Warmuth (1998) in this setting. We then apply these rules to the sequential short-term (one-day-ahead) forecasting of electricity consumption; to do so, we consider two data sets, a Slovakian one and a French one, respectively concerned with hourly and half-hourly predictions. We follow a general methodology to perform the stated empirical studies and detail in particular tuning issues of the learning parameters. The introduced aggregation rules demonstrate an improved accuracy on the data sets at hand; the improvements lie in a reduced mean squared error but also in a more robust behavior with respect to large occasional errors.
Recommendations
- scientific article; zbMATH DE number 6458281
- Online aggregation of unbounded losses using shifting experts with confidence
- Prediction with expert evaluators' advice
- Forecasting electricity consumption with extra-model information provided by consumers
- Additive stacking for disaggregate electricity demand forecasting
Cites work
- A Functional Wavelet–Kernel Approach for Time Series Prediction
- Adaptive and self-confident on-line learning algorithms
- Forecasting electricity consumption by aggregating specialized experts
- From external to internal regret
- Generalized additive models. An introduction with R.
- scientific article; zbMATH DE number 1512687 (Why is no real title available?)
- scientific article; zbMATH DE number 1559549 (Why is no real title available?)
- Improved second-order bounds for prediction with expert advice
- Internal regret in on-line portfolio selection
- Potential-based algorithms in on-line prediction and game theory
- Prediction with expert advice for the Brier game
- Prediction, Learning, and Games
- Tracking climate models
- Tracking the best expert
- Universal Portfolios
Cited in
(10)- Forecasting electricity consumption by aggregating specialized experts
- Sequential model aggregation for production forecasting
- Frequency-based ensemble forecasting model for time series forecasting
- Additive stacking for disaggregate electricity demand forecasting
- Forecasting electricity consumption with extra-model information provided by consumers
- Space-dependent turbulence model aggregation using machine learning
- Kalman recursions aggregated online
- Online aggregation of unbounded losses using shifting experts with confidence
- Space-dependent aggregation of stochastic data-driven turbulence models
- CRPS Learning
This page was built for publication: Forecasting electricity consumption by aggregating specialized experts
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1945028)
