Skip to content
All library documents

Hybrid Models for Forecasting Electricity Spot Prices

Article arXiv papers · Author: Tahir Miriyev et al.
Read the original

Summary

The document outlines a study of hybrid approaches to forecasting spot electricity prices in the EPEC market. The model components include a naive forecast, Fourier analysis, ARMA and GARCH models, a mean-reverting jump-diffusion process, and recurrent neural networks. It identifies these as elements of the hybrid modelling approach but does not explain how they are combined or how their forecasts are compared.

The study uses electricity prices from 2013–2014 for training and reserves 2015 as the test period. This time split provides a stated basis for evaluating forecasts on a later year. However, the document reports no accuracy measures, comparative results, market characteristics, or details about model settings. Readers therefore cannot determine which approach performed best or whether the results generalize beyond this market and period.

Key ideas

  • The study considers hybrid methods for forecasting spot electricity prices in the EPEC market.
  • Its listed model components include Fourier analysis, ARMA, GARCH, mean reversion with jumps, and recurrent neural networks.
  • Electricity price data from 2013–2014 serves as the training period.
  • The year 2015 is reserved for testing forecasts.
  • No performance results or model-combination details are provided.

Tags

CommoditiesStatisticsMachine learningMean reversionVolatility
Full text
# Hybrid Modelling Approaches for Forecasting Energy Spot Prices in EPEC market


# Hybrid Modelling Approaches for Forecasting Energy Spot Prices in EPEC market









In this work we considered several hybrid modelling approaches for forecasting energy spot prices in EPEC market. Hybridization is performed through combining a Naive model, Fourier analysis, ARMA and GARCH models, a mean-reversion and jump-diffusion model, and Recurrent Neural Networks (RNN). Training data was given in terms of electricity prices for 2013-2014 years, and test data as a year of 2015.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.