A skewed exponential power distribution to measure value at risk in electricity market

Aymeric Thibault (1) , Pascal Bondon (1)

1 L2S - Laboratoire des signaux et systèmes

Interest in risk measurement for spot price has increased since the worldwide deregulation and liberalization of electricity started in the early 90's. This paper is focused on quantifying risk for the Nordic Power Exchange (Nord Pool) system price. Our analysis is based on a generalized autoregressive conditional heteroskedastic (GARCH) process with skewed exponential power innovations to model the stochastic component of the system price. Value at risk (VaR) backtesting procedures are presented and our model performance is compared to commonly used distributions in risk measurement. We show that the skewed exponential power distribution outperforms the competitors for the upside risk (95%, 97.5% and 99% VaR), which is of high interest as electricity spot prices are positively skewed.

Domains: Statistics [stat]; Statistics Theory [stat.TH]; Engineering Sciences [physics]; Signal and Image processing

Aymeric Thibault, Pascal Bondon. A skewed exponential power distribution to measure value at risk in electricity market. 2016 IEEE Statistical Signal Processing Workshop (SSP), Jun 2016, Palma de Mallorca, Spain. 5 p., ⟨10.1109/ssp.2016.7551835⟩. ⟨hal-01577056⟩