Simulation of day-ahead electricity market prices using a statistically calibrated structural model

Abstract

Anticipating electricity prices on the day-ahead market has become a key issue for both risk assessment and revenue optimization. In this paper, we propose to generate time series of prices with an hourly resolution using a structural model that simulates a simplified market clearing process. The aggregated supply curves in this model are composed of orders based on the available capacity of generation units. The ask prices are parametrized, and the calibration is performed by applying statistical learning to historical market and power system data. To reflect the strategic behavior of market participants, these prices depend on the scarcity of power at the national level. The model's performance is assessed based on the case of France with a one-year horizon and data from 2013-2015. This approach illustrates how open data on the electric power system enable links to be drawn between technical constraints and price formation. Index Terms-day-ahead markets, electricity prices, statistical learning, structural model The authors wish to thank the French Environment and Energy Management Agency (ADEME), the Association pour la Recherche et le Développement des Méthodes et Processus Industriels (ARMINES) and Coruscant SA for financially supporting this research.

Neural modelling of electricity prices quoted on the Day-Ahead Market of TGE S.A. shaped by environmental and economic factors

“…Day-ahead market modelling using both different versions of ANN [1,12,20] as well as other modelling methods [5,8,9,10,11,13] is not a new issue and has been descripted in many papers. They referred both to finding the better model than the previous ones for classic power plants as well as for photovoltaic or wind farms.…”

Data-driven structural modeling of electricity price dynamics

“…In order words, exploiting real data ensures that the theory is coherent with the market phenomena observed in practice. In light of the scientific literature and extending [33], we propose a structural model in which the supply curve is constructed with a bottom-up approach. Market orders are associated with production units and their prices are parametrized, which means that we can leverage available market and power system data.…”