The high penetration of intermittence resources in the energy market accelerates significantly the decarbonization process, but, on the other hand, the electrical system has to face the problem of unbalances. Renewable energies sources are hard to precisely forecast, and power plants are not able to predict the amount of energy that they can provide far from the real-time delivery. In this frame, the intraday market gets a fundamental role allowing agents to adjust their position close to the delivery time. In this work, we suggest an agent-based model of intraday market combined with genetics algorithms to understand what the best strategy could be adopted by players in order to optimize the market efficiency in terms of welfare and unsold quantity. In the first part, we show the effect on the market prices of different scenarios in which players aim at maximizing their revenues and selling/buying all their volumes. In the second part, we show the effect of a particular genetic algorithm on the model, focusing on how agents can adapt their strategy to enhance the market efficiency. Comparative analyses are also performed to investigate how the welfare of the system increases as well as the unsold quantity decrease when genetic algorithm is introduced.
Optimization of an agent-based model for continuous trading energy market
Alberizzi A.;Di Barba P.;Mognaschi M. E.;
2024-01-01
Abstract
The high penetration of intermittence resources in the energy market accelerates significantly the decarbonization process, but, on the other hand, the electrical system has to face the problem of unbalances. Renewable energies sources are hard to precisely forecast, and power plants are not able to predict the amount of energy that they can provide far from the real-time delivery. In this frame, the intraday market gets a fundamental role allowing agents to adjust their position close to the delivery time. In this work, we suggest an agent-based model of intraday market combined with genetics algorithms to understand what the best strategy could be adopted by players in order to optimize the market efficiency in terms of welfare and unsold quantity. In the first part, we show the effect on the market prices of different scenarios in which players aim at maximizing their revenues and selling/buying all their volumes. In the second part, we show the effect of a particular genetic algorithm on the model, focusing on how agents can adapt their strategy to enhance the market efficiency. Comparative analyses are also performed to investigate how the welfare of the system increases as well as the unsold quantity decrease when genetic algorithm is introduced.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
