As mature electricity markets, the Italian spot ones provide substantial liquidity of the electrical trades through 3 interconnected markets with different pricing schemes. In this paper, we propose a framework for analyzing the behavior potential of the market players in the multi-market context to investigate if a different resources allocation in various spot market can increase the player's profit. Starting from forecast initial strategies obtained by a machine learning algorithm based on public data, bidding strategies for maximizing profit of players are iteratively derived by solving multiple market-clearings and settlements simultaneously. By simulating three cases, we find that small generators tend to use a survival-driven bidding approach, putting most of their production capacity on uniform price markets to guarantee a stable income. By contrast, due to the higher adjustment capabilities and risk resistances, large generators can take some risk to increase profits. Finally, with the player-specific strategy suggested by the framework, 180 operators are able to increase their profit by 139% on average.
A Hybrid Data-and-simulation-based Analysis of the Participants' Behavior Potential in the Italian Spot Electricity Markets / Huang, T.; Gioacchini, L.; Guaiana, F.; Huang, S.; Valente, B.; Pio Domiziani, G.. - (2020), pp. 1-6. ((Intervento presentato al convegno 55th International Universities Power Engineering Conference, UPEC 2020 tenutosi a ita nel 2020.
Titolo: | A Hybrid Data-and-simulation-based Analysis of the Participants' Behavior Potential in the Italian Spot Electricity Markets |
Autori: | |
Data di pubblicazione: | 2020 |
Abstract: | As mature electricity markets, the Italian spot ones provide substantial liquidity of the electri...cal trades through 3 interconnected markets with different pricing schemes. In this paper, we propose a framework for analyzing the behavior potential of the market players in the multi-market context to investigate if a different resources allocation in various spot market can increase the player's profit. Starting from forecast initial strategies obtained by a machine learning algorithm based on public data, bidding strategies for maximizing profit of players are iteratively derived by solving multiple market-clearings and settlements simultaneously. By simulating three cases, we find that small generators tend to use a survival-driven bidding approach, putting most of their production capacity on uniform price markets to guarantee a stable income. By contrast, due to the higher adjustment capabilities and risk resistances, large generators can take some risk to increase profits. Finally, with the player-specific strategy suggested by the framework, 180 operators are able to increase their profit by 139% on average. |
ISBN: | 978-1-7281-1078-3 |
Appare nelle tipologie: | 4.1 Contributo in Atti di convegno |