Data mining approach to support the generation of Realistic Scenarios for multi-agent simulation of electricity markets

Advances in Practical Applications of Agents, Multi-Agent Systems, and Sustainability: The PAAMS Collection

et al. 2015

Self Cite

IntroductionWorldwide electricity markets (EM) have undertaken a great revolution with the emergence of the liberalized market [1]. The restructuring of the constituent sectors of EM (production, marketing, transportation and distribution) turned EM into a more competitive environment, which in turn led to increased decision-making difficulty. In order to overcome the complexity and unpredictability of this sector, simulation tools began to be a great investment area. EM simulators are tools that help clarifying the functioning of markets in order to create profiles of the participant players through the analysis, study and forecast of different scenarios [2]. The profiles of participant players allow the understanding of the type of strategies taken by them and support their decision-making processes. The emergence of simulation platforms has been a huge added value since it revolutionized the understanding of the markets operation. Additionally, simulation platforms allow the testing of different participants' behaviors as well as new rules and operations of regulators and market participants [3][4][5].However, simulators of multi-agent energy markets face some problems when it comes to apply the simulated results in reality. In order to create realistic scenarios it is necessary to consider all the real information about the characteristics and behaviors of the players, as well as markets' specifications. This information is available on web platforms of market operators (e.g. MIBEL market data is available in [6]); however, it is not easily interpreted or extracted, which brings many limitations to the process of generating realistic scenarios. Once this limitation is surpassed and the necessary information is obtained, the main problem becomes the treatment of this information in order to create simulations of realistic scenarios.In order to overcome the difficulty that EM simulators face to create realistic scenarios, the Realistic Scenarios Generator (RealScen) has been developed [7]. RealScen uses real data gathered from diverse sources to define the amount, characteristics and behavior of the software agents used in EM simulations, depending on the simulation requirements and on each EM specifications.

Section: Main Purposementioning

confidence: 99%

mentioning

confidence: 99%

Demonstration of Realistic Multi-agent Scenario Generator for Electricity Markets Simulation

Silva

Teixeira

Advances in Practical Applications of Agents, Multi-Agent Systems, and Sustainability: The PAAMS Collection

et al. 2015

Self Cite

“…By combining real extracted data with the data resulting from simulations, RealScen offers the possibility of generating scenarios for different types of electricity markets. Taking advantage on MASCEM's ability to simulate a broad range of different market mechanisms, this framework enables users to consider scenarios that are the representation of real markets of a specific region; or even consider different configurations, to test the operation of the same players under changed, thoroughly defined scenarios [22]. When summarized, yet still realistic scenarios are desired (in order to decrease simulations' execution time or facilitate the interpretation of results), data mining techniques are applied to define the players that act in each market.…”

Section: A U T H O R ' S V E R S I O Nmentioning

confidence: 99%

“…Simulation scenarios in MASCEM are automatically defined, using the Realistic Scenario Generator (RealScen) [22]. RealScen uses real data that is available online, usually in market operators' websites.…”

Section: A U T H O R ' S V E R S I O Nmentioning

confidence: 99%

Reserve costs allocation model for energy and reserve market simulation

2017 19th International Conference on Intelligent System Application to Power Systems (ISAP)

Gazafroudi

Prieto‐Castrillo

et al. 2017

Self Cite

Abstract-This paper proposes a new model to allocate reserve costs among the involved players, considering the characteristics of the several entities, and the particular circumstances at each moment. The proposed model is integrated in the Multi-Agent Simulator of Competitive Electricity Markets (MASCEM), which enables complementing the multi-agent simulation of diverse electricity market models, by including the co-simulation of energy and reserve markets. In this context, the proposed model allows allocating the payment of reserve costs that result from the reserve market. A simulation based on real data from the Iberian electricity market -MIBEL, is presented. Simulation results show the advantages of the proposed model in sharing the reserve costs fairly and accordingly to the different circumstances. This work thus contributes the study of novel market models towards the evolution of power and energy systems, with the objective of adapting current and future models to the new paradigm of high renewable energy generation penetration.

“…Each one of the surrounding entities may present different behaviours resulting from the context and its goals, having an immediate impact on the results obtained in the market [4]. Therefore, simulators allow to perform a study of new types of participating entities, their behaviour, market models, types of market trading mechanisms, among others, to understand the impact of these variables on system performance and, therefore, to react in order to achieve the best possible results.Although multi-agent simulation tools present many advantages, most are not able to present results that can be applied to reality [5]. In order to deal with this problem, it is necessary to create realistic scenarios that consider real data about the behaviour and characteristics of market participants as well as the specifications of the markets [6,7].…”

mentioning

confidence: 99%

Generation of realistic scenarios for multi-agent simulation of electricity markets

Silva

Teixeira

et al. 2016

Energy

Self Cite

Most market operators provide daily data on several market processes, including the results of all market transactions. The use of such data by electricity market simulators is essential for simulations quality, enabling the modelling of market behaviour in a much more realistic and efficient way. RealScen (Realistic Scenarios Generator) is a tool that creates realistic scenarios according to the purpose of the simulation: representing reality as it is, or on a smaller scale but still as representative as possible. This paper presents a novel methodology that enables RealScen to collect real electricity markets information and using it to represent market participants, as well as modelling their characteristics and behaviours. This is done using data analysis combined with artificial intelligence. This paper analyses the way players' characteristics are modelled, particularly in their representation in a smaller scale, simplifying the simulation while maintaining the quality of results. A study is also conducted, comparing real electricity market values with the market results achieved using the generated scenarios. The conducted study shows that the scenarios can fully represent the reality, or approximate it through a reduced number of representative software agents. As a result, the proposed methodology enables RealScen to represent markets behaviour, allowing the study and understanding of the interactions between market entities, and the study of new markets by assuring the realism of simulations.The restructuring of Electricity Markets (EM) has created a new design of the electricity sector, becoming a new global trend. The monopoly model gave way to a non-vertical structure that allows the development of a free competition market, as it allows the liberalization of potentially competitive segments, such as production, transportation and distribution [1]. These changes provide conditions for the establishment of a more competitive market but also more complex, where the laws of supply and demand stimulate the quality of service, reduce costs and increase efficiency. The growth of complexity creates new challenges, namely the difficulty in decision making due to markets unpredictability and the high number of associated variables [2].Simulation started to play a key role in supporting decision-making in the electricity sector. It allows studying and analysing the profiles and strategies of market participants and, thus, model market behaviour and forecast proposals [3]. Such characteristics enable the establishment of conditions conductive to decision making, turning the simulators into essential tools to support the necessary decisions on major investment environments.Simulation tools applied to EM are designed to help market entities to respond efficiently to market unpredictability. Each one of the surrounding entities may present different behaviours resulting from the context and its goals, having an immediate impact on the results obtained in the market [4]. Therefore, simulators allow to perform a stu...