Six thinking hats: A novel metalearner for intelligent decision support in electricity markets
Introduction
The electricity industry has been facing an important challenge since the 1980s—a market environment is replacing the traditional centralised-operation approach, thereby creating a more competitive and complex environment [1]. This deregulation, often accompanied by privatisation processes, has brought many changes. For example, presently the industry is organised in a horizontal way, replacing the previous vertical organisation. Many electricity companies used to be responsible for the complete business chain; now, they are split into several companies, with each one focusing exclusively on one business area: generation, transmission, distribution, and retail. The changes also aim to give consumers a more active role in the market, ensuring their ability to choose their energy supplier [2]. The new electricity market environment is more complex and unpredictable, forcing interveners to rethink their strategies and behaviour. Several market models exist, with different rules and constraints, creating the need to foresee market behaviour. Regulators need to test the rules before they are implemented, and market players need to understand the market so that they can reap the benefits of well-planned actions. The employment of simulation tools is an adequate way to find market inefficiencies and to provide support for players' decisions. The multiagent paradigm is useful for the job because it can represent several constituents with their own individual features, interacting in a dynamic system. Relevant tools in this domain are the Electricity Market Complex Adaptive System (EMCAS) [3] and Agent-based Modelling of Electricity Systems (AMES) [4].
The Multi-Agent Simulator of Competitive Electricity Markets (MASCEM) [5], [6] is another simulator, which has been developed by the authors' research team to address the constant changes in the electricity market operation all around the world. With this purpose, MASCEM is always under improvement, updating the existent market mechanisms and integrating new ones to reflect different countries' approaches and realities [7], [8]. The different market opportunities, together with the necessity to address the increasing complexity in the electricity market environment, force players to adapt and act strategically to take the most advantage from their negotiations.
To complement the MASCEM simulator with new strategies, learning, and adaptability, a new system was developed in [6]: ALBidS—Adaptive Learning strategic Bidding System. This system implements several new strategies and behaviours along with those originally implemented in MASCEM. The purpose of ALBidS is to provide market players with the capability to act and react accordingly to the different contexts they encounter in the market, which is achieved using several different strategies and adaptive learning techniques to choose the most appropriate way to use each of them, according to the context [9]. The approach generally adopted by ALBidS is to take advantage of the differences and particularities of each strategy, considering them as different options that are most suitable for different contexts. However, the different natures of the strategies can provide complementary aspects, which, when combined, can prove to be much more powerful than the simple “sum of the parts.” It is in the understanding of these complementarities, and how to combine different approaches, that this paper gives its contribution.
The main goal of a metalearner is to use meta-data to improve the performance of existing learning algorithms [10]. By using meta-data derived from other learning algorithms, a metalearner creates flexibility in solving different types of learning problems [11]. Metalearners are especially useful when dealing with dynamic environments, with a high level of associated uncertainty, as is the case of the electricity market environment. The combination of the meta-data derived from the different existing learning algorithms must be performed appropriately to obtain a valuable output. Six Thinking Hats (STH) is a parallel thinking method built to change the way meetings are run and the way stakeholders work and interact [12]. For each direction of thinking, STH associates a hat with a distinct colour. Using this method, participants discard any conflict that emerges in the meeting. Taking advantage of stakeholders' capabilities should result in better decisions.
Using the principles of the STH method, this paper proposes a new metalearner that combines the different outputs from ALBidS strategies to support the choice of the best possible action for market players. This is performed using a set of different agents reasoning in a distinct STH point of view. Individual answers are then combined using genetic algorithms (GA) [13], [14] with the purpose of providing a better and evolutionary overall combination of all the answers. The proposed method, acting as a metalearner, offers the possibility of combining different strategic bidding approaches so that through cooperation they can contribute to an overall better response than individually. The best potential result that can be achieved from the use of different methodologies in parallel is equal to the result of the best individual approach. On the other hand, taking advantage of the cooperation and combination of the individual methodologies, the final result is not limited to the threshold of the best strategy; it is open to the accomplishment of better results, achieved by taking advantage of the best assets of each individual approach. These results are demonstrated by the case study that is presented in Section 4, which shows that the proposed STH-based metalearner is able to achieve better results than the individual strategies by themselves. GA has been applied in diverse fields, such as machine learning [15], [16], optimisation [17], scheduling [13], and many others [14]. However, the use of an evolutionary approach as a metalearner, combining the learning processes of different learning algorithms, has not been presented in the literature. Moreover, approaching the different meta-data resulting from the distinct learning processes in a way that each approach is considered dependently of its nature (or way of thinking) by using methods that result from fields that specifically study the interaction of different entities—sociology (such as the STH) is a novelty that complements the development of a GA-based metalearner.
After this introductory section, Section 2 examines the electricity markets simulation thematic, including an overview of the main electricity market models found worldwide and an outline of the main features of MASCEM and ALBidS. The characteristics and particularities of the STH method are addressed in Section 3, including its adaption to decision support by means of metalearning through integration in ALBidS and MASCEM. The results of the proposed method are presented in Section 4, using case studies based on real data from the Iberian Market—MIBEL [18], from which the performance of the STH-based metalearner is compared to other approaches. Finally, Section 5 presents the most relevant conclusions and contributions of this work.
Section snippets
Electricity markets simulation
The electricity industry has experienced major changes in the structure of its markets and in its regulation around the world. This transformation is often called the deregulation of the electricity market. The industry is becoming more competitive, as a market environment is replacing the traditional centralised-operation approach; this change allows market forces to drive electricity prices [2]. The liberalised market environment typically consists of a day-ahead spot market, based on a pool,
Six Thinking Hats
STH is a parallel thinking method built to change the way meetings are run and the way stakeholders work and interact [12]. This method proposes to, among other results, increase the speed at which decisions are made without hastening the process. The method also “promises” to harness and take full advantage of the intelligence, information, and experience of each party present in the meeting. By using this method, participants are invited to discard, almost entirely, any emerging conflict in
Case study
The case studies presented in this section illustrate some of the advantages of using the proposed metalearner to complement the previous ALBidS strategies.
Two different case studies are presented after the specifications sub-section, in which the market negotiation mechanism (which is used for both the simulations and also as a fitness function of the GA approach) is described, and the parameterisations of the used methods are depicted. The first case study, in Section 4.2, presents a
Conclusions
This paper presented a new path for research in agent-based decisions by converting a decision driven method into a metalearner with auspicious results in the fields of artificial intelligence and power systems, namely, through electricity market study (by using MASCEM and ALBidS).
ALBidS combines several different strategic approaches, perceived as tools by the main agent; this work extended ALBidS by presenting a new strategy combining previously existing strategies in a way so that they can
Acknowledgments
This work is supported by FEDER Funds through the COMPETE programme and by National Funds through FCT under the projects FCOMP-01-0124-FEDER: PEst-OE/EEI/UI0760/2014, PTDC/EEA-EEL/122988/2010, and SFRH/BD/80632/2011 (Tiago Pinto PhD); by the GID-MicroRede, project no. 34086, co-funded by COMPETE under FEDER via the QREN Programme; by the SASGER-MeC, project no. NORTE-07-0162-FEDER-000101, co-funded by COMPETE under FEDER; and by the ITEA2 project: 12004 SEAS (Smart Energy Aware Systems).
Tiago Pinto received the BSc degree in 2008 and the MSc in Knowledge-based and Decision Support Technologies in 2011, both from the Polytechnic Institute of Porto (ISEP/IPP), Portugal. Presently, he is a Researcher at GECAD—Knowledge Engineering and Decision-Support Research Center and he is also a PhD student with the University of Trás-os-Montes e Alto Douro. His research interests include multi-agent simulation and machine learning techniques.
References (45)
Development of the internal electricity market in Europe
The Electricity Journal
(2005)- et al.
Towards high dimensional instance selection: an evolutionary approach
Decision Support Systems
(May 2014) - et al.
An examination of evolved behavior in two, reinforcement learning systems
Decision Support Systems
(April 2013) A new approach for multi-agent coalition formation and management in the scope of electricity markets
Energy
(2011)A decision support system for planning and coordination of hybrid renewable energy systems
Decision Support Systems
(August 2014)A stochastic, contingency-based security-constrained optimal power flow for the procurement of energy and distributed reserve
Decision Support Systems
(December 2013)- et al.
A decision support system for sustainable energy supply combining multi-objective and multi-attribute analysis: an Australian case study
Decision Support Systems
(January 2014) - et al.
An auction design for local reserve energy markets
Decision Support Systems
(December 2013) A hybrid heuristic approach for attribute-oriented mining
Decision Support Systems
(January 2014)Market Operations in Electric Power Systems: Forecasting, Scheduling, and Risk Management
(2002)
Real-world market representation with agents: modeling the electricity market as a complex adaptive system with an agent-based approach
IEEE Power and Energy Magazine
Development of open source software for power market research: the AMES test Bed
Journal of Energy Markets
MASCEM: a multi-agent system that simulates competitive electricity markets
IEEE Intelligent Systems
MASCEM—electricity markets simulation with strategic players
IEEE Intelligent Systems
Balancing market integration in MASCEM electricity market simulator
Multi-agent simulation of continental, regional, and micro electricity markets
Bid definition method for electricity markets based on an adaptive multiagent system
Advances on Practical Applications of Agents and Multiagent Systems
The role of meta-learning in study process
British Journal of Educational Psychology
Meta-learner for unknown attribute values processing: dealing with inconsistency of meta-databases
Journal of Intelligent Information Systems
Six Thinking Hats
A genetic algorithm-based approach to flexible flow-line scheduling with variable lot sizes
IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics
Genetic algorithms in search, optimization, and machine learning
Cited by (15)
Consequences of different strategic decisions of market coupled zones on the development of energy systems based on coal and hydropower
2020, EnergyCitation Excerpt :Nevertheless, the interconnection would increase the social welfare (defined as socio-economic gain in three possible lines of revenue: consumer’s surplus, producer’s surplus, and congestion rent) on both electricity markets in optimal scenario for 110 M€/a. The use of multi-agent modelling has been exploited as a machine learning method, using available information in combination with genetic algorithms [23]. Further research has been conducted by multi-agent simulation [24] and by linking two neighbouring electricity markets [25], market-based modelling based on volume of trading [26] and exploring how market consolidation through their merger affects the possibilities of their planning [27].
The effects of the six thinking hats and speed on creativity in brainstorming
2019, Thinking Skills and CreativityCitation Excerpt :Finally, the black hat represents the pessimistic hat (De Bono, 1992). Since the publication of six thinking hats by De Bono, there have been suggestions in many articles and book chapters about the benefits of this technique, especially with the blue and green hat, in the educational settings (Kivunja, 2015; Pinto et al., 2015; Vernon & Hocking, 2014). To date, however, empirical evidence for the effectiveness of these suggestions has not been present in the literature yet.
A two-stage analytical approach to assess sustainable energy efficiency
2018, EnergyCitation Excerpt :A number of studies have taken into account the evaluation of renewable energy sources in order to show their substantial contributions from diverse aspects of human life and to help the governments deliver on a range of policy objectives—economic, environmental, and social. In this regard, some studies in the literature analyze renewable energy portfolio utilizing from various decision making and optimization tools while other studies just consider the energy efficiency issue to provide a comprehensive insight of renewable energy assessment [4,23–26]. Neves et al. [27] proposed a multi-criteria decision analysis model, initially utilizing soft systems methodology then, Keeney's Value-Focused Thinking approach to evaluating energy efficiency attempts.
VetPaw Pet Care Application: An Assessment of the Proposed Business Application using SWOT Analysis
2022, ACM International Conference Proceeding SeriesAn investment game with complete and incomplete information applied to the power market
2022, Contaduria y AdministracionMachine learning in information systems - a bibliographic review and open research issues
2021, Electronic Markets
Tiago Pinto received the BSc degree in 2008 and the MSc in Knowledge-based and Decision Support Technologies in 2011, both from the Polytechnic Institute of Porto (ISEP/IPP), Portugal. Presently, he is a Researcher at GECAD—Knowledge Engineering and Decision-Support Research Center and he is also a PhD student with the University of Trás-os-Montes e Alto Douro. His research interests include multi-agent simulation and machine learning techniques.
João Barreto received the BSc degree in 2007 and the MSc in Knowledge-based and Decision Support Technologies in 2012, both from the Polytechnic Institute of Porto (ISEP/IPP), Portugal. His research work is performed at GECAD—Knowledge Engineering and Decision-Support Research Center. His research interests include bio-inspired software applications, multi-agent simulation and electricity markets.
Isabel Praça is a professor and a researcher in the Knowledge Engineering and Decision Support Research Group (GECAD) of the School of Engineering, at Polytechnic Institute of Porto. Her research areas include multi-agent systems, simulation, decision support systems and electricity markets. She has a PhD in electrical engineering from the University of Trás-os-Montes e Alto Douro.
Tiago M. Sousa is a graduate student in the Knowledge Engineering and Decision Support Research Group (GECAD) of the School of Engineering, at Polytechnic Institute of Porto. His research interests include multi-agent simulation, electricity markets, and learning techniques. He has a bachelor's in informatics from Polytechnic institute of Porto.
Zita Vale (S'86–M'93–SM'10) is the director of the Knowledge Engineering and Decision Support Research Group (GECAD) and a professor at the Polytechnic Institute of Porto. Her main research interests concern artificial intelligence (A.I.), applications to power system operation and control, electricity markets and distributed generation. She received her diploma in electrical engineering in 1986 and her PhD in 1993, both from University of Porto, Portugal.
E. J. Solteiro Pires is a “auxiliary professor” at University of Trás-os-Montes e Alto Douro (UTAD). His main research interests are in evolutionary computation, multiobjective problems, and fractional calculus. He received the degree in electrical engineering at the University of Coimbra, in 1993 and the MSc in Electrical and Computer Engineering at the University of Oporto in 1999. In 2006, he graduated with a PhD degree at UTAD