Metalearning in ALBidS: A Strategic Bidding System for electricity markets

Metalearning is a subfield of machine learning with special pro-pensity for dynamic and complex environments, from which it is difficult to extract predictable knowledge. The field of study of this work is the electricity market, which due to the restructuring that recently took place, became an especially complex and unpredictable environment, involving a large number of different entities, playing in a dynamic scene to obtain the best advantages and profits. This paper presents the development of a metalearner, applied to the decision support of electricity markets’ negotia-tion entities. The proposed metalearner takes advantage on several learning algorithms implemented in ALBidS, an adaptive learning system that pro-vides decision support to electricity markets’ participating players. Using the outputs of each different strategy as inputs, the metalearner creates its own output, considering each strategy with a different weight, depending on its individual quality of performance. The results of the proposed meth-od are studied and analyzed using MASCEM - a multi-agent electricity market simulator that models market players and simulates their operation in the market. This simulator provides the chance to test the metalearner in scenarios based on real electricity market´s data.

Adaptive learning in multiagent systems: a forecasting methodology based on error analysis

Electricity markets are complex environments, involving a large number of different entities, playing in a dynamic scene to obtain the best advantages and profits. MASCEM is a multi-agent electricity market simu-lator to model market players and simulate their operation in the market. Market players are entities with specific characteristics and objectives, making their decisions and interacting with other players. MASCEM pro-vides several dynamic strategies for agents’ behaviour. This paper presents a method that aims to provide market players strategic bidding capabilities, allowing them to obtain the higher possible gains out of the market. This method uses an auxiliary forecasting tool, e.g. an Artificial Neural Net-work, to predict the electricity market prices, and analyses its forecasting error patterns. Through the recognition of such patterns occurrence, the method predicts the expected error for the next forecast, and uses it to adapt the actual forecast. The goal is to approximate the forecast to the real value, reducing the forecasting error.

Cost dependent strategy for electricity markets bidding based on adaptive reinforcement learning

Electricity markets are complex environments, involving a large number of different entities, playing in a dynamic scene to obtain the best advantages and profits. MASCEM is a multi-agent electricity market simulator to model market players and simulate their operation in the market. Market players are entities with specific characteristics and objectives, making their decisions and interacting with other players. MASCEM provides several dynamic strategies for agents’ behavior. This paper presents a method that aims to provide market players with strategic bidding capabilities, allowing them to obtain the higher possible gains out of the market. This method uses a reinforcement learning algorithm to learn from experience how to choose the best from a set of possible bids. These bids are defined accordingly to the cost function that each producer presents.

Strategic bidding methodology for electricity markets using adaptive learning

The very particular characteristics of electricity markets, require deep studies of the interactions between the involved players. MASCEM is a market simulator developed to allow studying electricity market negotiations. This paper presents a new proposal for the definition of MASCEM players’ strategies to negotiate in the market. The proposed methodology is implemented as a multiagent system, using reinforcement learning algorithms to provide players with the capabilities to perceive the changes in the environment, while adapting their bids formulation according to their needs, using a set of different techniques that are at their disposal. This paper also presents a methodology to define players’ models based on the historic of their past actions, interpreting how their choices are affected by past experience, and competition.

Identity – towards a conceptualization

The development of economical relations increases the interaction between organizations and stakeholders. It is no more acceptable to manage an organization under a transactional perspective where suppliers had a fundamental role. Nowadays organizations are being managed under a relational perspective where relations and relationship management in general have consequences in identity management (Hakansson e Snehota, 1989, 1995). A correct perception and management of identity is necessary to achieve distinctiveness in the competitive environment. This way, identity is influenced by relations with stakeholders in general and particularly with competitors. The ICIG concept states that identity is related with the values of the organization and it helps creating distinctiveness in the competitive environment (Van Riel, Balmer, 1997); Baker and Balmer (1997) state that identity is what the organization is; Suvatjis and de Chernatony (2005) refer that expressing identity is a dynamic process that evolves the use of a management model to face context changes; Kapferer (1991) states that brand identity is the project, the self conception of the brand. After reviewing and confronting literature under the plethora of identities’ concepts and perspectives (He, Balmer, 2007) one can’t find an integrative answer with all the elements that contribute to identity of organizations. The authors are strongly interested to contribute to the elimination of this limitation and to answer to strategic management needs. In a marketing context one can find: - the corporate identity approach that is focused in the distinctive attributes of an organization (Abratt, Balmer, Marwick e Fill, Stuart, Balmer and Gray, Alessandri, Suvatjis and de Chernatony) - the brand identity approach (related with the application of corporate identity studies to brands) - Kapferer, Semprini, Aaker, de Chernatony). Kapferer (1991), one of the most prolific authors in this field was the first author to integrate identity in a brand concept. In his view, identity is an emission concept. This idea is shared also by Aaker (1996). Yet, identity has to be managed in a competitive environment which is constantly changing. After reviewing and confronting literature, authors select concepts that are generally accepted by the investigators in order to design a model to analyze and manage identity: - corporate identity models: personality, image/reputation, culture, philosophy, mission, strategy, structure, communication - some of these concepts derive from identity models and others from identity management models; - brand identity models – Kapferer (1991, 2008) identity prism, witch is basis of literature in this field: culture, physical facet, personality, relationship (between brand and consumer), reflected consumer, consumers` self-concept. After discussion authors decide to include other concept in line with other authors` view: country of origin (Aaker, 1996). A discussion eliminates the twin concepts and the final selection is as follows: personality, image/reputation, culture (including philosophy and mission), strategy, structure, communication, culture, physical facet, relationship (between brand and consumer), reflected consumer, consumers` self-concept and according to authors` reflections “relationships” deriving from competitors` actions in competitive environment. Competitors’ actions and decisions have a stronger influence in the organizations` positioning than any other stakeholder as stated before. This is a work in progress towards a new model in identity analysis and management so an exploratory study will follow inquiring experts on identity in order to evaluate these concepts and correct the theoretical perspectives.

Utilização de metodologias multicritério de apoio à decisão como ferramenta de suporte numa empresa de serviços energéticos

Atualmente e devido às conjunturas sócio económicas que as empresas atravessam, é importante maximizar tanto os recursos materiais como humanos. Essa consciência faz com que cada vez mais as empresas tentem que os seus colaboradores possam desempenhar um papel importante no processo de decisão. Cada vez mais a diferença entre o sucesso e o fracasso depende da estratégia que cada empresa opte por envergar. Sendo assim cada atividade desempenhada por um seu colaborador deve estar alinhada com os objetivos estratégicos da empresa. O contexto em que a presente tese se insere tem por base uma pesquisa aos vários métodos multicritério existentes, de forma a que o serviço que seja adjudicado possa ser executado de forma transparente e eficiente, sem nunca descorar a sua otimização. O método de apoio à decisão escolhido foi o Analytic Hierarchy Process (AHP). A necessidade de devolver aos decisores/gestores a melhor solução resultante da aplicação de um método de apoio à decisão numa empresa de serviços energéticos foi a base para a escolha da tese. Dos resultados obtidos conclui-se que a aplicação do método AHP foi adequada, conseguindo responder a todos os objetivos inicialmente propostos. Foi também possível verificar os benefícios que advêm da sua aplicação, que por si só, ajudaram a perceber que é necessário haver uma maior entreajuda e consenso entre as decisões a tomar.

Slow down or race to halt: towards managing complexity of real-time energy management decisions

Existing work in the context of energy management for real-time systems often ignores the substantial cost of making DVFS and sleep state decisions in terms of time and energy and/or assume very simple models. Within this paper we attempt to explore the parameter space for such decisions and possible constraints faced.

Simultaneous decisions or leadership in an international competition

In this paper, we study an international market with demand uncertainty. The model has two stages. In the first stage, the home government chooses an import tariff to maximize the revenue. Then, the firms engage in a Cournot or in a Stackelberg competition. The uncertainty is resolved between the decisions made by the home government and by the firms. We compare the results obtained in the three different ways of moving on the decision make of the firms.

Adaptive learning in agents behaviour: A framework for electricity markets simulation

Electricity markets are complex environments, involving a large number of different entities, playing in a dynamic scene to obtain the best advantages and profits. MASCEM (Multi-Agent System for Competitive Electricity Markets) is a multi-agent electricity market simulator that models market players and simulates their operation in the market. Market players are entities with specific characteristics and objectives, making their decisions and interacting with other players. This paper presents a methodology to provide decision support to electricity market negotiating players. This model allows integrating different strategic approaches for electricity market negotiations, and choosing the most appropriate one at each time, for each different negotiation context. This methodology is integrated in ALBidS (Adaptive Learning strategic Bidding System) – a multiagent system that provides decision support to MASCEM's negotiating agents so that they can properly achieve their goals. ALBidS uses artificial intelligence methodologies and data analysis algorithms to provide effective adaptive learning capabilities to such negotiating entities. The main contribution is provided by a methodology that combines several distinct strategies to build actions proposals, so that the best can be chosen at each time, depending on the context and simulation circumstances. The choosing process includes reinforcement learning algorithms, a mechanism for negotiating contexts analysis, a mechanism for the management of the efficiency/effectiveness balance of the system, and a mechanism for competitor players' profiles definition.

Strategic Planning and Organizational Effectiveness in Social Service Organizations in Portugal

This study aims to understand the reality of social service organizations, the level of implementation of the strategic planning as well as the impact of its application on organizational effectiveness. At first, we will group organizations in clusters according to the level of strategic planning implementation and its degree of effectiveness. Secondly, we will analyse all the different groups. Given the growing number of social service organizations and the consequent complexity of their structures, it turns out the need for these organizations adopt formal management techniques. Strategic planning is a valuable strategic management tool and one of its main objectives is to make organizations more effective. Therefore, the research has been conducted in order to determine if strategic planning is implemented in social service organizations and which effects has its application on organizational effectiveness. The survey, applied to 220 social service organizations, allowed us to gather them into different clusters, showing that different levels of strategic planning determine distinct degrees of organizational efficiency. Finally, it should be noted that findings of this research may be essential to decision makers of these organizations, because it was shown that the adoption of strategic planning has a positive influence on organizational effectiveness of social service organizations.

Adapting Meeting Tools to Agent Decision

Electricity markets are complex environments comprising several negotiation mechanisms. MASCEM (Multi- Agent System for Competitive Electricity Markets) is a simulator developed to allow deep studies of the interactions between the players that take part in the electricity market negotiations. ALBidS (Adaptive Learning Strategic Bidding System) is a multiagent system created to provide decision support to market negotiating players. Fully integrated with MASCEM it considers several different methodologies based on very distinct approaches. The Six Thinking Hats is a powerful technique used to look at decisions from different perspectives. This paper aims to complement ALBidS strategies usage by MASCEM players, providing, through the Six Thinking Hats group decision technique, a means to combine them and take advantages from their different perspectives. The combination of the different proposals resulting from ALBidS’ strategies is performed through the application of a Genetic Algorithm, resulting in an evolutionary learning approach.

Stochastic Framework for Strategic Decision-making of Load-serving Entities for Day-ahead Market

The deregulation of electricity markets has diversified the range of financial transaction modes between independent system operator (ISO), generation companies (GENCO) and load-serving entities (LSE) as the main interacting players of a day-ahead market (DAM). LSEs sell electricity to end-users and retail customers. The LSE that owns distributed generation (DG) or energy storage units can supply part of its serving loads when the nodal price of electricity rises. This opportunity stimulates them to have storage or generation facilities at the buses with higher locational marginal prices (LMP). The short-term advantage of this model is reducing the risk of financial losses for LSEs in DAMs and its long-term benefit for the LSEs and the whole system is market power mitigation by virtually increasing the price elasticity of demand. This model also enables the LSEs to manage the financial risks with a stochastic programming framework.

Strategic Bidding for Electricity Markets Negotiation Using Support Vector Machines

Energy systems worldwide are complex and challenging environments. Multi-agent based simulation platforms are increasing at a high rate, as they show to be a good option to study many issues related to these systems, as well as the involved players at act in this domain. In this scope the authors’ research group has developed a multi-agent system: MASCEM (Multi- Agent System for Competitive Electricity Markets), which simulates the electricity markets environment. MASCEM is integrated with ALBidS (Adaptive Learning Strategic Bidding System) that works as a decision support system for market players. The ALBidS system allows MASCEM market negotiating players to take the best possible advantages from the market context. This paper presents the application of a Support Vector Machines (SVM) based approach to provide decision support to electricity market players. This strategy is tested and validated by being included in ALBidS and then compared with the application of an Artificial Neural Network, originating promising results. The proposed approach is tested and validated using real electricity markets data from MIBEL - Iberian market operator.

Automatic Electricity Markets Data Extraction for Realistic Multi-agent Simulations

Electricity markets worldwide suffered profound transformations. The privatization of previously nationally owned systems; the deregulation of privately owned systems that were regulated; and the strong interconnection of national systems, are some examples of such transformations [1, 2]. In general, competitive environments, as is the case of electricity markets, require good decision-support tools to assist players in their decisions. Relevant research is being undertaken in this field, namely concerning player modeling and simulation, strategic bidding and decision-support.

Metalearner based on Dynamic Neural Network for Strategic Bidding in electricity Markets

The restructuring of electricity markets, conducted to increase the competition in this sector, and decrease the electricity prices, brought with it an enormous increase in the complexity of the considered mechanisms. The electricity market became a complex and unpredictable environment, involving a large number of different entities, playing in a dynamic scene to obtain the best advantages and profits. Software tools became, therefore, essential to provide simulation and decision support capabilities, in order to potentiate the involved players’ actions. This paper presents the development of a metalearner, applied to the decision support of electricity markets’ negotiation entities. The proposed metalearner executes a dynamic artificial neural network to create its own output, taking advantage on several learning algorithms implemented in ALBidS, an adaptive learning system that provides decision support to electricity markets’ players. The proposed metalearner considers different weights for each strategy, depending on its individual quality of performance. The results of the proposed method are studied and analyzed in scenarios based on real electricity markets’ data, using MASCEM - a multi-agent electricity market simulator that simulates market players’ operation in the market.