A Data Mining Framework for Electric Load Profiling

This paper consists in the characterization of medium voltage (MV) electric power consumers based on a data clustering approach. It is intended to identify typical load profiles by selecting the best partition of a power consumption database among a pool of data partitions produced by several clustering algorithms. The best partition is selected using several cluster validity indices. These methods are intended to be used in a smart grid environment to extract useful knowledge about customers’ behavior. The data-mining-based methodology presented throughout the paper consists in several steps, namely the pre-processing data phase, clustering algorithms application and the evaluation of the quality of the partitions. To validate our approach, a case study with a real database of 1.022 MV consumers was used.

Consumers Performance Evaluation of the Participation in Demand Response Programs Using Baseline Methods

Demand response has gain increasing importance in the context of competitive electricity markets environment. The use of demand resources is also advantageous in the context of smart grid operation. In addition to the need of new business models for integrating demand response, adequate methods are necessary for an accurate determination of the consumers’ performance evaluation after the participation in a demand response event. The present paper makes a comparison between some of the existing baseline methods related to the consumers’ performance evaluation, comparing the results obtained with these methods and also with a method proposed by the authors of the paper. A case study demonstrates the application of the referred methods to real consumption data belonging to a consumer connected to a distribution network.

Intelligent Micro Grid Management using a Multi-Agent approach

Recent changes in electricity markets (EMs) have been potentiating the globalization of distributed generation. With distributed generation the number of players acting in the EMs and connected to the main grid has grown, increasing the market complexity. Multi-agent simulation arises as an interesting way of analysing players’ behaviour and interactions, namely coalitions of players, as well as their effects on the market. MASCEM was developed to allow studying the market operation of several different players and MASGriP is being developed to allow the simulation of the micro and smart grid concepts in very different scenarios This paper presents a methodology based on artificial intelligence techniques (AI) for the management of a micro grid. The use of fuzzy logic is proposed for the analysis of the agent consumption elasticity, while a case based reasoning, used to predict agents’ reaction to price changes, is an interesting tool for the micro grid operator.

Decision support tool for Virtual Power Players: Hybrid Particle Swarm Optimization applied to Day-ahead Vehicle-To-Grid Scheduling

This paper presents a decision support tool methodology to help virtual power players (VPPs) in the Smart Grid (SGs) context to solve the day-ahead energy resource scheduling considering the intensive use of Distributed Generation (DG) and Vehicle-To-Grid (V2G). The main focus is the application of a new hybrid method combing a particle swarm approach and a deterministic technique based on mixedinteger linear programming (MILP) to solve the day-ahead scheduling minimizing total operation costs from the aggregator point of view. A realistic mathematical formulation, considering the electric network constraints and V2G charging and discharging efficiencies is presented. Full AC power flow calculation is included in the hybrid method to allow taking into account the network constraints. A case study with a 33-bus distribution network and 1800 V2G resources is used to illustrate the performance of the proposed method.

Multi-Agent Based Smart Grid Management and Simulation: Situation Awareness and Learning in a Test Bed with Simulated and Real Installations and Players

The rising usage of distributed energy resources has been creating several problems in power systems operation. Virtual Power Players arise as a solution for the management of such resources. Additionally, approaching the main network as a series of subsystems gives birth to the concepts of smart grid and micro grid. Simulation, particularly based on multi-agent technology is suitable to model all these new and evolving concepts. MASGriP (Multi-Agent Smart Grid simulation Platform) is a system that was developed to allow deep studies of the mentioned concepts. This paper focuses on a laboratorial test bed which represents a house managed by a MASGriP player. This player is able to control a real installation, responding to requests sent by the system operators and reacting to observed events depending on the context.

Adaptive Learning in Games: Defining Profiles of Competitor Players

Artificial Intelligence has been applied to dynamic games for many years. The ultimate goal is creating responses in virtual entities that display human-like reasoning in the definition of their behaviors. However, virtual entities that can be mistaken for real persons are yet very far from being fully achieved. This paper presents an adaptive learning based methodology for the definition of players’ profiles, with the purpose of supporting decisions of virtual entities. The proposed methodology is based on reinforcement learning algorithms, which are responsible for choosing, along the time, with the gathering of experience, the most appropriate from a set of different learning approaches. These learning approaches have very distinct natures, from mathematical to artificial intelligence and data analysis methodologies, so that the methodology is prepared for very distinct situations. This way it is equipped with a variety of tools that individually can be useful for each encountered situation. The proposed methodology is tested firstly on two simpler computer versus human player games: the rock-paper-scissors game, and a penalty-shootout simulation. Finally, the methodology is applied to the definition of action profiles of electricity market players; players that compete in a dynamic game-wise environment, in which the main goal is the achievement of the highest possible profits in the market.

Reinforcement Learning Based on the Bayesian Theorem for Electricity Markets Decision Support

This paper presents the applicability of a reinforcement learning algorithm based on the application of the Bayesian theorem of probability. The proposed reinforcement learning algorithm is an advantageous and indispensable tool for ALBidS (Adaptive Learning strategic Bidding System), a multi-agent system that has the purpose of providing decision support to electricity market negotiating players. ALBidS uses a set of different strategies for providing decision support to market players. These strategies are used accordingly to their probability of success for each different context. The approach proposed in this paper uses a Bayesian network for deciding the most probably successful action at each time, depending on past events. The performance of the proposed methodology is tested using electricity market simulations in MASCEM (Multi-Agent Simulator of Competitive Electricity Markets). MASCEM provides the means for simulating a real electricity market environment, based on real data from real electricity market operators.

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.

MASCEM Restructuring: Ontologies For Scenarios Generation in Power Systems Simulators

The electricity market restructuring, along with the increasing necessity for an adequate integration of renewable energy sources, is resulting in an rising complexity in power systems operation. Various power system simulators have been introduced in recent years with the purpose of helping operators, regulators, and involved players to understand and deal with this complex environment. This paper focuses on the development of an upper ontology which integrates the essential concepts necessary to interpret all the available information. The restructuring of MASCEM (Multi-Agent System for Competitive Electricity Markets), and this system’s integration with MASGriP (Multi-Agent Smart Grid Platform), and ALBidS (Adaptive Learning Strategic Bidding System) provide the means for the exemplification of the usefulness of this ontology. A practical example is presented, showing how common simulation scenarios for different simulators, directed to very distinct environments, can be created departing from the proposed ontology.

Smart Grid Communication Technologies in the Brazilian Electrical Sector

Intelligent electrical grids can be considered as the next generation of electrical energy transportation. The enormous potential leads to worldwide focus of research on the technology of smart grids. This paper aims to present a review of the Brazilian electricity sector in context with the integration of communication technologies for smart grids. The work gives an overview of the generation, transmission and distribution of electrical energy in the Brazil and a brief summary of the current electricity market. Smart grid technologies are introduced and the requirements for the Brazilian power system are pointed out. Various technologies for communication within an intelligent network are presented and their characteristics, advantages and disadvantages are compared to the Brazilian conditions. In addition, a summary is given of current pilot projects for Smart Grid technologies within Brazil, as well as a presentation of individual selected projects.

Load Control Timescales Simulation in a Multi-Agent Smart Grid Platform

Environmental concerns and the shortage in the fossil fuel reserves have been potentiating the growth and globalization of distributed generation. Another resource that has been increasing its importance is the demand response, which is used to change consumers’ consumption profile, helping to reduce peak demand. Aiming to support small players’ participation in demand response events, the Curtailment Service Provider emerged. This player works as an aggregator for demand response events. The control of small and medium players which act in smart grid and micro grid environments is enhanced with a multi-agent system with artificial intelligence techniques – the MASGriP (Multi-Agent Smart Grid Platform). Using strategic behaviours in each player, this system simulates the profile of real players by using software agents. This paper shows the importance of modeling these behaviours for studying this type of scenarios. A case study with three examples shows the differences between each player and the best behaviour in order to achieve the higher profit in each situation.

Analysis of Consumption Data to Detect Commercial Losses Using Performance Evaluation Methods in a Smart Grid

Electric power networks, namely distribution networks, have been suffering several changes during the last years due to changes in the power systems operation, towards the implementation of smart grids. Several approaches to the operation of the resources have been introduced, as the case of demand response, making use of the new capabilities of the smart grids. In the initial levels of the smart grids implementation reduced amounts of data are generated, namely consumption data. The methodology proposed in the present paper makes use of demand response consumers’ performance evaluation methods to determine the expected consumption for a given consumer. Then, potential commercial losses are identified using monthly historic consumption data. Real consumption data is used in the case study to demonstrate the application of the proposed method.

Estudo da exposição profissional a formaldeído em laboratórios hospitalares de anatomia patológica

RESUMO - A exposição a formaldeído é reconhecidamente um dos mais importantes factores de risco presente nos laboratórios hospitalares de anatomia patológica. Neste contexto ocupacional, o formaldeído é utilizado em solução, designada comummente por formol. Trata-se de uma solução comercial de formaldeído, normalmente diluída a 10%, sendo pouco onerosa e, por esse motivo, a eleita para os trabalhos de rotina em anatomia patológica. A solução é utilizada como fixador e conservante do material biológico, pelo que as peças anatómicas a serem processadas são previamente impregnadas. No que concerne aos efeitos para a saúde do formaldeído, os efeitos locais parecem apresentar um papel mais importante comparativamente com os efeitos sistémicos, devido à sua reactividade e rápido metabolismo nas células da pele, tracto gastrointestinal e pulmões. Da mesma forma, a localização das lesões correspondem principalmente às zonas expostas às doses mais elevadas deste agente químico, ou seja, o desenvolvimento dos efeitos tóxicos dependerá mais da intensidade da dose externa do que da duração da exposição. O efeito do formaldeído no organismo humano mais facilmente detectável é a acção irritante, transitória e reversível sobre as mucosas dos olhos e aparelho respiratório superior (naso e orofaringe), o que acontece em geral para exposições frequentes e superiores a 1 ppm. Doses elevadas são citotóxicas e podem conduzir a degenerescência e necrose das mucosas e epitélios. No que concerne aos efeitos cancerígenos, a primeira avaliação efectuada pela International Agency for Research on Cancer data de 1981, actualizada em 1982, 1987, 1995 e 2004, considerando-o como um agente cancerígeno do grupo 2A (provavelmente carcinogénico). No entanto, a mais recente avaliação, em 2006, considera o formaldeído no Grupo 1 (agente carcinogénico) com base na evidência de que a exposição a este agente é susceptível de causar cancro nasofaríngeo em humanos. Constituiu objectivo principal deste estudo caracterizar a exposição profissional a formaldeído nos laboratórios hospitalares de anatomia patológica Portugueses. Pretendeu-se, ainda, descrever os fenómenos ambientais da contaminação ambiental por formaldeído e explorar eventuais associações entre variáveis. Considerou-se uma amostra de 10 laboratórios hospitalares de anatomia patológica, avaliada a exposição dos três grupos profissionais por comparação com os dois referenciais de exposição e, ainda, conhecidos os valores de concentração máxima em 83 actividades. Foram aplicados simultaneamente dois métodos distintos de avaliação ambiental: um dos métodos (Método 1) fez uso de um equipamento de leitura directa com o princípio de medição por Photo Ionization Detection, com uma lâmpada de 11,7 eV e, simultaneamente, realizou-se o registo da actividade. Este método disponibilizou dados para o referencial de exposição da concentração máxima; o outro método (Método 2) traduziu-se na aplicação do método NIOSH 2541, implicando o uso de bombas de amostragem eléctricas de baixo caudal e posterior processamento analítico das amostras por cromatografia gasosa. Este método, por sua vez, facultou dados para o referencial de exposição da concentração média ponderada. As estratégias de medição de cada um dos métodos e a definição dos grupos de exposição existentes neste contexto ocupacional, designadamente os Técnicos de Anatomia Patológica, os Médicos Anatomo-Patologistas e os Auxiliares, foram possíveis através da informação disponibilizada pelas técnicas de observação da actividade da análise (ergonómica) do trabalho. Estudaram-se diversas variáveis independentes, nomeadamente a temperatura ambiente e a humidade relativa, a solução de formaldeído utilizada, as condições de ventilação existentes e o número médio de peças processadas por dia em cada laboratório. Para a recolha de informação sobre estas variáveis foi preenchida, durante a permanência nos laboratórios estudados, uma Grelha de Observação e Registo. Como variáveis dependentes seleccionaram-se três indicadores de contaminação ambiental, designadamente o valor médio das concentrações superiores a 0,3 ppm em cada laboratório, a Concentração Média Ponderada obtida para cada grupo de exposição e o Índice do Tempo de Regeneração de cada laboratório. Os indicadores foram calculados e definidos através dos dados obtidos pelos dois métodos de avaliação ambiental aplicados. Baseada no delineado pela Universidade de Queensland, foi ainda aplicada uma metodologia de avaliação do risco de cancro nasofaríngeo nas 83 actividades estudadas de modo a definir níveis semi-quantitativos de estimação do risco. Para o nível de Gravidade considerou-se a informação disponível em literatura científica que define eventos biológicos adversos, relacionados com o modo de acção do agente químico e os associa com concentrações ambientais de formaldeído. Para o nível da Probabilidade utilizou-se a informação disponibilizada pela análise (ergonómica) de trabalho que permitiu conhecer a frequência de realização de cada uma das actividades estudadas. A aplicação simultânea dos dois métodos de avaliação ambiental resultou na obtenção de resultados distintos, mas não contraditórios, no que concerne à avaliação da exposição profissional a formaldeído. Para as actividades estudadas (n=83) verificou-se que cerca de 93% dos valores são superiores ao valor limite de exposição definido para a concentração máxima (VLE-CM=0,3 ppm). O “exame macroscópico” foi a actividade mais estudada e onde se verificou a maior prevalência de resultados superiores ao valor limite (92,8%). O valor médio mais elevado da concentração máxima (2,04 ppm) verificou-se no grupo de exposição dos Técnicos de Anatomia Patológica. No entanto, a maior amplitude de resultados observou-se no grupo dos Médicos Anatomo-Patologistas (0,21 ppm a 5,02 ppm). No que respeita ao referencial da Concentração Média Ponderada, todos os valores obtidos nos 10 laboratórios estudados para os três grupos de exposição foram inferiores ao valor limite de exposição definido pela Occupational Safety and Health Administration (TLV-TWA=0,75 ppm). Verificou-se associação estatisticamente significativa entre o número médio de peças processadas por laboratório e dois dos três indicadores de contaminação ambiental utilizados, designadamente o valor médio das concentrações superiores a 0,3 ppm (p=0,009) e o Índice do Tempo de Regeneração (p=0,001). Relativamente à temperatura ambiente não se observou associação estatisticamente significativa com nenhum dos indicadores de contaminação ambiental utilizados. A humidade relativa apresentou uma associação estatisticamente significativa apenas com o indicador de contaminação ambiental da Concentração Média Ponderada de dois grupos de exposição, nomeadamente com os Médicos Anatomo-Patologistas (p=0,02) e os Técnicos de Anatomia Patológica (p=0,04). A aplicação da metodologia de avaliação do risco nas 83 actividades estudadas permitiu verificar que, em cerca de dois terços (35%), o risco foi classificado como (pelo menos) elevado e, ainda, constatar que 70% dos laboratórios apresentou pelo menos 1 actividade com a classificação de risco elevado. Da aplicação dos dois métodos de avaliação ambiental e das informações obtidas para os dois referenciais de exposição pode concluir-se que o referencial mais adequado é a Concentração Máxima por estar associado ao modo de actuação do agente químico. Acresce, ainda, que um método de avaliação ambiental, como o Método 1, que permite o estudo das concentrações de formaldeído e simultaneamente a realização do registo da actividade, disponibiliza informações pertinentes para a intervenção preventiva da exposição por permitir identificar as actividades com a exposição mais elevada, bem como as variáveis que a condicionam. As peças anatómicas apresentaram-se como a principal fonte de contaminação ambiental por formaldeído neste contexto ocupacional. Aspecto de particular interesse, na medida que a actividade desenvolvida neste contexto ocupacional e, em particular na sala de entradas, é centrada no processamento das peças anatómicas. Dado não se perspectivar a curto prazo a eliminação do formaldeído, devido ao grande número de actividades que envolvem ainda a utilização da sua solução comercial (formol), pode concluir-se que a exposição a este agente neste contexto ocupacional específico é preocupante, carecendo de uma intervenção rápida com o objectivo de minimizar a exposição e prevenir os potenciais efeitos para a saúde dos trabalhadores expostos. ---------------- ABSTRACT - Exposure to formaldehyde is recognized as one of the most important risk factors present in anatomy and pathology laboratories from hospital settings. In this occupational setting, formaldehyde is used in solution, typically diluted to 10%, and is an inexpensive product. Because of that, is used in routine work in anatomy and pathology laboratories. The solution is applied as a fixative and preservative of biological material. Regarding formaldehyde health effects, local effects appear to have a more important role compared with systemic effects, due to his reactivity and rapid metabolism in skin, gastrointestinal tract and lungs cells. Likewise, lesions location correspond mainly to areas exposed to higher doses and toxic effects development depend more on external dose intensity than exposure duration. Human body formaldehyde effect more easily detectable is the irritating action, transient and reversible on eyes and upper respiratory tract (nasal and throat) membranes, which happen in general for frequent exposure to concentrations higher than 1 ppm. High doses are cytotoxic and can lead to degeneration, and also to mucous membranes and epithelia necrosis. With regard to carcinogenic effects, first assessment performed by International Agency for Research on Cancer in 1981, updated in 1982, 1987, 1995 and 2004, classified formaldehyde in Group 2A (probably carcinogenic). However, most recent evaluation in 2006, classifies formaldehyde carcinogenic (Group 1), based on evidence that exposure to this agent is likely to cause nasopharyngeal cancer in humans. This study principal objective was to characterize occupational exposure to formaldehyde in anatomy and pathology hospital laboratories, as well to describe formaldehyde environmental contamination phenomena and explore possible associations between variables. It was considered a sample of 10 hospital pathology laboratories, assessed exposure of three professional groups for comparison with two exposure metrics, and also knows ceiling concentrations in 83 activities. Were applied, simultaneously, two different environmental assessment methods: one method (Method 1) using direct reading equipment that perform measure by Photo Ionization Detection, with 11,7 eV lamps and, simultaneously, make activity description and film. This method provided data for ceiling concentrations for each activity study (TLV-C). In the other applied method (Method 2), air sampling and formaldehyde analysis were performed according to NIOSH method (2541). This method provided data average exposure concentration (TLV-TWA). Measuring and sampling strategies of each methods and exposure groups definition (Technicians, Pathologists and Assistants) was possible by information provided by activities (ergonomic) analysis. Several independent variables were studied, including temperature and relative humidity, formaldehyde solution used, ventilation conditions, and also anatomic pieces mean value processed per day in each laboratory. To register information about these variables was completed an Observation and Registration Grid. Three environmental contamination indicators were selected has dependent variables namely: mean value from concentrations exceeding 0,3 ppm in each laboratory, weighted average concentration obtained for each exposure group, as well each laboratory Time Regeneration Index. These indicators were calculated and determined through data obtained by the two environmental assessment methods. Based on Queensland University proposal, was also applied a methodology for assessing nasopharyngeal cancer risk in 83 activities studied in order to obtain risk levels (semi-quantitative estimation). For Severity level was considered available information in scientific literature that defines biological adverse events related to the chemical agent action mode, and associated with environment formaldehyde concentrations. For Probability level was used information provided by (ergonomic) work analysis that helped identifies activity frequency. Environmental assessment methods provide different results, but not contradictory, regarding formaldehyde occupational exposure evaluation. In the studied activities (n=83), about 93% of the values were above exposure limit value set for ceiling concentration in Portugal (VLE-CM = 0,3 ppm). "Macroscopic exam" was the most studied activity, and obtained the higher prevalence of results superior than 0,3 ppm (92,8%). The highest ceiling concentration mean value (2,04 ppm) was obtain in Technicians exposure group, but a result wider range was observed in Pathologists group (0,21 ppm to 5,02 ppm). Concerning Method 2, results from the three exposure groups, were all lower than limit value set by Occupational Safety and Health Administration (TLV-TWA=0,75ppm). There was a statistically significant association between anatomic pieces mean value processed by each laboratory per day, and two of the three environmental contamination indicators used, namely average concentrations exceeding 0,3 ppm (p=0,009) and Time Regeneration Index (p=0,001). Temperature was not statistically associated with any environmental contamination used indicators. Relative humidity had a statistically significant association only with one environmental contamination indicator, namely weighted average concentration, particularly with Pathologists group (p=0,02) and Technicians group (p=0,04). Risk assessment performed in the 83 studied activities showed that around two thirds (35%) were classified as (at least) high, and also noted that 70% of laboratories had at least 1 activity with high risk rating. The two environmental assessment methods application, as well information obtained from two exposure metrics, allowed to conclude that most appropriate exposure metric is ceiling concentration, because is associated with formaldehyde action mode. Moreover, an environmental method, like Method 1, which allows study formaldehyde concentrations and relates them with activity, provides relevant information for preventive information, since identifies the activity with higher exposure, as well variables that promote exposure. Anatomic pieces represent formaldehyde contamination main source in this occupational setting, and this is of particular interest because all activities are focused on anatomic pieces processing. Since there is no prospect, in short term, for formaldehyde use elimination due to large number of activities that still involve solution use, it can be concluded that exposure to this agent, in this particular occupational setting, is preoccupant, requiring an rapid intervention in order to minimize exposure and prevent potential health effects in exposed workers.

Multiagent System Architecture for Short-term Operation of Integrated Microgrids

The forthcoming smart grids are comprised of integrated microgrids operating in grid-connected and isolated mode with local generation, storage and demand response (DR) programs. The proposed model is based on three successive complementary steps for power transaction in the market environment. The first step is characterized as a microgrid’s internal market; the second concerns negotiations between distinct interconnected microgrids; and finally, the third refers to the actual electricity market. The proposed approach is modeled and tested using a MAS framework directed to the study of the smart grids environment, including the simulation of electricity markets. This is achieved through the integration of the proposed approach with the MASGriP (Multi-Agent Smart Grid Platform) system.

A Communication and Resources Management Scheme to Support the Smart Grid Integration of Multiplayers Access to Resources Information

The increasing and intensive integration of distributed energy resources into distribution systems requires adequate methodologies to ensure a secure operation according to the smart grid paradigm. In this context, SCADA (Supervisory Control and Data Acquisition) systems are an essential infrastructure. This paper presents a conceptual design of a communication and resources management scheme based on an intelligent SCADA with a decentralized, flexible, and intelligent approach, adaptive to the context (context awareness). The methodology is used to support the energy resource management considering all the involved costs, power flows, and electricity prices leading to the network reconfiguration. The methodology also addresses the definition of the information access permissions of each player to each resource. The paper includes a 33-bus network used in a case study that considers an intensive use of distributed energy resources in five distinct implemented operation contexts.