Dynamic artificial neural network for electricity market prices forecast

This paper presents an artificial neural network applied to the forecasting of electricity market prices, with the special feature of being dynamic. The dynamism is verified at two different levels. The first level is characterized as a re-training of the network in every iteration, so that the artificial neural network can able to consider the most recent data at all times, and constantly adapt itself to the most recent happenings. The second level considers the adaptation of the neural network’s execution time depending on the circumstances of its use. The execution time adaptation is performed through the automatic adjustment of the amount of data considered for training the network. This is an advantageous and indispensable feature for this neural network’s integration in ALBidS (Adaptive Learning strategic Bidding System), a multi-agent system that has the purpose of providing decision support to the market negotiating players of MASCEM (Multi-Agent Simulator of Competitive Electricity Markets).

A regulatory framework for short-term stochastic maintenance outage scheduling in smart grids

The current regulatory framework for maintenance outage scheduling in distribution systems needs revision to face the challenges of future smart grids. In the smart grid context, generation units and the system operator perform new roles with different objectives, and an efficient coordination between them becomes necessary. In this paper, the distribution system operator (DSO) of a microgrid receives the proposals for shortterm (ST) planned outages from the generation and transmission side, and has to decide the final outage plans, which is mandatory for the members to follow. The framework is based on a coordination procedure between the DSO and other market players. This paper undertakes the challenge of optimization problem in a smart grid where the operator faces with uncertainty. The results show the effectiveness and applicability of the proposed regulatory framework in the modified IEEE 34- bus test system.

A decision-support system based on particle swarm optimization for multiperiod hedging in electricity markets

This paper proposes a particle swarm optimization (PSO) approach to support electricity producers for multiperiod optimal contract allocation. The producer risk preference is stated by a utility function (U) expressing the tradeoff between the expectation and variance of the return. Variance estimation and expected return are based on a forecasted scenario interval determined by a price range forecasting model developed by the authors. A certain confidence level is associated to each forecasted scenario interval. The proposed model makes use of contracts with physical (spot and forward) and financial (options) settlement. PSO performance was evaluated by comparing it with a genetic algorithm-based approach. This model can be used by producers in deregulated electricity markets but can easily be adapted to load serving entities and retailers. Moreover, it can easily be adapted to the use of other type of contracts.

An integrated approach for distributed energy resource short term scheduling in smart grids considering realistic power system simulation

The large increase of distributed energy resources, including distributed generation, storage systems and demand response, especially in distribution networks, makes the management of the available resources a more complex and crucial process. With wind based generation gaining relevance, in terms of the generation mix, the fact that wind forecasting accuracy rapidly drops with the increase of the forecast anticipation time requires to undertake short-term and very short-term re-scheduling so the final implemented solution enables the lowest possible operation costs. This paper proposes a methodology for energy resource scheduling in smart grids, considering day ahead, hour ahead and five minutes ahead scheduling. The short-term scheduling, undertaken five minutes ahead, takes advantage of the high accuracy of the very-short term wind forecasting providing the user with more efficient scheduling solutions. The proposed method uses a Genetic Algorithm based approach for optimization that is able to cope with the hard execution time constraint of short-term scheduling. Realistic power system simulation, based on PSCAD , is used to validate the obtained solutions. The paper includes a case study with a 33 bus distribution network with high penetration of distributed energy resources implemented in PSCAD .

A short-term risk management tool applied to OMEL electricity market using particle swarm optimization

Short-term risk management is highly dependent on long-term contractual decisions previously established; risk aversion factor of the agent and short-term price forecast accuracy. Trying to give answers to that problem, this paper provides a different approach for short-term risk management on electricity markets. Based on long-term contractual decisions and making use of a price range forecast method developed by the authors, the short-term risk management tool presented here has as main concern to find the optimal spot market strategies that a producer should have for a specific day in function of his risk aversion factor, with the objective to maximize the profits and simultaneously to practice the hedge against price market volatility. Due to the complexity of the optimization problem, the authors make use of Particle Swarm Optimization (PSO) to find the optimal solution. Results from realistic data, namely from OMEL electricity market, are presented and discussed in detail.

Multiagent system for adaptive strategy formulation in electricity markets

Electricity markets are complex environments with very particular characteristics. MASCEM is a market simulator developed to allow deep studies of the interactions between the players that take part in the 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 multiagent based, 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.

LMP based bid formation for virtual power players operating in smart grids

Power system organization has gone through huge changes in the recent years. Significant increase in distributed generation (DG) and operation in the scope of liberalized markets are two relevant driving forces for these changes. More recently, the smart grid (SG) concept gained increased importance, and is being seen as a paradigm able to support power system requirements for the future. This paper proposes a computational architecture to support day-ahead Virtual Power Player (VPP) bid formation in the smart grid context. This architecture includes a forecasting module, a resource optimization and Locational Marginal Price (LMP) computation module, and a bid formation module. Due to the involved problems characteristics, the implementation of this architecture requires the use of Artificial Intelligence (AI) techniques. Artificial Neural Networks (ANN) are used for resource and load forecasting and Evolutionary Particle Swarm Optimization (EPSO) is used for energy resource scheduling. The paper presents a case study that considers a 33 bus distribution network that includes 67 distributed generators, 32 loads and 9 storage units.

Intelligent behavior in a Cyber-Ambient training system for control center operators

This paper deals with the application of an intelligent tutoring approach to delivery training in diagnosis procedures of a Power System. In particular, the mechanisms implemented by the training tool to support the trainees are detailed. This tool is part of an architecture conceived to integrate Power Systems tools in a Power System Control Centre, based on an Ambient Intelligent paradigm. The present work is integrated in the CITOPSY project which main goal is to achieve a better integration between operators and control room applications, considering the needs of people, customizing requirements and forecasting behaviors.

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.

ANN based day-ahead ancillary services forecast for electricity market simulation

Adequate decision support tools are required by electricity market players operating in a liberalized environment, allowing them to consider all the business opportunities and take strategic decisions. Ancillary services (AS) represent a good negotiation opportunity that must be considered by market players. Based on the ancillary services forecasting, market participants can use strategic bidding for day-ahead ancillary services markets. For this reason, ancillary services market simulation is being included in MASCEM, a multi-agent based electricity market simulator that can be used by market players to test and enhance their bidding strategies. The paper presents the methodology used to undertake ancillary services forecasting, based on an Artificial Neural Network (ANN) approach. ANNs are used to day-ahead prediction of non-spinning reserve (NS), regulation-up (RU), and regulation down (RD). Spinning reserve (SR) is mentioned as past work for comparative analysis. A case study based on California ISO (CAISO) data is included; the forecasted results are presented and compared with CAISO published forecast.

AI in power systems and energy markets

In a world increasingly conscientious about environmental effects, power and energy systems are undergoing huge transformations. Electric energy produced from power plants is transmitted and distributed to end users through a power grid. The power industry performs the engineering design, installation, operation, and maintenance tasks to provide a high-quality, secure energy supply while accounting for its systems’ abilities to withstand uncertain events, such as weather-related outages. Competitive, deregulated electricity markets and new renewable energy sources, however, have further complicated this already complex infrastructure.Sustainable development has also been a challenge for power systems. Recently, there has been a signifi cant increase in the installation of distributed generations, mainly based on renewable resources such as wind and solar. Integrating these new generation systems leads to more complexity. Indeed, the number of generation sources greatly increases as the grid embraces numerous smaller and distributed resources. In addition, the inherent uncertainties of wind and solar energy lead to technical challenges such as forecasting, scheduling, operation, control, and risk management. In this special issue introductory article, we analyze the key areas in this field that can benefi t most from AI and intelligent systems now and in the future.We also identify new opportunities for cross-fertilization between power systems and energy markets and intelligent systems researchers.

A internacionalização das empresas portuguesas da indústria do calçado e a relação com a volatilidade das vendas e resultados

Dissertação de Mestrado em Finanças Empresariais

Estratégias de oferta em leilões simétricos no âmbito dos mercados liberalizados de electricidade

Mestrado em Engenharia Electrotécnica – Sistemas Eléctricos de Energia

Avaliação preliminar do potencial eólico com recurso a um modelo de Mesoescala

Mestrado em Engenharia Química. Ramo optimização energética na indústria química.

Produção de hidrogénio através da gasificação da biomassa

A procura de uma forma limpa de combustível, aliada à crescente instabilidade de preços dos combustíveis fósseis verificada nos mercados faz com que o hidrogénio se torne num combustível a considerar devido a não resultar qualquer produto poluente da sua queima e de se poder utilizar, por exemplo, desperdícios florestais cujo valor de mercado não está inflacionado por não pertencer à cadeia alimentar humana. Este trabalho tem como objetivo simular o processo de gasificação de biomassa para produção de hidrogénio utilizando um gasificador de leito fluidizado circulante. O oxigénio e vapor de água funcionam como agentes gasificantes. Para o efeito usou-se o simulador de processos químicos ASPEN Plus. A simulação desenvolvida compreende três etapas que ocorrem no interior do gasificador: pirólise, que foi simulada por um bloco RYIELD, combustão de parte dos compostos voláteis, simulada por um bloco RSTOIC e, por fim, as reações de oxidação e gasificação do carbonizado “char”, simuladas por um bloco RPLUG. Os valores de rendimento dos compostos após a pirólise, obtidos por uma correlação proposta por Gomez-Barea, et al. (2010), foram os seguintes: 20,33% “char”, 22,59% alcatrão, 36,90% monóxido de carbono, 16,05%m/m dióxido de carbono, 3,33% metano e 0,79% hidrogénio (% em massa). Como não foi possível encontrar valores da variação da composição do gás à saída do gasificador com a variação da temperatura, para o caso de vapor de água e oxigénio, optou-se por utilizar apenas vapor na simulação de forma a comparar os seus valores com os da literatura. Às temperaturas de 700, 770 e 820ºC, para um “steam-to-biomass ratio”, (SBR) igual a 0,5, os valores da percentagem molar de monóxido de carbono foram, respetivamente, 56,60%, 55,84% e 53,85%, os valores de hidrogénio foram, respetivamente, 17,83%, 18,25% e 19,31%, os valores de dióxido de carbono foram, respetivamente, 16,40%, 16,85% e 17,93% e os valores de metano foram, respetivamente, 9,00%, 8,95% e 8,83%. Os valores da composição à saída do gasificador, à temperatura de 820ºC, para um SBR de 0,5 foram: 53,85% de monóxido de carbono, 19,31% de hidrogénio, 17,93% de dióxido de carbono e 8,83% de metano (% em moles). Para um SBR de 0,7 a composição à saída foi de 54,45% de monóxido de carbono, 19,01% de hidrogénio, 17,59% de dióxido de carbono e 8,87% de metano. Por fim, quando SBR foi igual a 1 a composição do gás à saída foi de 55,08% de monóxido de carbono, 18,69% de hidrogénio, 17,24% de dióxido de carbono e 8,90% de metano. Os valores da composição obtidos através da simulação, para uma mistura de ar e vapor de água, ER igual a 0,26 e SBR igual a 1, foram: 34,00% de monóxido de carbono, 14,65% de hidrogénio, 45,81% de dióxido de carbono e 5,41% de metano. A simulação permitiu-nos ainda dimensionar o gasificador e determinar alguns parâmetros hidrodinâmicos do gasificador, considerando que a reação “water-gas shift” era a limitante, e que se pretendia obter uma conversão de 95%. A velocidade de operação do gasificador foi de 4,7m/s e a sua altura igual a 0,73m, para um diâmetro de 0,20m.