Abstract
This paper presents a context analysis methodology to improve the management of residential energy resources by making the decision making process adaptive to different contexts. A context analysis model is proposed and described, using a clustering process to group similar situations. Several clustering quality assessment indices, which support the decisions on how many clusters should be created in each run, are also considered, namely: the Calinski Harabasz, Davies Bouldin, Gap Value and Silhouette. Results show that the application of the proposed model allows to identify different contexts by finding patterns of devices' use and also to compare different optimal k criteria. The data used in this case study represents the energy consumption of a generic home during one year (2014) and features the measurements of several devices' consumption as well as of several contextual variables. The proposed method enhances the energy resource management through adaptation to different contexts. © 2017 IEEE.

Abstract
One of the most challenging tasks for energy domain stakeholders is to have a better preview of the electricity consumption. Having a more trustable expectation of electricity consumption can help minimizing the cost of electricity and also enable a better control on the electricity tariff. This paper presents a study using a Methodology to Obtain Genetic fuzzy rule-based systems Under the iterative rule Learning approach (MOGUL) methodology in order to have a better profile of the electricity consumption of the following hours. The proposed approach uses the electricity consumption of the past hours to forecast the consumption value for the following hours. Results from this study are compared to those of previous approaches, namely two fuzzy based systems: and several different approaches based on artificial neural networks. The comparison of the achieved results with those achieved by the previous approaches shows that this approach can calculate a more reliable value for the electricity consumption in the following hours, as it is able to achieve lower forecasting errors, and a less standard deviation of the forecasting error results. © 2017 IEEE.

Abstract
SEAS Shared Intelligence (SEAS SI) is a platform for algorithms sharing and execution developed under the scope of Smart Energy Aware Systems (SEAS) project to promote the intelligent management of smart grids and microgrids, by means of the shared usage of algorithms and tools, while ensuring code and intellectual protection. In this paper the platform goals and architecture are described, focusing on the recent achievement regarding the connection of distinct algorithms, which enables the execution of dynamic simulations using sequences of algorithms from distinct sources. A case study based on several SEAS SI available algorithms is presented with the objective of showing the advantages of the SEAS SI capability of supporting simulations based on sequences of algorithms. Namely, electricity market bid values are calculated by a metalearner, which is fed by market price forecasts using different methods, and by their respective forecasting errors. A case study presents some results to validate the presented work, through the simulation of the MIBEL electricity market using MASCEM (Multi-Agent Simulator of Competitive Electricity Markets). © 2017 IEEE.

Abstract
Worldwide microgrid capacity is expected to reach 7 GW and a market value of $35 billion dollars in the next few years. The decentralization of the generation dispatch role and different ownership models concerning microgrids, will contribute to increase the complexity of the future power systems. Analyzing new policies and strategies as well as evaluating those impacts is only possible with the use of sophisticated simulation tools. This paper presents a scalable computational simulation to address microgrid dispatch and the impact in the electricity market. Computational intelligence techniques are integrated to improve the effectiveness of the simulation tool. These techniques include CPLEX; differential search algorithm and quantum particle swaiin optimization. Each microgrid player is able to solve a day-ahead scheduling problem and submit bids to the electricity market agent (spot market), which calculates the market clearing price. The developed case study with a large number of players totaling about 150,000 consumers suggest the relevance of the developed computational framework.

Abstract
A key challenge in the power and energy field is the development of decision-support systems that enable studying big problems as a whole. The interoperability between systems that address specific parts of the global problem is essential. Ontologies ease the interoperability between heterogeneous systems providing semantic meaning to the information exchanged between the various parties. The use of ontologies within Smart Grids has been proposed based on the Common Information Model, which defines a common vocabulary describing the basic components used in electricity transportation and distribution. However, these ontologies are focused on utilities needs. The development of ontologies that allow the representation of diverse knowledge sources is essential, aiming at supporting the interaction between entities of different natures, facilitating the interoperability between these systems. This paper proposes a set of ontologies to enable the interoperability between different types of simulators, namely regarding electricity markets, the smart grid, and residential energy management. A case study based on real data shows the advantages of the proposed approach in enabling comprehensive power system simulation studies. © 2018 Power Systems Computation Conference.

Abstract
Power and energy systems are being subject to relevant changes, mostly due to the large increase of distributed generation. These changes include the deregulation of electricity markets, which has become a more competitive marketplace due to the increase of the number of players based on renewable energy sources. This paper proposes a new portfolio optimization model for the participation in multiple alternative/complementary market opportunities, considering the risk management. The proposed model considers electricity as the asset to be negotiated. The risk is measured using the prediction error of electricity prices. A case study based on real data from Iberian electricity market-MIBEL assesses the results of the proposed model, using a particle swarm based optimization. Results show that using the proposed portfolio optimization model, market players are able to balance their market participation strategies depending on their risk aversion and profit seeking nature. © 2018 Power Systems Computation Conference.