Abstract
This paper proposes a case-based reasoning methodology to automatically choose the most appropriate optimization algorithms and respective parameterizations to solve the problem of optimal resource scheduling in smart energy grids. The optimal resource scheduling is, however, a heavy computation problem, which deals with a large number of variables. Moreover, depending on the time horizon of this optimization, fast response times are usually required, which makes it impossible to apply traditional exact optimization methods. For this reason, the application of metaheuristic methods is the natural solution, providing near-optimal solutions in a much faster execution time. Choosing which optimization approaches to apply in each time is the focus of this work, considering the requirements for each problem and the information of previous executions. A case-based reasoning methodology is proposed, considering previous cases of execution of different optimization approaches for different problems. A fuzzy logic approach is used to adapt the solutions considering the balance between execution time and quality of results Copyright © 2017 for this paper by its authors.

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
The electricity markets restructuring process encouraged the use of computational tools in order to allow the study of different market mechanisms and the relationships between the participating entities. Automated negotiation plays a crucial role in the decision support for energy transactions due to the constant need for players to engage in bilateral negotiations. This paper proposes a methodology to estimate bilateral contract prices, which is essential to support market players in their decisions, enabling adequate risk management of the negotiation process. The proposed approach uses an adaptation of the Q-Learning reinforcement learning algorithm to choose the best from a set of possible contract prices forecasts that are determined using several methods, such as artificial neural networks (ANN), support vector machines (SVM), among others. The learning process assesses the probability of success of each forecasting method, by comparing the expected negotiation price with the historic data contracts of competitor players. The negotiation scenario identified as the most probable scenario that the player will face during the negotiation process is the one that presents the higher expected utility value. This approach allows the supported player to be prepared for the negotiation scenario that is the most likely to represent a reliable approximation of the actual negotiation environment. © 2017 IEEE.