Abstract
This paper describes a research where the main goal was to predict the future values of a time series of the hourly demand of Portugal global electricity consumption in the following day. In a preliminary phase several regression techniques were experimented: K Nearest Neighbors, Multiple Linear Regression, Projection Pursuit Regression, Regression Trees, Multivariate Adaptive Regression Splines and Artificial Neural Networks (ANN). Having the best results been achieved with ANN, this technique was selected as the primary tool for the load forecasting process. The prediction for holidays and days following holidays is analyzed and dealt with. Temperature significance on consumption level is also studied. Results attained support the adopted approach.

Abstract
This paper presents a new and efficient methodology for network reconfiguration with optimal power flow based on Benders Decomposition approach. The objective minimizes the power losses, balancing load among the feeders and subject to the constraints: capacity limit of the branches, minimal and maximal limits of the substation or generator, minimum deviation of the nodes voltages and radial operation of the networks. A variant of the generalized Benders decomposition algorithm is applied for solving the problem, since the formulation can be embedded under two stages. The first one is the Master problem and Is formulated as Mixed Integer non-Linear Programming. This stage determines the radial topology of the distribution network. The second stage is the Slave problem and is formulated as a non-Linear Programming problem. This stage is used to determine the feasibility of the Master problem solution by means of an Optimal Power Flow and provides information to formulate the linear Benders cuts. The model is programmed in GAMS mathematical modeling language. The effectiveness of the proposal is demonstrated through an example extracted from the specialized literature.

Abstract
In this paper a tool for the evaluation of transmission system adequacy is presented. Although similar in the basic assumptions to the classic versions of the Fuzzy Power Flow (FPF), the approach has significant differences in the formulation. First, it is symmetrical (no influence of the slack bus in the results), so all the fuzzy power injections are in the same situation. Second, by including line constraints, only feasible deterministic power flows are accepted in the fuzzy variables calculations, leading to a more correct representation of the possible impact of uncertainty. Third, recalculation of the estimated node fuzzy injections leads to a clear picture of the repressed power flows and thus of the adequacy of the grid. On the other hand, the Constrained Fuzzy Power Flow (CFPF) separates completely the analysis of the network from the generation influence and costs, which is indispensable in a unbundled organization of the power system.

Abstract
The concept of microgrid (mu grid) has been emerging as a way to integrate microgeneration (mu G) in LV networks and simultaneously improve its potential benefits. Technical requirements to connect mu grids to LV networks have been studied in order to make this concept technologically feasible and safe to operate. However, the regulatory framework for economic integration of mu G and mu grids on distribution systems, despite being crucial, is still an open issue. The main purpose of this paper is to contribute for the development of an appropriate economic regulation framework that removes the barriers to mu G and mu grid development To do so, the relevant costs and benefits resulting from the establishment of mu G and mu grid are identified and a methodology for sharing those costs and benefits among the involved economic agents is presented. The only pre-requisite of such a methodology is that a net benefit to all economic agents exists, which is the case most of the times. An illustrative example is included

Abstract
In a competitive energy market environment, the procedure for fair loss allocation constitutes a matter of considerable importance. This task is often based on rough principles, given the difficulties on the practical implementation of a fairest process. This paper proposes a methodology based on neural networks for the distribution of power distribution losses among the loads. The process is based on the knowledge of load profiles and on the usual consumption measures. Simulations ere carried out for a typical MV network, with an extensive variety of load scenarios. For each scenario, losses were calculated and distributed by the consumers. The allocation criterion is established assuming a distribution proportional to the squared power. Finally, a neural network is trained in order to obtain a fast and accurate losses allocation. Illustrative results support the feasibility of the proposed methodology.

Abstract
Most of the approaches to decision problems under uncertainty are based on decision paradigms, generally associated to an optimization process that leads to a final solution. For the Decision Maker, the basic decision is thus what paradigm to choose, the rest of the procedure being mainly technical. In this paper, a different approach is advocated for this kind of problems. The main idea is to leave prescriptive models in favor of a more flexible approach, where risk related criteria are explicitly considered, conducting to an '' equivalent '' multicriteria (deterministic) model where decision-aid procedures can be used, with a greater involvement of the Decision Maker. The paper discusses first the uncertainty model and then reviews existing paradigms for the single criterion problem under uncertainty. Proposed risk and opportunity attributes come mainly from the analysis of those methodologies and from risk perception studies reports. Some hints about multicriteria aid methods and an illustrative example complete the paper.