This paper proposes a method (denoted by WD-ANN) that combines the Artificial Neural Networks (ANN) and the Wavelet Decomposition (WD) to generate short-term global horizontal solar radiation forecasting, which is an essential information for evaluating the electrical power generated from the conversion of solar energy into electrical energy. The WD-ANN method consists of two basic steps: firstly, it is performed the decomposition of level p of the time series of interest, generating p + 1 wavelet orthonormal components; secondly, the p + 1 wavelet orthonormal components (generated in the step 1) are inserted simultaneously into an ANN in order to generate short-term forecasting. The results showed that the proposed method (WD-ANN) improved substantially the performance over the (traditional) ANN method.

The theft of electrical energy is one of the main problems faced by electricity distribution utilities, especially in developing countries. Aware of the difficulties in combating non-technical losses (NTLs) in Brazil, the National Electric Energy Agency (ANEEL) established tolerable limits for the percentage of non-technical losses to each Brazilian distribution utility. Despite the notable progress made by ANEEL, when comparing public utility NTLs and their regulatory targets in the last decade, it was observed that the goals defined by this agency were not able to lead to a general reduction in NTLs in the country. Thus, the search for alternative methodologies to deal with the topic is necessary. A more attractive alternative to the ANEEL’s model is an efficient frontier model. This paper describes a stochastic frontier cost model for panel data whose equation is specified to provide the tolerable limits for the percentage of NTLs. The proposed model was applied to a panel of data containing annual observations, over 10 years, of 41 distribution utilities in the Brazilian electrical system.

Non-technical losses (NTLs) are one of the main problems that electricity distribution utilities face in developing regions such as Latin America, the Caribbean, sub-Saharan Africa, and South Asia. Particularly in Brazil, based on the socioeconomic and market variables concerning all the distribution utilities, the National Electric Energy Agency (ANEEL) has formulated several specifications of econometric models for panel data with random effects, all aimed at determining an index that reflects the difficulty of combating NTLs according to the intrinsic characteristics of each distribution area. Nevertheless, given the exhaustive search for combinations of explanatory variables and the complexity inherent to defining regulatory NTL targets, this process still requires the evaluation of many models through hypothesis and goodness-of-fit tests. In this regard, this article proposes an automatic model-selection technique for panel data regressions to better assist the Agency in establishing NTL regulatory targets for the distribution of utilities in this country. The proposed technique was applied to panel data containing annual observations from 62 Brazilian electricity distribution utilities from 2007 to 2017, thus generating 1,097,789 models associated with the regression types in the panel data. The main results are three selected models that showed more adherence to the actual capacity of Brazilian distribution utilities to reduce their NTLs.