The forecasting of solar irradiance in photovoltaic power generation is an important tool for the integration of intermittent renewable energy sources (RES) in electrical utility grids. This study evaluates two machine learning (ML) algorithms for intraday solar irradiance forecasting: multigene genetic programming (MGGP) and the multilayer perceptron (MLP) artificial neural network (ANN). MGGP is an evolutionary algorithm white-box method and is a novel approach in the field. Persistence, MGGP and MLP were compared to forecast irradiance at six locations, within horizons from 15 to 120 min, in order to compare these methods based on a wide range of reliable results. The assessment of exogenous inputs indicates that the use of additional weather variables improves irradiance forecastability, resulting in improvements of 5.68% for mean absolute error (MAE) and 3.41% for root mean square error (RMSE). It was also verified that iterative predictions improve MGGP accuracy. The obtained results show that location, forecast horizon and error metric definition affect model accuracy dominance. Both Haurwitz and Ineichen clear sky models have been implemented, and the results denoted a low influence of these models in the prediction accuracy of multivariate ML forecasting. In a broad perspective, MGGP presented more accurate and robust results in single prediction cases, providing faster solutions, while ANN presented more accurate results for ensemble forecasting, although it presented higher complexity and requires additional computational effort.

This paper is focused on the on-load back-electromotive force (EMF) assessment in a permanent magnet synchronous machine (PMSM) using Maxwell stress tensor along with the frozen permeability method (FPM). Although the back EMF is only measured at open-circuit condition, it is known that the on-load back EMF is heavily affected by electric loading and magnetic saturation. Since the main torque component of the PMSM is the mutual torque and it is based on the interaction between the back EMF and stator current, any distortion in the on-load back EMF will affect the electromagnetic torque and increase the torque ripple. A misleading on-load back-EMF waveform with some spikes around the commutation points is found if the on-load back EMF is assessed by means of differentiating the on-load PM flux linkage. This way, this paper proposes a new numerical method to assess the on-load back EMF in order to avoid all the shortcomings of the existing method. First of all, a quick review on the results achieved by other researchers is shown. Next, a review on the FPM is done in order to clarify the points where this method will be changed to overcome the drawbacks highlighted previously. Furthermore, a new method is introduced and explained in small details. Finally, the results for different rotor configurations and different electrical loads are presented in order to validate the proposed method's accuracy against experiments and other numerical techniques.

The purpose of this paper is to present an innovative methodology for 3-D soil stratification based on geoelectrical prospection. This methodology is useful in optimal substation grounding system designs by providing an accurate 3-D soil resistivity model. In the present methodology, the area being studied is subdivided into squared subareas and a recently developed geoelectrical prospection method based on the Wenner's method and on a genetic algorithm is applied to each subarea's edge. For each subarea, the soil stratification result consists of the number of layers and of its electrical resistivities and thicknesses. A global 3-D soil stratification solution is then obtained from these data. Results obtained with this new method are presented and discussed.

Having the property to modify only the geometry of a polygonal structure, preserving its physical magnitudes, the Conformal Mapping is an exceptional tool to solve electromagnetism problems with known boundary conditions. This work aims to introduce a new developed mathematical operator, based on polynomial extrapolation. This operator has the capacity to accelerate an optimization method applied in conformal mappings, to determinate the equipotential lines, the field lines, the capacitance, and the permeance of some polygonal geometry electrical devices with an inner dielectric of permittivity ε. The results obtained in this work are compared with other simulations performed by the software of finite elements method, Flux 2D.

Renewable energy sources (RES) like solar and wind, naturally present high daily and seasonal variability of power generation. This paper presents a real case study of solar photovoltaic (PV) power forecasting of a building-integrated PV plant as a tool for power systems operation. A new methodology composed of data processing strategy, Artificial Neural Networks (ANN) modelling, and error metrics definitions are proposed and validated for the intra-day PV power forecasting. Data were modelled in time steps of 15-minute averages and the forecasts obtained from 15 minutes to 120 minutes ahead. A persistence model is developed for the building-integrated PV systems (BIPVS) case. The forecast skills achieved range from 9.79% to 23.75%, which measures the ANN improvement in relation to the proposed benchmark persistence model.