A photovoltaic (PV) plant model is presented. It is based on a detailed electrothermal description of the panels forming strings that, in turn, form the power plant. It accounts for environmental working conditions, such as temperature and wind speed, and specific plant configuration, such as plant topology and power losses due to interconnections. The input variables of the model are the ambient temperature, irradiance, and wind speed. The model derives the working temperature of the panel taking into account also the power conversion performed by the panel; the electrical operating point is determined by simulating the actions done by the maximum power point tracker that operates at plant level. This model has been tested using a large database of experimental data from industrial PV plants characterized by power levels ranging from 250 kW to 1 MW. As shown, the model is capable to predict power production when “fed” by forecast irradiance, ambient temperature, and wind speed data.

Lithium-ion (Li-Ion) batteries are rechargeable batteries which can maximize battery lifespan thanks to their chemical abilities, at the same time increasing power energy density. For these reasons, Li-Ion batteries have earned considerable popularity, and they are widely used both in mobile computing devices (e.g. smartphones and smartwatches) and automotive systems (e.g. hybrid and electric vehicles). A fundamental parameter for battery health monitoring is the State of Health (SoH), which is computed from the maximum releasable capacity, and which represents battery functionality in energy storage and delivery. Among the most used data-driven approaches are Machine Learning (ML) algorithms, such as Support Vector Machines (SVMs), Random Forest (RF) regressions, and Artificial Neural Networks (ANNs). This article presents a comparison of different ML algorithms for estimating maximum releasable capacity of Li-Ion batteries, with a special focus on the implementation of both Forward and Recurrent ANNs (FNNs and RNNs, respectively), using prognostic Li-Ion battery data sets provided by the National Aeronautics and Space Administration (NASA). After an evaluation of models performances in terms of RMSE and MAE, STM32Cube.AI tool was used to convert pre-trained ANNs to optimized ANSI C code for STM32 microcontrollers (MCUs), and to profile their complexity automatically. Finally, in order to decrease models size with minimal accuracy loss, the implemented ANNs were quantized via STM32Cube.AI, converting weights and activations from 32-bit floating-point to 8-bit integer precision. TensorFlow Lite for Microcontrollers (TFLM) was used as benchmark in the analysis and validation of both non-quantized and quantized models, and the performances obtained via STM32Cube.AI and TFLM were compared.

As new services and business models are being associated to the power distribution network, it becomes of great importance to include load uncertainty in predictive computational tools. In this paper, an efficient uncertainty-aware load flow analysis is described which relies on generalized Polynomial Chaos and Stochastic testing methods. It is described how the method can be implemented in order to account for real data-based load profiles due to two different usage models: residential loads and Electrical Vehicle charging profiles. Hence, it is shown how some relevant information affecting the quality of service can be deduced by means of non-elementary post-processing computations. The proposed technique is tested by using a benchmark scenario for typical European low voltage networks, considering the variation of both residential loads and EV charging profiles. The results are compared with the same simulation done by means of Monte Carlo methodology. The consideration done during the analysis will be useful to clarify the application of the methodology but also to understand the effect of load variations on the grid characteristic quantities.