In recent years, there has been a noticeable shift towards electric mobility and an increasing emphasis on integrating renewable energy sources. Consequently, batteries and their management have been prominent in this context. A vital aspect of the BMS revolves around accurately determining the battery pack’s SOC. Notably, the advent of advanced microcontrollers and the availability of extensive datasets have contributed to the growing popularity and practicality of data-driven methodologies. This study examines the developments in SOC estimation over the past half-decade, explicitly focusing on data-driven estimation techniques. It comprehensively assesses the performance of each algorithm, considering the type of battery and various operational conditions. Additionally, intricate details concerning the models’ hyperparameters, including the number of layers, type of optimiser, and neuron, are provided for thorough examination. Most of the models analysed in the paper demonstrate strong performance, with both the MAE and RMSE for the estimation of SOC hovering around 2% or even lower.

As human activities are increasingly exploiting our planet’s scarce resources, managing them has become of primary importance. Specifically, this study examines the management of photovoltaic (PV) waste that is produced when PV modules reach end-of-life (EoL). PV modules contain precious and valuable materials, as well as toxic materials that may be harmful to human health and the environment if not disposed of properly. First, this study aims to review and analyze the current literature in order to gain a deeper understanding of the recycling of PV modules, particularly c-Si modules, which represent the largest market share. In the second part, an analysis is conducted of the energy consumption of these recycling processes using a proposed model based on the full recovery end-of-life photovoltaic (FRELP) process. PV modules manufactured from raw materials and PV modules manufactured from recycled materials are also compared in this section. In addition, improvements are suggested with respect to the design of PV modules (eco-design). According to this study, c-Si PV modules can be recycled with an energy consumption as low as 130 ÷ 300 kWh/ton of treated PV waste, estimating an overall recycling yield of about 84%.

Given the strong penetration of electric vehicles (EVs) and renewable energy sources, battery demand is dramatically increasing. To satisfy this huge request for batteries, a possible solution, taking into account a circular-economy framework, is given by second-life batteries (SLBs), a new technology that exploits deteriorated batteries from the EV sector for less demanding applications, such as stationary storage. On the one hand, SLBs make it possible to use batteries to their full extent. On the other hand, specific standards for SLBs are still missing and, from an industrial point of view, there are several factors that influence whether this business would be convenient or not. This article presents a possible lifecycle for EV batteries where SLBs are considered with different business strategies, also taking into account the possible SLB applications that can be derived from the reuse of batteries before being recycled. From an economic point of view, an economic assessment is introduced, providing possible parameters that may affect the SLB business either positively or negatively.

State of Charge (SOC) estimation is vital for battery management systems (BMS), impacting battery efficiency and lifespan. Accurate SOC estimation is challenging due to battery complexity and limited data for training Machine Learning based models. Transfer learning (TL) leverages pre-trained models, reducing training time and improving generalization in SOC estimation. In this paper, 8 different transfer learning techniques are examined, which were applied in four different models (LSTM, GRU, BiLSTM, and BiGRU) for SOC estimation. These transfer learning techniques have been applied to three datasets for re-training the models and results have been compared with the same models defined by Bayesian Hyperparameter Optimization. The TL4 and TL5 techniques consistently stood out as among the most efficient in both accuracy and computational time.