To combat global climate change moving towards sustainable, mobility is one of the most holistic approaches. Hence, decarbonization of the transport sector by employing electric vehicles (EVs) is currently an environmentally benign and efficient solution. The EV includes the hybrid EV (HEV), the plug-in hybrid EV (PHEV), and the battery EV (BEV). A storage system, a charging station, and power electronics are the essential components of EVs. The EV charging station is primarily powered from the grid which can be replaced by a solar photovoltaic system. Wide uptake of EVs is possible by improving the technologies, and also with support from the government. However, greenhouse gas emission (GHG) saving potential of the EV is debatable when the required power to charge the EV comes from traditional fossil fuel sources.

The durability and reliability of battery management systems in electric vehicles to forecast the state of charge (SoC) is a tedious task. As the process of battery degradation is usually non-linear, it is extremely cumbersome work to predict SoC estimation with substantially less degradation. This paper presents the SoC estimation of lithium-ion battery systems using six machine learning algorithms for electric vehicles application. The employed algorithms are artificial neural network (ANN), support vector machine (SVM), linear regression (LR), Gaussian process regression (GPR), ensemble bagging (EBa), and ensemble boosting (EBo). Error analysis of the model is carried out to optimize the battery’s performance parameter. Finally, all six algorithms are compared using performance indices. ANN and GPR are found to be the best methods based on MSE and RMSE of (0.0004, 0.00170) and (0.023, 0.04118), respectively.

Perovskite solar cells (PSC) have been identified as a game-changer in the world of photovoltaics. This is owing to their rapid development in performance efficiency, increasing from 3.5% to 25.8% in a decade. Further advantages of PSCs include low fabrication costs and high tunability compared to conventional silicon-based solar cells. This paper reviews existing literature to discuss the structural and fundamental features of PSCs that have resulted in significant performance gains. Key electronic and optical properties include high electron mobility (800 cm²/Vs), long diffusion wavelength (>1 μm), and high absorption coefficient (10⁵ cm⁻¹). Synthesis methods of PSCs are considered, with solution-based manufacturing being the most cost-effective and common industrial method. Furthermore, this review identifies the issues impeding PSCs from large-scale commercialisation and the actions needed to resolve them. The main issue is stability as PSCs are particularly vulnerable to moisture, caused by the inherently weak bonds in the perovskite structure. Scalability of manufacturing is also a big issue as the spin-coating technique used for most laboratory-scale tests is not appropriate for large-scale production. This highlights the need for a transition to manufacturing techniques that are compatible with roll-to-roll processing to achieve high throughput. Finally, this review discusses future innovations, with the development of more environmentally friendly lead-free PSCs and high-efficiency multi-junction cells. Overall, this review provides a critical evaluation of the advances, opportunities and challenges of PSCs.