Because of the fluctuating demands for electricity and the growing awareness of the need to protect the environment from global warming and the depletion of nonrenewable natural resources, battery‐powered electric vehicles, or EVs, are being used in the transportation sector as an alternative to internal combustion engine vehicles. However, charging these EVs with conventional fossil fuels is neither economically sustainable nor structurally viable. Therefore, this manuscript proposes a renewable energy‐powered EV charging station featuring a combination of solar energy, standby battery systems, sophisticated control techniques such as neural network‐integrated grids, the enhanced Cuckoo Search Algorithm for Maximum Power Point Tracking, and the Proportional‐Integral‐Derivative controller. This idea beats current methods and presents a viable way to drive the EV revolution while lessening environmental effects. It maximizes energy management and guarantees a steady power supply even in erratic weather. Grid integration ensures the consistency of power supplies at charging terminals. When compared to other algorithms that have been investigated in the literature, the designed algorithm exhibits excellent performance. Grid integration, in addition to the standby battery, is essential in ensuring that the charging station has a constant power supply, even during unpredictable weather.

The output of photovoltaic (PV) systems is significantly impacted by the vagaries of ambient temperature, solar irradiance, and environmental fluctuations. To achieve the utmost attainable power from PV systems, it is desired to be efficient at the maximum power point in diverse weather climates. Maximum power point tracking (MPPT) is used to schedule a designated location from where the highest power can be harvested. In the context of solar photovoltaic systems connected with DC microgrid platforms, this study introduces a recently developed drone squadron optimization (DSO) scheme that tracks the global maximum power point under PSCS difficulties. Furthermore, an exhaustive comparative analysis has been presented among particle swarm optimization (PSO), cuckoo search algorithm (CUSA), and grey wolf optimization (GWO) under different operating environments to endorse the supremacy of the nominated technique. The suggested method performs noticeably faster than many other methods currently in use, and in addition to offering the highest power, it can also use bidirectional power flow regulation in both constant and variable air conditions. Lastly, an MPPT system interfaced with the DC microgrid based on DSO ensures a sustainable and reliable architecture to provide at load in low power generating situations.

The rising demand from consumers for sustainable energy in recent years has lowered prices and opened the door of nonconventional energy for the next decades. A storage system is necessary since these energies are intermittent and the load pattern does not match their generating trend. The need for complex transportation networks is increasing due to the rapid advancement of civilization and cultural modernity, as well as the Global warming's prevalence and certain disastrous climatic changes. Energy regulation is an inevitable duty in this scenario due to the operation of distributed alternative energy sources that are connected to the grid. Intermittent sources, daytime expenses, battery and solar panel size constraints, and battery charging and discharging rate limitations are some of the factors contributing to the challenge. This work presents improved control strategies for hybrid photo-voltaic and battery storage system under changeable atmospheric conditions in comparison to other studies documented in the literature. Here, in this article, a hybrid model that blends the Pelican Optimization Algorithm (POA) with the adaptive neuro-fuzzy inference system (ANFIS) is developed and maximum power is obtained by tracking the global maximum power point using this novel technique known as POA–ANFIS. To further validate the proposed method, it is evaluated in uniform irradiance conditions and with different partial shading scenarios. Three well-known soft computing-based maximum power point tracking (MPPT) method–flying squirrel search algorithm, marine predator algorithm, and particle swarm optimization (PSO) have taken consideration as benchmark and proposed system's efficacy is compared with these three MPPT methods. It is worthwhile to say that in all four observations proposed method's performance is superior compare to the other three MPPT-based techniques. In each of partial shading conditions, the efficiency range of proposed methods is 82.16% and 89.92%, respectively, and in temperature variation case, the efficiency is 84.67%, which is far better than other three approach, and it is almost 21.60% more efficient compare with PSO in each case. The settling time is 0.60 s in standard test circumstances, 0.81 and 0.72 s in practical site climate scenarios cases, and 0.63 s in temperature variation case which is lowest compare with other three methods. For better system energy management, this study also looks at solar models and the condition of the battery storage device. Finally, the suggested technique helps to rapidly determine the possible advantages of a battery-operated, grid-connected rooftop solar system.