S2NA-GEO method-based charging strategy of electric vehicles to mitigate the volatility of renewable energy sources

In this manuscript, an efficient hybrid strategy is proposed to mitigate the negative impact of RES output fluctuations and smart charging method of electric vehicles (EVs). The proposed hybrid system is the joint implementation of Spike Neural Network Learning Algorithm (S2NA) algorithm and Golden Eagle Optimizer (GEO) algorithm; hence, it is known as S2NA-GEO strategy. An innovative uncertainty mode of renewable energy sources (RESs) based upon S2NA-GEO strategy is proposed, which can avert the difficult parameter collection and formula derivation. Price-based mode is accepted as EVs are considered responsive loads, which also take into account the spatial-temporal uncertainty of electric vehicles. Here, two fluctuation indexes are determined as quantitative evaluation of the volatility of RESs, then the charging cost is adopted as a guideline for the satisfaction of electric vehicle charging. The main purpose of the proposed system is diminishing the real and reactive power loss through the optimal allocation of the EVs as parking spot and minimizes the cost. In this article, the sensitivity of the voltage is conducted via four sensitivity indexes computation for regulating the candidate sites for charging and discharging. The charging infrastructure integrates the entire equipment and programming for the exchange of energy as electrical grid to the vehicle for this purpose; the sensitivity analysis is carried out assessing the inverse Jacobian matrix as power flow studies. To optimally decide the parking lot size, the biogeography-based optimization (BBO) system is assumed. The optimal size parking lot is estimated via the proposed WFS-CGO technique. The proposed method is activated in MATLAB/Simulink site, and the performance is compared with existing methods.