This manuscript proposes the optimal power quality reinforcement in grid‐connected hybrid renewable energy sources like solar photovoltaic, wind turbine, battery storage using an intelligent approach. The proposed hybrid approach is the consolidation of Egyptian vulture optimization algorithm (EVOA) and random forest algorithm (RFA); hence, it is known as EVORFA technique. The major objective of this research is voltage stabilizing, power loss reduction, extenuating harmonic distortion. EVOA is mainly used to the offline way to differentiate the perfect combination and forms the dataset of proportional integral gain parameters; load current, DC‐link voltage, and voltage sources are based on reduced error objective function. In EVOA, multiple parameters are considered that is identified to the power quality (PQ) issues. The RFA predicts most optimal control signal with minimum error based on the accomplished dataset. The proposed EVORFA approach is executed in MATLAB/Simulink work site. The EVORFA approach performance is carried out in two modes, that is, simultaneous PQ reinforcement and RES power injection P_RES > 0 and PQ reinforcement (P_RES = 0). By then the experimental results are compared to the existing methods like gravitational search algorithm (GSA) and RFA.

中文翻译：

---

并网HRES系统中用于优化电能质量的智能技术：EVORFA技术

该手稿提出了使用智能方法在并网混合可再生能源（例如太阳能光伏，风力涡轮机，电池存储）中优化电能质量的建议。提出的混合方法是合并埃及秃optimization优化算法（EVOA）和随机森林算法（RFA）；因此，它被称为EVORFA技术。这项研究的主要目的是稳定电压，降低功率损耗，减轻谐波失真。EVOA主要用于离线方式来区分完美组合，并形成比例积分增益参数的数据集；负载电流，直流母线电压和电压源均基于降低的误差目标函数。在EVOA中，考虑了针对电能质量（PQ）问题确定的多个参数。RFA根据已完成的数据集预测具有最小误差的最佳控制信号。提出的EVORFA方法在MATLAB / Simulink工作站点中执行。EVORFA进近性能以两种模式执行，即同时进行PQ增强和RES功率注入P _RES  > 0和PQ增强（P _RES = 0）。届时，将实验结果与重力搜索算法（GSA）和RFA等现有方法进行比较。