The characteristic curve of Photovoltaic (PV) modules is not linear due to environmental conditions. However, there exist only one point in the nonlinear curve of the solar system where the maximum possible power can be extracted. One of the key parts in designing solar systems to increase the output power production is the improvement in Maximum power point tracking (MPPT) methods. Due to fast response and low fluctuations, the adaptive neural-fuzzy inference system (ANFIS) is one of the best methods to find the maximum power point (MPP) in solar systems among various methods. Nevertheless, in proper design of an efficient ANFIS-MPPT, accurate training data is one of the most important challenges. The irradiance and temperature are considered as input variables, while the optimal voltages are output variable optimizing using hybrid whale optimization and pattern search (HWO-PS) algorithm to be used for tuning the incremental conductance (INC). The simulations are performed using Matlab/Simulink to confirm the tracking efficiency of the suggested model. Simulations are performed in different climatic conditions to make the results reliable. The results indicate the proper performance of the proposed method in different climatic conditions with the efficiency of more than 99.3%.

由于环境条件，光伏（PV）模块的特性曲线不是线性的。但是，在太阳系的非线性曲线中只有一个点可以提取最大可能的功率。设计太阳能系统以增加输出功率产生的关键部分之一是最大功率点跟踪（MPPT）方法的改进。由于响应速度快且波动小，因此自适应神经模糊推理系统（ANFIS）是在各种方法中找到太阳能系统中最大功率点（MPP）的最佳方法之一。然而，在正确设计有效的ANFIS-MPPT时，准确的训练数据是最重要的挑战之一。辐照度和温度被视为输入变量，最佳电压是使用混合鲸鱼优化和模式搜索（HWO-PS）算法进行输出变量优化，以用于调节增量电导（INC）。使用Matlab / Simulink执行仿真以确认所建议模型的跟踪效率。模拟是在不同的气候条件下进行的，以使结果可靠。结果表明，该方法在不同气候条件下均能达到99.3％以上的效率。