Rules embedded harris hawks optimizer for large-scale optimization problems

Harris Hawks Optimizer (HHO) is a recent optimizer that was successfully applied for various real-world problems. However, working under large-scale problems requires an efficient exploration/exploitation balancing scheme that helps HHO to escape from possible local optima stagnation. To achieve this objective and boost the search efficiency of HHO, this study develops embedded rules used to make adaptive switching between exploration/exploitation based on search performances. These embedded rules were formulated based on several parameters such as population status, success rate, and the number of consumed search iterations. To verify the effectiveness of these embedded rules in improving HHO performances, a total of six standard high-dimensional functions ranging from 1000-D to 10,000-D and CEC'2010 large-scale benchmark were employed in this study. In addition, the proposed Rules Embedded Harris Hawks Optimizer (REHHO) applied for one real-world high dimensional wavelength selection problem. Conducted experiments showed that these embedded rules significantly improve HHO in terms of accuracy and convergence curve. In particular, REHHO was able to achieve superior performances against HHO in all conducted benchmark problems. Besides that, results showed that faster convergence was obtained from the embedded rules. Furthermore, REHHO was able to outperform several recent and state-of-the-art optimization algorithms.