bonobo optimizer (BO) is a recent metaheuristic algorithm inspired by the social behavior of bonobos. BO maintains a robust search strategy based on two distinct phases that involve interesting mechanisms, such as the...
详细信息
bonobo optimizer (BO) is a recent metaheuristic algorithm inspired by the social behavior of bonobos. BO maintains a robust search strategy based on two distinct phases that involve interesting mechanisms, such as the fission-fusion method for selection and an efficient process for producing new candidate solutions. Despite its remarkable capacity, BO presents a critical flaw that corresponds to an inappropriate balance between exploration and exploitation. Under such conditions, suboptimal or even poor solutions can be obtained. This paper proposes a modified BO algorithm in which the trajectory of each search agent is modified dynamically through the adaptation of the main parameters of the algorithm. With this new mechanism, the algorithm allows for the exploration and exploitation of different regions of the solution space and determines the global optimum in a faster manner. The performance of the proposed algorithm is evaluated by considering two scenarios. One is the optimization of 23 benchmark functions and the second is the problem of power allocation in wireless networks. The results show that the proposed scheme enhances the performance of the basic BO method by increasing the robustness and providing a better solution quality.
Multilevel inverters play a crucial role in energy conversion and power electronics applications. However, the harmonics generated during the operation of such inverters can harm electrical grids and reduce system eff...
详细信息
ISBN:
(纸本)9783031628702;9783031628719
Multilevel inverters play a crucial role in energy conversion and power electronics applications. However, the harmonics generated during the operation of such inverters can harm electrical grids and reduce system efficiency. Therefore, effectively controlling and eliminating harmonics is critical to enhancing the performance of multilevel inverters. This study focuses on achieving selective harmonic elimination (SHE) in multilevel inverters using the bonobo optimization algorithm (BO). The BO algorithm draws inspiration from the social behaviors of bonobo monkeys and is an artificial intelligence algorithm. It employs evolutionary approaches to solve complex problems and offers a population-based approach to optimizing the target function. The application of the BO algorithm for seven- and eleven-level inverters is compared to the genetic algorithm (GA) and particle swarm optimization (PSO). The results demonstrate that BO provides a more effective harmonic elimination solution than GA and PSO. With this algorithm, it becomes possible to maintain harmonic levels below a specified threshold while improving the overall performance and efficiency of the inverter. In conclusion, this study successfully applies the BO algorithm for selective harmonic elimination in multilevel inverters, contributing significantly to future energy conversion and power electronics research. This approach has the potential to assist in making energy systems cleaner, more reliable, and more efficient.
Low-carbon shipping plays a pivotal role in ship operations, and this study is dedicated to optimizing economic benefits and environmental friendliness concurrently while adhering to carbon intensity indicator (CII) r...
详细信息
Low-carbon shipping plays a pivotal role in ship operations, and this study is dedicated to optimizing economic benefits and environmental friendliness concurrently while adhering to carbon intensity indicator (CII) regulation. The study proposes a comprehensive flowchart incorporating multiobjective optimization and multivariate analysis, aimed at maximizing economic benefits and minimizing fuel consumption, with the CII regulation serving as a key constraint. By leveraging the Multi-objective bonobo optimizer (MOBO), the study identifies the Pareto set to determine the final compromise solution using the multi-attribute decision-making (MADM) approach, TOPSIS, coupled with entropy weighting. The study employs four multivariate analysis (MVA) methods - self-organizing mapping (SOM), hierarchical clustering analysis (HCA), principal component analysis (PCA), and Student t-test - to gain in-depth insights into the decision variable space and corresponding performance space. The efficacy and versatility of the proposed flowchart are demonstrated through the analysis of two oil carriers, showcasing the impact of CII regulations and operational parameters on economic benefits and fuel consumption. Upgrading rank B to A will lead to a 3.50 % and 1.64 % reduction in total distance traveled at full load, while degrading to rank C will result in a 5.74 % and 6.93 % improvement in the distance for these two ships. This study underscores the ability to achieve trade-offs within the same CII rank and unveils valuable relationships between speeds, proportions, and overall performance through MVA. Ultimately, the study offers solid support for ship operations in compliance with CII regulations.
暂无评论