Composite Differential Evolution Research Articles

Classification- and Regression-Assisted Differential Evolution for Computationally Expensive Problems

Differential Evolution (DE) has been well accepted as an effective evolutionary optimization technique. However, it usually involves a large number of fitness evaluations to obtain a satisfactory solution. This disadvantage severely restricts its application to computationally expensive problems, for which a single fitness evaluation can be highly time-consuming. In the past decade, a lot of investigations have been conducted to incorporate a surrogate model into an evolutionary algorithm (EA) to alleviate its computational burden in this scenario. However, only limited work was devoted to DE. More importantly, although various types of surrogate models, such as regression, ranking, and classification models, have been investigated separately, none of them consistently outperforms others. In this paper, we propose to construct a surrogate model by combining both regression and classification techniques. It is shown that due to the specific selection strategy of DE, a synergy can be established between these two types of models, and leads to a surrogate model that is more appropriate for DE. A novel surrogate model-assisted DE, named Classification- and Regression-Assisted DE (CRADE) is proposed on this basis. Experimental studies are carried out on a set of 16 benchmark functions, and CRADE has shown significant superiority over DE-assisted with only regression or classification models. Further comparison to three state-of-the-art DE variants, i.e., DE with global and local neighborhoods (DEGL), JADE, and composite DE (CoDE), also demonstrates the superiority of CRADE.

Optimal synthesis of linear antenna array with composite differential evolution algorithm

Linear antenna array design is one of the most important electromagnetic optimization problems of current interest. This article describes the application of a recently develop metaheuristic algorithm, known as the composite differential evolution (CoDE), to optimize a spacing between the elements of the linear element that provides a radiation pattern with minimum side lobe level and null placement in the specified direction. The CoDE has been used to solve three difficult instances of the design problem, and the optimization goal in each example is easily achieved. The experimental results of the CoDE algorithm have been shown to be better than the recently published results obtained using other state-of–the-art metaheuristics like DE, jDE, SaDE, JADE, BBO, GA, PSO and ES in a statistically meaningful way.

Comparison of computational intelligence algorithms for loadability enhancement of restructured power system with FACTS devices

This paper proposes the use of computational intelligence algorithms to determine the optimal location and control of Flexible AC Transmission System (FACTS) devices to enhance the loadability of pool and hybrid models in restructured power system. Particle Swarm Optimization (PSO), Differential Evolution (DE) and Composite Differential Evolution (CoDE) algorithms are used and their performances were compared. For this study, Thyristor Controlled Series Compensator (TCSC), Static VAR Compensator (SVC) and Thyristor Controlled Phase Shifting Transformer (TCPST) are considered. This approach uses AC load flow equations with constraints on real and reactive power generations, transmission line flow, magnitude of bus voltages and FACTS device settings. For the hybrid model, bilateral transactions are modeled using secured bilateral transaction matrix utilizing the AC distribution factor with slack bus contribution. Simulations are performed on IEEE 118 bus system. Maximum loadability, computation time and convergence characteristics are compared. The results indicate that by optimal location and control of FACTS devices, DE enhances the loadability of the pool and hybrid models with less computation time and faster convergence than PSO. Further the performance of DE is improved by using its variant, CoDE. Among the three FACTS devices, TCSC gives maximum loadability than SVC and TCPST. To conclude, for enhancing the loadability of restructured power system with FACTS devices using the computational intelligence algorithm, DE with TCSC gives maximum loadability with less computational time and faster convergence. The computational effort is further reduced by using CoDE.