dFDBARO: An Enhanced Metaheuristic Algorithm

Dynamic Fitness-Distance Balance-Based Artificial Rabbits Optimization Algorithm

Abstract

Artificial rabbits optimization (ARO) is a swarm intelligence-based algorithm inspired by the survival strategies of rabbits. Although ARO has a good convergence rate, it is prone to get stuck in the local optima and converge prematurely. To overcome this , the present paper redesigns the exploration operator of the ARO algorithm with the roulette fitness-distance balance (RFDB) and dynamic fitness-distance balance (dFDB) strategies. In this context, three different versions of the fitness-distance balance-based artificial rabbits optimization (FDBARO) algorithm are developed. The performance of the original ARO and FDBARO versions (FDBARO-1, FDBARO-2, and FDBARO-3) are evaluated on CEC 2017 and CEC 2020 benchmark functions. The obtained results are analyzed with the Wilcoxon and Friedman statistical tests. Statistical and convergence analysis results showed that the FDBARO-3 algorithm designed with the dFDB selection method can explore the search space more successfully compared to other algorithms. This version was named the dynamic FDBARO (dFDBARO) algorithm. Moreover, the practicability of the proposed dFDBARO is highlighted by the solution of the optimal power flow (OPF) problem formulated with renewable energy sources (RESs) and flexible alternating current transmission system (FACTS) devices considering fixed and uncertain load demands. Experimental results showed that the proposed dFDBARO is a competitive algorithm for solving global optimization and constrained OPF problems.

Highlights

• A novel metaheuristic optimization algorithm called dFDBARO is proposed.
• The efficiency and performance of dFDBARO are verified on CEC benchmark functions.
• The proposed algorithm is used to optimize the constrained OPF problem with fixed and uncertain load demands.