Economic load dispatch solution of large-scale power systems using an enhanced beluga whale optimizer

The aim of the optimization economic load dispatch (ELD) problem is to assign the optimal generated power of the thermal units for cost reduction with satisfying the loading of the operational constraints. The ELD is a high-dimensional and non-convex problem that became a more complex problem in the case of optimizing the output generated power of large-scale systems. In this regard, an enhanced version of the Beluga whale optimization (EBWO) is proposed to deal with the ELD of the large-scale systems. Beluga whale optimization (BWO) is an efficient new optimization technique that mimics the behavior of the Beluga whales (BWs) in preying, swimming, and whale fall. However, the BWO may suffer from stagnation in local optima and scarcity of population diversity like other metaheuristics. The proposed EBWO algorithm is presented to render the standard BWO more robust and powerful search by using two strategies including the cyclone foraging motion for boosting the exploitation phase of the optimization algorithm and the quasi-oppositional based learning (QOBL) for improving population diversity. Firstly, Simulations are carried out on seven benchmark functions to prove the validation of the proposed EBWO algorihm compared with five recent algorithms. Then, The performance of the EBWO is checked on 11-units, 40-units, and also 110-unit test systems, and the obtained results of EBWO are compared with other well-known techniques such as the classical BWO, FOX Optimization Algorithm (FOX), Skill Optimization Algorithm (SOA), and Sand Cat swarm optimization (SCSO) as well as the with existing algorithms from the literature including DE, TLBO, MPSO, NGWO, IGA, NPSO, CJAYA, SMA, PSO, PPSO, SSA, MPA, MGMPA, and HSSA. The Numerical results show that the proposed algorithm is very competitive compared with the other reported optimization algorithms in obtaining low fuel costs.