Improved sine algorithm for global optimization

An improved sine cosine algorithm (abbreviated MSA) is presented to overcome the disadvantages of the sine cosine algorithm (SCA), such as its low accuracy, premature convergence, and slow local convergence. We changed the method for setting the conversion parameters of the SCA algorithm from a linear decline into a nonlinear decline in order to optimize the timing of global exploration and local exploration. In order to improve the convergence accuracy and to increase the convergence speed of the SCA, an inertia weight is introduced in the position update equation. Ten high-dimensional complex are simulated with five improved SCA algorithms, under the same particle numbers and maximum iteration times. According to our experiments, the MSA algorithm is not only much better than two of the improved SCA algorithms in optimization accuracy but also better than the other three improved SCA algorithms in terms of stability.