Modified Cuckoo Search Algorithm And Its Applications

As two research hotspots in the computer automatic control domain,the nature of control and optimization is information processing.With the continuous improvement of industrial informatization technology,the scale of information is also increased rapidly.Hence,the traditional approaches could not solve the high-dimensional information problem and obtain the appreciated results.It is further hindered in settling the actual application scenario requirements using this kind of methods.As a new swarm intelligence algorithm,the cuckoo search(CS)algorithm has certain advantages in solving optimization problems.Inspired by the behavior of "seeking nests and laying eggs," the CS is proposed by simulating the parasitic brooding behavior of cuckoos and the Levy flight mechanism.However,some shortcomings in the iterative optimization of this algorithm still exist,such as slow convergence speed and poor accuracy.Therefore,a series of research is carried out to overcome the mentioned bottlenecks of the CS from two aspects: single-objective and multi-objective combinatorial optimization problems.The core contributions of this study are summarized as follows.(1)The standard CS is easy to fall into local extremum with slow convergence speed and poor accuracy in the process of high-dimensional optimization.A modified CS by combing the HS framework(HS-CS)by utilizing the improved HS and CS advantages.The main modifications could be classified into the following four viewpoints.Firstly,by adjusting the harmony algorithm’s local search strategy,the adaptive inertia weights will be generated according to the quality of the solutions in the harmony memory and reconstruct and fine-tunes the bandwidth for optimization for improving the optimization efficiency and accuracy of HS.Secondly,Amend the global search ability of the CS algorithm by adjusting the step factor of the CS operator for expanding the search range of the solution space and improving the population density in the random generation harmony and update phases in HS.At the same time,a prediction strategy of the current search state in the late stage of the iterative search is discussed to jump out of the local extreme.When the HS-CS is inactive,the CS operator searches the suboptimal solution in the acoustic database to enhance local optimization efficiency.Finally,a dynamic adjustment variable formula is constructed to speed up the efficiency of algorithm optimization.In addition,it is proved that the algorithm is a globally convergent optimal algorithm using the relevant mathematical mechanism.Two different kinds of experiments are employed to verify the performance of the HS-CS algorithm.On the one hand,12 classical test functions are selected to optimize the solution in high-dimensional problems.The numerical analysis results show that HS-CS is significantly better than other algorithms dealing with high-dimensional function optimization problems.On the other hand,the HS-CS is also used to optimize the BP neural network for weighted fuzzy productions extraction.The simulation results show that the BP neural network optimized by HS-CS can obtain higher rule classification accuracy.(2)Aiming at the problem that multi-objective cuckoo search(MOCS)can not obtain diverse,uniform and non-dominated solutions that converge to the optimal Pareto front in the continuous multi-objective optimization problem,an improved multi-objective CS(IMOCS)proposed by investigating the balance between development and exploration to obtain more accurate solutions while solving the multi-objective problem.The main contributions of the IMOCS could be separated into two aspects.On the one hand,a dynamic adjustment is utilized to enhance the efficiency of searching non-dominated solutions in different periods utilizing the Levy flight.On the other hand,a reconstructed local dynamic search mechanism and disturbance strategy are employed to strengthen the accuracy while searching non-dominated solutions and to prevent local stagnation when solving complex problems.Two experiments are implemented from different aspects to verify the performance of the IMOCS.Firstly,seven different multi-objective problems are optimized using three typical approaches,and some statistical methods are used to analyze the experimental results.Secondly,the IMOCS is applied to the obstacle avoidance problem of multiple unmanned aerial vehicles(UAVs),for seeking a safe route through optimizing the coordinated formation control of UAVs to ensure the horizontal airspeed,yaw angle,altitude,and altitude rate are converged to the expected level within a given time.The experimental results illustrate that the IMOCS can make the multiple UAVs converge in a shorter time than other comparison algorithms.The above two experimental results indicate that the proposed IMOCS is superior to other algorithms in convergence and diversity.