Firefly Optimization Based On Rough Data Reasoning Theory Algorithms And Applications Research

In order to improve the solving ability of firefly algorithm(FA)and its efficiency in related applications,this paper optimizes the traditional firefly algorithm around the research of rough data reasoning theory,and applies the firefly algorithm combined with rough reasoning theory to the economic dispatching of power system.This paper provides a feasible solution to power system problems involving valve point effect,network loss,climbing constraint and dynamic dispatching.The main work of this paper is as follows:(1)The basic theories involved in this paper are analyzed in detail,the related concepts such as rough sets and inference spaces in the rough data inference theory are described in detail,the inference process of the rough data inference theory is discussed,and the equivalence relation inference and inference are extracted.The two reasoning theories of correlation reasoning provide a strong theoretical basis for the subsequent algorithm optimization;the principle and iterative mechanism of the basic firefly algorithm are elaborated,and the parameters are optimized and adjusted,which speeds up the convergence speed of the algorithm and facilitates the follow-up.Finally,a complete study and analysis of the power system dispatch model and dynamic dispatch model considering the valve point effect are carried out.(2)By analyzing the inherent disadvantages and shortcomings of the FA algorithm,an optimization algorithm is proposed based on the theory of rough reasoning — the Firefly Algorithm(CRFA)based on chaotic optimization and rough reasoning.First,the initialization method of chaotic optimization is added to the algorithm,in order to improve the population diversity of the initialized population and improve the stability of the algorithm;and the chaotic optimization is used to make the population approximately uniformly distributed within the solution range,which provides a good reason for using rough data.Secondly,the iterative process of the algorithm is optimized through the rough data reasoning theory,and the accuracy of the algorithm is improved.Finally,the optimization algorithm is analyzed by several groups of experiments to test the performance of the algorithm.The improved algorithm is applied to the power system scheduling considering the valve point effect,and the advantages and disadvantages of the algorithm are verified through simulation experiments compared with other algorithms.(3)According to the rough reasoning theory and the shortcomings of the optimization algorithm proposed above,the algorithm is further improved.In order to better combine the algorithm with practical applications,improve the accuracy of the algorithm and ensure the convergence speed of the algorithm,a multi-strategy firefly algorithm(MSRFA)based on rough reasoning theory is proposed.The algorithm mainly proposes three different strategies to optimize the algorithm:(a)Combining the selection mechanism in the greedy algorithm,the attractiveness selection strategy is proposed;(b)The approximate relational reasoning strategy optimizes the iterative process of the algorithm;(c)Equivalence relation reasoning strategy to improve the escape ability of the algorithm when it falls into a local optimum.The improved algorithm is tested using the CEC2013 standard test set,and the test results are analyzed.The optimization algorithm is applied to the dynamic dispatching model of the power system,and simulation experiments are carried out.The example analysis shows that this method has obvious advantages in solution accuracy and algorithm convergence speed compared with other methods.