A novel metaheuristic optimizer：Influenza Virus Immune Algorithm (IVIA)

Abstract In this paper, a new metaheuristic optimization algorithm is proposed which is named as Influenza Virus Immune Algorithm (IVIA). The algorithm is derived by studying the process of influenza virus transmission and immunization in the population. Different infection strategies are developed by classifying the contact distance between the infected person and other individuals in the population into different situations. The process of an individual being infected is divided into three states: uninfected, infected, and immune. The immune individual will not be infected when confronted with the virus again. The population has herd immunity when the number of immune individuals in the population exceeds 60% of the total population. In order to test the optimization effect of IVIA, this paper tests IVIA with 23 sets of standard test functions and compares it with 7 optimization algorithms which were proposed in recent years,such as TFWO, GEO, PPA, RSO, GWO, PSO and WOA. The results of the tests show that IVIA converges faster with higher accuracy, optimizes the function better, and finds the minimum value of the function in fewer iterations. Then IVIA is applied to short-term power load forecasting in order to verify its practical application performance. Least Squares Support Vector Machine(LSSVM) and Long Short-Term Memory(LSTM) are used as the base prediction models respectively, and then different optimization algorithms are used to find the best initial parameters for them.The example results show that the model of IVIA-LSSVM has the smallest error evaluation index and the best overall forecasting effect among all the combined forecasting models. it can meet the accuracy requirements of load prediction results. Therefore, it is proved that IVIA has better optimization effect and it can be applied to practical engineering field.