Multi-objective Task Scheduling Algorithm Based on Harmony Search for Grid Microservice Optimization

In order to solve the multi-objective task scheduling optimization problem of data platform microservice combination, this paper proposes an improved harmony search algorithm MODRHS, which fuses the multi-objective optimization NSGA-II algorithm, and improve its elite selection strategy by a circular elimination method, and strengthens the uniformity of the non-dominated solutions at first layer and improves the algorithm's Pareto optimization ability. At the same time, it describes the mathematical expression of the Dockers model and service optimization goals of the data platform microservice scheduling. The improved harmony search algorithm is applied to practical problems. The performance test of MODRHS is carried out through standard test functions and real data sets. Compared with other classic multi-objective optimization algorithms, the convergence and diversity of the MODRHS algorithm have been effectively improved.