Implementation and Evaluation of the PO-HEFT Problem-oriented Workflow Scheduling Algorithm for Cloud Environments Gleb Radchenko (✉) , Ivan Lyzhin, and Ekaterina Nepovinnyh Department of System Programming, South Ural State University, Chelyabinsk, Russia gleb.radchenko@susu.ru, lyzhinia@susu.ru, kwadraterry@gmail.com Abstract. Modern computational experiments imply that the resources of the cloud computing environment are often used to solve a large number of tasks, which differ only in the values of a relatively small set of simulation parameters. Such sets of tasks may occur while implementing multivariate calculations aimed at finding the simulation parameter values, which optimize certain characteristics of the computational model. Applications of this type make a large percentage of modern HPC systems load, which implies a need for methods and algorithms for efficient allocation of resources in order to optimize systems for solving such problems. The aim of this work is to implement a PO-HEFT problem-oriented scientific workflow scheduling algorithm and to compare it with other workflow scheduling algorithms. Keywords: Problem-oriented environment  Workflow  Cloud  Simulation  Scheduling algorithm  HEFT  PO-HEFT 1 Introduction The last thirty years a revolutionary turn in the fundamentals of science and engineering takes place. Computational methods have become the "third branch" of the scientific approach, along with theory and experiment. Computational methods are used in appli- cations that involve data analysis and visualization of experiments results [1]. The use of supercomputer simulation and data mining provides a qualitatively new level of re- sults in all fields of knowledge, allowing for numerical studies of physical, biological, social and others processes, providing a real alternative for expensive (or impossible) experiments [2, 3]. The typical scenario of computational experiment is a repetitive cycle consisting of: 1. transferring data to a supercomputer for analysis or simulation; 2. performing calculations; 3. storing results of calculations. Thus, a typical computational experiment scenario can be implemented by the so-called "workflows". In [4] the following workflow definition is proposed: the automation of