Authors:
Mikhail Melnik
1
;
Denis Nasonov
1
and
Alexey Liniov
2
Affiliations:
1
ITMO University, Saint-Petersburg and Russian Federation
;
2
Lobachevsky State University of Nizhni Novgorod, Nizhny Novgorod and Russia
Keyword(s):
Parallel Computation, Co-design, Scheduling, Supercomputer, Multi-agent Model.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Computational Intelligence
;
Evolutionary Computing
;
Genetic Algorithms
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Soft Computing
Abstract:
In the modern world, with the growth of the volume of processed data arrays, the logic of solving problems also becomes more complex. This leads more and more often to the need to use high-performance computational clusters, such as supercomputers. Created multi-agent simulation applications require not only significant resources but often perform time-consuming complex scenarios, which significantly affects the efficiency of the executed process. However, there are various mechanisms for optimizing application execution for different needs. Unfortunately, the specificity of multi-agent simulation does not allow the use of traditional and modern algorithms due to the iteratively variable workload and limitations of a system software installed on the supercomputers. In this paper, we propose a four-level scheme for organizing the symbiotic execution (co-design) of multi-agent applications on supercomputers, as well as an effective two-level algorithm for optimizing the flow of the exe
cution of an urban mobility simulation application. The algorithm is based on evolutionary approach and machine learning techniques.
(More)