Применение суперкомпьютерных технологий для моделирования социально-экономических систем

Abstract

To date, an extensive experience has been accumulated in investigation of problems related to quality, assessment of management systems, modeling of economic system sustainability. The performed studies have created a basis for development of a new research area - Economics of Quality. Its tools allow to use opportunities of model simulation for construction of the mathematical models adequately reflecting the role of quality in natural, technical, social regularities of functioning of the complex socio-economic systems. Extensive application and development of models, and also system modeling with use of supercomputer technologies, on our deep belief, will bring the conducted research of socio-economic systems to essentially new level. Moreover, the current scientific research makes a significant contribution to model simulation of multi-agent social systems and that is not less important, it belongs to the priority areas in development of science and technology in our country. This article is devoted to the questions of supercomputer technologies application in public sciences, first of all, - regarding technical realization of the large-scale agent-focused models (AFM). The essence of this tool is that owing to the power computer increase it has become possible to describe the behavior of many separate fragments of a difficult system, as socio-economic systems are. The article also deals with the experience of foreign scientists and practicians in launching the AFM on supercomputers, and also the example of AFM developed in CEMI RAS, stages and methods of effective calculating kernel display of multi-agent system on architecture of a modern supercomputer will be analyzed. The experiments on the basis of model simulation on forecasting the population of St. Petersburg according to three scenarios as one of the major factors influencing the development of socio-economic system and quality of life of the population are presented in the conclusion.

Рассмотрены наиболее известные примеры запусков агент-ориентированных моделей на суперкомпьютерах, приведены типы агентов. Проанализированы этапы и методы эффективного отображения счетного ядра мультиагентной системы на архитектуру современного суперкомпьютера. Представлены эксперименты на основе имитационного моделирования по трем сценариям прогнозирования численности населения региона как одного из важнейших факторов, влияющих на развитие социально-экономической системы и качество жизни населения.