Foresight of Volga Federal District Innovation System Development using a Multi-Objective Genetic Algorithm

The application of simulation modeling in public administration is under study at the level of interregional interaction in specific federal districts. The main indicator for development success of a particular federal district is the natural growth of its population. For this purpose, a model of foresight of federal district innovation system development based on the use of a multi-objective genetic algorithm was proposed. Stages of this foresight included preparation of statistical data for clusters, obtaining predictive functions for clusters and Pareto frontiers of predictive functions, and planning synergy effects of clusters of regions and the entire federal district. In this case, to increase the synergy effect of a federal district, investment resources and research and development (R&D) costs were planted to be redirected to those regions where economic and financial resources are insufficient. This will eventually increase the average per capita income of the population in the regions of the federal district, which will lead to population growth in these regions. If R&D costs are redistributed, there are also information and logistics interactions that confirm the practical effectiveness of the open innovation model within the federal district. For the Volga Federal District, this foresight resulted in its total positive reserve for R&D in the amount of 8,412 million rubles. It should be forwarded to the Samara Region. Then, the synergy effect of the whole Volga Federal District will be equal to 429,344 million rubles.

Foresight; Intercluster interaction; Multi-objective genetic algorithm; Simulation modeling

Currently, fundamental research on strategic development issues is increasingly moving into the subject area of regional economics (Rodionov and Velichenkova, 2020; Rytova and Gutman, 2020). At the present time, one of the most important approaches includes the introduction of technologies for simulation modeling in business processes based on the handling of bulk data (Big Data) and its application to the analysis of regional cluster data (Kudryavtseva et al., 2020b). The creation and promotion of clusters in the Russian Federation is one of the main aims of the Russian government and is supported by two governmental programs: the program of the Ministry of Economic Development of the Russian Federation "Pilot innovative territorial clusters" and The Program of the Ministry of Industry and Trade of the Russian Federation “Industrial clusters". Since the debate on the measurement of cluster performance is ongoing in the EU (Ketels and Protsiv, 2020), USA (Delgado et al., 2016), Russia (Stepanova, 2019), and other countries, it is essential to provide adequate approaches and tools for analysis of regional cluster development (Kudryavtseva et al., 2020a). One of the possible solutions to this problem could be the application of Genetic algorithms (Snytyuk and Suprun, 2017).

Genetic algorithm (GA) is an evolutionary search method used to solve optimization problems using mechanisms similar to biological evolution (Holland, 1992; Chen et al., 2011). The genetic algorithm itself consists of several steps: (1) preparatory step – formation of an initial population; (2) selection; (3) cross breeding; (4) mutation; and (5) solution evaluation and algorithm stopping (Morov, 2012). An important concept in GA is the fitness function, otherwise known as the evaluation function. It represents a measure of fitness for a certain individual in the population. In optimization problems, the fitness function is usually maximized and called an objective function (Rutkowska et al., 1999). Tate and Smith (1995) developed a standard GA. In this, they implemented mutation and cross breeding independently of each other, unlike most GA implementations, where mutation is used as an auxiliary procedure for individuals in the population. The algorithm used a chromosome mutation with a paired exchange (Kravets and Safronova, 2013). Many other modifications were developed for the GA, for example, greedy GA (Ahuja et al., 1995) and self-adapting algorithms with the application of heterogeneous mutations (Michalewicz, 1996), among others. Evolutionary algorithms are relatively new but are very powerful methods used to find solutions to many real search and optimization problems. Many of these problems have multiple objectives, resulting in the need for a set of optimal solutions, known as effective solutions (Nasruddin et al., 2018). The use of evolutionary algorithms is a highly effective way to find many effective solutions in a single simulation run (Kalyanmoy, 2001).

This paper suggests the application of simulation modeling at the level of interregional interaction in the Volga Federal District of Russian Federation using GA. 

This paper presented novel approach to the assessment of regional cluster performance using genetic algorithms. From the theoretical point of view, we presented stages of foresight, including preparation of statistical data for clusters, obtaining predictive functions for clusters and Pareto frontiers of predictive functions, and planning of synergy effects of clusters of regions and the entire federal district. From a practical point of view, this study resulted in the estimation of the reserve for R&D for the Volga Federal District based on the data of 25 clusters from 2009–2018. As a result of foresight, we estimated a total positive reserve for R&D in the amount of 8,412 million rubles, which should be forwarded to the Samara Region. Then, the synergy effect of the entire VFD would be equal to 429,344 million rubles.

    This paper has been accomplished within the framework of the basic part of the state task of the Ministry of Education and Science of the Russian Federation, project 0729-2020-0056 “Modern methods and models of diagnostics, monitoring, prevention and overcoming of crisis phenomena in the economy under conditions of digitalization as a way to ensure economic security of the Russian Federation”.  

 Ahuja, R.K., Orlin, J.B., Tivari, A., 1995. A Greedy Genetic Algorithm for the Quadratic Assignment Problem. Working Paper Sloan School of Management, Volume 2, pp. 13–17

Chen, Y., Feng, C., Wang, Y., Wu, H., 2011. Using BIM Model and Genetic Algorithms to Optimize the Crew Assignment for Construction Project Planning. International Journal of Technology, Volume 2(3), pp. 179–187

Delgado, M., Porter, M.E., Stern, S., 2014. Clusters, Convergence, and Economic Performance. Research Policy, Volume 43(10), pp. 1785–1799

Delgado, M., Porter, M.E., Stern, S., 2016. Defining Clusters of Related Industries. Journal of Economic Geography, Volume 16(1), pp. 1–38

Holland, J.H., 1992. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence. Cambridge: The MIT Press

Kalyanmoy, D., 2001. Multiobjective Optimization using Evolutionary Algorithms. New York: John Wiley & Sons, Inc

Ketels, C., Protsiv, S., 2020. Cluster Presence and Economic Performance: A New Look Based on European Data. Regional Studies, 10 Aug 2020, pp. 1–13

Kravets, O.Y., Safronova, A.P., 2013. Overview of Structural Synthesis Methods to Solve Quadratic Assignment Problems. Modern Science: Current Problems of Theory and Practice: Scientific and Practical Journal: Series Natural and Economic Sciences, Volume 9(10), pp. 66–72

Kudryavtseva, T., Kulagina, N., Lysenko, A., Berawi, M.A., Skhvediani, A., 2020a. Developing Methods to Assess and Monitor Cluster Structures: The Case of Digital Clusters. International Journal of Technology, Volume 11(4), pp. 667–676

Kudryavtseva, T., Skhvediani, A., Berawi, M.A., 2020b. Modeling Cluster Development using Programming Methods: Case of Russian Arctic Regions. Entrepreneurship and Sustainability Issues, Volume 8(1), pp. 150–176

Martin, B.R., 1983. Project Foresight, a Proposal Submitted to the Cabinet Office. Brighton, UK: SPRU, University of Sussex

Martin, B.R., 1989. Research Foresight: Priority-setting in Science. London and New York: Pinter Publishers

Martin, B.R., 2010. The Origins of the Concept of ‘Foresight’ in Science and Technology: An Insider’s Perspective. Technological Forecasting and Social Change, Volume 77(9), pp. 1438–1447

Michalewicz, Z., 1996. Genetic Algorithms + Data Structures = Evolution Programs. New York: Springer-Verlag

Morov, V.A., 2012. Application of the Genetic Algorithm to Optimization Problems. Implementation of the Genetic Algorithm for the Traveling Salesman Problem. Journal of the Amur State University: Series Natural and Economic Sciences, Volume 57, pp. 18–22

Nasruddin, Nasution, S., Aisyah, N., Surachman, A., Wibowo, A.S., 2018. Exergy Analysis and Exergoeconomic Optimization of a Binary Cycle System using a Multi Objective Genetic Algorithm. International Journal of Technology, Volume 9(2), pp. 275–286

Rodionov, D., Velichenkova, D., 2020. Relation between Russian Universities and Regional Innovation Development. Journal of Open Innovation: Technology, Market, and Complexity, Volume 6(4), pp. 118–144

Rutkowska, D., Pilinski, M., Rutkowski, L., 1999. Sieci Neuronowe, Algorytmy Genetyczne i Systemy Rozmyte. Warszawa, Lodz: Wydawnictwo Naukowe PWN

Rytova, E., Gutman, S., 2020. Assessment of Regional Development Strategy in the Context of Economy Digitization on the Basis of Fuzzy Set Method. IOP Conference Series: Materials Science and Engineering, Volume 497(1), pp. 12–60

Skhvediani, A., Kudryavtseva, T., Rodionov, D. 2020. Regional Industrial Specialization: Case of Russian Electrical Equipment, Electronic and Optical Equipment Industry. In: Rodionov D., Kudryavtseva T., Berawi M.A., Skhvediani A. (eds) Innovations in Digital Economy. SPBPU IDE 2019. Communications in Computer and Information Science, Volume 1273. Springer, Cham, pp. 125–139

Snytyuk, V.Y., Suprun, O.O., 2017. Evolutionary Clustering as Technique of Economics Problems Solving. Electronics and Control Systems, Volume 4(54), pp. 95–101

Stepanova, E.V., 2019. Evaluation of Innovation Potential in Russian Clusters. IOP Conference Series: Earth and Environmental Science, Volume 315(2), pp. 22–91

Tate, D.M., Smith A.E., 1995. A Genetic Approach to the Quadratic Assignment Problem. Computers & Operations Research, Volume 22(1), pp. 73–83

Tukkel, I.L., Golubev, S.A., Surina, A.V., Tsvetkova, N.A., 2013. Methods and Tools of Innovative Development of Industrial Enterprises.  St.-Petersburg: BHV-Petersburg

Yashin, S.N., Trifonov, Yu.V., Koshelev, E.V., 2017. Methods of Foresight of the Cluster using the Arbitrage Technology. Innovations, Volume 11, pp. 42–53

Yashin, S.N., Koshelev, E.V., Kostrigin, R.V., 2019. Compilation of Linear Functional of the Value of the Innovation and Industrial Cluster for the Region. Management of Economic Systems: Scientific Electronic Journal, Volume 130(12), pp. 1–19