Neiro-evolucionāra pieeja meta modelēšanai un krājumu kontroles sistēmu optimizēšanai

Projekta tips: Metodiskais

Galvenais izaicinājums:

Ņemot vērā steidzamo rūpniecisko vajadzību metamodelēšanas automatizācijā un nesenos neiroevolūcijas pieeju panākumus neironu arhitektūras meklēšanā un hiperparametru optimizācijā, tā mērķis ir pārbaudīt mākslīgā neironu tīkla un ģenētiskā algoritma kombinācijas iespējamību un efektivitāti krājumu kontroles sistēmu automatizētai metamodelēšanai. Izstrādātais ietvars ir balstīts uz visizcilāko modernāko praksi, un tas parāda stabilas skaitļošanas iespējas klasiskajā metamodelēšanā, kas formulēts kā regresijas problēma. Turklāt reālās situācijas izpētē tiek apspriesta iespēja izmantot piedāvāto sistēmu optimālu kontroles parametru iegūšanai.

Finansējums: VIAA stipendija doktora studijām, lēmums N.1. -50,3/3889, lēmums N.1. -50,3/2978.

DA&AI rīki:

• Mākslīgie neironu tīkli
• Neironu arhitektūras meklēšana
• Ģenētiskais algoritms

Rezultāti (publikācijas, ziņojumi, apliecinājumi utt.)

• Jackson, I. (2020) GitHub repository “metainventory” [online] Available at: https://github.com/Jackil1993/metainventory
• Jackson, I. and Tolujevs, J. (2018) The Discrete-Event Approach to Simulate Stochastic Multi-Product (Q, r) Inventory Control Systems. In: proceedings of the 28th International Conference on Information Modelling and Knowledge Bases (EJC-2018), June 4-8, 2018, Riga, Latvia. pp. 94-101 [indexed by Scopus].
• Jackson, I., Tolujevs, J. and Reggelin, T. (2018) The Combination of Discrete-Event Simulation and Genetic Algorithm for Solving the Stochastic Multi-Product Inventory Optimization Problem. Transport and Telecommunication Journal, 19(3), pp. 233-243 [indexed by Scopus, indexed by Web of Science].
• Jackson, I., Tolujevs, J., Lang, S. and Kegenbekov, Z. (2019) Metamodeling of Inventory-Control Simulations Based on a Multilayer Perceptron. Transport and Telecommunication Journal, 20(3), pp. 251-259 [indexed by Scopus, indexed by Web of Science].
• Jackson, I. and Tolujevs, J. (2018) A combination of simulation and genetic algorithm for solving a stochastic inventory optimization problem. In: proceedings of 11th International Doctoral Student Workshop on Logistics, June 19, 2018, Magdeburg, Germany, pp. 31-35.
• Jackson, I. and Tolujevs, J. (2018) Simulation-driven artificial intelligence for solving stochastic combinatorial optimization problems in production and logistics. In: proceedings of PhD seminar Sci-Bi: Digitalization in Logistics and Transport, Riga, Latvia, pp. 30-36
• Jackson, I. and Tolujevs, J. (2019) Metamodeling of Inventory-Control Systems Based on Artificial Neural Networks. In: proceedings of 12th International Doctoral Student Workshop on Logistics, June 6, 2019, Magdeburg, Germany, pp. 82-86.
• Jackson, I. (2019) Simulation-Optimization Approach to Stochastic Inventory Control with Perishability. Information Technology & Management Science, 22, pp. 9-14.
• Jackson, I. (2019) Combining Simulation with Genetic Algorithm for Solving Stochastic Multi-Product Inventory Optimization Problem. The Journal of Economic Research & Business Administration, 130(4), pp. 96-102.
• Jackson, I. (2019) Neuroevolutionary Approach to Metamodeling of Production-Inventory Systems with Lost-Sales and Markovian Demand. In: proceedings of International Conference on Reliability and Statistics in Transportation and Communication. Springer, Cham, pp. 90-99 [indexed by Scopus].
• Jackson, I., Tolujevs, J. and Kegenbekov, Z. (2020) Review of Inventory Control Models: A Classification Based on Methods of Obtaining Optimal Control Parameters. Transport and Telecommunication Journal, 21(3), pp. 191-202 [Scopus, Web of Science].