Implementation of intelligent forecasting subsystem of real-time

Abstract

The paper describes architecture of intelligent forecasting subsystem of real-time based on multiagent temporal differences reinforcement learning, statistical module and monitoring module with milestone anytime algorithm. Analysis of anytime algorithms were made in terms of using into the forecasting subsystem type of intelligent decision support system of real-time for improving performance and reducing response and execution time. The considered tools can be used to implement the possibility of self-learning and adaptation both in the intelligent systems of real-time created on their basis, and in the actual tools for creating such systems. The work was supported by BRFFR projects 17-07-00553 a, 18-51-00007 Bel a, F16R-102.