Adaptive optimal control method and adaptive optimal control system

Abstract

The invention discloses an adaptive optimal control method and an adaptive optimal control system. The method can comprise the following steps: determining an uplink iterative performance index function by using a neural network; secondly, judging whether the uplink iterative performance index function is converged or not, and determining an uplink optimal performance index function according to a convergence result; thirdly, determining a downlink iterative optimal performance index function by using the neural network; fourthly, judging whether the downlink iterative optimal performance index function is converged or not, and determining a downlink optimal performance index function according to a convergence result; fifthly, judging whether the uplink optimal performance index function is equal to the downlink optimal performance index function or not; lastly, determining that the control system reaches an optimal state under the condition that the uplink optimal performance index function is equal to the downlink optimal performance index function. In the embodiment of the invention, the presence of a saddle point is judged according to whether an uplink function is equal to a downlink function, so that the technical problem in control of system stability is solved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of intelligent control, and in particular to an adaptive optimal control method and an adaptive optimal control system. Background technique [0002] Zero-sum game (zero-sum game), as opposed to non-zero-sum game, is a concept of game theory and belongs to non-cooperative game. It refers to the parties participating in the game. Under strict competition, the gain of one party must mean the loss of the other party. The sum of the gains and losses of all parties in the game is always "zero", and there is no possibility of cooperation between the two parties. It can also be said: One's own happiness is based on the pain of others, and the two are exactly equal in size, so both parties try their best to realize "benefiting others at the expense of others". The result of a zero-sum game is that one party eats the other, and what one party gains is exactly what the other party loses, and...

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the embodiments of the present invention is to provide an adaptive optimal control method, which at least partly solves the technical problem of how to stabilize the control system

Images