Free associating wireless resource management system and method based on reinforcement learning

Abstract

This invention discloses an independent united radio resource managent system and a method based on intensified study, in which, when a re-configurable mobile terminal starts up a new session request, a radio re-configuration support function module collects the resource management information of isomeric radio access networks provided by a local resource manager, applies an intensified study mode to carry out attempted error interaction to decide if it accesses a new session immediately according to a related judgment rule and decides which network it accesses into and distributes related service bandwidth, otherwise, it refuses the session, then reports the united radio resource management deciding information to the re-configured manager.

Description

technical field [0001] The present invention relates to a wireless resource management system and method in the technical field of wireless communication, in particular to an autonomous joint wireless resource management system and method based on reinforcement learning. Background technique [0002] With the development of technology, the coexistence of multiple heterogeneous wireless access technologies will become an important feature of the future B3G wireless communication environment. Overlapping network coverage, diverse service requirements, and complementary technical features make collaboration and resource sharing among heterogeneous wireless access technologies necessary. To this end, various joint radio resource management methods have been proposed to obtain better system performance, spectrum efficiency and user experience. The emergence of end-to-end reconfiguration technology provides terminals and related network elements with the ability to dynamically se...

AI Technical Summary

Problems solved by technology

[0004] In the prior art, for the problem of joint admission control and bandwidth allocation in heterogeneous wireless networks, there are shortcomings in that the definition of fuzzy inference rules and the selection of fuzzy / defuzzification function parameters largely rely on manual control, subjectivity Large, lack of guidance and rationality demonstration of certain design principles

Although the introduction of reinforcement learning overcomes the subjectivity of function parameter selection to a certain extent, it fails to independently and dynamically adjust and control the inference rules, and the performance of the final result of the algorithm is difficult to guarantee.

If more input language variables (such as terminal moving speed, reconfiguration ability, etc.) are considered, the arrangement and combination of various fuzzy inference rules will grow geometrically. The manual definition method will face great design complexity and reduce practicability

Images