Resource allocation and power control combined optimization method based on reinforcement learning in heterogeneous network

Abstract

The invention belongs to the technical field of wireless communication, in particular to a resource distribution and power control combined optimization method based on reinforcement learning in a heterogeneous network. The method aims at dynamic and time-varying characteristics of factors such as transmission channels and transmission power, and an optimal resource distribution, user associationand power control combined strategy is obtained by utilizing a distributed Q learning method through establishing a multi-agent enhanced learning framework in combination with the conditions of user satisfaction degree and operator benefit seeking on the basis of establishing a heterogeneous cellular network system model on the premise that the user selfishness and the operator benefit in the heterogeneous network are considered, so that the maximization of the long-term system utility of the whole network is achieved.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and in particular relates to a joint optimization method for resource allocation and power control based on reinforcement learning in a heterogeneous network. Background technique [0002] With the rapid development of wireless devices and the continuous increase of people's demand for wireless services, the cellular network is facing the huge challenge of increasing network capacity requirements. By deploying multiple femto base stations (Femto Base Station, FBS) with different transmission power and coverage in the macro base station (Macro Base Station, MBS), not only can reduce the communication load and the cost of the operator, but also can use the same wireless frequency to improve the utilization of wireless spectrum. Therefore, heterogeneous cellular networks are expected to improve the system capacity and resource utilization of next-generation cellular networks. [000...

AI Technical Summary

Problems solved by technology

Existing studies mostly consider the above optimization problem separately

At the same time, due to the non-convex and combinatorial nature of joint optimization problems, it is very difficult to obtain a globally optimal strategy

Existing literature proposes optimization methods such as game theory, linear programming, and Markov approximation, but most of these optimization methods require almost all network information, however, in general, such information is difficult to obtain

Images