Heterogeneous network resource allocation method based on reinforcement learning

Abstract

The invention discloses a heterogeneous network resource allocation method based on reinforcement learning, and the method comprises the steps: firstly deploying a DNN frame at each base station, enabling the frame to be based on an ADMM algorithm, and taking channel information as the weight of a network; giving an optimal resource allocation strategy in the current state according to the data obtained by the base station, namely the current user association information and the average interference power; taking each base station as an independent main body, and the state of the base stationas a modeling environment; enabling a plurality of agent programs to observe the same heterogeneous network environment and take action, wherein the agent programs communicate with one another throughrewards of the environment; and enabling agents to adjust policies according to rewards; the resource allocation method provided by the invention is based on the deep learning network, a resource allocation scheme can be given without all CSI information, the spectral efficiency is considered at the same time, and the spectral efficiency function is set as the award of the agent, so that the spectral efficiency can be ensured while the throughput of the system is ensured.

Description

technical field [0001] The invention relates to the technical field of wireless communication, and mainly relates to a method for allocating heterogeneous network resources based on reinforcement learning. Background technique [0002] With the rapid growth of mobile devices and the emergence of the Internet of Things, next-generation wireless networks face the great challenge of coping with the proliferation of wireless applications. The most promising solution is to augment existing cellular networks with picocells and femtocells with various transmission powers and coverages. These heterogeneous networks (HetNets) can transfer user equipment (UE) from macro base stations (MBS) to pico base stations (PBS), which differ in transmission power and coverage. Furthermore, in order to achieve high spectral efficiency in heterogeneous networks, PBS can reuse MBS and share the same channel with MBS. Therefore, heterogeneous networks are considered to be a good strategy to increa...

AI Technical Summary

Problems solved by technology

However, these methods require nearly complete information, which may not often be available

Therefore, for the above methods, it is challenging to achieve an optimal solution without such complete information

Images