A 5g ultra-dense networking resource allocation method and device

Abstract

Embodiments of the present invention provide a method and device for allocating 5G ultra-dense networking resources. The method includes: according to the state of the 5G ultra-dense networking system at each moment, making a decision based on a greedy strategy, and calculating an instant reward corresponding to each state; Input the instant reward corresponding to each state into the deep neural network, and obtain approximate long-term value by fitting; compare the approximate long-term value with the actual long-term value to update the long-term value function; when the long-term value function converges, A resource allocation scheme at each moment is obtained, and resource allocation is performed according to the resource allocation scheme at each moment. A 5G ultra-dense networking resource allocation method and device provided by the embodiments of the present invention solve the stochastic optimization problem based on deep reinforcement learning, so that the allocation of resources can adapt to the randomness of user arrival and departure, and at the same time reduce the complexity of solving sex.

Description

technical field [0001] The invention relates to the technical field of 5G ultra-dense networking and reinforcement learning, and in particular, to a method and device for allocating 5G ultra-dense networking resources. Background technique [0002] With the rapid development of mobile Internet and Internet of Things technologies, the demand for mobile communication services is also growing rapidly. The communication needs of smart devices and the massive IoT environment have contributed to the densification of network infrastructure. Ultra-dense network UDN came into being and will become the key technology of 5G network. In the UDN architecture, the radius of the cells is further reduced, resulting in increased interference between cells. In addition, as the network environment changes, the performance requirements of the system may also change. Therefore, the network resource configuration should consider the interaction with the environment, and the resource management...

AI Technical Summary

Problems solved by technology

In the UDN architecture, the radius of the cells will be further reduced, resulting in increased interference between cells

In addition, as the network environment changes, the performance requirements of the system may also change

Therefore, the network resource configuration should consider the interaction with the environment, and the resource management of UDN is more difficult due to the heterogeneity of user equipment in space and time

[0003] The existing network resource allocation methods cannot well adapt to the highly dynamic nature of user arrival and departure, and the existing methods have high complexity in solving, which makes it unable to meet the application's quality of service requirements and is difficult to implement in the actual environment

Images