Multi-base-station cooperative wireless network resource allocation method based on spatial-temporal feature extraction reinforcement learning

Abstract

The invention discloses a multi-base-station cooperative wireless network resource allocation method based on spatial-temporal feature extraction reinforcement learning, which comprises the following steps of: extracting position information and spatial features of each 5G base station through a graph attention mechanism, learning behavior habits of network users by using a long-short-term memory mechanism, extracting time features, and analyzing the fluctuation condition of each slice data packet in time and space.Compared with a resource allocation policy based on an optimization algorithm and a genetic algorithm and a resource allocation policy based on traditional reinforcement learning, the method has the advantages that higher system return, namely higher spectrum efficiency and better user experience, can be obtained, and meanwhile, the method can adapt to a dynamically changing environment, and is more flexible and robust.

Description

technical field [0001] The present invention relates to the technical field of wireless communication, in particular to a multi-base station collaborative wireless network resource allocation method based on spatio-temporal feature extraction reinforcement learning. Background technique [0002] At present, 5G network has become an indispensable key link in the development of digital society. Compared with 4G network, the massive services it provides can meet our wider needs, and most of them cannot be realized by 4G. [0003] The ITU defines three main application scenarios for 5G: enhanced mobile broadband (eMBB), massive machine-type communication (mMTC), ultra-reliable low-latency communication (ultra-reliable low- latency communication, URLLC). Among them, eMBB is mainly applied to services such as AR / VR due to its high bandwidth, mMTC is applied to services such as the Internet of Things and smart home due to its high connection density, and URLLC with low latency and...

AI Technical Summary

Problems solved by technology

[0006] Traditional dedicated resource allocation schemes and resource allocation strategies based on optimization algorithms and heuristic algorithms often have strict restrictions and complex derivations to form specific optimization problems. Such methods lack flexibility and scalability. When user characteristics and The proportion of users with various performances changes, and these algorithms cannot cope well

Images