Jumping knowledge graph attention network for resource allocation in wireless cellular system

Abstract

Next-generation wireless networks are characterized by two essential features: ubiquitous connectivity and high-speed data transmission. The realization of these features hinges on the development of rational resource allocation strategies to optimize the utilization of radio resources. This study addresses the beamforming design problem for downlink transmission in multi-cell cellular networks, with a focus on maximizing user data rates while adhering to stringent power constraints. To tackle this challenge, we propose a novel graph learning-based optimization framework that learns the mapping from channel states to beamforming vectors in an unsupervised manner. At the core of this framework is an attention-based graph neural network (GNN), which efficiently captures complex inter-node relationships by dynamically computing the importance of neighboring nodes. Furthermore, a jumping knowledge network is integrated to enhance structural representation learning, enabling the model to adaptively capture diverse neighborhood ranges for each node and mitigate the issue of over-smoothing. Extensive simulations demonstrate that the proposed algorithm significantly outperforms existing benchmark methods, exhibiting robust performance and strong generalization capabilities across a wide range of system parameter configurations.

Fig. 1

Cellular system and its graph model. We interpret the graph model from the perspective of the direct link between the 1-st base station and the 1-st user. The circular vertex represents this direct communication link, corresponding to the primary signal path within the system, distinct from the interference links depicted separately. The yellow solid arrows indicate intra-cell interference affecting , while the red solid arrows represent inter-cell interference impacting . The black solid arrows illustrate interference among other direct links.

Fig. 2

Illustration of the overall architecture of JGAT.

Fig. 3

Illustration of the overall Jumping knowledge network with LSTM aggregating layer.

Algorithm 1

Jumping Knowledge Graph Attention Network

Fig. 4

Average data rate per UE versus the training set size.

Fig. 5

Average data rate per UE versus cell size.

Fig. 6

Average data rate per UE versus noise level.