Learning Wireless Data Knowledge Graph for Green Intelligent Communications: Methodology and Experiments
Yongming Huang, Xiaohu You, Hang Zhan, Shiwen He, Ningning Fu, Wei Xu
TL;DR
The paper tackles the data-scale and energy constraints of native AI for future 6G networks by introducing a wireless data knowledge graph (KG) as the core of a pervasive multi-level (PML) native AI architecture. It develops STREAM, a spatio-temporal heterogeneous graph attention network, to learn embeddings and enable link prediction on a dynamic wireless data KG, and proposes a feature dataset generation workflow that selects minimal, high-impact data fields for KPI prediction. Through experiments, the authors show that the KG-driven approach dramatically reduces data and computational requirements while maintaining predictive performance, with feature datasets reducing inputs by roughly two orders of magnitude and lowering training cost by an order of magnitude. The work demonstrates a practical pathway to green, real-time intelligent wireless networks by combining knowledge-driven KG construction, dynamic graph embedding, and on-demand feature dataset generation, enabling efficient training, inference, and validation.
Abstract
Intelligent communications have played a pivotal role in shaping the evolution of 6G networks. Native artificial intelligence (AI) within green communication systems must meet stringent real-time requirements. To achieve this, deploying lightweight and resource-efficient AI models is necessary. However, as wireless networks generate a multitude of data fields and indicators during operation, only a fraction of them imposes significant impact on the network AI models. Therefore, real-time intelligence of communication systems heavily relies on a small but critical set of the data that profoundly influences the performance of network AI models. These challenges underscore the need for innovative architectures and solutions. In this paper, we propose a solution, termed the pervasive multi-level (PML) native AI architecture, which integrates the concept of knowledge graph (KG) into the intelligent operational manipulations of mobile networks, resulting in the establishment of a wireless data KG. Leveraging the wireless data KG, we characterize the massive and complex data collected from wireless communication networks and analyze the relationships among various data fields. The obtained graph of data field relations enables the on-demand generation of minimal and effective datasets, referred to as feature datasets, tailored to specific application requirements. Consequently, this architecture not only enhances AI training, inference, and validation processes but also significantly reduces resource wastage and overhead for communication networks. To implement this architecture, we have developed a specific solution comprising a spatio-temporal heterogeneous graph attention neural network model (STREAM) as well as a feature dataset generation algorithm. Experiments are conducted to validate the effectiveness of the proposed architecture.