Spatiotemporal Self-Attention-Based Network Traffic Prediction in IIoT

Abstract

The sixth-generation (6G) mobile communications are considered as a future network and very closed to the Industrial Internet of Things (IIoT) due to its low latency and high throughput. Massive nodes supported by 6G make up the complexity of the network. Moreover, the heterogeneous traffic brings difficulties to the network management. Long-term network traffic matrix (TM) prediction is a crucial technology for realizing network edge intelligence and dealing with the above issues. However, predicting long-term network traffic in heterogeneous IIoT is challenging. Due to the powerful feature extraction capability over long sequences, self-attention is widely applied in language inference tasks. Motivated by these observations, we propose a self-attention traffic matrix prediction (SATMP) model for long-term network TM prediction in IIoT scenarios. SATMP consists of three components: (a) a spatial–temporal encoding for obtaining the spatial–temporal features of network TM; (b) a learnable positional encoding for providing positional correlation to the traffic sequence; and (c) a self-attention module for capturing long-term dependence. These components work together to enhance long-term prediction performance in complex networks effectively. Extensive experiments on three publicly available datasets demonstrate that SATMP is feasible and accurate in IIoT long-term network TM prediction.