During the past decade, Industry 4.0 has greatly promoted the improvement of industrial productivity by introducing advanced communication and network technologies in the manufacturing process. With the continuous emergence of new communication technologies and networking facilities, especially the rapid evolution of cellular networks for 5G and beyond, the requirements for smarter, more reliable, and more efficient cellular network services have been raised from the Industry 5.0 blueprint. To meet these increasingly challenging requirements, proactive and effective allocation of cellular network resources becomes essential. As an integral part of the cellular network resource management system, cellular traffic prediction faces severe challenges with stringent requirements for accuracy and reliability. One of the most critical problems is how to improve the prediction performance by jointly exploring the spatial and temporal information within the cellular traffic data. A promising solution to this problem is provided by Graph Neural Networks (GNNs), which can jointly leverage the cellular traffic in the temporal domain and the physical or logical topology of cellular networks in the spatial domain to make accurate predictions. In this paper, we present the spatial-temporal analysis of a realworld cellular network traffic dataset and review the state-ofthe-art researches in this field. Based on this, we further propose a time-series similarity-based graph attention network, TSGAN, for the spatial-temporal cellular traffic prediction. The simulation results show that our proposed TSGAN outperforms three classic prediction models based on GNNs or GRU on a real-world cellular network dataset in short-term, mid-term, and long-term prediction scenarios.

Recent years have witnessed the remarkable development of wireless embedded network systems (WENS) such as cyber-physical systems and sensor networks. Reliable bulk data dissemination is an important building module in WENS, supporting various applications, e.g., remote software update, video distribution. The existing studies often construct network structures to enable time-slotted multi-hop pipelining for data dissemination. However, the adopted transmission mechanism was originally designed for structureless protocols, and thus posing significant challenges on efficient structured data dissemination. In this paper, we investigate the problem of structured bulk data dissemination. Specifically, we propose reliable out-of-order transmission and bursty encoding mechanisms to transmit packets as many as possible in each transmission slot. As a consequence, the resulting transmission protocol (ULTRA) can fully utilize each transmission slot and propagate data in the network as fast as possible. The performance results obtained from both testbed and simulation experiments demonstrate that, compared to the state-of-the-art protocols, ULTRA can greatly enhance the dissemination performance by reducing the dissemination delay by 34.8%.

No abstract

No abstract