International audience

With the explosive growth of communication networks, the unmet demand for spectrum has created escalating interference issues, necessitating high-precision multi-step interference prediction methods. However, collecting interference data can impose significant sensor overhead. To address this challenge, we propose a framework that leverages physical resource block (PRB) traffic for interference prediction. Given the intricate spatial-temporal characteristics of PRB traffic and interference intensity, capturing these intrinsic features accurately poses a considerable challenge. In response, we introduce a novel Diverse Spatial-Temporal Graph Attention Network (DSTGAT) designed to precisely predict interference intensity from PRB traffic. The DSTGAT comprises two main components: first, a multi-feature extraction module that integrates four adjacency matrices to characterize the spatial features of PRB traffic; second, a time-encoding temporal self-attention module crafted to uncover temporal correlations. Experimental results substantiate the superior performance of our proposed model, especially in managing multi-step prediction scenarios.

In the context of the telecom network trending towards centralization, the relatively decentralized and citizen-centric, non-profit network architecture known as Wireless Community Network (WCN) has emerged. However, WCN faces challenges related to unintentional shifts towards centralization, the lack of automation and verifiability to handle increasing volumes of information, and the absence of real-time and more flexible incentive mechanisms to incentivize a diverse range of contributors based on the quality of their contributions. As the network expands, maintenance becomes more challenging for small volunteer teams, potentially compromising network performance, reliability, and overall trustworthiness. With the development of the decentralized physical infrastructure network (DePIN), this paper proposes a methodology for designing a decentralized wireless community network (DeWCN) system. This methodology includes the design of a consensus layer, a trust and reputation management layer, and presents incentive-driven oracle design methodologies for verifiable common resource pools. This is the first work in the DePIN domain discussing the design of DeWCNs. Unlike projects like Helium [1], we eliminate the need for specialized devices and mining-based token systems.

Satellite spectrum-sharing systems exhibit longer transmission delays and occupy larger bandwidths in comparison to terrestrial spectrum-sharing systems. These extended latencies, coupled with the time needed for devices to process broadband data, often render short-term prediction results ineffective. Hence, the need for rapid and precise Wide-band Multi-Step (WBMS) satellite spectrum prediction arises as an effective solution to address this challenge. To tackle this problem, we propose the Clustering-ConvTransformer Network (CCTNet). CCTNet significantly enhances the computation speed of the system through its clustering module. Additionally, it incorporates an improved Transformer network combined with convolution to ensure reliable multi-step prediction accuracy. Experimental evaluations on real-world satellite spectrum data demonstrate that CCTNet achieves a computational speed of only 0.38 seconds, marking a 55-fold improvement over non-clustered networks. Furthermore, in terms of prediction accuracy, the CCTNet has also illustrated superiority compared to other state-of-the-art (SOTA) baselines.

A decentralized community network is a network that is managed by the crowd without a central authority. Within the network, participants are incentivized to lease out their surplus network resources to consumers in exchange for compensation. Therefore, a network selection strategy is crucial for ensuring the quality of service (QoS) and the integrity of the system to avoid fraudulent activities. This paper proposes an auction-based peer-score mechanism as a network selection strategy for consumers. In addition to considering QoS param-eters, the model also incorporates consumer feedback and peer scoring among providers. This facilitates fair transactions while eliminating the need for a dedicated auctioneer. The proposed model simplifies network selection for consumers and exhibits Byzantine fault tolerance characteristics.