We propose the Kuramoto Graph Neural Network (KuramotoGNN), a novel class of continuous-depth graph neural networks (GNNs) that employs the Kuramoto model to mitigate the over-smoothing phenomenon, in which node features in GNNs become indistinguishable as the number of layers increases. The Kuramoto model captures the synchronization behavior of non-linear coupled oscillators. Under the view of coupled oscillators, we first show the connection between Kuramoto model and basic GNN and then over-smoothing phenomenon in GNNs can be interpreted as phase synchronization in Kuramoto model. The KuramotoGNN replaces this phase synchronization with frequency synchronization to prevent the node features from converging into each other while allowing the system to still reach a stable synchronized state. We experimentally verify the advantages of the KuramotoGNN over the baseline GNNs and existing methods in reducing over-smoothing on various graph deep learning benchmark tasks.

This paper proposes an algorithm for disaster avoidance control against heavy rainfall. According to weather information, the algorithm reconfigures a logical network (slice), including the migration of virtual machines (VMs), to avoid disasters. It was applied to a nationwide network of 105 nodes and 140 edges, including cases with more than 10 000 slices. Through numerical simulations using actual data of rainfall that caused significant damage in Japan, we found that the probability of service disruption under the proposed control with suitable parameter settings is 10%–30% of that without control, on average. Our proposed control experimental system is implemented by using the software-defined network technology. It can migrate VMs and estimates VM migration time to determine how many VMs should be migrated. By using the experimental system, we found that the control interval has an optimal value, which depends on the management system processing capacity.

This paper proposes a disaster avoidance control method for use against heavy rainfall and discusses its effectiveness through actual weather data. The proposed control method uses geographical information data including weather data, hazard area data, and physical network data. By applying technologies related to meteorology, erosion control, and civil engineering to such data, the proposed method can evaluate the risk of a physical network being disconnected. On the basis of the evaluated risk, the proposed method reconfigures a logical network to reduce service disruption. The proposed method is applied to a cloud computing service network where, in addition to route changes, the relocation of virtual machines is possible, increasing its effectiveness. By using empirical data, we show that the proposed method reduces the probability of service disconnection to almost zero even for heavy rainfall causing landslides. Finally, an experimental system of the proposed method was implemented through software defined network technology and successfully controlled the experimental network.

In this paper, we analyze the performance of vehicle-to-infrastructure (V2I) communications on a highway, in which the transmission distance between a road side unit (RSU) and a vehicle rapidly changes due to movement of vehicles. By theoretically analyzing the interference received at an RSU, we derive a closedform expression of a desired performance metric of V2I communications. Furthermore, by considering the trade-off between the interference at an RSU and the transmission range of a running vehicle, we obtain a closed-form optimal transmission-range for V2I communications. We evaluate our analysis results by conducting numerical simulations and show the effectiveness of the optimal transmissionrange.

In this paper, we propose a mathematical model for intelligent transportation systems (ITS) in an urban environment, which takes into account both the urban structure and vehicles. Using the stochastic geometry approach, we model the locations of vehicles with a Poisson point process on roads whose interval is a fixed value. We consider typical vehicle-to-infrastructure and vehicle-to-vehicle communication scenarios and derive theoretical values of the probability of successful transmission. Our results from numerical experiments reveal how the urban structure can affect wireless communications in ITS.