The space–air–ground Integrated Network (SAGIN) is considered to be a significant framework for realizing the vision of “6G intelligent connection of all things”. The birth of 6G SAGIN also brings many problems, such as ultra-dense dense networks, leading to a decrease in the efficiency of traditional flat network management, and traditional satellite networking solidified network functions, etc. Therefore, combining the 6G SAGIN network with the software-defined network (SDN) is an excellent solution. However, the satellite network topology changes dynamically and the ground user unbalanced distribution leads to the unbalanced load of the SDN controller, which further leads to the increased communication delay and throughput drop, etc. For these problems, a hierarchical multi-controller deployment strategy of an SDN-based 6G SAGIN is proposed. Firstly, the delay model of the network, the load model of the SDN controller, and a loss value as a measure of whether the network delay and controller load are optimal are defined. Then, using the distribution relationship between the SDN controller and the switch node as the solution space, and taking the loss value as the optimization goal, a multi-controller deployment strategy based on the simulated annealing algorithm is used to search for the optimal solution space. Lastly, considering the network topology changes dynamically and the SDN controller imbalance, a switch migration strategy oriented toward load balancing is proposed. We aimed to determine the controller deployment plan through the above two points, balance the controller load, and then improve the network performance. The simulation results show that the controller load is increased by about 7.71% compared to OCLDS, and the running time is increased by 17.7% compared to n-k-means.
Water conservancy personnel usually need to know the water level by water gauge images in real-time and with an expected accuracy. However, accurately recognizing the water level from water gauge images is still a complex problem. This article proposes a composite method applied in the Wuyuan City, Jiangxi Province, in China. This method can detect water gauge areas and number areas from complex and changeable scenes, accurately detect the water level line from various water gauges, and finally, obtain the accurate water level value. Firstly, FCOS is improved by fusing a contextual adjustment module to meet the requirements of edge computing and ensure considerable detection accuracy. Secondly, to deal with scenes with indistinct water level features, we also apply the contextual adjustment module for Deeplabv3+ to segment the water gauge area above the water surface. Then, the area can be used to obtain the position of the water level line. Finally, the results of the previous two steps are combined to calculate the water level value. Detailed experiments prove that this method solves the problem of water level recognition in complex hydrological scenes. Furthermore, the recognition error of the water level by this method is less than 1 cm, proving it is capable of being applied in real river scenes.
Floods have brought a great threat to the life and property of human beings. Under the premise of strengthening flood control engineering measures and following the strategic thinking of sustainable development, many achievements have been made in flood forecasting recently. However, due to the complexity of the traditional lumped model and distributed model, the hydrologic parameter calibration process is full of difficulties, leading to a long development cycle of a reasonable hydrologic prediction model. Even for modern data-driven models, the spatial distribution characteristics of the rainfall data are also not fully mined. Based on this situation, this paper abstracts the rainfall data into the graph structure data, uses remote sensing images to extract the elevation information, introduces the graph attention mechanism to extract the spatial characteristics of rainfall, and employs long-term and short-term memory (LSTM) network to fuse the spatial and temporal characteristics for flood prediction. Through well-designed experiments, the forecasting effect of flood peak value and flood arrival time is verified. Furthermore, compared with the LSTM model and BIGRU model without spatial feature extraction, the advantages of spatiotemporal feature fusion are highlighted. The specific performance is that the RMSE (the root means square error) and (coefficient of determination) of the GA-RNN model have been significantly improved. Finally, we conduct experiments on the observed ten rainfall events in the history of the target watershed. According to the hydrological prediction specifications, the model can be evaluated as a Class B flood forecasting model.