Abstract: Disclosed are an isolation method for a high-performance computer system, and a high-performance computer system. The isolation method comprises node-level isolation performed. The node-level isolation comprises: configuring a routing table for each computing node, and configuring, in the routing table, valid routing information for computing node pairs; when any one source computing node needs to communicate with a target computing node, determining, by lookup, whether valid routing information exists between the source computing node and the target computing node according to the configured routing table; if so, allowing the source computing node to communicate with the target computing node; otherwise, forbidding the source computing node from communicating with the target computing node.

Abstract: A high-temperature disaster forecast method based on a directed graph neural network is provided, and the method includes the following steps: S1, performing standardization processing on meteorological elements respectively to scale the meteorological elements into a same value range; S2, taking the meteorological elements as nodes in the graph, and describing relationships among the nodes by an adjacency matrix of graph; then learning node information by a stepwise learning strategy and continuously updating a state of the adjacency matrix; S3, training the directed graph neural network model after determining a loss function, obtaining a model satisfying requirements by adjusting a learning rate, an optimizer and regularization parameters as a forecast model, and saving the forecast model; and S4, inputting historical multivariable time series into the forecast model, changing an output stride according to demands, and thereby obtaining high-temperature disaster forecast for a future period of time.

Abstract: A high-temperature disaster forecast method based on a directed graph neural network is provided, and the method includes the following steps: S1, performing standardization processing on meteorological elements respectively to scale the meteorological elements into a same value range; S2, taking the meteorological elements as nodes in the graph, and describing relationships among the nodes by an adjacency matrix of graph; then learning node information by a stepwise learning strategy and continuously updating a state of the adjacency matrix; S3, training the directed graph neural network model after determining a loss function, obtaining a model satisfying requirements by adjusting a learning rate, an optimizer and regularization parameters as a forecast model, and saving the forecast model; and S4, inputting historical multivariable time series into the forecast model, changing an output stride according to demands, and thereby obtaining high-temperature disaster forecast for a future period of time.