Abstract: Methods and apparatuses for using a neural network based model to predict an output port for a destination Internet Protocol (IP) address in a network are described. Some embodiments can construct an untrained model comprising a graph neural network (GNN), a first artificial feed-forward neural network (ANN), and a second ANN. Next, the embodiments can train the untrained model to obtain a trained model by: training the first ANN using at least IP addresses of destination nodes in the network, training the GNN using at least an adjacency matrix of the network and initial node features computed using the IP addresses of destination nodes in the network, and training the second ANN by combining the output of the first ANN and an output of the GNN using an attention mechanism. The embodiments can then use the trained model to predict the output port for the destination IP address.

Abstract: Methods and apparatuses for using a neural network based model to predict an output port for a destination Internet Protocol (IP) address in a network are described. Some embodiments can construct an untrained model comprising a graph neural network (GNN), a first artificial feed-forward neural network (ANN), and a second ANN. Next, the embodiments can train the untrained model to obtain a trained model by: training the first ANN using at least IP addresses of destination nodes in the network, training the GNN using at least an adjacency matrix of the network and initial node features computed using the IP addresses of destination nodes in the network, and training the second ANN by combining the output of the first ANN and an output of the GNN using an attention mechanism. The embodiments can then use the trained model to predict the output port for the destination IP address.

Abstract: Methods and apparatuses for building a programmable dataplane are described. Specifically, the programmable dataplane can work on a list of identifiers, such as those part of OpenFlow 1.5. Specifically, the programmable dataplane can be built by creating a virtual network graph at a controller node using binary identifiers such that a node is broken into an n-ary tree and the tree has 1×2 or 1×1 nodes.

Abstract: Methods and apparatuses for building a programmable dataplane are described. Specifically, the programmable dataplane can work on a list of identifiers, such as those part of OpenFlow 1.5. Specifically, the programmable dataplane can be built by creating a virtual network graph at a controller node using binary identifiers such that a node is broken into an n-ary tree and the tree has 1×2 or 1×1 nodes.