Network automation and orchestration using state-machine neural networks

A system, comprising:

• one or more computer processors;
• and
• a memory containing computer program code that, when executed by operation of the one or more computer processors, performs an operation comprising:
• receiving a Directed Acyclic Graph (DAG) that defines a plurality of computer network configuration tasks to be executed to configure a computer networking environment and a plurality of orders between the plurality of tasks, wherein the DAG includes the plurality of tasks and a plurality of connections that connect pairs of tasks within the plurality of tasks;
• generating a State-Machine Neural Network (SNN) based on the received DAG, comprising:
• generating a plurality of SNN neurons for the SNN, based on the plurality of computer network configuration tasks within the received DAG, each of the plurality of SNN neurons relating to at least one configuration task for the computer networking environment and comprising a Finite State Machine (FSM) storing a state for the respective SNN neuron and used to determine state changes for the respective neuron according to one or more inputs, comprising:
• determining a state transition for the respective neuron, using a state transition function, based on the one or more inputs to the respective neuron and the stored state for the respective neuron;
• and
• generating one or more outputs from the respective neuron using an activation function and based on the determined state transition;
• and
• generating a plurality of SNN connections for the SNN, connecting pairs of SNN neurons within the plurality of SNN neurons, based on the plurality of connections within the received DAG, wherein connecting pairs of SNN neurons comprises connecting pairs of FSMs each determining a state change based on both one or more inputs and a stored state;
• and
• executing the SNN to configure a plurality of networking devices within the computer networking environment by sending and receiving events to and from the SNN neurons.

A non-transitory computer-readable medium containing computer program code that, when executed by operation of one or more computer processors, performs an operation comprising:

• receiving a Directed Acyclic Graph (DAG) that defines a plurality of computer network configuration tasks to be executed to configure a computer networking environment and a plurality of orders between the plurality of tasks, wherein the DAG includes the plurality of tasks and a plurality of connections that connect pairs of tasks within the plurality of tasks;
• generating a State-Machine Neural Network (SNN) based on the received DAG, comprising:
• generating a plurality of SNN neurons for the SNN, based on the plurality of computer network configuration tasks within the received DAG, each of the plurality of SNN neurons relating to at least one configuration task for the computer networking environment and comprising a Finite State Machine (FSM) storing a state for the respective SNN neuron and used to determine state changes for the respective neuron according to one or more inputs, comprising:
• determining a state transition for the respective neuron, using a state transition function, based on the one or more inputs to the respective neuron and the stored state for the respective neuron;
• and
• generating one or more outputs from the respective neuron using an activation function and based on the determined state transition;
• and
• generating a plurality of SNN connections for the SNN, connecting pairs of SNN neurons within the plurality of SNN neurons, based on the plurality of connections within the received DAG, wherein connecting pairs of SNN neurons comprises connecting pairs of FSMs each determining a state change based on both one or more inputs and a stored state;
• and
• executing the SNN to configure a plurality of networking devices within the computer networking environment workflow by sending and receiving events to and from the SNN neurons.