State-Machine Neural Network for Workflow Orchestration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Complex computer network operations, such as configuring large-scale Software-Defined Networks (SDNs), become infeasible due to the exponential growth of Finite State Machine (FSM) states, making manual configuration and orchestration difficult and error-prone, especially under dynamic conditions.
Innovation Solution
A State-Machine Neural Network (SNN) is generated based on a Directed Acyclic Graph (DAG) that defines tasks and their orders, allowing for efficient orchestration of complex workflows by reducing the number of states and enabling intuitive modeling and customization of operations across thousands of devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a Finite State Machine (FSM) is used to model complex network operations, then the system can track execution states, but the number of states grows exponentially making the system infeasible
Solution Approach 1:
The patent segments the monolithic FSM into a hierarchical structure with a root FSM and multiple worker FSMs. Each worker FSM handles a specific task or sub-process, breaking down the exponential state space into manageable linear sequences. This segmentation allows the system to track complex network operations without requiring an exponentially large state machine, directly resolving the contradiction between reliable state tracking and system feasibility.
2Reliability
If manual FSM construction is used for complex operations, then expert control is achieved, but the system becomes difficult to define and configure
Solution Approach 1:
The patent implements self-service through automated FSM generation from workflow definitions and self-healing capabilities where worker FSMs automatically retry failed tasks. The system generates FSM configurations automatically based on workflow specifications, eliminating the need for manual expert construction while maintaining reliability through structured automation and error handling mechanisms.
3Adaptability or versatility
If FSM size increases to handle more tasks, then more operations can be modeled, but the system becomes infeasible for use
Solution Approach 1:
The patent transitions from a two-dimensional FSM state space to a multi-dimensional hierarchical structure by introducing layers of FSM organization (root FSM, worker FSMs, task sequences). This dimensional change allows the system to model complex multi-task operations without proportional increases in overall complexity, as each layer manages a specific aspect of the workflow independently.
Data Source
AI summary
Techniques for orchestrating a workflow for configuring a computer networking environment or other complex workflows are described. A Directed Acyclic Graph (DAG) that defines a plurality of tasks to be executed to complete the workflow and a plurality of orders between the tasks is received. Embodiments generate a State-Machine Neural Network (SNN) based on the received DAG, by generating a plurality of SNN neurons for the SNN, based on the plurality of tasks within the received DAG 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. The SNN is executed to orchestrate the workflow by sending and receiving signals to and from the SNN neurons.