Network Intent Synthesis via Graph State Exploration

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for achieving desired network behavior in telecommunication networks require manual design and application of low-level policies, which is time-consuming, error-prone, and lacks formal guarantees of achieving the intended behavior.

Innovation Solution

Implementing a state exploration process to compose and apply policies automatically, using a graph representation of the network to determine the necessary policy actions to transition from an existing state to a desired state, thereby automating the network intent verification and policy execution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual design and application of low-level policies is used to achieve desired network behavior, then network operators can control network behavior, but the process becomes time-consuming and error-prone

Engineering Contradiction:

Improveaccuracy of achieving desired network behaviorVSAvoidtime required to design and apply policies

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables self-service by allowing the network to automatically compose and execute policies to achieve desired behavior. The policy composition engine autonomously generates policies from high-level intents without requiring manual intervention, and the self-healing mechanisms automatically detect and correct deviations from desired network states, eliminating the need for continuous manual policy management.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent introduces a policy composition engine as an intermediary between high-level network intents and low-level policy execution. This intermediary automatically translates operator intents into executable policies, managing the complexity and time-consuming aspects of policy design while ensuring accurate implementation of desired network behavior.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If manual design of low-level policies is used, then operators can implement network behavior changes, but the process lacks formal guarantees of achieving intended behavior

Engineering Contradiction:

Improveformal guarantee of achieving desired behaviorVSAvoidcomplexity of policy design process

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system implements continuous feedback mechanisms where the network state is monitored against desired behavior specifications. The policy composition engine uses this feedback to automatically adjust and refine policies, providing formal guarantees that the intended behavior is achieved. The feedback loop ensures that deviations from desired states are detected and corrected through automated policy execution.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent employs dynamic policy composition where policies are not statically designed but continuously adapted based on current network conditions and desired behavior requirements. This dynamic approach allows the system to respond to changing conditions while maintaining formal guarantees through automated verification and adjustment mechanisms.

Inventive Principle:

Principle #15Dynamics

3Productivity

If automated policy composition is implemented, then time and effort are reduced, but system complexity increases

Engineering Contradiction:

Improvespeed of implementing network behavior changesVSAvoidcomplexity of automated policy composition system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The automated policy composition system is segmented into distinct functional modules: intent interpretation, policy generation, policy validation, and execution monitoring. This segmentation manages system complexity by dividing the automated composition process into manageable, independently verifiable components while maintaining high productivity through their coordinated operation.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11356329B2Network intent synthesis

Publication Date: 2022.06.07 AT&T INTELLECTUAL PROPERTY I L P

AI summary

A processing system may obtain an intent comprising a desired network state for a telecommunication network, determine an existing network state, where the desired network state and the existing network state are defined in accordance with a graph representing the telecommunication network, where the graph includes objects and relationships between the plurality of objects, and where each of the objects includes one or more properties. The processing system may compose a strategy that includes a plurality of policies to obtain the desired network state from the existing network state, where each of the policies comprises an action that is to be implemented in the telecommunication network, where the composing comprises performing a state exploration process over the graph, and where each state transition of the process corresponds to one of the policies. The processing system may then implement the strategy to place the telecommunication network in the desired network state.