Network Substrate Control for Dynamic Workload Placement

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Distributed networks face challenges in quickly adapting to dynamic workload placement across locations due to fluctuating load, resource availability, and financial costs, necessitating a network that is aware of workload dynamics without relying on manual administration.

Innovation Solution

A network controller observes network configurations and patterns to coordinate workload placement and resource allocation based on telemetry data and workload rules, determining optimal resource environments and dynamically configuring or migrating workloads to ensure efficient and cost-effective hosting.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If manual administration is used to manage workload placement, then network control and security are maintained, but adaptability to dynamic workload conditions deteriorates

Engineering Contradiction:
Improveadaptability to workload dynamicsVSAvoidnetwork complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The network system performs self-service by automatically observing its own configuration and telemetry data, then autonomously coordinating workload placement decisions without requiring external manual administration. The network controller monitors workload dynamics, resource availability, and cost factors, then automatically places or migrates workloads to optimal locations, enabling the system to serve itself while maintaining security and control.

Inventive Principle:
Principle #25Self-service

2Productivity

If workload placement is made dynamic across locations, then cost efficiency and resource utilization improve, but network stability and security deteriorate

Engineering Contradiction:
Improveresource allocation efficiencyVSAvoidworkload stability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system implements feedback by continuously observing network configuration and telemetry data from workload environments, then using this information to coordinate workload placement decisions. The network controller monitors workload performance, resource availability, and cost factors in real-time, adjusting workload placement dynamically while maintaining stability through informed, data-driven decisions rather than random or purely reactive movements.

Inventive Principle:
Principle #23Feedback

3Loss of energy

If network resources are allocated dynamically based on workload presence, then operational costs reduce, but response time to workload changes increases

Engineering Contradiction:
Improveoperational costVSAvoidnetwork adaptation speed
Core Design Contradiction:
Loss of energyVSSpeed

Solution Approach 1:

The system applies preliminary action by proactively observing network configuration and workload patterns to anticipate placement opportunities before they become critical. The network controller continuously monitors telemetry data and workload rules, preparing placement decisions in advance based on predicted workload dynamics, resource availability trends, and cost factors, enabling faster response when actual placement decisions are required.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20260052178A1Adaptable network substrate for workloads with dynamic location placement
Publication Date: 2026.02.19 CISCO TECHNOLOGY INC
  • US20260052178A1 patent drawing
  • US20260052178A1 patent drawing
  • US20260052178A1 patent drawing

AI summary

Techniques for observing network configuration(s) and/or pattern(s) for coordinating workload placement and resource/infrastructure allocation according to present network and/or workload conditions are described herein. A controller of a network may receive telemetry data from resources, associated with a workload orchestrator, that are allocated to host workloads in the network. The controller may also receive workload rules indicative of configuration data associated with a workload that is to be provisioned in the network. Using the telemetry data and the workload rules, the controller may determine specific resources in specific workload environment(s) of the network are most favorable to host the workload. Once the resources and/or the workload environment is determined, the network controller may negotiate with the workload orchestrators to configure resources to host the workload, provision additional resources in a workload environment to host the workload, migrate workloads from first resources in workload environments to second resources, and/or the like.