Virtualized Network Service Bundles for Latency Reduction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Network service function chains in NFV systems face end-to-end latency issues due to the distributed location of virtual network functions across different racks or data centers, leading to message drops and re-transmissions, which deteriorate the quality of service.

Innovation Solution

Implementing virtualized network service bundles using lightweight virtualization technology, such as containers or virtual machines, to instantiate virtual network functions in close proximity, managing these bundles to distribute workload and reduce latency by dynamically creating, managing, and deleting instances based on transaction volume and rate.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If virtual network functions are distributed across different racks or data centers, then resource utilization and scalability are improved, but end-to-end latency increases and message reliability deteriorates

Engineering Contradiction:
Improveresource utilizationVSAvoidend-to-end latency
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system segments virtual network functions into service function chains that can be independently managed and deployed. Each service function chain is a logical unit that can be distributed or consolidated based on latency requirements, allowing flexible resource utilization while maintaining low latency for time-sensitive functions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a service chain manager as an intermediary that coordinates communication between distributed virtual network functions. This manager optimizes message routing and timing, reducing end-to-end latency while maintaining the benefits of distributed deployment across multiple racks and data centers.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If virtual network functions are distributed across different racks or data centers, then resource utilization and scalability are improved, but message reliability deteriorates due to message drops and re-transmissions

Engineering Contradiction:
ImprovescalabilityVSAvoidmessage reliability
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system establishes service function chains and pre-configures communication paths before messages need to be transmitted. This preliminary setup ensures that routing information and communication protocols are already optimized, preventing message drops and re-transmissions during actual operation while maintaining scalable distributed architecture.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The service chain manager implements feedback mechanisms that monitor message transmission success rates between distributed virtual network functions. When message drops or re-transmissions are detected, the system dynamically adjusts routing and resource allocation to improve reliability while maintaining scalability.

Inventive Principle:
Principle #23Feedback

3Productivity

If virtualized network service bundles are dynamically created and managed, then productivity and resource optimization are improved, but device complexity increases

Engineering Contradiction:
Improveresource optimizationVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The service chain manager is designed as a universal control system that handles multiple functions including service bundle creation, deployment, monitoring, and optimization. This multi-functional approach consolidates complexity into a single management layer, allowing dynamic resource optimization without proportionally increasing overall system complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS10594621B2Managing virtualized network service bundles
Publication Date: 2020.03.17 HEWLETT PACKARD ENTERPRISE DEV LP
  • US10594621B2 patent drawing
  • US10594621B2 patent drawing
  • US10594621B2 patent drawing

AI summary

Examples provided herein describe a method for managing virtualized network service bundles. For example, a physical processor may implement machine readable instructions to receive a first data packet in a virtual network, determine a first type of the first data packet, determine a first active virtualized network service bundle instance associated with a first virtualized network service bundle that handles the first type of data packet, and direct the first data packet to the first active virtualized network service bundle instance. In some examples, the first virtualized network service bundle may comprise a first set of virtual network functions, and the first virtualized network service bundle may be associated with a set of active virtualized network service bundles instances, where the set of active virtualized network service bundle instances may comprise the first active virtualized network service bundle instance.