Heterogeneous Multi-Protocol Stack Resource Allocation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing protocol stacks struggle to simultaneously meet the diverse quality of service (QoS) requirements of different types of applications in resource-limited environments, as they are typically designed for general service scenarios and fail to efficiently allocate resources based on application characteristics.

Innovation Solution

A heterogeneous multi-protocol stack system is introduced, where a manager dynamically allocates resources to protocol stack instances based on QoS requirements, creating resource pools and dispatching data packets to appropriate instances for optimized processing, ensuring that high-concurrency, high-throughput, and low-delay applications receive the necessary resources and processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a general-purpose protocol stack is used, then it can support multiple application types, but it cannot efficiently allocate resources to meet different QoS requirements of specific applications

Engineering Contradiction:
Improvesupport for multiple application typesVSAvoidresource allocation efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The protocol stack is segmented into multiple independent protocol stack instances, each optimized for specific application types (e.g., high-concurrency, high-throughput, low-delay applications). The manager divides resource pools and assigns them to different instances based on application characteristics, enabling specialized resource allocation while maintaining support for multiple application types.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically creates and manages protocol stack instances based on application requirements. The manager can dynamically allocate resources from resource pools to different protocol stack instances according to real-time QoS requirements, enabling flexible and efficient resource allocation that adapts to different application scenarios.

Inventive Principle:
Principle #15Dynamics

2Quantity of substance

If system resources are limited, then resource utilization must be optimized, but a single protocol stack cannot simultaneously meet diverse QoS requirements of different applications

Engineering Contradiction:
Improveavailable system resourcesVSAvoidability to meet diverse QoS requirements
Core Design Contradiction:
Quantity of substanceVSAdaptability or versatility

Solution Approach 1:

Multiple protocol stack instances share common resource pools (socket resources, data buffer resources, CPU resources) managed by the manager. Each protocol stack instance can utilize resources from the pools based on its specific QoS requirements, enabling the system to meet diverse application needs while efficiently utilizing limited resources through shared infrastructure.

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

Solution Approach 2:

The manager changes resource allocation parameters dynamically by adjusting the quantity and type of resources assigned to each protocol stack instance based on application characteristics. For example, high-concurrency applications receive more socket resources, high-throughput applications receive more data buffer resources, and low-delay applications receive priority CPU allocation, optimizing resource utilization for limited systems.

Inventive Principle:
Principle #35Parameter changes

3Ease of manufacture

If protocol stack resources are allocated uniformly, then implementation is simple, but resource utilization is inefficient for applications with different characteristics

Engineering Contradiction:
Improveprotocol stack implementation simplicityVSAvoidresource utilization efficiency
Core Design Contradiction:
Ease of manufactureVSLoss of energy

Solution Approach 1:

The manager acts as an intermediary between resource pools and protocol stack instances, handling the complexity of resource allocation. This allows protocol stack instances to focus on their core processing functions while the manager optimizes resource distribution, maintaining implementation simplicity at the protocol stack level while achieving efficient resource utilization through the intermediary management layer.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3550799B1Heterogeneous multi-protocol stack method, device and system
Publication Date: 2023.08.30 HUAWEI TECH CO LTD
  • EP3550799B1 patent drawingFigure 1
  • EP3550799B1 patent drawingFigure 2
  • EP3550799B1 patent drawingFigure 3

AI summary

Embodiments of the present invention provide a heterogeneous multi-protocol stack system, including a plurality of heterogeneous protocol stack instances. Resource allocation between the protocol stack instances is unbalanced, and algorithms are independently configured, so that QoS capacities of different protocol stack instances are different. In addition, by using a dispatcher, data packets of applications or connections with different QoS requirements can be dispatched to corresponding protocol stack instances at a high speed by using a mapping rule for processing. When system resources are limited, the heterogeneous multi-protocol stack system provided in the embodiments of the present invention is capable of simultaneously supporting classification optimization processing performed on data of a high-concurrency application, a high-throughput application, and a low-delay application, so as to meet QoS requirements of different types of applications, thereby improving user experience.