Cloud-Native Scheduling Policy Adaptation to Production Environment Changes

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing scheduling optimization methods for cloud-native infrastructure fail to consider the impact of changes in the actual production environment, leading to high labor costs and low optimization efficiency, and adaptive methods from other fields are not applicable due to differences in application scenarios.

Innovation Solution

A scheduling optimization method that acquires information about the current production environment, determines new scheduling actions and policies using a performance optimization model trained on historical data, and replaces existing scheduling parameters to adapt to environmental changes, thereby optimizing scheduling performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual scheduling optimization is used, then scheduling performance can be optimized based on expert experience, but labor costs increase and optimization efficiency decreases

Engineering Contradiction:

Improvescheduling performanceVSAvoidoptimization efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent replaces manual scheduling optimization (mechanical system) with an automated machine learning-based optimization system. The scheduling optimization model, trained on historical data and equipped with an explanation module, automatically determines optimal scheduling actions and policies, eliminating the need for manual expert intervention while maintaining high optimization effectiveness.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The scheduling optimization system performs self-service by automatically acquiring production environment information, determining optimization actions, and executing scheduling adjustments without requiring continuous manual input. The system monitors production environment changes and autonomously adapts scheduling policies to maintain optimal performance.

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If existing scheduling optimization methods are used, then scheduling can be performed, but they fail to consider the impact of changes in the actual production environment

Engineering Contradiction:

Improveadaptability to production environment changesVSAvoidscheduling performance

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent implements a feedback mechanism where the scheduling optimization model continuously monitors production environment information and adjusts scheduling policies accordingly. The explanation module provides feedback on why certain scheduling actions are taken, enabling the system to adapt to changing production conditions while maintaining transparent and reliable decision-making.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The scheduling optimization system transitions from static scheduling policies to dynamic policies that automatically adapt to production environment changes. The system continuously updates scheduling actions based on real-time production information, ensuring optimal performance under varying conditions.

Inventive Principle:

Principle #15Dynamics

3Productivity

If adaptive scheduling optimization methods from other fields are applied, then optimization can be achieved, but they cannot be directly applied due to difference in application scenarios

Engineering Contradiction:

Improveoptimization efficiencyVSAvoidapplicability to cloud-native scheduling

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent applies local quality by customizing the scheduling optimization model specifically for cloud-native scheduling scenarios. The model incorporates cloud-specific concepts such as pod scheduling, resource quotas, and Kubernetes API interactions, making the optimization approach tailored to the specific domain rather than a generic solution.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The scheduling optimization model is designed with universal applicability to cloud-native scheduling scenarios. It can handle various scheduling tasks including pod scheduling, resource allocation, and workload management within the Kubernetes ecosystem, making it a multi-functional solution that addresses different scheduling needs through a unified approach.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20260064478A1Scheduling optimization method of scheduling apparatus, scheduling apparatus and storage medium

Publication Date: 2026.03.05 ZTE CORP

AI summary

Disclosed in the present application are a scheduling optimization method, a scheduling apparatus and a storage medium. The method includes: acquiring information of the current production environment of a scheduling apparatus; acquiring a first scheduling action, a first scheduling policy and a first parameter value thereof which are used by the current scheduling of the scheduling apparatus; determining a second scheduling action, a second scheduling policy and a second parameter value thereof which are used by the optimized scheduling apparatus; and blocking in a scheduling queue a workload to be scheduled, replacing the first scheduling action, the first scheduling policy and the first parameter value in the first scheduling policy which are used by the current scheduling of the scheduling apparatus with the second scheduling action, the second scheduling policy and the second parameter value thereof, and relieving the blocking of the scheduling queue.