Distributed Resource Scheduling via Timing-Based Workload Inference

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Centralized resource management systems in cloud computing are inefficient due to high costs and communication overhead, and distributed systems struggle with balanced resource allocation and maintaining privacy of server resource states.

Innovation Solution

A distributed resource search protocol that allows users to indirectly infer server workloads by analyzing the timing of reply messages, enabling balanced resource allocation without disclosing explicit resource information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a centralized resource management system is used, then resource allocation can be controlled, but communication overhead and costs increase

Engineering Contradiction:

Improveresource allocation controlVSAvoidcommunication overhead

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The patent segments the centralized resource management system into distributed components. Each server independently manages its own resource information and responds to client requests, eliminating the need for a centralized controller. This segmentation reduces communication overhead while maintaining resource allocation control through distributed coordination.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent implements self-service mechanisms where servers autonomously respond to resource requests without centralized coordination. Each server independently evaluates its own resource availability and sends reply messages, reducing the communication burden on centralized management while ensuring reliable resource allocation.

Inventive Principle:

Principle #25Self-service

2Productivity

If server resource information is disclosed to clients, then resource selection can be optimized, but privacy of server resource states is compromised

Engineering Contradiction:

Improveresource selection efficiencyVSAvoidserver resource state privacy

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The patent introduces timing information as an intermediary that indirectly conveys server workload status. Instead of disclosing explicit resource state information, servers embed their workload characteristics in the timing of reply messages, allowing clients to infer resource availability without compromising privacy.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the parameter used for resource selection from explicit resource state information to implicit timing-based indicators. Clients analyze the timing of reply messages rather than direct resource state data, enabling optimized resource selection while preserving server privacy through parameter transformation.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250030758A1System and Method for Resource Scheduling in a Distributed Computing System

Publication Date: 2025.01.23 ELEMENTO SRL

AI summary

A method for sharing and selecting a shared resource in a cloud computing system includes a first step in which a server of the system receives a message requesting a resource, and a second step in which said server transmits a reply message at a predetermined instant of transmission computed as a function of a utilization index of the shared resources included in the server. The method for selecting a resource includes a first step in which a user equipment transmits a message requesting a resource, a second step in which the user equipment receives a first reply message at a first instant of reception from a first server, and a third step in which the user equipment receives a second reply message at a second instant of reception from a second server.