Intelligent Workload Router Dynamic Platform Routing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Distributed computer systems face challenges in efficiently routing workload requests to appropriate processing platforms, as existing methods either hardcode distribution or distribute all or none of the workload, failing to dynamically adapt to changing conditions such as platform availability, performance, and load.

Innovation Solution

An intelligent workload router that receives status updates from processing platforms and applies routing rules based on characteristics like platform status, utilization, health, and anticipated workload to dynamically route requests to the most suitable platform, including rules for load balancing, latency minimization, and cost management.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If workload requests are routed using hardcoded distribution or all-or-none distribution methods, then system simplicity is maintained, but system adaptability to changing platform conditions deteriorates

Engineering Contradiction:

Improvesystem adaptabilityVSAvoidrouting system complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic workload routing by continuously monitoring platform characteristics (CPU utilization, memory availability, network latency) and adapting routing decisions in real-time based on current system conditions, replacing static hardcoded distribution methods with a flexible dynamic routing architecture

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system employs feedback mechanisms by collecting performance metrics from processing platforms and using this information to adjust routing decisions, creating a closed-loop control system that continuously optimizes workload distribution based on actual platform performance and availability

Inventive Principle:

Principle #23Feedback

2Reliability

If all workload is routed to a single processing platform, then routing simplicity is maintained, but system reliability deteriorates due to lack of redundancy

Engineering Contradiction:

Improvesystem reliabilityVSAvoidrouting architecture complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the workload routing architecture into multiple independent processing platforms, dividing the monolithic routing approach into distributed routing decisions across multiple platforms, thereby creating redundancy and improving system reliability

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system dynamically changes routing parameters (destination platform selection) based on real-time platform status, health metrics, and load conditions, allowing flexible redistribution of workload to maintain reliability when individual platforms fail or become overloaded

Inventive Principle:

Principle #35Parameter changes

3Productivity

If workload routing does not consider platform performance characteristics, then routing decision speed is maintained, but system productivity deteriorates

Engineering Contradiction:

Improvesystem productivityVSAvoidrouting evaluation complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent performs preliminary evaluation of platform characteristics and pre-calculates routing options based on historical performance data and current platform capabilities, preparing routing decisions in advance to enable quick dispatch without sacrificing productivity optimization

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system replaces simple mechanical routing rules with intelligent algorithms that evaluate multiple platform parameters (CPU utilization, memory availability, network latency, queue depth), using software-based decision logic to optimize productivity while managing evaluation complexity

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Loss of time

If workload is not dynamically balanced across platforms, then system operation simplicity is maintained, but latency increases

Engineering Contradiction:

Improveworkload processing latencyVSAvoidrouting control complexity

Core Design Contradiction:

Loss of timeVSDevice complexity

Solution Approach 1:

The patent implements periodic monitoring and evaluation of platform performance metrics, continuously updating routing decisions at regular intervals to maintain optimal load distribution and minimize processing latency through systematic periodic reassessment of platform capacity

Inventive Principle:

Principle #19Periodic action

Solution Approach 2:

The system introduces asymmetric routing strategies by directing different types of workload requests to different platforms based on their specific capabilities and current load conditions, optimizing latency for different workload categories rather than using uniform symmetric distribution

Inventive Principle:

Principle #4Asymmetry

Data Source

PatentEP3117337B1Systems and methods for intelligent workload routing

Publication Date: 2020.10.21 JPMORGAN CHASE BANK NA

Figure 1
Figure 2
Figure 3

AI summary

Systems and methods for intelligent workload routing are disclosed. According to one embodiment, a system for intelligent workload routing may include a first processing platform having a first characteristic; a second processing platform having a second characteristic; and a workload router in communication with the first processing platform and the second processing platform the workload router receiving a message comprising a workload request and routing the workload request to one of the first processing platform and the second processing platform based on at least one of a workload request characteristic, the first characteristic and the second characteristic.