Distributed Computing Profiles for Job Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technical computing applications are limited by their single-workstation design, which restricts the complexity and speed of problem-solving due to processing capacity and time constraints, and transitioning to distributed computing environments is costly and complex.
Innovation Solution
A system and method that allow users to create and utilize profiles, scheduler components, and project components to perform jobs in a distributed computing environment without modifying programming code, enabling execution across multiple devices and facilitating the sharing of these components between devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If technical computing is performed on a single workstation, then the application can be simple and easy to operate, but the processing capacity and problem complexity are limited
Solution Approach 1:
The system segments the computing environment into distinct components: profile components (defining computing environment characteristics), scheduler components (managing job distribution), and project components (organizing computational tasks). This segmentation allows the computing workload to be divided across multiple workstations while maintaining a unified interface for users, thus increasing processing capacity without complicating the user experience.
Solution Approach 2:
The patent introduces profile components as intermediaries that act as templates or blueprints for distributed computing environments. These profile components abstract the complexity of distributed system configuration, allowing users to define computing environment characteristics once and reuse them across multiple workstations. The scheduler component serves as another intermediary that automatically distributes jobs between the user and available computing resources based on the profile definitions.
2Productivity
If distributed computing is implemented to increase processing capacity, then productivity improves, but device complexity and implementation cost increase
Solution Approach 1:
The profile components are designed to be universal templates that can define computing environment characteristics applicable across multiple different workstations and computing resources. A single profile component can be reused to configure identical distributed computing environments on different hardware platforms, reducing the complexity of implementing distributed computing across multiple systems. The scheduler component also provides universal functionality by handling job distribution, monitoring, and result collection across diverse computing resources through a standardized interface.
3Productivity
If new technical computing applications are developed for distributed computing, then processing capacity increases, but development cost and time increase
Solution Approach 1:
The system performs preliminary action by pre-defining computing environment characteristics in profile components before actual distributed computing tasks are executed. These profile components contain all necessary configuration information, scheduler settings, and environment parameters that would otherwise need to be configured for each new application. This preliminary preparation allows existing technical computing applications to be deployed in distributed environments without requiring redevelopment, as the profile components provide the necessary distributed computing infrastructure configuration in advance.
4Speed
If computational tasks are distributed across multiple workstations, then processing speed increases, but system coordination and management become more complex
Solution Approach 1:
The scheduler component implements feedback mechanisms that continuously monitor the state of distributed computing resources and adjust job distribution accordingly. The system collects feedback information about workstation availability, computational load, and task progress, then uses this feedback to dynamically allocate computing tasks across the distributed network. This automated feedback loop simplifies system coordination by replacing complex manual management with intelligent, adaptive resource allocation that responds to real-time system conditions.
Data Source
Figure 1
Figure 2
Figure 3A~3B
AI summary
A system is configured to create a profile that allows a job to be performed within a distributed computing environment comprising one or more computing devices; provide an interface that allows the profile to be specified; obtain a scheduler component via the interface, where the scheduler component identifies a scheduler to be used to perform the job and an application that at least one of the computing devices, that is specified by the scheduler, is to use when performing the job; obtain, via the interface, a project component that identifies data on which the job is to be based; and create the profile based on the scheduler component and the project component.