Distributed Computing Grid Task Partitioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current distributed computing systems face inefficiencies and resource consumption issues, particularly in cloud computing, as they rely heavily on centralized servers, leading to high energy costs and environmental impact due to cooling requirements.
Innovation Solution
A method and system for distributed computing that utilizes a customer platform to split computational jobs into chunks and distribute them across user devices such as personal computers, smartphones, and smart TVs, allowing for efficient task execution and heat dissipation without the need for extensive cooling systems, while ensuring reliability and timely job results through proactive task replication and assignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If centralized cloud servers are used for distributed computing, then computing power and resource availability are improved, but energy consumption and cooling requirements increase significantly
Solution Approach 1:
The patent segments the centralized cloud computing architecture into distributed edge computing nodes deployed across multiple locations. Each edge device performs local computations, dividing the overall computing workload across many small units rather than one large centralized server, thereby reducing the energy consumption and cooling requirements of any single stationary object while maintaining total computing power.
2Loss of energy
If computational jobs are distributed across user devices, then resource consumption is reduced, but system complexity and coordination overhead increase
Solution Approach 1:
The patent introduces an intermediary coordination layer that manages task distribution, monitoring, and result aggregation across distributed user devices. This intermediary system handles the complexity of coordinating numerous edge devices, providing a simplified interface for job submission and result retrieval, thereby managing system complexity without increasing resource consumption at the edge devices.
3Productivity
If job data is split and distributed to multiple user devices, then processing efficiency is improved, but data transmission and task management overhead increase
Solution Approach 1:
The patent performs preliminary actions by pre-processing job data into appropriate chunks, pre-configuring task descriptors, and pre-establishing communication channels before distributing to user devices. This preliminary preparation reduces the overhead during actual execution, as devices receive ready-to-execute tasks with all necessary information, minimizing the time lost to task management and data preparation at the edge.
Data Source
AI summary
A method and a system for high-throughput distributed computing of computational jobs, comprise setting up a data storage system and a grid of user devices that offer computational capacity. Customer entities upload in a customer platform first job specification parameters, and then the full job data. A partitioning scheme is selected based on the job specification and on the grid status, that is periodically updated by querying the user devices. Based on the partitioning scheme, the job data are split on the fly in input chunks, that are included in executable tasks and assigned to different user devices. To this end, devices may be selected based on computing capacity and availability parameters, and on a priority level selected for the job. Output chunks are generated by executing the tasks, and after verification of timely arrival of all the required output chunks, they are assembled as a complete job result, for download by the customer.