Distributed Resource Management via Attribute Element Sets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In large-scale computing environments, efficiently scheduling workloads across distributed resources becomes time-consuming due to the need to consider thousands of resources with varying hardware, software, locations, and statuses, leading to performance trade-offs.
Innovation Solution
A distributed resource management system uses resource attribute element sets to identify candidate resources by performing element-wise operations on requested attributes, reducing the search space and scheduling time while ensuring all suitable resources are evaluated.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional workload scheduling evaluates all resources in the system, then resource selection accuracy is improved, but scheduling time increases significantly
Solution Approach 1:
The patent segments the resource evaluation process into two distinct phases: (1) rapid filtering phase that uses attribute element sets to quickly identify candidate resources meeting basic criteria, and (2) detailed evaluation phase that performs comprehensive assessment only on the filtered candidate set. This segmentation allows the system to maintain high resource selection accuracy while dramatically reducing overall scheduling time by avoiding exhaustive evaluation of all resources.
Solution Approach 2:
The patent implements preliminary action by pre-computing and maintaining attribute element sets for all resources before scheduling decisions are needed. These attribute element sets contain pre-processed resource characteristics that enable rapid filtering. When a scheduling request arrives, the system can immediately perform the filtering operation without time-consuming data collection and processing, thus resolving the contradiction between thorough evaluation and fast scheduling.
2Adaptability or versatility
If the system considers all resources with varying hardware, software, locations, and statuses, then scheduling completeness is improved, but system complexity increases
Solution Approach 1:
The patent transforms the complex, multi-dimensional resource description problem into a simplified parameter-based filtering problem. By representing resources as collections of attribute element sets with specific parameters (hardware type, software version, location, status), the system can efficiently query and filter resources based on scheduling requirements without being overwhelmed by the underlying complexity of individual resource configurations.
Solution Approach 2:
The patent introduces attribute element sets as an intermediary layer between the raw resource data and the scheduling decision-making process. This intermediary structure standardizes and organizes resource information, enabling efficient comparison and filtering operations while abstracting away the complexity of heterogeneous resource configurations from the scheduling logic.
3Productivity
If the system reduces the number of candidate resources considered, then scheduling speed is improved, but resource evaluation thoroughness decreases
Solution Approach 1:
The patent segments the resource set into three categories: (1) resources that definitely do not meet requirements (filtered out using attribute element sets), (2) candidate resources that potentially meet requirements (retained for detailed evaluation), and (3) resources not yet evaluated. This segmentation ensures that while the number of resources undergoing time-consuming detailed evaluation is reduced, the filtering process itself is thorough and accurate, preventing loss of suitable resources.
Solution Approach 2:
The patent performs preliminary filtering action using pre-computed attribute element sets before the detailed resource evaluation process. This preliminary action eliminates obviously unsuitable resources in advance, allowing the system to focus computational resources on thoroughly evaluating only the candidate resources that have a genuine chance of meeting the scheduling requirements, thus maintaining evaluation thoroughness while improving speed.
Data Source
Figure 1
Figure 2
Figure 3A~3B
AI summary
Methods and systems of managing a resource in a distributed resource management system can include: receiving a resource request including data identifying at least one requested resource attribute; identifying one or more candidate resources from a plurality of resources by performing element-wise operations on one or more resource attribute element sets corresponding to the at least one requested resource attribute, each resource attribute element set comprising an element for each of the plurality of resources, each element representing a resource attribute for a respective resource of the plurality of resources; and scheduling a workload associated with the resource request for execution based on the one or more identified candidate resources.