Node Selection System for Dynamic Work Group Resource Borrowing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In computing networks, workload fluctuations across work groups often lead to resource bottlenecks, resulting in increased costs when additional resources are purchased from service providers, as existing methods fail to efficiently manage resource allocation and handle interruptions effectively.
Innovation Solution
A node selection system that predicts idleness durations and runtimes using machine learning models, allowing for the 'borrowing' of nodes from one work group to execute transactions of another, while managing credits and optimizing parallel execution and dependency information to handle interruptions and resource allocation efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If network resources are increased to address workload spikes, then the capacity to handle transactions is improved, but the cost to the company increases
Solution Approach 1:
The patent enables network resources to serve multiple work groups dynamically. A node belonging to a first work group can be borrowed to execute transactions of a second work group when the second work group experiences workload spikes and its dedicated nodes are unavailable. This multi-functionality allows the same physical infrastructure to serve different computational purposes based on real-time demand, improving overall transaction handling capacity without proportionally increasing total resources or cost.
Solution Approach 2:
The system dynamically allocates network resources based on real-time workload conditions. The node selection system continuously monitors the availability and utilization state of nodes across different work groups, and dynamically assigns transactions to appropriate nodes. This dynamic allocation allows the system to adapt to fluctuating workloads, ensuring high transaction handling capacity during peak periods while maintaining cost efficiency by utilizing existing resources rather than provisioning for maximum peak demand.
2Productivity
If nodes are borrowed from one work group to execute transactions of another work group, then resource utilization is optimized, but the complexity of managing node selection and credit systems increases
Solution Approach 1:
The node selection system incorporates feedback mechanisms to manage complexity. It continuously monitors the utilization state of nodes, the availability of dedicated nodes for each work group, and the credit balances of work groups. This feedback information drives automated decision-making in the node selection process, allowing the system to dynamically adjust resource allocation without requiring complex manual management. The feedback loop ensures that borrowed nodes are returned when their original work group needs them, maintaining balance across the system.
Solution Approach 2:
The patent introduces an intermediary node selection system that mediates between work groups and network resources. This intermediary layer handles the complexity of cross-work group node borrowing by implementing a credit-based permission system and automated node selection logic. Instead of work groups directly managing complex resource sharing arrangements, the intermediary system abstracts this complexity, providing a simplified interface where work groups can request transaction execution while the intermediary handles node selection, credit verification, and resource coordination.
3Reliability
If dedicated nodes are used for each work group, then transaction execution reliability is ensured, but resource bottlenecks occur during workload fluctuations
Solution Approach 1:
The patent merges the resource pools of multiple work groups while maintaining logical separation through the node selection system. When a work group has available capacity, its nodes can be combined with nodes from other work groups to form a shared resource pool for executing transactions. This merging approach ensures that each work group maintains reliable dedicated nodes for its primary transactions while also having access to additional combined resources from other work groups during peak periods, thereby eliminating resource bottlenecks without sacrificing execution reliability.
Data Source
AI summary
A computing network includes nodes of different work groups. Nodes of a work group are dedicated to transactions of the work group. If a node of a first work group is predicted to have an idleness window, a second work group may borrow the node to execute a transaction of the second work group. At least a subset of steps of the transaction may be categorized into a step group. Trees of a transaction may be categorized into one or more tree groups. A node is selected for executing a transaction, if the predicted idleness duration of the node is sufficient relative to the predicted runtime of the transaction, the step group, and/or tree group. A credit system is maintained. A first work group transfers a credit to a second work group when borrowing a node of the second work group for executing a transaction of the first work group.