Dynamic Computing Resource Allocation via ML Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Coordinating the use of computing resources among multiple users or tasks is challenging, particularly in environments where users may perform both computationally intensive and non-intensive tasks simultaneously, leading to inefficiencies and waiting times.
Innovation Solution
A method and system that utilize machine learning to create models for allocating computing resources based on user data, including calendar information and sensor data, to optimize resource allocation across cloud, edge, and local computing environments, incorporating feedback loops for model improvement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If computing resources are shared among multiple users and tasks, then resource utilization efficiency is improved, but coordination difficulty and waiting time increase
Solution Approach 1:
The system continuously monitors computing resource usage, task progress, and user preferences, then uses this feedback to dynamically adjust resource allocation decisions. This closed-loop control enables the system to adapt to changing conditions and optimize coordination among multiple users and tasks, resolving the contradiction between shared resource efficiency and coordination complexity
Solution Approach 2:
The patent implements dynamic resource allocation where computing resources are not statically assigned but continuously reallocated based on real-time system state, task priorities, and user needs. This dynamic approach allows the system to handle multiple users and tasks efficiently while adapting to changing coordination requirements, thus improving resource utilization without proportionally increasing coordination difficulty
2Speed
If computing resources are allocated to computationally intensive tasks, then task completion speed is improved, but waiting time for other tasks increases
Solution Approach 1:
The system allocates computing resources partially to multiple tasks rather than fully to a single task. By distributing resources across several tasks simultaneously based on their priorities and requirements, the system enables progress on multiple fronts, reducing overall waiting time while still making meaningful progress on computationally intensive tasks
Solution Approach 2:
The patent implements periodic reevaluation and reallocation of computing resources among tasks. Instead of dedicating resources to one task until completion, the system periodically reassesses task priorities and redistributes resources, ensuring that computationally intensive tasks receive adequate resources for fast completion while other tasks also progress, thereby balancing task completion speed with reduced waiting time
Data Source
AI summary
The exemplary embodiments disclose a method, a computer program product, and a computer system for allocating computing resources. The exemplary embodiments may include collecting data of one or more users, wherein the collected data comprises calendar data of the one or more users, extracting one or more features from the collected data, and allocating one or more computing resources to one or more of the users based on the extracted one or more features and one or more models.