AI-Based Task Allocation in Computing Power Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The construction of computing power networks is hindered by high costs due to the separation of network and computing power infrastructure, requiring additional hardware for computing power cards or servers.
Innovation Solution
An artificial intelligence-based method that allocates tasks to clusters based on predicted idle computing power resources, utilizing existing base band units (BBUs) to optimize resource allocation without the need for additional hardware, by determining clusters matched with task and application requirements through orchestration and scheduling models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If independent computing power cards or dedicated computing servers are added to network equipments, then computing power network construction is enabled, but construction cost increases
Solution Approach 1:
The patent makes network equipment perform both network processing and computing tasks by integrating computing power capabilities into existing base band units. The same hardware infrastructure serves dual purposes: traditional network functions and AI computing workloads, eliminating the need for separate dedicated computing servers and reducing overall construction costs.
Solution Approach 2:
The system utilizes idle computing power resources within existing network equipment to provide computing services. By orchestrating and scheduling available computing resources from base band units, the network infrastructure serves itself for computing tasks without requiring additional external computing hardware, thereby reducing construction costs.
2Productivity
If idle computing power resources are utilized through orchestration and scheduling, then resource allocation efficiency improves, but system complexity increases
Solution Approach 1:
The patent introduces an orchestration and scheduling system that acts as an intermediary between computing power supply (base band units with idle resources) and computing power demand (AI tasks). This mediator manages resource allocation, matches tasks with suitable computing resources, and coordinates execution, thereby improving resource allocation efficiency while managing system complexity through a dedicated control layer.
Solution Approach 2:
The system dynamically adjusts scheduling parameters and resource allocation based on real-time computing power availability and task requirements. By changing operational parameters such as resource allocation ratios, scheduling priorities, and matching criteria, the system optimizes resource utilization efficiency while adapting to varying workload conditions without requiring fundamental system restructuring.
Data Source
AI summary
Embodiments of the present disclosure provide an artificial intelligence-based data processing method and apparatus, and relate to the technical field of a computing power network. The method includes: in response to at least one task request for a target application, acquiring at least one task respectively corresponding to the at least one task request; determining a second cluster respectively corresponding to each task from at least one first cluster corresponding to the target application, based on task information respectively corresponding to each task; and for each task, allocating the task to the second cluster corresponding to the task so that the second cluster performs the task based on a calculation computing power resource.