Task Dependency Graph Scheduling for Computing Servers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless communication systems face challenges in efficiently scheduling computing tasks across computation servers to minimize latency and optimize processing time, especially in 5G communication systems where ultra-low latency services are required for applications like augmented reality and virtual reality.
Innovation Solution
A control server is introduced to schedule computing tasks based on task dependency graphs, computation processing capacity information, and transmission latency between servers, allowing for parallel processing across multiple computation servers to reduce overall processing time and latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If computing tasks are scheduled across multiple computation servers, then processing throughput and resource utilization are improved, but scheduling complexity increases
Solution Approach 1:
The patent segments the computing task into multiple sub-tasks that can be independently scheduled and executed on different computation servers. The task dependency graph divides the overall task into hierarchical levels, where each level contains tasks that can be processed in parallel. This segmentation enables distributed processing across multiple servers, improving throughput while maintaining manageable scheduling complexity through structured task division.
Solution Approach 2:
The patent introduces a temporal dimension to the scheduling problem by organizing tasks into levels based on their execution order and dependencies. Tasks at the same level can be executed in parallel, creating a multi-dimensional scheduling space (spatial distribution across servers + temporal ordering of levels). This dimensional approach transforms the complex scheduling problem into a more manageable structure where parallel execution is naturally facilitated.
2Device complexity
If tasks are executed sequentially on a single server, then scheduling complexity is reduced, but processing time increases
Solution Approach 1:
By segmenting the computing task into independent sub-tasks organized in a dependency graph, the patent enables parallel execution on multiple servers simultaneously. This segmentation transforms the single-server sequential processing model into a multi-server parallel processing model, significantly reducing processing time while maintaining scheduling manageability through the structured task hierarchy.
Solution Approach 2:
The patent performs preliminary analysis to build the task dependency graph before execution, identifying all tasks and their dependencies in advance. This preliminary action allows the system to pre-determine the optimal execution order and parallelization strategy, enabling efficient parallel processing without complex runtime scheduling decisions. The preprocessing step reduces runtime complexity while maximizing parallel execution benefits.
3Productivity
If tasks are distributed across multiple servers, then processing capacity is improved, but transmission latency increases
Solution Approach 1:
The patent applies local quality by optimizing task allocation based on server-specific characteristics and task-specific requirements. Tasks are distributed to servers that best match their computational needs, and data transmission is optimized by keeping related tasks on the same or nearby servers. This localized optimization reduces unnecessary data transmission distances while maintaining the benefits of distributed processing capacity.
Solution Approach 2:
The patent merges tasks that have dependency relationships into the same computation server whenever possible, eliminating the need for inter-server data transmission between dependent tasks. By combining related tasks on a single server, the system reduces transmission latency while still utilizing multiple servers for independent task parallelization, thus maintaining processing capacity without the penalty of increased transmission delays.
Data Source
AI summary
The disclosure relates to a method and a control server for scheduling a computing task including a plurality of tasks to be performed by computation servers. The control server according to some embodiments includes: a transceiver; a memory; and at least one processor configured to receive the computing task from a terminal, generate a task dependency graph based on a dependency relationship of each of the plurality of tasks included in the computing task, obtain computation processing capacity information of each of the plurality of computation servers and information of transmission latency between the plurality of computation servers, schedule the plurality of tasks to be performed by at least two computation severs of the plurality of computation servers, based on the task dependency graph, the computation processing capacity information, and the information of transmission latency, and transmit, to the terminal, an execution result of the plurality of tasks received from at least one of the plurality of computation servers.