Network Batch Scheduling with Model-Based Launch Times

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing communication systems face challenges in optimizing the scheduling of multiple data flows to minimize execution time duration and improve throughput and reduce latency.

Innovation Solution

A network entity determines launch times for batches of data flows based on a data flow model to minimize execution time duration, using processors to schedule these flows accordingly.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If data flows are scheduled using conventional methods, then network connectivity is maintained, but execution time duration is not minimized and throughput is not optimized

Engineering Contradiction:

ImprovethroughputVSAvoidexecution time duration

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by determining launch times for batches of flows before actual data transfer begins. The network entity calculates optimal launch times based on data flow models, allowing flows to be prepared and scheduled in advance, thereby minimizing execution time duration and maximizing throughput when the batches are executed.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If multiple batches of flows are transmitted simultaneously, then network resource utilization increases, but execution time duration increases and latency increases

Engineering Contradiction:

Improvenetwork resource utilizationVSAvoidlatency

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system dynamically determines optimal launch times for different batches of flows based on real-time network conditions and data flow models. Rather than fixed scheduling, the network entity adjusts launch times dynamically to minimize latency while maintaining high resource utilization, allowing flexible optimization of the trade-off between concurrent transmission and execution time.

Inventive Principle:

Principle #15Dynamics

3Device complexity

If launch times are determined without considering data flow models, then scheduling is simpler, but execution time duration cannot be minimized

Engineering Contradiction:

Improvescheduling complexityVSAvoidexecution time duration

Core Design Contradiction:

Device complexityVSLoss of time

Solution Approach 1:

The system uses data flow models as feedback mechanisms to determine optimal launch times. The network entity continuously references the data flow model to understand network conditions, flow characteristics, and bottlenecks, thereby determining launch times that minimize execution time duration while managing scheduling complexity through model-guided decision making.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12388764B2Multiple batch scheduling in a network

Publication Date: 2025.08.12 QUALCOMM INC

AI summary

Various aspects of the present disclosure generally relate to wired and/or wireless communication. In some aspects, a network entity may determine, based at least in part on a data flow model, a respective launch time for each flow of a first batch of flows and for each flow of a second batch of flows, such that an execution time duration for transferring at least one of the first batch of flows and the second batch of flows in a portion of a network is minimized. The network entity may schedule the first batch of flows and the second batch of flows based at least in part on the respective launch times. Numerous other aspects are described.