Wireless Neural Network Scheduling for Lower Device Power

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The increasing complexity of wireless communication devices strains battery life due to power requirements, necessitating improved management of neural network processing resources to maintain accurate signal transmission and reception.

Innovation Solution

Wireless devices determine their neural network processing capability and communicate this information to a cellular base station, allowing the base station to schedule tasks accordingly, prioritize tasks, and manage occupancy time to optimize resource use.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If neural network processing capability is increased to maintain communication accuracy, then signal transmission and reception accuracy is improved, but power consumption increases

Engineering Contradiction:

Improvesignal transmission and reception accuracyVSAvoidpower consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system dynamically adjusts neural network processing based on occupancy time indicators. The base station determines occupancy time for neural network processing units and schedules tasks accordingly, allowing the processing capability to be activated only when needed rather than continuously operating at full capacity

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system uses periodic occupancy time indicators to trigger neural network processing tasks. Instead of continuous processing, the base station schedules tasks at specific periodic intervals based on the determined occupancy time, reducing overall power consumption while maintaining accuracy when required

Inventive Principle:

Principle #19Periodic action

2Productivity

If neural network processing tasks are scheduled beyond device capability, then task completion speed is improved, but processing reliability deteriorates

Engineering Contradiction:

Improvetask completion speedVSAvoidprocessing reliability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system implements feedback through occupancy time indicators that provide information about current processing unit availability. The base station uses this feedback to adjust scheduling decisions, ensuring tasks are assigned only when processing capacity is available, thus maintaining both speed and reliability

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The base station determines occupancy time in advance before scheduling neural network processing tasks. This preliminary action ensures that task scheduling is based on predicted available capacity, preventing overload and maintaining processing reliability while optimizing completion speed

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250287196A1Neural Network Processing Management

Publication Date: 2025.09.11 APPLE INC

AI summary

This disclosure relates to techniques for managing neural network processing resources in a wireless communication system. A wireless device and a cellular base station can establish a wireless link. The wireless device can determine its neural network processing capability. The wireless device can provide neural network processing capability information to the cellular base station. The cellular base station can determine whether and when to configure activities that use neural network processing for the wireless device based at least in part on the neural network processing capability information for the wireless device.