Distributed Compute Offloading for XR Battery Life
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Extended reality (XR) systems face challenges with battery life and weight due to the high power consumption of powerful processors and data transmission, making them non-portable and uncomfortable to wear.
Innovation Solution
Implementing a distributed processing system that allows compute offloading by transmitting data to nearby devices for processing, using a discovery message, offloading request, and credit-based incentives to encourage participation, thereby reducing the computational load on the XR device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If powerful processors are used in XR systems to perform feature analysis and complex functions, then processing speed and performance are improved, but power consumption increases and battery life decreases
Solution Approach 1:
The patent segments processing tasks into local execution (for time-critical functions) and remote execution (for computationally intensive tasks). The XR device divides workload between on-device processors and remote servers, transferring only necessary data rather than complete processing loads, thereby extending battery life while maintaining processing speed for critical functions.
Solution Approach 2:
The patent introduces a remote server as an intermediary to handle computationally intensive processing tasks. The server acts as a mediator between the XR device and complex computations, receiving data packets, performing heavy processing (e.g., SLAM, feature matching), and returning results, thereby reducing the power consumption burden on the XR device's battery.
2Power
If powerful processors are included in portable XR devices, then computational capability is improved, but device weight increases and portability decreases
Solution Approach 1:
The patent extracts computationally intensive processing functions from the portable XR device and relocates them to remote servers. By removing heavy processing requirements from the device, the patent enables use of lighter, lower-power processors while maintaining high computational capability through cloud-based processing, thereby improving portability without sacrificing power.
Solution Approach 2:
The patent moves processing capability from the physical dimension (on-device hardware) to the network dimension (remote servers). By leveraging external computational resources accessible through communication networks, the system achieves high processing power without physically embedding heavy processors in the wearable device, thus maintaining portability.
3Duration of action of moving object
If large batteries are included in XR devices to extend battery life, then duration of operation is improved, but device weight increases and comfort decreases
Solution Approach 1:
The patent extracts the battery extension problem from the device itself by implementing compute offloading to remote servers. Instead of solving the battery life issue through larger onboard batteries, the system transfers energy-intensive processing tasks externally, reducing power consumption and enabling lighter battery designs that maintain adequate operational duration.
4Power
If data is transmitted to remote servers for processing, then computational load on the XR device is reduced, but power consumption for data transmission increases
Solution Approach 1:
The patent implements partial offloading where only specific computationally intensive tasks are transferred to remote servers, while time-critical and low-complexity functions remain on-device. This selective approach balances transmission power consumption against local processing savings, ensuring that the energy spent on data transmission is offset by the reduction in local computational load.
Data Source
AI summary
Systems and techniques are provided for distributed processing. For instance, a process can include transmitting a discovery message, receiving a response to the discovery message, the response including an identifier of a neighboring device, transmitting an offloading request to an offloading server, the offloading request including the identifier of the neighboring device, receiving, from the offloading server, an indication that the neighboring device is selected to perform offloaded processing, transmitting data for processing to the neighboring device, receiving, from the neighboring device, processed data, and transmitting an indication of an amount of completed offloaded processing.