Vehicle Edge Computing Middleware for Latency Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern vehicles face challenges in processing large volumes of data generated by sensors and components, leading to computational burdens on centralized systems, which limits real-time or near-real-time data analysis due to processing constraints and high latency in data offloading.
Innovation Solution
The implementation of a middleware layer to establish an edge computing infrastructure on line-replaceable units (LRUs) within vehicles, utilizing unallocated system resources as edge nodes to distribute computing tasks efficiently, thereby leveraging existing resources without additional hardware and maintaining interaction with external systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If centralized computing resources are used to process large volumes of sensor data, then data processing capability is improved, but processing latency increases and real-time analysis becomes unavailable
Solution Approach 1:
The patent segments the centralized computing architecture into a distributed edge computing infrastructure where computing tasks are divided and assigned to multiple LRUs across the vehicle. Each LRU processes data locally, eliminating the single-point bottleneck and enabling parallel processing, which simultaneously improves processing capability and reduces latency through distributed computation.
Solution Approach 2:
The patent transitions from a single-dimensional centralized processing model to a multi-dimensional distributed architecture. By adding spatial distribution across multiple LRUs positioned throughout the vehicle, the system creates additional processing pathways and parallel computation streams, effectively increasing processing capacity without proportionally increasing latency.
2Productivity
If additional computing hardware is added to increase processing power, then data processing capability is improved, but device complexity and cost increase
Solution Approach 1:
The patent makes existing LRUs multi-functional by enabling them to perform both their original specialized functions and additional edge computing tasks. The middleware layer allows any LRU with unallocated resources to participate in data processing, transforming single-purpose components into versatile computing nodes without adding new hardware.
Solution Approach 2:
The system utilizes unallocated computing resources that already exist within LRUs, allowing the vehicle's existing infrastructure to serve dual purposes. Rather than requiring new dedicated computing hardware, the patent enables current components to self-serve additional computational functions through the edge computing platform.
3Productivity
If centralized computing resources are used, then data processing is centralized, but the system cannot efficiently utilize unallocated resources distributed across LRUs
Solution Approach 1:
The patent introduces a middleware layer as an intermediary between the existing LRU infrastructure and the edge computing tasks. This software intermediary manages resource allocation, task distribution, and coordination across LRUs, enabling efficient utilization of distributed unallocated resources while maintaining a relatively simple underlying hardware architecture.
Data Source
AI summary
A method for managing computing resources on a vehicle with line-replaceable units (LRUs) including respective allocated system resources for tasks the LRUs are designed to perform and respective unallocated system resources that are available is provided. Implementations of the method include identifying the LRUs and applying a middleware layer across the LRUs to establish an edge computing infrastructure in which the LRUs operate as edge nodes. The middleware layer receives information from the edge nodes identifying the unallocated system resources and identifies data sources onboard the vehicle, data provided by those sources, and tasks to be performed using the data. The middleware further determines expected operational performance of the edge computing infrastructure and distributes the tasks to be performed across the edge nodes based on the expected operational performance of the edge computing infrastructure.