Hierarchical Data Storage for Vehicle-Embedded Computing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data management solutions for vehicle-embedded computer devices (VECDs) are inadequate for handling large quantities of data, particularly in applications like autonomous driving, vehicle-to-everything (V2X), vehicle-to-infrastructure (V2I), and vehicle-to-vehicle (V2V) services, due to limitations in existing storage solutions and network usage constraints.
Innovation Solution
Implementing a hierarchical data storage system that classifies data based on source, destination, intended use, processing requirements, and delivery time, using different storage devices such as DRAM, 3D Xpoint SSDs, SATA SSDs, and cloud storage to optimize storage efficiency and speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If cloud-based storage and processing are used, then data storage capacity is improved, but response time becomes too slow for vehicle-based services
Solution Approach 1:
The patent divides the storage system into multiple segments: local storage devices (SSDs, HDDs) for immediate data access and cloud storage for long-term archival. This segmentation allows time-critical data to be stored locally for fast access while less time-sensitive data is stored in the cloud, resolving the contradiction between storage capacity and response time.
Solution Approach 2:
The patent introduces an intermediary layer (local storage devices and edge computing platforms) between the vehicle sensors and the cloud storage. This intermediary enables fast local processing and storage of time-critical data while still utilizing cloud storage for capacity, thereby mediating the conflict between speed and capacity.
2Speed
If solid state drives and persistent memories are used instead of hard disk drives, then data access speed is improved, but storage capacity and cost-effectiveness deteriorate
Solution Approach 1:
The patent applies local quality by assigning different storage media to different data types and access patterns. High-speed SSDs and persistent memories are used for frequently accessed and time-critical data, while lower-cost HDDs are used for bulk storage of less frequently accessed data. This resolves the contradiction by optimizing the speed-capacity tradeoff at different locations in the storage hierarchy.
Solution Approach 2:
The storage system is segmented into multiple tiers with different performance and cost characteristics. The patent divides storage into fast but expensive local storage (SSDs, persistent memory) and slower but cheaper bulk storage (HDDs, cloud storage), allowing the system to achieve both high speed for critical data and high capacity for bulk data.
3Quantity of substance
If compression algorithms and timestamps are used for data management, then storage efficiency is improved, but data quality and retrieval accuracy deteriorate
Solution Approach 1:
The patent applies different data management strategies to different data types based on their quality requirements. For data where quality is critical (sensor data for autonomous driving), the system uses minimal compression and preserves full fidelity. For less critical data (log files, historical records), more aggressive compression is applied. This resolves the contradiction by matching compression levels to data quality requirements.
Data Source
AI summary
Systems, apparatus, and computer-readable media for managing data storage for vehicle-embedded computer devices (VECDs) are disclosed. Embodiments include a data hierarchy, which classifies data based on the data source, data destination, the intended use of the data or a target application, data processing requirements of the data, and/or delivery time requirements of the data. A VECD may classified obtained data according to the hierarchy and may store the data in different storage devices based on the classification of data. Other embodiments are described and/or claimed.