Mobile Data Storage Units for Petabyte Archive
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage technologies are inadequate to handle the rapid growth of machine-generated data, which is large, immutable, and persistent, leading to high costs and inefficiencies in storage, retrieval, and analysis, particularly in environments with limited resources and infrastructure.
Innovation Solution
A method and system utilizing mobile data storage units connected in a peer-to-peer network for efficient collection, storage, and analysis of large amounts of data, allowing for real-time data processing and seamless integration into enterprise data warehouses, with features like self-management, self-healing, and self-replication, and the ability to handle petabytes of data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional data storage architectures are used, then data can be stored centrally, but the system cannot scale to handle the increase in information and network transfer capacity is too small to move massive amounts of data with acceptable latency
Solution Approach 1:
The patent divides the centralized storage system into distributed mobile data storage units that operate independently. Each unit is a self-contained segment capable of storing and processing data locally, eliminating the need for a single centralized repository and reducing network dependency.
Solution Approach 2:
The patent transitions from a two-dimensional centralized storage model to a multi-dimensional distributed network where data can be accessed from multiple locations simultaneously. This adds spatial and temporal dimensions to data access, allowing parallel operations across multiple mobile units.
2Ease of operation
If data is transferred to a central location for processing and storage, then centralized management is achieved, but network transfer capacity is insufficient to move massive amounts of data with acceptable latency
Solution Approach 1:
The patent implements preliminary indexing and metadata tagging of data before it needs to be accessed. Mobile data storage units maintain local indexes and can pre-process data, so when queries are issued, results can be retrieved quickly without transferring entire datasets across the network.
Solution Approach 2:
The patent introduces mobile data storage units as intermediary nodes between data sources and end users. These units act as local repositories that can serve data requests without requiring constant communication with a central server, reducing network latency while maintaining manageable access patterns.
3Speed
If more network infrastructure is deployed to increase transfer capacity, then data movement capability improves, but cost and infrastructure requirements increase significantly
Solution Approach 1:
The patent extracts the storage and processing functions from the network infrastructure and embeds them directly into mobile data storage units. This removes the dependency on high-capacity network infrastructure for data movement, as data remains stationary in local units and is accessed through wireless connections when needed.
4Quantity of substance
If traditional storage systems are used, then data can be stored, but the cost of storage, retrieval and analysis becomes expensive and prohibitive
Solution Approach 1:
The patent employs mobile data storage units that can be deployed, used, and replaced economically. These units use cost-effective storage media and can be disposed of or recycled after their service life, avoiding the high capital expenditure associated with traditional enterprise-grade storage systems.
Data Source
AI summary
A scalable network of mobile data storage containers that are connected in peer-to-peer networks to archive large data storage capacities. The various embodiments provide a method of extracting a large amount of data from a variety of sources and storing the extracted data in mobile, storage units. The various embodiments provide storage units housed in mobile containers that can store multiple days/weeks of sensor data in the order of petabytes (1024 terabytes). The various embodiments, integrate high performance computing devices into the mobile storage containers that are able to perform critical extraction, pattern, and index processing on the sensor data. The various embodiments, provide a method for the efficient physical transport of the mobile storage containers from current locations to a center analysis location for re-connecting in another peer-to-peer network for integration into a central enterprise data warehouses.