Storage System Snapshot Generation via Measurement Interval Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional storage systems face inefficiencies in data management and security, particularly in handling security threats and ensuring data integrity across distributed storage nodes, where existing solutions often rely on complex and unreliable mechanisms for data redundancy and failover.
Innovation Solution
The implementation of a storage system that utilizes non-volatile solid state storage units with embedded CPUs and energy reserves to manage data across multiple storage nodes, employing erasure coding and redundancy schemes to ensure data integrity and facilitate proactive rebuilds, while also incorporating a cloud-based monitoring system for enhanced security and data protection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional storage systems use complex redundancy and failover mechanisms, then data reliability is improved, but system complexity increases and reliability decreases due to unreliability of existing solutions
Solution Approach 1:
The storage system is divided into multiple storage nodes, each independently managing its own data segments with local redundancy mechanisms. Each node operates autonomously with embedded CPUs that can detect and respond to failures independently, reducing the complexity of centralized control while maintaining overall system reliability through distributed segmentation.
Solution Approach 2:
Storage nodes are equipped with embedded CPUs and energy reserves that enable them to autonomously detect failures, initiate rebuild operations, and manage their own redundancy without external intervention. The system performs self-diagnosis and self-repair through automated anomaly detection and proactive data rebuilding mechanisms.
2Reliability
If storage systems implement proactive data rebuilding and redundancy management, then data integrity is improved, but processing time and system overhead increase
Solution Approach 1:
The system performs proactive data rebuilding by detecting anomalies in measurement intervals and initiating rebuild operations before actual data loss occurs. Energy reserves are pre-charged in storage nodes to enable immediate rebuild operations without waiting for external power or control signals, reducing the time penalty of redundancy management.
Solution Approach 2:
Traditional mechanical or centralized control-based redundancy management is replaced with software-based anomaly detection algorithms that monitor measurement intervals and trigger automated responses. The embedded CPUs use intelligent algorithms to distinguish between normal variations and actual failures, reducing unnecessary rebuild operations and optimizing processing time.
3Reliability
If storage nodes use embedded CPUs with energy reserves for autonomous operation, then system resilience is improved, but device complexity and energy consumption increase
Solution Approach 1:
Energy reserves are implemented locally at each storage node rather than centrally, allowing nodes to autonomously operate during failures without draining the entire system. Each node maintains just enough energy capacity for critical rebuild operations, optimizing the balance between resilience and energy consumption through localized energy management.
Solution Approach 2:
The system dynamically adjusts energy consumption parameters based on operational conditions. Embedded CPUs monitor system state and modulate energy usage, activating full power only when anomalies are detected and entering low-power modes during normal operation. This parameter adaptation reduces overall energy consumption while maintaining resilience when needed.
Data Source
AI summary
An illustrative method includes a data protection system determining a metric associated with operations performed with respect to a storage system during a measurement interval, determining that the metric deviates by more than a threshold amount from a historical baseline metric associated with the storage system, and directing, based on the determining that the metric deviates by more than the threshold amount from the historical baseline metric, the storage system to generate a recovery dataset for data maintained by the storage system.


