Adaptive Power Management for Federated Storage Drives

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Data storage system managers face challenges in reducing electrical consumption without impacting host storage request response times, as they lack statistically significant history of utilization variations for individual drives and struggle to predict overall power consumption due to interacting conditions.

Innovation Solution

Implement a method involving continuous monitoring of individual data storage drive and system electrical usage rates, creating models for usage trends, and automatically switching drives to reduced power modes during predicted low utilization periods based on statistical analysis and client-supplied limits.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If data storage drives are kept in power-on state to ensure availability for host requests, then host storage request response time is maintained, but electrical power consumption increases

Engineering Contradiction:

Improvehost storage request response timeVSAvoidelectrical power consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary actions by continuously monitoring drive utilization patterns and predicting future utilization states before making power state changes. The controller analyzes historical data and projections to determine optimal times to transition drives between power states, ensuring requests are met when needed while saving power during predicted low-utilization periods.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts drive power states based on real-time and historical utilization patterns. The controller continuously adapts power management decisions by analyzing changing utilization trends, allowing the system to respond flexibly to varying demand patterns while optimizing the balance between availability and energy consumption.

Inventive Principle:

Principle #15Dynamics

2Loss of energy

If manual power management decisions are made by system managers, then power consumption can be reduced, but implementation is difficult and decisions are made later than optimum

Engineering Contradiction:

Improveelectrical consumption costVSAvoidimplementation difficulty

Core Design Contradiction:

Loss of energyVSEase of operation

Solution Approach 1:

The system performs self-service by automatically monitoring its own utilization patterns and making power management decisions without human intervention. The controller continuously collects utilization data, analyzes patterns, and autonomously determines optimal power state transitions, eliminating the need for manual management while optimizing energy consumption.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring actual drive utilization and comparing it against predicted patterns. This feedback loop allows the controller to adjust power management decisions based on actual performance, improving accuracy of power state predictions and optimizing energy savings while maintaining service availability.

Inventive Principle:

Principle #23Feedback

3Loss of energy

If individual drive utilization is monitored continuously to predict power state changes, then power consumption optimization is achieved, but system complexity increases

Engineering Contradiction:

Improvepower consumptionVSAvoidmonitoring and analysis system complexity

Core Design Contradiction:

Loss of energyVSDevice complexity

Solution Approach 1:

The system achieves universality by having the controller perform multiple functions: it monitors utilization data, analyzes patterns, predicts future states, and executes power management decisions all within a single integrated component. This multi-functionality reduces overall system complexity compared to having separate dedicated components for each function.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS9846478B1Adaptive power manipulation of federated storage systems

Publication Date: 2017.12.19 EMC IP HLDG CO LLC

AI summary

A technique of automatically managing power consumption by predicting data storage utilization events based upon individual data storage drive utilization history, drive properties, client storage usage and behavior trends is described. The behavior trends may include customer actions, such as reduced weekend and holiday data storage system usage rates. The technique collects operational data and calculates statistical trends in utilization rates for each data storage drive, and for the overall data storage system. The technique automatically switches individual data storage drives to an appropriate power and performance level based upon predicted utilization demand, including shut down and restarts to reduce data storage system power consumption without adversely impacting data storage system performance.