Cognitive Device Management Using AI for Telemetry Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional approaches to telemetry data collection in data centers use a fixed frequency, leading to inefficient resource usage and inadequate data collection, as jobs may run too frequently or too infrequently across all devices.

Innovation Solution

Implementing cognitive device management using artificial intelligence, which determines an initial telemetry data collection frequency through machine learning techniques, collects and compares data sets, and updates the frequency based on neural network analysis to optimize data collection and initiate automated actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If a fixed frequency is used for telemetry data collection across all devices, then the system is simple to implement, but resource efficiency deteriorates and data collection adequacy worsens

Engineering Contradiction:

Improveimplementation simplicityVSAvoidresource efficiency

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The patent transforms the static fixed-frequency approach into a dynamic adaptive system where the telemetry data collection frequency automatically adjusts based on real-time device conditions, event types, and historical patterns. The system continuously learns from incoming data streams and modifies collection rates to optimize resource efficiency while maintaining data adequacy.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the frequency parameter dynamically based on device state, event severity, and historical analysis. Different devices and different time periods receive different frequency values, allowing the system to adapt to varying conditions and optimize both resource usage and data collection quality.

Inventive Principle:

Principle #35Parameter changes

2Loss of information

If telemetry data collection frequency is increased, then data collection adequacy improves, but system resource consumption increases

Engineering Contradiction:

Improvedata collection adequacyVSAvoidsystem resource consumption

Core Design Contradiction:

Loss of informationVSUse of energy by moving object

Solution Approach 1:

The patent applies different data collection frequencies to different devices, device components, and data types based on their specific characteristics and importance. Critical devices or critical data fields receive higher frequency collection, while less critical elements receive lower frequency collection, optimizing the balance between data adequacy and resource consumption.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system collects data at high frequency only when necessary (e.g., during anomalies, critical events, or for high-priority devices), and reduces frequency during normal operation. This partial action approach ensures adequate data collection for critical situations while minimizing resource consumption during stable periods.

Inventive Principle:

Principle #16Partial or excessive action

3Use of energy by moving object

If telemetry data collection frequency is decreased, then system resource consumption reduces, but data collection adequacy deteriorates

Engineering Contradiction:

Improvesystem resource consumptionVSAvoiddata collection adequacy

Core Design Contradiction:

Use of energy by moving objectVSLoss of information

Solution Approach 1:

The system continuously monitors incoming telemetry data for anomalies, patterns, and critical events, using this feedback to dynamically adjust collection frequency. When the system detects unusual conditions or potential issues, it automatically increases data collection frequency to ensure adequate monitoring, while maintaining lower frequencies during normal operation to conserve resources.

Inventive Principle:

Principle #23Feedback

4Ease of operation

If a single fixed frequency is used for all devices, then device management is simplified, but adaptability to different device conditions deteriorates

Engineering Contradiction:

Improvedevice management simplicityVSAvoidadaptability to device conditions

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent implements a universal adaptive frequency determination system that automatically adjusts parameters based on device type, condition, and operational context. The same system framework handles diverse device conditions by dynamically selecting appropriate frequency values, providing both simplicity of management and adaptability to specific device requirements.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11410034B2Cognitive device management using artificial intelligence

Publication Date: 2022.08.09 EMC IP HLDG CO LLC

AI summary

Methods, apparatus, and processor-readable storage media for cognitive device management using artificial intelligence are provided herein. An example computer-implemented method includes determining an initial telemetry data collection frequency value for a given device by applying machine learning techniques to historic data pertaining to additional devices; collecting an initial set of telemetry data associated with the given device and one or more subsequent sets of telemetry data associated with the given device in accordance with the initial telemetry data collection frequency value; performing a comparison of the one or more subsequent sets of telemetry data to the initial set of telemetry data; updating the initial telemetry data collection frequency value by applying the machine learning techniques to information resulting from the comparison; determining automated actions related to the given device by utilizing a neural network in connection with the collected telemetry data; and automatically initiating the automated actions.