Hybrid Data Analytics Algorithm Segmentation for IoT Edge Cloud

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current data analytics systems in cloud computing face challenges in optimizing the distribution of analytical tasks between local devices and cloud platforms, balancing real-time processing needs with network bandwidth and security considerations, particularly in industrial IoT applications.

Innovation Solution

The system modularizes analytical algorithms into sub-algorithms that can be executed independently or in parallel, with specific affinity indicators determining their optimal execution location between local devices and cloud platforms, allowing for dynamic reassignment based on resource availability and performance requirements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If data analytics is performed on the cloud computing platform, then the quality and speed of data analytics is improved, but network bandwidth consumption increases and real-time processing capability deteriorates

Engineering Contradiction:
Improvedata analytics qualityVSAvoidnetwork bandwidth consumption
Core Design Contradiction:
Measurement precisionVSLoss of energy

Solution Approach 1:

The patent segments the analytical algorithm into multiple sub-algorithms that can be distributed and executed across different locations (local device and cloud platform). This segmentation allows critical real-time processing to occur locally while less time-sensitive analytics are performed in the cloud, thereby improving data analytics quality without proportionally increasing network bandwidth consumption.

Inventive Principle:
Principle #1Segmentation

2Speed

If data analytics is performed at the local device, then real-time processing capability is improved, but data analytics quality and computational power are limited

Engineering Contradiction:
Improvereal-time processing capabilityVSAvoiddata analytics quality
Core Design Contradiction:
SpeedVSMeasurement precision

Solution Approach 1:

The analytical algorithm is divided into sub-algorithms that can be selectively executed at different locations. Time-critical sub-algorithms are executed locally on the device to maintain real-time processing capability, while computationally intensive sub-algorithms are executed on the cloud platform to enhance overall data analytics quality.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a spatial dimension to data analytics by distributing computation across multiple locations (device and cloud). This multi-dimensional execution environment allows the system to simultaneously achieve real-time processing for local sub-algorithms and high-quality analytics for cloud-based sub-algorithms.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Reliability

If analytical algorithms are executed centrally in the cloud computing platform, then intellectual property protection is improved, but device complexity and deployment difficulty increase

Engineering Contradiction:
Improveintellectual property protectionVSAvoiddeployment complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the analytical algorithm into sub-algorithms with different affinity indicators. Sub-algorithms with high cloud affinity are executed centrally in the cloud platform, protecting sensitive intellectual property. Sub-algorithms with low cloud affinity are executed locally, reducing deployment complexity and avoiding the need to deploy entire complex algorithms to each device.

Inventive Principle:
Principle #1Segmentation

4Productivity

If the system uses a hybrid approach with sub-algorithms executed at both device and cloud, then resource utilization is improved, but system complexity increases

Engineering Contradiction:
Improveresource utilizationVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent implements a dynamic execution environment where the system can adaptively assign sub-algorithms to device or cloud based on real-time conditions such as resource availability, data characteristics, and performance requirements. This dynamic approach optimizes resource utilization while managing system complexity through automated decision-making rather than static complex configurations.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3791557B1System for data analytics using a local device and a cloud computing platform
Publication Date: 2024.10.16 SIEMENS AG
  • EP3791557B1 patent drawingFigure 1~2
  • EP3791557B1 patent drawingFigure 3
  • EP3791557B1 patent drawingFigure 4~6

AI summary

The present invention relates to a system for data analytics in a network between one or more local device(s) (130) and a cloud computing platform (120), in which data collected and/or stored on the local device(s) (130) and/or stored on the cloud computing platform (120) are processed by an analytical algorithm (A) which is subdivided into at least two sub-algorithms (SA1, SA2), wherein one sub-algorithm (SA1) is executed on the local device(s) (130) and the other sub-algorithm (SA2) is executed on the cloud computing platform (120).