Dynamic Resource Reallocation for Sensor Data Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing stream-based sensor networks face inefficiencies in resource utilization and data processing due to centralized data warehouse approaches, which lead to high transmission costs and underutilization of processing resources, while decentralized querying is limited by low-capability edge devices, and prior solutions fail to adapt to varying network conditions and query rate variations.

Innovation Solution

A method for dynamic reallocation of data processing resources that determines optimal operator placement and caching within the network to minimize communication, computation, and storage costs, using a system with nodes equipped for data transmission, processing, and storage cost modules, and query minimization, allowing for stochastic query anticipation and varying query frequencies.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a centralized data warehouse approach is used to store and process sensor data, then data storage and processing capabilities are improved, but data transmission costs increase and processing resources within the network are underutilized

Engineering Contradiction:

Improvedata storage and processing capabilityVSAvoiddata transmission cost

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The patent segments the centralized data processing function into distributed processing units deployed across multiple network nodes. Instead of consolidating all processing at a central warehouse, the system divides processing tasks and data storage across geographically distributed nodes, enabling local processing while maintaining data availability and reducing the need to transmit all data to a central location.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent implements local processing capabilities at distributed network nodes, allowing each node to process and filter data locally before transmission. This local quality enhancement reduces the volume of data that needs to be transmitted across the network while maintaining comprehensive data processing and storage capabilities through the distributed architecture.

Inventive Principle:

Principle #3Local quality

2Loss of energy

If queries are pushed to remote sensors for processing, then bandwidth efficiency is improved, but the low capability and reliability of edge devices limits processing effectiveness

Engineering Contradiction:

Improvebandwidth efficiencyVSAvoidprocessing capability

Core Design Contradiction:

Loss of energyVSReliability

Solution Approach 1:

The patent segments the query processing function across multiple levels of the distributed network architecture. Instead of pushing all queries to individual remote sensors, the system divides processing tasks among edge devices, intermediate processing nodes, and central coordination services, allowing complex queries to be handled by more capable nodes while simpler processing occurs at the edge.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediary processing nodes that act as mediators between remote sensors and central processing systems. These intermediary nodes receive queries, determine which sensors need to be queried, coordinate the data collection, and aggregate results, thereby reducing the processing burden on individual low-capability edge devices while maintaining bandwidth efficiency.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Device complexity

If operator locations are pre-defined to simplify system design, then device complexity is reduced, but the system cannot adapt to varying network conditions and query rates

Engineering Contradiction:

Improveoperator placement simplicityVSAvoidadaptability to network conditions

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic operator placement that automatically adapts to varying network conditions and query patterns. Instead of pre-defining fixed operator locations, the system continuously monitors network state, query rates, and resource availability, then dynamically relocates processing operators to optimal positions across the distributed network, balancing simplicity of operation with high adaptability.

Inventive Principle:

Principle #15Dynamics

4Loss of information

If all sensor data is transmitted to the central data warehouse, then complete data availability is improved, but transmission costs increase and network resources are wasted

Engineering Contradiction:

Improvedata availabilityVSAvoidtransmission cost

Core Design Contradiction:

Loss of informationVSLoss of energy

Solution Approach 1:

The patent extracts and processes data locally at distributed network nodes before transmission to the central warehouse. Instead of transmitting all raw sensor data, the system extracts only the relevant information that has not been processed or filtered locally, thereby maintaining complete data availability for queries while significantly reducing transmission costs and network resource consumption.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS7710884B2Methods and system for dynamic reallocation of data processing resources for efficient processing of sensor data in a distributed network

Publication Date: 2010.05.04 X CORP

AI summary

Methods and system for dynamic reallocation of data processing resources for efficient processing of sensor data in a distributed network is provided. The methods and system include determining a data transmission cost ft; determining a data processing cost fp; determining a data storage cost fs; and determining a data query Q which minimizes f(ft+fp+fs) for a system of networked data processing resources.