Graph-Based Data Analysis for IoT Sensor Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing volume of data generated by IoT devices poses a challenge for traditional systems, which struggle to efficiently store, process, and analyze this data due to limited capacity, leading to unnecessary network usage and resource expenditure, and lack of scalability.
Innovation Solution
A graph-based analysis method is implemented, where data from IoT devices is organized into a graphical representation, allowing for efficient data visualization, analysis, and alert generation, determining typical operating modes and identifying deviations in real-time without the need for extensive processing, thereby reducing storage and processing demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If traditional centralized systems collect and store raw data from IoT devices, then data storage capacity must increase to accommodate growing data volumes, but this leads to unnecessary expenditure of network capacity, storage space, and computing resources
Solution Approach 1:
The system performs preliminary analysis at the edge devices before data transmission. Each IoT device locally analyzes its own operational data and only transmits condensed results (e.g., minimum, maximum, average values) when changes exceed predefined thresholds. This preliminary processing eliminates the need to transmit and store complete raw data sets, reducing network capacity consumption and centralized storage requirements while maintaining data integrity for analysis purposes
Solution Approach 2:
The system extracts only the essential features from raw IoT data by implementing local analysis algorithms that identify and transmit only meaningful changes in operational parameters. Instead of transmitting all raw sensor readings, each device extracts and communicates only the critical information that indicates state changes or anomalies, thereby reducing the quantity of data that needs to be stored and processed centrally
2Measurement precision
If sampling rate of IoT devices is increased to capture more operational data, then measurement precision improves, but the volume of data generated increases rapidly
Solution Approach 1:
The system implements different processing strategies at different levels of the data hierarchy. At the device level, high-resolution local measurements are maintained for precise operational monitoring and immediate decision-making. At the centralized level, only aggregated and condensed data representations are stored and analyzed. This local quality differentiation allows high sampling rates to be maintained at the source while the overall data volume in the system remains manageable
Solution Approach 2:
Data condensation and filtering operations are performed preliminarily at the edge devices before data leaves the local system. The devices maintain high-resolution local records for precise measurement while pre-processing the data to extract only essential information for centralized storage, thereby preserving measurement precision locally while controlling overall data volume
3Loss of information
If all raw data from IoT devices is transmitted to central servers, then data completeness is improved, but network capacity and processing resources are unnecessarily consumed
Solution Approach 1:
The system extracts and transmits only the essential features from complete raw data sets. Each IoT device performs local analysis to identify meaningful changes in operational parameters and transmits only these extracted features (such as threshold exceedances, statistical summaries, or anomaly detections) to the central server. This extraction process maintains data completeness for analysis purposes while eliminating redundant information that would consume network and processing resources
Solution Approach 2:
Preliminary data processing and filtering are performed at the edge devices before transmission. The devices maintain complete local data records for immediate operational needs while pre-processing and condensing the information before centralized transmission. This preliminary action ensures that data completeness is preserved locally for real-time operations while network-transmitted data is optimized for centralized storage and historical analysis
Data Source
AI summary
Techniques are described for graph-based analysis of data generated on sensor networks, such as Internet-of-Things (IoT) networks. Data may be collected from various computing devices, or sensors, on a network. The data is discretized and analyzed to provide a graphical representation of at least a portion of the data. In some instances, the graph may be determined based on various relationships between nodes that correspond to discrete portions of the data, and the relationships between nodes may be time-based correlations between the data of the nodes. The graph accumulates, compresses, and organizes the data to enable efficient data visualization, analysis, alert generation, and/or other activities. A previously generated version of a graph may be compared to a current version to identify a changing situation, such as new usage of the monitored devices, failure or anomalous behavior of the devices, and so forth.