Distributed Load Processing Using Sampled IoT Clusters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The exponential growth of IoT devices leads to an astronomical amount of data exchange, causing significant data communication challenges, and existing methods fail to efficiently utilize geographical proximity and spare compute cycles for workload processing, resulting in excessive packet transmissions.
Innovation Solution
A method for distributed load processing using sampled clusters of location-based IoT devices, where a central device identifies and configures nearby IoT devices to form clusters, leveraging spare compute cycles for workload processing, thereby reducing data communications by forming localized clusters based on geographical proximity and resource availability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If distributed processing using sampled clusters of location-based IoT devices is implemented, then data communication overhead is dramatically reduced, but system complexity increases due to cluster management and device selection algorithms
Solution Approach 1:
The system segments the IoT device population into geographically proximate clusters based on their proximity to data sources. Each cluster is independently managed and processed, allowing parallel computation and reducing the need for global communication across all devices. This segmentation reduces communication overhead while distributing computational load across multiple manageable clusters.
Solution Approach 2:
The patent implements local quality by selecting IoT devices based on their geographical proximity to specific data sources. Each cluster is composed of devices locally optimized for processing particular data sources, creating heterogeneity in cluster composition based on spatial relationships. This local optimization reduces communication distance and data transmission requirements.
2Productivity
If more IoT devices are selected to form clusters, then workload processing capacity increases, but data communication overhead increases due to more devices needing to coordinate
Solution Approach 1:
The system employs sampling techniques to select a representative subset of IoT devices from the available pool, rather than utilizing all potential devices. This partial action approach forms clusters with sufficient processing capacity to handle workloads effectively, while avoiding the communication overhead that would result from coordinating a larger number of devices. The sampling methodology ensures adequate representation without excessive coordination requirements.
3Productivity
If IoT devices are dynamically selected and configured based on location and resource availability, then processing efficiency improves, but the complexity of device management and configuration increases
Solution Approach 1:
The patent implements self-service by enabling IoT devices to autonomously determine their own participation in clusters based on their location relative to data sources and their available computing resources. Devices perform self-assessment of their capabilities and geographical position, then self-configuring into appropriate clusters without requiring centralized assignment. This reduces management complexity while maintaining high processing efficiency through location-aware resource allocation.
Solution Approach 2:
The system dynamically selects and reconfigures IoT device clusters based on real-time conditions including device location, resource availability, and workload requirements. Cluster composition is not static but adapts as devices move or their resource states change, optimizing processing efficiency continuously. This dynamic approach allows the system to respond to changing conditions without manual intervention.
Data Source
AI summary
For distributed processing using sampled clusters of location-based Internet of Things (IoT) devices, at a central device, a data source to be used for processing a workload is determined. A set is selected of devices operating within a threshold distance from the data source at a first time. A first subset including a first sample number of devices is selected from the set. A ratio is determined of a first amount of a computing resource needed to process the workload and a second amount of the computing resource available in the first subset to process the workload. From the set, to form a cluster, a second subset is selected of a size at least equal to a multiple of the ratio and the first sample number. Each device in the second subset satisfies a clustering condition. A lightweight application is configured at the first device to process the workload.