Adaptive IoT Optimization Strategy Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current IoT systems require manual re-architecting or redesigning when adjusting the computational workload between IoT devices and cloud servers, making it inefficient for adaptive optimization and management.
Innovation Solution
A system that allows IoT devices to select optimization strategies based on device context and user preferences, enabling local or global processing of data through plugins, adapting to changing conditions without needing additional system development, and allowing for easy configuration of user preferences like power management and privacy policies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If cloud servers perform all optimization algorithms on aggregated device data, then optimization performance is improved, but system adaptability and power efficiency deteriorate
Solution Approach 1:
The patent segments the optimization computation into two parts: aggregation algorithms executed on cloud servers and device-specific optimization algorithms executed locally on IoT devices. This segmentation allows the system to leverage cloud computing power for data aggregation while maintaining device-level adaptability through local processing, thereby resolving the contradiction between optimization performance and system adaptability.
Solution Approach 2:
The patent implements local quality by enabling IoT devices to execute optimization algorithms locally using their own sensor data and context information. This local processing capability allows each device to adapt optimization parameters to its specific conditions (e.g., battery level, network connectivity, sensor characteristics) while the cloud handles aggregate pattern recognition, thus improving both optimization performance and adaptability simultaneously.
2Loss of energy
If computational workload is shifted from cloud servers to IoT devices, then power efficiency is improved, but system complexity increases
Solution Approach 1:
The patent employs universal optimization algorithms that can be executed on both cloud servers and IoT devices with minimal modification. The same algorithm framework runs in both environments, with the cloud executing aggregation versions and devices executing local versions. This universality reduces system complexity by avoiding the need for entirely separate algorithm implementations while still enabling local processing for improved power efficiency.
3Productivity
If the system architecture is manually re-architected to adjust computational workload, then processing efficiency is improved, but development time and cost increase
Solution Approach 1:
The patent implements a dynamic workload distribution mechanism where the division of computational tasks between cloud and device is not fixed but can be adjusted based on runtime conditions. The system can dynamically shift which devices perform local optimization versus relying on cloud processing based on factors like device capability, network availability, and data characteristics. This dynamic approach allows processing efficiency to be optimized without requiring manual re-architecture, as the system adapts automatically to changing conditions.
Data Source
AI summary
Technologies for collaborative optimization include multiple Internet-of-Things (IoT) devices in communication over a network with an optimization server. Each IoT device selects an optimization strategy based on device context and user preferences. The optimization strategy may be full-local, full-global, or hybrid. Each IoT device receives raw device data from one or more sensors/actuators. If the full-local strategy is selected, the IoT device generates processed data based on the raw device data, generates optimization results based on the processed data, and generates device controls/settings for the sensors/actuators based on the optimization results. If the full-global strategy is selected, the optimization server performs those operations. If the hybrid strategy is selected, the IoT device generates the processed data and the device controls/settings, and the optimization server generates the optimization results. The optimization server may provision plugins to the IoT devices to perform those operations. Other embodiments are described and claimed.