Adaptive Surrogate Models for IoT Battery Life

Solution Overview

Problem

In edge computing, IoT devices face challenges in maintaining battery lifespan and data quality due to adverse conditions and computationally intensive processes, leading to power depletion and reduced coverage, necessitating a solution to balance sensor uptime and data precision.

Innovation Solution

The adaptive surrogate modeling system creates and deploys surrogate models on smart IoT devices to replace resource-consuming models, extending battery lifespan and ensuring data quality by predicting device lifespan and deploying models based on thresholds and constraints, using existing models from a repository if applicable.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If computationally intensive processes are used to maintain data quality, then data precision is improved, but battery lifespan is reduced

Engineering Contradiction:

Improvedata precisionVSAvoidbattery lifespan

Core Design Contradiction:

Measurement precisionVSDuration of action of moving object

Solution Approach 1:

The patent creates surrogate models that are simplified copies of complex computational models. These surrogate models replicate the essential functionality and data processing capabilities of the original complex models but with significantly reduced computational requirements, allowing edge devices to maintain data precision while consuming less energy and extending battery lifespan.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent employs lightweight surrogate models that are computationally inexpensive and can be rapidly deployed and updated on resource-constrained edge devices. These simpler models trade off some computational complexity for dramatically reduced energy consumption, enabling continuous operation and extending the effective operational lifespan of battery-powered IoT devices.

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

2Reliability

If resource-consuming models are deployed on IoT devices, then data quality is maintained, but energy consumption increases

Engineering Contradiction:

Improvedata qualityVSAvoidenergy consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent creates surrogate models that are simplified copies of complex computational models. These surrogate models replicate the essential functionality and data processing capabilities of the original complex models but with significantly reduced computational requirements, allowing edge devices to maintain data precision while consuming less energy and extending battery lifespan.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent transforms complex models into surrogate models by changing key parameters such as model complexity, computational depth, and processing intensity. This parameter transformation allows the system to maintain acceptable data quality thresholds while dramatically reducing energy consumption on resource-constrained edge devices.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If complex models are used for processing, then analysis accuracy is improved, but device complexity increases

Engineering Contradiction:

Improveanalysis accuracyVSAvoiddevice complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the computational workload by separating complex model processing into two parts: (1) a simplified surrogate model that runs locally on the resource-constrained edge device for real-time processing, and (2) the full complex model that can be used for offline validation or when computational resources are available. This segmentation allows the edge device to maintain lower complexity while preserving analysis accuracy through the surrogate model.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent creates surrogate models that are simplified copies of complex computational models. These surrogate models replicate the essential functionality and data processing capabilities of the original complex models but with significantly reduced computational requirements, allowing edge devices to maintain data precision while consuming less energy and extending battery lifespan.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS12101224B2Device lifetime-aware creation of customizable surrogate-based models

Publication Date: 2024.09.24 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

According to one embodiment, a method, computer system, and computer program product for adaptive surrogate modeling is provided. The embodiment may include capturing a plurality of system information for a smart Internet of Things (IoT) device. The embodiment may also include calculating a lifespan value of the smart IoT device based on the plurality of captured system information. The embodiment may further include, in response to the calculated lifespan value being below a threshold and a surrogate model fitting one or more parameters of the smart IoT device not existing, creating the surrogate model for the smart IoT device. The embodiment may also include deploying the created surrogate model to the smart IoT device through an update transmission.