WASM Microservices for Edge AI Data Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current approaches to real-time AI-assisted data processing on edge devices face limitations such as high bandwidth requirements for data transfer to the cloud, security concerns, limited resource constraints, and lack of customization and scalability to meet specific use case requirements.

Innovation Solution

A modular microservices architecture in WebAssembly (WASM) is implemented, allowing for the creation of microservice modules for real-time data processing on edge devices, which are compiled into bytecode format and deployed in a WASM runtime environment, enabling flexible and scalable AI-assisted data processing with modules for machine learning, data streaming, database management, and peer-to-peer networking.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If data is transferred from edge devices to the cloud for AI model training, then AI models can be updated regularly, but bandwidth requirements increase and connectivity challenges arise

Engineering Contradiction:

ImproveAI model update capabilityVSAvoidbandwidth requirement

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The system segments the monolithic software into modular microservices that can be independently updated and deployed. Each microservice can be trained and updated separately using federated learning, eliminating the need to transfer large datasets to the cloud while maintaining model update capabilities.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The edge device performs AI model training locally using federated learning, where multiple edge devices contribute gradients or model updates without sharing raw data. This self-service approach enables continuous model improvement while keeping data processing at the edge, reducing bandwidth requirements.

Inventive Principle:

Principle #25Self-service

2Ease of manufacture

If traditional monolithic software is used on edge devices, then implementation is straightforward, but customization and scalability are limited

Engineering Contradiction:

Improvesoftware implementation simplicityVSAvoidcustomization capability

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The software is divided into independent microservices that can be selectively deployed and customized based on specific use case requirements. Each microservice encapsulates a specific functionality, allowing flexible composition and scaling without affecting the entire system.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The microservice architecture provides universal interfaces and standardized communication protocols that allow the same framework to support multiple different functionalities and use cases. Microservices can be reused across different applications, enhancing versatility while maintaining ease of implementation.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Speed

If AI computations are performed on edge devices, then real-time processing speed increases, but resource constraints become more challenging

Engineering Contradiction:

Improvereal-time processing speedVSAvoidcomputational resource consumption

Core Design Contradiction:

SpeedVSUse of energy by moving object

Solution Approach 1:

Computational tasks are segmented into separate microservices that can be executed independently and parallelized. This allows efficient utilization of limited edge device resources by distributing computational load across multiple specialized services rather than requiring a single resource-intensive monolithic system.

Inventive Principle:

Principle #1Segmentation

4Reliability

If manual software updates are performed on edge devices, then security measures can be implemented, but update complexity increases significantly

Engineering Contradiction:

Improvesecurity measure implementationVSAvoidsoftware update complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

Software updates are segmented into individual microservice updates rather than requiring full system reinstallation. Each microservice can be independently updated, validated, and deployed, significantly reducing update complexity while maintaining security through incremental verification.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system implements automated update mechanisms where microservices can self-update and self-validate security measures. The modular architecture enables automated dependency resolution and conflict detection, reducing the complexity of manual security updates.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS20240394081A1Modular microservices architecture in webassembly (WASM) for real-time ai-assisted data processing on edge devices

Publication Date: 2024.11.28 VBRL HOLDINGS INC

AI summary

A method and system for real-time AI-assisted data processing on edge, where the method includes creating a set of microservice modules for real-time data processing on an edge device, compiling the set of microservice modules into a bytecode format for implementation in a WebAssembly (WASM) runtime environment, and embedding the compiled microservice modules on the edge device configured to provide the WASM runtime environment. The compiled microservice modules include at least one microservice module configured to implement real-time data processing on a live data stream collected from one or more sensors included in the edge device.