Edge AI Suite: DeviceOn End-to-End Solution for Edge AI
An Edge Orchestration Platform for AI/ML Apps
Edge AI with Power and Scale
Advantech understands what a headache it is to find hardware devices with optimized price performance when consuming large amounts of energy for Artificial Intelligence (AI) and Machine Learning (ML) algorithms and model development. Even if all datasets, algorithms, trainings, UI/UX, and more are functioning, how can you easily deploy an AI application to hundreds, or thousands, of inference devices in production? How can you efficiently manage AI models (software updates, CI/CD), in addition to all remote, hardware devices, such as sensors?
- If you don't have any viable answers, you are certainly not alone. This is why Advantech designed its end-to-end solution, DeviceOn. DeviceOn is a device management and edge orchestration software solution for Internet of Things (IoT) and industrial applications. Advantech Edge AI devices are powered by leading-edge AI chipsets from NVIDIA (Jetson) and Intel (Tiger Lake CPU). Together with our technology partners, the Edge AI Suite: DeviceOn end-to-end Edge AI solution helps power and scale your AI/ML applications. This allows end-users to focus on what they do best - AI and ML development.
Edge AI with Power and Scale
Architecture
Solution Advantages
Performance Booster
- Inference optimization
- Open Neural Network Compiler (ONNC)
- Reduce DRAM consumption by 45%
Large-Scale Mgmt.
- Remote batch control for power, reboot, and terminal
- Real-time monitoring, diagnostics and notifications
- Over 10,000 devices around the globe
Container and OTA
- Streamlined deployment process
- Docker container management
- Software (over-the-air) OTA updates
AI Security
- AI containers deployed via Azure Container Registry and Harbor
- Secured data connection (TLS/SSL)
- Integrity protection based on digital signatures
DeviceOn - IoT Device Management Platform
IoT deployment and management involves hundreds of thousands of devices spread out over multiple sites. DeviceOn makes it easy to onboard, visualize, operate, and manage your industrial IoT devices. With its easy-to-use interface, you can monitor device health status, take real-time actions such as power on/off, troubleshoot problems, and send software and firmware updates over-the-air (OTA).
Recommended Hardware
- NVIDIA Jetson Series
ARM-based system designed for accelerating machine learning applications
-
AI Inference system based on NVIDIA Jetson Nano/TX2 NX/ Xavier NX
-
Industrial-Grade NVIDIA Jetson barebone PC
-
An industrial AI camera equipped with NVIDIA Jetson AI system on module
-
Edge AI systems for the surveillance, transportation and manufacturing
-
- Nvidia Tesla/Quadro series
High performance for deep learning and high capacity for complex multi-task
-
Industrial motherboard with NVIDIA Quadro GPU to accelerate edge AI deployment
-
Extreme AI Edge server supporting dual PCIe x16 350W high performance GPU cards
-
Extreme performance box PC with 3 expansion slots
-
Up to 4 PCIE expansions to deal with intricate AI algorithms
-
Compact fanless system supporting various GPU card expansion modules
-
- Intel 12/11th Gen Intel® Core™ processors series
High performance CPU and iGPU combined with AI and deep learning capabilities
-
Din-rail fanless box PC with Intel® 11th gen Core™ i processor
-
Edge intelligence system with Intel® 11th gen with EdgeX API and WISE-Device On
-
Compact fanless system with with Intel® 12th gen processor
-
Regular fanless DIN rail controller with 11th gen Intel® Core™ i processor
-