Making Big Data Small and Relevant
Edge Analytics software allows data produced by sensor-rich assets like machines, equipment and devices to be pre-processed in real-time closer to where it is created.
There are several technical and business drivers and benefits with Crosser Edge Analytics architecture, including:
Significant data reduction by removing dirty data and irrelevant data. Get significant cloud, analytics and network connectivity cost savings.
Innovate with More Data
Edge Analytics allows you to collect more data points without increasing your cost of data. More data - more innovation possibilities.
Transform Raw Data to Insights
Collect raw data, transform it, analyze it and act on the insights in real-time.
Local Intelligence and Automation
Run local triggers between machines or PLC’s with ultra-low latency. Runs autonomously without cloud connectivity.
Typical Deployment Scenarios
The Edge Analytics software is deployed on a IoT gateway on a remote unit, or embedded, and processes the sensor data from that single unit.
Field Edge Aggregation
Also called Fog Computing. The Edge Analytics software is typically deployed on an IoT gateway and processes the sensor data from multiple field units.
Typically on a factory shop floor or building with multiple machines. The Edge Analytics software is installed on a server/virtual machine and processes sensor data from multiple on-premise machines and data sources.
Business case objectives and use-cases
Edge Analytics is a key layer in the Industrial IoT or Industry4.0 technology stack. Smart and cost efficient data collection and analytics is a fundamental part.
Business case objectives includes:
The main use-cases to achieve this are:
Industrial Process Optimization
Asset Performance Management
No data. No party.
Getting access to relevant data in a central location,
either cloud or data center, is the fundamental starting-point
to enable these main use-cases and meet the business objectives.
Crosser Edge Analytics solution is purpose-built to address
the key challenges for Industrial IoT, including:
Factory floor challenges
- High number of sensor tags - constant changes
- Many data sources: PLC, DCS, MES, Historians and databases
- Many protocols: OPC, Modbus, MQTT, SCADA and more
- Separated networks
- OT and IT team collaboration
Remote assets challenges
- Moving from basic telemetry to monitoring all subcomponent
- How to collect more data but transfer less?
- Limited and costly connectivity
- Unreliable and intermittent connectivity
- Managing large volume of assets
- Inside customer firewalls
Bring Your Own AI - Edge MLOps made Easy
Bring, Manage and Deploy your own ML models with Crosser Edge MLOps functionality:
- The Crosser Edge Node is open to run any ML framework
- Central Resource Library for your trained models in Crosser Cloud
- Drag-and-drop for all other steps in the data pipeline
- One operation to deploy ML models to any number of Edge Nodes
Crosser for Azure
Run Crosser with your favourite Azure service, or any other cloud.
- Edge Analytics for Azure
- Edge Analytics for Azure IoT Edge
- On-Premise Streaming Analytics for Azure Stack
- Cloud Streaming Analytics on your Azure VM