Business Benefits

Reduce IoT Cycle Times

Highly optimized decision engine can process
> 1000 records per second on a single watt SBC

Operates in a resource constrained / low bandwidth environment

Proprietary execution algorithm accelerates performance far beyond simple code optimization

Complexity Simplified

Meltdown Prevention, tune logic coupling and cohesion with real-time decision making

Simple interfaces allow non programmers to rapidly adjust logic and see real time results at the edge using our decision engine

Human configured decisions combined with AI insights to provide new levels of automation

Watch How Phizzle’s IoT Edge Decision Engine Changes the Landscape For Real-time Anomaly Detection with Transportation and Connected Vehicles

✓ Processing is 100% dictated by configuration that describes the environment
✓ Automates trigger detection and handling to determine reaction to data-driven circumstances
✓ Our algorithm provides speed and scale – this demo shows 390 microseconds to process a single vehicle report in a resource constrained environment

Our IOT Edge Decision Engine detects any hazard or future hazard and alerts the driver in sub millisecond timing

What is IoT Edge Decision Engine

IoT data demand is exploding. Cloud-based solutions, with their long cycle times will require an edge computing solution to keep IoT devices running at lightning speed, efficiently without latency issues. Phizzle IoT Edge Decision Engine combines data with triggers, aggregations, actions, and analytics enabling more decision making at the edge while continuously updating data points while aggregating high volumes of data in near-real-time.

Edge Decision Engine


Data is combined with triggers, aggregations, actions, and analytics using IoT Edge Decision Engine to bring intelligence to the edge with the highest possible performance.

Edge Manager


Manages configuration, ETL, deployment, automation compilation, APIs, database, IoT brokers, and other microservices.

 

Edge Controller


User interfacing application to exercise all edge engine APIs and allows non-programmers to create evaluate and deploy edge engine rule definitions.

 

Use IoT Edge Decision Engine to bring intelligence to the edge with
the highest possible performance

Phizzle’s IoT Edge Decision Engine maximizes the amount of processing done on the edge, offloading the workload required by cloud applications and dramatically decreasing the response time. Create triggers and distributed data models that are pushed and applied to the edge. Deep learning and AI processes running in both fog and cloud environments, continually update edge enabling devices to make decisions and respond in a time efficient manner.

Use-Case_v7_Ubuntu

Technical Benefits

Maximize the amount of processing done on the edge, offloading the required cloud applications workload and dramatically decrease response time and costs.

Speed at the Edge on Low-Powered Devices

  • Operate in low bandwidth / resource constrained environments
  • Highly optimized decision engine can process > 1000 records per second on a single watt SBC
  • Hyperoptimize execution through our proprietary algorithm accelerates performance far beyond simple code optimization
  • High efficiency in less constrained environments

Make AI and Deep Learning Actionable

  • Use automated decision making to make results of analysis actionable in real-time
  • Mix deep and shallow data for situationally aware reactions
  • Create Hierarchies of Action giving the right of way to high priority reactions
  • Human configured decisions combined with AI insights to provide new levels of automation
  • Deep learning and AI processes running in both fog and cloud environments, continually update edge devices enabling them to make decisions and respond quickly and easily

Tuneable Edge Decision Making

  • Simple interfaces allow non programmers to rapidly adjust logic and see real-time results at the edge using our decision engine
  • Centralized viewpoint helps address issues by correlating events to give better context
  • Meltdown Prevention, tune logic coupling and cohesion with real-time rules
  • Improved real-time visibility on infrastructure

Optimization Improves as Complexity Increases

  • Maintain high performance on low powered devices for complex rules and decisions
  • Local actions are taken or remote actions are triggered
  • Data is combined with triggers, aggregations, actions, and analytics using our proprietary algorithm to bring intelligence to the edge with the highest possible performance

Continuously Update Edge Decision Making Logic Via Fog Computing

  • Apply machine learning at fog level used by edge devices
  • Aggregate large volumes of data in real-time and apply cloud analytics
  • Data is continually analyzed at the edge and in the fog
  • The fog uses cloud-based analytics and local computing to continually enhance and refine the rules implemented on the edge

Trusted By Leading Brands

Contact Us

Contact Us
Sending