iot - life at the edge - cambridge wireless · 13.12.2018 · the comms part is largely done lpwan...
TRANSCRIPT
IoT – Life at the Edge
Nick Hunn – WiFore Consulting
The IoT story so far…
Towards 50 Billion Connected Devices
Amount of time spent discussing
LPWAN
Amount of time spent discussing the rest of
the IoT
Amount of time spent designing products
Amount of time spent discussing AI
The Comms part is largely done
LPWAN exists
• Sigfox
• LoRa
• Telensa
• Ingenu
• NB-IoT
Low cost data exists
• Sigfox
• LoRa
• 1NCE
Just because it will get better is not a reason for prevarication.
IoT Basics
Data Capture Data Insight
There’s a lot of detail in between…
The IoT value stack
Deployment & Physical installation
Algorithm Development
Additional Data Sourcing
Business Applications (vertical)
Business Applications (packaged)
IoT Analytics
Cloud
Device Management
Data Contracts
Comms
Project Management
Data Cleansing & Verification
Security & Updates
Provisioning
Sensor & Physical
Deployment
Applications& Analytics
M2M / IoT Infrastructure
(DLC – DeviceLife Cycle)
Connectivity
HardwareEDGE
The world is producing excessive amounts of “unstructured data” that need to be reconstructed.
Rob High – CTO, IBM
Big Data doesn’t need to reside in one place.
Lots of Little Data is also Big Data.
Learning can be distributed.
Because Intel wants to sell more server chips.
Because CISCO wants to sell more infrastructure.
Because the network operators need a story to support 5G.
Why is edge computing such a well kept secret?
And also because it’s difficult.
The balance of power
Cloud
• Limited processing power• Limited resources• Limited battery life• Intermittent connectivity
• Lots of processing power• Lots of resources• Mains powered• Aggregated Data• Additional Data Sources
Processing Power
Thing
The balance of power
Thing Cloud
• May need to make real time decisions• Can’t guarantee a connection
• May have limited data throughput• Intermittent uploads • Very limited downloads• Little access to additional data
• Difficult to make real-time control decisions for millions of devices
Autonomy
The processing hierarchy
Cloud• Heavy Lifting• “Unlimited” resources
Mobile• Pre-programmed and
learned models• Video processing, etc.
ThingEdge• Real-time learning• Autonomous operation
Giga (Billion) Operations per second and Trillion Operations per second
TOPS and GOPS
Intel Xeon 8180M 0.3 TOPS / WNVIDIA 0.4 TOPS / W
Thing
< 0.05 TOPS 2 - 3 TOPS 25 - 50 TOPS
GreenWaves 0.6 TOPS / WKneron offers 1.5 TOPS / WARM ML 3 TOPS / WNovumind 3 TOPS / W
Cambricon 3 TOPS / WMythic 4 TOPS / WGroq 8 TOPS / WSyntiant 20 TOPS / W
Is it training or is it inference?
MLP - Multi-layer Perceptron
CNN - Convolutional Neural Networks
RNN - Recurrent Neural Networks
DNN - Deep Neural Networks – image recognition & voice
The AI Landscape
Machine Learning
Neural Networks
Deep Learning
Video Neural Network Engines and AI accelerators
Sunrise AI chip for Facial Recognition
Supports 4 x 1920 x 1080 30fps video inputs at under 1.5W
Horizon Robotics
Automotive and Audio
Google’s Edge TPU
“Edge-based ML inference is vital to delivering reliable, live, low-latency, and cost-effective smart city IoT. Cloud IoT Edge and Edge TPU unlock these capabilities in new ways for the next generation of Smart Parking systems.”
John Heard, Chief Technology Officer, Smart Parking Limited
Edge TPU Features“The first step in a roadmap that will leverage Google's AI expertise to follow and reflect in hardware the rapid evolution of AI.”
• Inference Accelerator• Dev boards coming soon
The IoT is getting smarter…
Are you?
Nick HunnCTO
mob: +44 7768 890 148
email: [email protected]
web: www.wifore.com
Creative Connectivity Blog: www.nickhunn.com
LinkedIn: www.linkedin.com/in/nickhunn
Questions?