Edge computing is set to be the next big thing in the Internet of Things. There is a rush to bring new low power AI chips to market which will allow devices to have greater autonomy, particularly in areas like video processing and self-driving vehicles. This presentation looks at the current state of development and the emergence of a new generation of silicon startups.
5. 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.
7. 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 – Device
Life Cycle)
Connectivity
HardwareEDGE
8. The world is producing excessive amounts of
“unstructured data” that need to be reconstructed.
Rob High – CTO, IBM
9. Big Data doesn’t need to reside in one place.
Lots of Little Data is also Big Data.
Learning can be distributed.
10. 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.
11. 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
12. 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
13. The processing hierarchy
Cloud
• Heavy Lifting
• “Unlimited” resources
Mobile
• Pre-programmed and
learned models
• Video processing, etc.
ThingEdge
• Real-time learning
• Autonomous operation
14. Giga (Billion) Operations per second and Trillion Operations per second
TOPS and GOPS
Intel Xeon 8180M 0.3 TOPS / W
NVIDIA 0.4 TOPS / W
Thing
< 0.05 TOPS 2 - 3 TOPS 25 - 50 TOPS
GreenWaves 0.6 TOPS / W
Kneron offers 1.5 TOPS / W
ARM ML 3 TOPS / W
Novumind 3 TOPS / W
Cambricon 3 TOPS / W
Mythic 4 TOPS / W
Groq 8 TOPS / W
Syntiant 20 TOPS / W
15. 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
19. 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