Krishna Mayuram, Lead Architect (Big Data & IOT) @krismayuram Han Yang, Senior Product Manager @hanyang1234 April 10, 2018 Powered by Cisco, SAS Edge to Enterprise Analytics Platform Edge to Enterprise IoT Analytics for Electric Utilities and Manufacturing
11
Embed
Edge to Enterprise IoTAnalytics for Electric Utilities and ...d24wuq6o951i2g.cloudfront.net/img/events/2962440/... · Edge to Enterprise IOT Analytics Platform: Electric Utility AI
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Krishna Mayuram, Lead Architect (Big Data & IOT) @krismayuram
Han Yang, Senior Product Manager @hanyang1234
April 10, 2018
Powered by Cisco, SAS Edge to Enterprise Analytics Platform
Edge to Enterprise IoT Analytics for Electric Utilities and Manufacturing
Analytics Lifecycle with AI/ML/DLTrain, Predict and Act
ETL
Analytics Data Storage
Alerts / Reports/ Decisioning
Dep
loy
f
IoT & Sensor Data Intelligent Filter / Transform
InferenceModel Execution
Training
Inference
Data Quality /
Transform
Event Detection(did something
happen?)
Event Identification(what happened?)
Event Qualification(how bad was it?)
Develop analytics to:• Detect events on the network• Categorize the event on the network• Direct appropriate action based on the
event• Capture data for post event analysis
Data: power frequency, voltage, current, phasor angle, …
Power Plant
Primary Substation
SecondarySubstation
High-voltage transmission line
Streaming data analysis:the system generates n measurements/sec
Analytical techniques can be used to detect
deviation from the normal.
An event can be normal or represents an equipment
falere.
What is the magnitude of equipment failure events?
Main goal: detect and understand events that are affecting the power grid, with the objective of keeping the grid stable.
Offline Advanced Analytics and Exploration(how to prevent it?)
1. In Stream @ Edge
2. In Stream @ Edge & Data Center
3. At rest @ Data Center
Electric Utility AI : Sensor Data Flow
Inference (Edge)
Training (Data Center)
Data Mgmt. & Pattern Detection using ESP
Data: power frequency,
voltage, current, phasor
angle, …
Cisco UCS
Pattern Detection using ESP
Visualization of streaming data using SAS ESP Streamviewer
Application Life
Cycle Mgmt
(Cisco
FogDirector)
Update
Streaming
models
Connect to
external apps
with ESP
connectors
Edge to Enterprise IOT Analytics Platform: Electric Utility AI
Cisco UCS
Cisco UCS
Cisco UCS
Pattern discovery using SAS Visual Analytics and SAS Visual
Statistics
Cisco UCS C
Cisco
ISACisco
Firepowe
r
KAFKA
Cisco
Firepower
Inference (Edge) Training (Data Center)
Visualization of streaming data using
SAS ESP Streamviewer
Cisco CGR1K
End-to-End
Network
Mgmt.
(Cisco IOT
FN. Director)
Smart ManufacturingAI, Analytics, and Machine Learning in
Edge Architecture With Cisco Kinetic
Data Mgmt. & Pattern Detection using ESP
Data: power frequency,
voltage, current, phasor
angle, …
Cisco UCS
Pattern Detection using ESP
Visualization of streaming data using SAS ESP Streamviewer
Update
Streaming
models
Connect to
external apps
with ESP
connectors
Edge to Enterprise IOT Analytics Platform: Manufacturing AI
Cisco UCS
Cisco UCS
Pattern discovery using SAS Visual Analytics and SAS Visual
Statistics
Cisco UCS C
Cisco
ISACisco
Firepowe
r
KAFKA
Cisco
Firepower
Inference (Edge) Training (Data Center)
Visualization of streaming data using
SAS ESP Streamviewer
Application Lifecycle Managements
(Cisco Fog Director)
End-to-End Network Manamgnet
(Cisco IOT FN Director)
Analytics Lifecycle Managements
(AI/ML/DL – SAS ESP)
Demo
ResourcesCisco Edge-to-Enterprise IoT Analytics for Electric Utilities Solution Briefhttps://www.cisco.com/c/en/us/solutions/collateral/data-center-virtualization/big-data/solution-overview-c22-740248.html
Cisco and SAS Edge-to-Enterprise IoT Analytics Cisco Validated Designhttps://www.cisco.com/c/en/us/td/docs/unified_computing/ucs/UCS_CVDs/Cisco_SAS_Edge_to_Enterprise_IoT_Analytics_Platform.html