The document discusses the concept of a Machine Intelligent Cluster in data centers, focusing on leveraging machine learning to optimize power consumption, resource management, and operation efficiency. It explains the architecture and functionalities such as self-optimization, self-learning, and self-recovery. The applications include IoT, gaming, and e-commerce, highlighting the need for predictive capabilities in modern data environments.

1. Machine Intelligent Cluster:
The next generation of data center
Evan Lin @Linker Networks

2. About me
Cloud Architect @ Linker
Networks
Golang User Group - Co-
Organizer
Top 5 Taiwan Golang open
source contributor (github
award)
Developer, Curator, Blogger

3. Recap Cloud Summit 2016

4. Agenda
• Problems on data center
• How machine learning helps
• Machine Intelligent Cluster
• Applications
• Q&A

5. Data center

6. • Power consumption
• Low usage
• Unpredictable peak
• Noisy neighbors
Efficiency
• Physical damage
• Networking problem
• Anomaly
• Attack
Risk
Real data center

7. Power consumption

8. Low usage and Unpredictable peak

9. Noisy neighbor

10. Use machine learning improve DC power
consumption

11. None of your business?

12. Modern Data center: Machine Cluster

13. Before machine cluster
DB Master:
IP: 192.168.1.222
DB Slave:
IP: 192.168.1.223
Web Server 1:
IP: 192.168.1.101
Web Server 2:
IP: 192.168.1.102
Web Server 3:
IP: 192.168.1.103
Load Balancer:
IP: 1.2.3.4

14. Container orchestration
Resource arrangement
Scalability
Portability
Automation migration

15. Resource management
3 Web App Servers
2 DB Servers
1 Load Balancer

16. Scalability

17. Automation migration

18. Automation migration

19. Automation migration

20. Automation migration

21. But .. we need better ..

22. No prediction

23. How to define scale out threshold?
50 %?
75 %?
25 %?

24. Machine Intelligent Cluster

25. Efficiency
Maximize
Utilization
Operation
Optimization
Accident
Risk
Mitigation
Serviceability
Management
Machine
Intelligence
Cluster
How MIC helps

26. Operation Optimization
1. Reinforcement learning
2. Adjust thermostat
3. Check the reward (CPU performance).
[1]: Refer from https://goo.gl/ly3zyX

27. Maximize Utilization
Analyze utilization and reduce working
machines to save our customer budget
- Predict utilization trend
- Provide auto-scaling threshold
adjustment

28. Prediction and dynamic threshold

29. Optimized
Scheduler
Node 1 Node 2
Node 3
Node 1 Node 2 Node 3
Nginx
(CPU 30%)
DB- MySQL
(IO 25%)
DB- Mongo
(IO 30%)
Apache
(CPU 30%)
Backend Process
(CPU 35%)
DB- Oracle
(IO 35%)
NodeJS
(CPU 7%)
Go backend
(CPU 8%) Nginx
(CPU 30%)
DB- MySQL
(IO 25%)
NodeJS
(CPU 7%)
Go backend
(CPU 8%)
Apache
(CPU 30%)
Backend Process
(CPU 35%)
DB- Mongo
(IO 30%)
DB- Oracle
(IO 35%)
Maximize Utilization
P.S. Not rearrange processes, we change the scheduler to avoid it happen..

30. Model 1
Serial Number Prediction
S.M.A.R.T. RNN Prediction
Serviceability Management (cont.)
Model 2

31. Dummy VM Detection Outlier Attack Detection
Mitigate risk

32. Storage SDN
Zombie Tagging system

33. Architecture

34. Cloud Native Architecture

35. HPC (with GPU) Server
Storage SDN
Storage SDN
Data Collect Probe & Sensor & Smart GW
Visualization
Data Process
Data Analysis &
Machine Learning
DCOS/
Kubernetes
Spark ML Tensorflow
DCOS / Kubernetes
Cassandra (Storage)
Kafka (Queueing)
Go/Akka (Connector)
Spark (ETL/Streaming)
D3.js
Scikit Learn R
Interactive
Dashboard
Jupyter Notebook
Zeppelin
ML Job
Scheduler
Chronos
MIC System Architecture

36. Data Agent Kafka
Spark
Streaming
Cassandra
Spark ML
(Classification,
Clustering)
TensorFlow
(Deep
Learning)
Backend Server
API
Portal
TensorFlow
Predict
SparkML Predict
MIC Data Flow

37. Applications on MIC
Machine Intelligent Cluster
IOT Gaming 5G NFV E-Commerce

38. Machine Intelligent Cluster Summary
• Machine cluster with Intelligent
• Features
• Self-Optimization
• Self-Learning
• Self-Recovery
• Green, Secure and Predictive machine cluster

39. 歡迎訂閱 碼天狗
http://weekly.codetengu.com/

40. Thank You