Is Machine Learning the Solution to Your Capacity Management Challenges?
Download as PPTX, PDF1 like155 views
The document discusses the role of machine learning in addressing capacity management challenges, emphasizing the importance of data in improving performance and decision-making. It explores various machine learning techniques, such as supervised and unsupervised learning, and highlights their applications in predictive and prescriptive analytics. The use case section underscores the necessity of effective data analysis to identify and solve capacity management issues.
Is Machine Learning the Solution to Your Capacity Management Challenges?
- 1. Is Machine Learning the Solution to Your Capacity Management Challenges? Charles Johnson Senior Technical Consultant 1
- 2. Agenda • Capacity Management Overview • Machine Learning Overview • Machine Learning Algorithms • Use Case • Summary
- 3. “ ” “As one Google Translate engineer put it, "when you go from 10,000 training examples to 10 billion training examples, it all starts to work. Data trumps everything.” Garry Kasparov, Deep Thinking: Where Machine Intelligence Ends and Human Creativity Begins
- 5. • Ensure the right level of ITI investment • Identify and resolve bottlenecks • Evaluate tuning strategies • Improve and report/publish performance • “Right-size” or “consolidate” • Ensure accurate and timely procurements • Ensure effective service level management • Plan for workload growth, new apps / sites • Avoid performance disasters Capacity Management Objectives 5
- 6. • Trends • What-If Trend • Analytical Modelling • Machine Learning • Simulation Modelling • Benchmarking 6 Capacity Management Techniques
- 8. • The ability for a system to take basic knowledge and apply that knowledge to new data • The ability to find unknowns in data • Main points • Learning • Pattern detection • Follow the data • Self-programming What is Machine Learning? 8
- 9. Supervised Learning • Established set of data • Data is classified • Find patterns in the data Unsupervised Learning • Massive amounts of data • Data is not classified or labeled • Find patterns in the data Other approaches • Reinforcement learning • Neural networks / Deep Learning 9 Machine Learning Approaches
- 10. Descriptive Analytics • Current reality • Historical context • Aggregates data for insights Predictive Analytics • Anticipate changes by understanding patterns • Constantly needs new data • Looks into the future Prescriptive Analytics • New for machine Learning • Combination of business rules, machine learning and computational modelling 10 Forms of Data Analysis
- 12. Self-Driving Vehicles Automated Recommendations Computer Translation Machine Learning Uses 12
- 13. The Machine Learning Cycle 13
- 15. • Linear Regression • Logistic Regression • Decision Tree • kNN (k-Nearest Neighbors) Common Machine Learning Algorithms 15
- 16. • Predict scores on one variable from the scores on a second variable • Study the relationship between real values based upon continuous variables • Create the best fitting straight line based on the data 16 Linear Regression
- 17. Should I play Golf? 17 Decision Tree Outlook Overcast Rain Sunny Low Humidity Wind High True False Yes Yes Yes No No
- 19. Trending • OK for utilizations, business volumes • Useless for service levels (response time) Analytical models • Quick and easy to set up • Potentially very accurate Simulation models • Time-consuming and difficult to set up • Potentially more accurate Benchmarks and Workload Generators • Perfect, but expensive and complicated (or impossible) • Required depending on industry or question to answer Forecasting Techniques 19
- 20. Join Capacity Management - Machine Learning
- 21. • Need data to make it work • More data the best (Big Data) • Need to understand and trust the data • Remove assumptions and bias • Reduce time to analyze data Join Capacity Management - Machine Learning 21
- 22. Use Case
- 23. • What is the problem you are attempting to solve? • What data is available? • Do you have a representative period of time? • What is the “Story” you are attempting to tell? Capacity Management Use Case 23
- 24. Analyze Environment by Region 24
- 26. Summary
- 27. • Machine Learning provides value to Capacity Management • Reduce time spent analyzing data • Follow the data • Understand the data • Trust the data 27 Take Away
- 28. References Machine Learning for dummies – IBM (Judith Hurwitz & Daniel Kirsch) M. Asokan Syncsort Chief Architect, Distributed Systems & Big Data masokan@Syncsort.com John Greenwood Syncsort Technical Architect John.Greenwood@Syncsort.com 28
- 29. Questions
Editor's Notes
- #6: Ensure the right level of ITI investment (Match the equipment to the need, Optimise on computer expenditure, Money not wasted on redundant hardware, Users able to meet business demands) Optimise the resources available, “right-sizing” or “consolidating servers” as necessary Ensure accurate and timely capacity procurements to minimise disruption and expenditure, Reliable hardware plans, Impact of upgrade properly sized, Timely procurement planning Ensure effective service level management in terms of response times and throughputs Help prepare for new application implementations or new sites or new acquisitions The essential objective is to achieve the most cost-effective balance between business demands and the size and form of the ITI needed to support it.