Essential elements of data center operations
6 likes1,939 views
The document discusses essential elements of data center operations programs. It identifies 12 essential elements including environmental health and safety, personnel management, emergency preparedness, maintenance management, and performance monitoring. For each element, it outlines key tasks, risks, and opportunities. It also discusses common mistakes such as ineffective change management, lack of training, and failure to implement quality systems or metrics. Finally, it provides a process for building a world-class data center operations program with steps like assessing current practices, analyzing results, and optimizing operations.
Essential elements of data center operations
- 1. Schneider Electric 1- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Essential Elements of Data Center Operations Bob Woolley Senior Director, Global Data Center Services Tweet Live! #SchneiderXE
- 2. Schneider Electric 2- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Objectives Upon Completion of this course, you will be able to: ●Define key tasks associated with Data Center Facility Operation (DCFO) Programs ●Define risks associated with DCFO Programs ●Define opportunities associated with DCFO Programs ●Define the 12 Essential Program Elements ●Identify the most common mistakes made by data center facility operators ●Identify a process for building a world class DCFO Program
- 3. Schneider Electric 3- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 The Importance of Facility Operations ●The majority of data center lifecycle cost is in OPEX, vs. CAPEX. ●Most data center outages are attributable to human error. ●Energy costs account for the largest portion of the operating budget, and the cost of power is rising. ●New technologies and the trend towards reducing redundancy to save cost has increased the need for operational effectiveness and efficiency. ●A properly designed Facility Operations & Maintenance program will minimize risk, reduce costs, and even provide a competitive advantage.
- 4. Schneider Electric 4- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Preventative Maintenance Operational Tasks and Challenges Energy Management Performance Monitoring Capacity Management AuditsSpares ManagementEmployee Satisfaction Cost Analysis Receiving Documentation Project Management RepairsDrillsDCIM Vendor Management Incident Response Walk-throughs ReportingChange ManagementSafetyUptime SLAs
- 5. Schneider Electric 5- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 12 Essential Elements Environmental Health & Safety Personnel Management Emergency Preparedness and Response Maintenance Management Change Management Documentation Training Infrastructure Management Quality Management Energy Management Financial Management Performance Monitoring
- 6. Schneider Electric 6- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Levels of Maturity Level 5 Optimized Level 4 Managed & Measurable Level 3 Defined Process Level 2 Repeatable but Intuitive Level 1 Initial/Ad-hoc Level 0 Non-Existent
- 7. Schneider Electric 7- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Environmental Health & Safety Tasks ●Injury and Illness Prevention ●Electrical Safety ●Hazard Analysis and Communication Risks ●Injury, illness and lost time ●Fines and citations ●Equipment damage and service disruptions Opportunities ●Happy and healthy workforce ●Good safety ratings ●Positive corporate image
- 8. Schneider Electric 8- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Personnel Management Tasks ●Resource modeling and utilization ●Personnel development ●Team building Risks ●Inefficient resource utilization ●Unstable workforce ●Dysfunctional workplace Opportunities ●Stable and skilled workforce ●Fewer service disruptions ●Greater opportunities for innovation
- 9. Schneider Electric 9- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Emergency Preparedness & Response Tasks ●Emergency Operating Procedures ●Scenario Drills ●Incident Management ●Business Continuity / Disaster Recovery Risks ●Inability to prevent major service disruptions ●Injury or property damage ●Uncoordinated response Opportunities ●Increased uptime ●Cost avoidance ●End-user confidence and loyalty
- 10. Schneider Electric 10- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Maintenance Management Tasks ●Asset Management ●Work Order Management ●Spare Parts Management Risks ●Lack of information on asset performance, replacement costs ●High cost, low performance reactive maintenance program ●Excessive downtime awaiting repairs Opportunities ●Good asset intelligence and proactive maintenance boosts system reliability ●Accurate budget forecasts ●Lower TCO and less downtime
- 11. Schneider Electric 11- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Change Management Tasks ●Risk Analysis and Communication ●Vendor Supervision ●Operational Procedures Development and Review ●Structured Work Practices Risks ●Unidentified, misidentified, or miscommunicated operational risks ●Excessive human error ●Service interruptions and re-dos Opportunities ●Achieving predicted goals ●Minimizing errors and associated downtime costs ●Fewer change windows and vendor re-dispatch costs
- 12. Schneider Electric 12- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Documentation Tasks ● Critical Facility Work Rules ● Drawings, Schedules and Engineering Studies ● Shift and Rounds Logs ● Document Management and Version Control Risks ● Outdated or poor documentation introduces errors ● Communication failures cause issues to go unaddressed ● Poor documentation inhibits proper training and process improvement Opportunities ● Fewer errors resulting in injury and downtime ● More effective training ● More efficient operations and processes
- 13. Schneider Electric 13- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Training Tasks ●Fewer errors resulting in injury and downtime ●More effective training ●More efficient operations and processes Risks ●Poorly trained workers are mistake prone and inefficient ●Assumptions about worker capability can be grossly incorrect ●Allowing unqualified individuals to perform work is hazardous Opportunities ●Prevention of errors and increased worker confidence ●Ability to do more self-performed maintenance, saving money and increasing job satisfaction ●Ability to lower costs by optimizing system performance
- 14. Schneider Electric 14- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Infrastructure Management Tasks ● Facility Monitoring ● Capacity Management ● IT and Facilities Integration Risks ● Unnoticed and unaddressed facility issues/alarms ● Stranded power and cooling capacity ● Wasted space ● Disconnect between IT and Facilities systems Opportunities ● Avoidance of service interruptions through reporting and trending ● Resource optimization ● Actionable business intelligence resulting from integrated systems and teams
- 15. Schneider Electric 15- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Quality Management Tasks ● Process and Procedure Standardization ● Quality Checks, Inspections and Audits ● Root Cause Analysis and Lessons Learned ● Continuous Improvement Risks ● Introduction of errors due to poor processes and procedures ● Undiagnosed errors result in avoidable service disruptions and costs ● Repetition of errors Opportunities ● Increased productivity and uniform end-user experience through standardized best practices ● Fewer, less consequential and lest costly errors ● System and process optimization
- 16. Schneider Electric 16- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Energy Management Tasks ●Performance Benchmarking ●Efficiency Analysis ●Strategic Sourcing Risks ●Making decisions with inadequate or inaccurate data ●Missing proven energy reduction strategies ●Paying too much for energy supplies Opportunities ●Lowering costs through better energy management ●Increased demonstration of corporate social responsibility ●Regulatory avoidance
- 17. Schneider Electric 17- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Financial Management Tasks ●Purchasing ●Invoice Matching ●Financial Reporting & Analysis Risks ●Slow procurement due to inefficient purchasing ●Payment for products and services not or partially received ●Overpayment for products and services Opportunities ●Shorter periods of reduced redundancy ●Delivery assurance on purchases ●More “bang for the buck”
- 18. Schneider Electric 18- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Performance Monitoring Tasks ●Service Level Agreement (SLA) ●Key Performance Indicators (KPI) ●Performance Measurement and Reporting Risks ●Misplaced priorities generate unproductive activity ●Punitive attitudes that stifle “good” risk taking ●You can’t manage what you don’t measure Opportunities ●Alignment of business goals with operational activities ●Positive reinforcement systems that stimulate innovation ●Solid performance metrics to underpin good business decisions
- 19. Schneider Electric 19- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Most Common Mistakes ●Ineffective Change Management ● Inadequate risk analysis ● Poor or non-existent procedures ● No defined process for performing critical works ●Lack of Formal Training ● Shadowing used as the predominant training method ● Poor evaluation process, no link between certification level and tasking ●Maintenance program is not metrics driven ● Poor asset management ● Few maintenance KPIs ● No linkage between PM and corrective/break-fix maintenance ●Failure to consistently and test evaluate skills ● Existing skills and training comprehension is not formally evaluated ● Scenario drills are not employed ● Incident and Drill results are not evaluated
- 20. Schneider Electric 20- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Most Common Mistakes ●Failure to develop and implement a quality system ● Quality Assurance & Quality Control ● Continuous Quality Improvement ●Poor documentation ● No coherent Sequence of Operations, outdated drawings and schedules, undocumented processes, lack of version control, not digitalized. ●Stuck in manual mode ● Failure to implement CMMS, EDMS, LMS, DCIM ● Buried in spreadsheets and manual reports ●Overconfidence ● Assumption that future performance can be predicted by past experience.
- 21. Schneider Electric 21- Division - Name – Date Schneider Electric – Bob Woolley- 20130502 Building a World Class DCFO Program • Inspect • Assess • Analyze • Report • Review Results • Refresh Goals • Take Corrective Action • Optimize • Design and Develop • Communicate • Train • Implement and Operate • Obtain Support of Senior Management • Align Business Goals and Operational Objectives • Establish Success Metrics Do Act Plan Check
- 22. Thank You Bob Woolley Sr. Director, Global Data Center Services Robert.Woolley@Schneider-Electric.com
Editor's Notes
- #3: Identify the Most Common Mistakes made by Data Center Facility OperatorsIdentify a process for building a World Class DCFO Program