DCM 18.1 How to Prepare a Data Center Strategy What you need to know to build a business case for data center sourcing Presented by: Steve Miano, Managing Principal, & Gary Davis, Principal/Director, Data Center Practice at PlanNet Consulting 1
DCM 18.1 How to Prepare a Data Center Strategy We will present an informative how-to-guide for data center managers looking to understand the process of developing a data center strategy. Along with helpful tips, real-life project examples will be utilized for decisionmakers to decide whether to upgrade, build, consolidate or co-locate their data centers. 2
Agenda What is a data center strategy? Getting started Assessing the current state Developing a future state model Building a business case What your decision makers want to know Case studies 3
Data Center Strategy A data center strategy is usually initiated for any or all of the following reasons: Data center failures are impacting the business Growth is expected to exceed power, cooling and/or space capacities Risk real or perceived Lowering Cost of Operation Improve systems availability and disaster recovery Inform a decision to build, co-locate or a combination of approaches 4
Getting Started Define your objectives Business drivers Technology imperatives Desired outcome Assemble a Core Team Identify/appoint a project sponsor Sponsorship typically comes from Real Estate, Facilities or IT Typical make-up of a Core Team Facilities representative (VP, Director) IT representatives - CIO, IT Infrastructure VP, Network, user representative(s) Procurement, sourcing and finance 5
Identify Stakeholders A data center strategy has many stakeholders It s critical to engage to appropriate stakeholder resources to gain consensus and eliminate surprises Missing a key stakeholder is analogous to missing a tire on your car 6
Gather Information Formalize the project with a stakeholder kick-off Introduce the initiative and objectives Layout timelines Set expectations 7
Assessing the Current State Develop and issue a Comprehensive Request for Information and meet with Stakeholders to gather information Some of the information is available electronically (e.g., CMDB, As-Built drawings, energy bills, etc.) Some of the information will be drawn out in Stakeholder meetings (e.g., application portfolio, financial models, etc.) RFI Categories Equipment/application inventory Data Center Facilities Real Estate Operations Network Business Systems and Services Business Continuity Finance Growth and Capacity Planning IT Strategic Plan 8
Assessing the Current State Key Points Establish current demand load KW is the currency Determine historical demand growth (3-5 years) Assess existing facility s attribute and constraints (e.g., Tier rating, power, cooling, space, SPOCs) Identify applications and their tier levels Identify network constraints (e.g., latency sensitive applications) Identify adjacency requirements/constraints Identify key business and IT initiatives (e.g., new business ventures, merger/acquisition, virtualization, etc.) Document outage history (many executives are unaware of outages) 9
Outages.what outages? 10
Future State Identify the future state scenario Establish operational objectives and service levels Establish availability targets Tier Rating Geography Determine efficiency objectives (PUE) Define sustainability goals Consider adaptability needs Plan for the Unplanned 11
Establish the Future State Determine relevant sourcing models Co-Location Greenfield Tenant Improvement Retrofit Existing Facilities Cloud Managed Services Select markets to be evaluated Ideally, markets with co-location options, cheap power and free-cooling potential Determine business affinity to particular markets Existing operations Business drivers Existing or future real estate or facility programs Include any market bias of executive management 12
Establish Demand Forecast Align business growth with IT growth Optimize IT deployment as part of the deployment of a new data center 30,000 28,000 26,000 24,000 22,000 Capacity Demand Forecast Capacity Demand - k Watts 20,000 18,000 16,000 14,000 12,000 10,000 8,000 6,000 4,000 2,000 0 FY09 FY10 FY11 FY12 FY13 FY14 FY15 FY16 FY17 FY18 Un-optimized Managed Optimized 13
Establish Demand Forecast Establish capacity threshold vs. demand forecast Depict historical growth with future planning Identify strategies to mitigate capacity constraints 14
Define Day 1/Day 2 Plan for incremental deployment based on demand forecast 16,000 14,000 Site 1 - Production Buildout Phases 12,000 k Watts 10,000 8,000 6,000 4,000 * DAY 1: 3,900 kw, 22.5K SF *DAY 2: 7,900 kw, 22.5K SF 2,000 0 FY09 FY10 FY11 FY12 FY13 FY14 FY15 FY16 FY17 FY18 Managed Forecast Deployed Capacity 15
Market Analysis Qualitative Metrics use to disqualify markets Energy Rates vs. Nat l average Sustainability Free cooling Reliability Telecommunications Labor Facilities Diversity Relative costs Latency Availability Relative costs Control/Lease Terms Transportation/Accessibility Flight Availability Door to Door Time Vendor and Services Support Proximity to critical vendors Environmental Risk Seismic/Volcanic Hurricane/Tidal Severe Weather Incentives (very dependent on specific properties) Enterprise Zones Sales Tax Energy rebate programs 16
Qualitative Market Rankings What s important to you? Keep it simple 17
Building a Business Case Determine Capital Expenditures Determine Operational Expenditures Develop a Multi-Year Total Cost of Ownership for each model (5/10 yr) Compare TCO for each model 18
Determine CapEx & OpEx CAPEX Construction and Soft Costs (Greenfield, TI) Cable Plant Network Electronics Depreciation Migration Equipment IT Labor / Services OPEX Lease costs Power Maintenance Facility Management Security IT Operations Staff Telecommunications Services Sales Tax Migration 19
Total Cost of Operation Co-location Example 20
Total Cost of Operation Tenant Improvement Example Seattle TI/Lease Year 1 Year 2 Year 3 Year 4 Year 5 5 year Total Year 6 Year 7 Year 8 Year 9 Year 10 10- Year Total Operating Costs Power $ 297 $ 320 $ 345 $ 371 $ 400 $ 1,734 $ 429 $ 460 $ 494 $ 530 $ 568 $ 4,216 Predictive Maintenance $ 131 $ 221 $ 279 $ 233 $ 240 $ 1,104 $ 247 $ 254 $ 262 $ 270 $ 278 $ 2,415 Rent $ 462 $ 476 $ 490 $ 505 $ 520 $ 2,453 $ 536 $ 552 $ 568 $ 585 $ 603 $ 5,296 IT Staff $ 250 $ 258 $ 265 $ 273 $ 282 $ 1,328 $ 290 $ 299 $ 308 $ 317 $ 326 $ 2,868 Facilities Staff $ 147 $ 151 $ 155 $ 160 $ 165 $ 778 $ 170 $ 175 $ 180 $ 186 $ 191 $ 1,680 Telecommunications $ 828 $ 845 $ 861 $ 879 $ 896 $ 4,309 $ 914 $ 932 $ 951 $ 970 $ 990 $ 9,066 Other Costs $ - $ - $ - $ - $ - $ - $ - $ - $ - $ - $ - $ - DC Equipment Sales Tax $ 131 $ 134 $ 137 $ 139 $ 142 $ 683 $ 145 $ 148 $ 148 $ 151 $ 151 $ 1,425 Operating Costs Subtotal $ 2,246 $ 2,405 $ 2,533 $ 2,561 $ 2,644 $ 12,388 $ 2,730 $ 2,820 $ 2,911 $ 3,009 $ 3,107 $ 26,966 Capital Costs DC TI $ 6,078 $ - $ - $ - $ - $ 6,078 $ 876 $ - $ - $ - $ - $ 6,954 Racks / Cabling $ 1,112 $ - $ - $ - $ - $ 1,112 $ 127 $ - $ - $ - $ - $ 1,240 Network Electronics $ 1,157 $ - $ - $ - $ - $ 1,157 $ 378 $ - $ - $ - $ - $ 1,535 Migration Costs $ - $ - $ - $ - $ - $ - $ - $ - $ - $ - $ - $ - Capital Costs Subtotal $ 8,347 $ - $ - $ - $ - $ 8,347 $ 1,381 $ - $ - $ - $ - $ 9,728 Depreciation $ 796 $ 796 $ 859 $ 796 $ 796 $ 4,041 $ 716 $ 716 $ 557 $ 557 $ 557 $ 7,145 Total $ 3,041 $ 3,200 $ 3,392 $ 3,357 $ 3,440 $ 16,429 $ 3,447 $ 3,537 $ 3,468 $ 3,566 $ 3,664 $ 34,111 21 In thousands
Compare Models Annual Operating Costs Years 1-10 (in 1000's) Year 1 Year 2 Year 3 Year 4 Year 5 5 year Total Dif $ Dif % 10 Year Total Dif $ Dif % As-Is Owned $ 2,929 $ 3,125 $ 3,461 $ 3,661 $ 3,878 $ 17,054 $ - 0% $ 39,639 $ - 0% Optimized Owned $ 2,669 $ 2,869 $ 3,047 $ 3,232 $ 3,433 $ 15,251 $ (1,804) -11% $ 35,527 $ (4,112) -10% Market 1 Co-Lo $ 3,145 $ 3,117 $ 3,281 $ 3,298 $ 3,383 $ 16,224 $ (830) -5% $ 33,773 $ (5,866) -15% Market 2 Co-Lo $ 3,205 $ 3,188 $ 3,362 $ 3,391 $ 3,489 $ 16,635 $ (419) -2% $ 34,896 $ (4,743) -12% Market 3 TI / Lease $ 4,388 $ 3,653 $ 3,900 $ 3,882 $ 3,993 $ 19,816 $ 3,620 21% $ 44,423 $ 4,784 12% Market 4 Co-Lo $ 3,327 $ 3,400 $ 3,610 $ 3,677 $ 3,814 $ 17,828 $ 3,449 20% $ 38,203 $ (1,436) -4% Market 5 TI / Lease $ 3,302 $ 3,497 $ 3,730 $ 3,717 $ 3,823 $ 18,068 $ 3,447 20% $ 38,071 $ (1,569) -4% Market 6 Co-Lo $ 3,306 $ 3,368 $ 3,557 $ 3,622 $ 3,746 $ 17,599 $ 3,425 20% $ 37,778 $ (1,861) -5% 22
Scenario Analysis Annual Operating Expense Comparison $10,000 Annual Operting Expenses (1,000's) $9,000 $8,000 $7,000 $6,000 $5,000 $4,000 $3,000 $2,000 $1,000 2009 2009 w/stabalization Scenario 2 $65.5M 10 Yr TOC 0 1 2 3 4 5 6 7 8 9 10 Year Scenario 2 Scenario 1 Scenario 3 Senario 1 $68.1M 10 Yr TOC Scenario 3 (Current-state with expansion) $58.7M 10Yr TOC 23
Case Studies Major Regional Bank Issues Aging primary data center in a high risk region Sub Tier 2 design History of outages Running out of capacity Facing major capital expenditures to retrofit the primary data center Lease expiring on Disaster Recovery site Results Analysis Assess deficiencies of existing facilities Determine amount of time before the DC reaches capacity Evaluate low-risk markets Evaluate own vs. co-lo Outcome Move primary DC to co-lo Retrofit existing DC to Tier 2 Repurpose existing DC to sub-production and DR Improved availability with nominal increases in TOC 24
Case Studies Global Technology Company Issues 40+ data centers worldwide Growing through acquisition Unsustainable operating costs Unmanageable data center footprint Business driver to consolidate operations Latency sensitivity from global engineering applications Results Analysis Outcome Assess operation efficiencies and costs Evaluate multiple markets and corporate owned real estate Evaluate geo-regional consolidation alternatives Analyze enterprise architecture Evaluate own vs. co-lo Geo-regional consolidation (N.A, ENAME, PAC-RIM) Deploy owned Tier 2+ DCs Multi-site recovery $100M+ 10-year future cost avoidance 25
Case Studies Global Entertainment Company Issues Significantly high energy costs High-risk location Planning for significant business technology initiatives Facing future capital expenditures to uplift primary data center Results Analysis Assess deficiencies of existing facilities Determine impact of new computing demand Evaluate low-cost markets Evaluate own vs. co-location Outcome Expand primary DC to co-lo Leverage existing facility for business partner and DR Recommended phased deployment to optimize ROI 26
Case Studies Regional Healthcare Company Issues Aging primary data center in a high risk region Sub Tier 2 design History of outages Running out of capacity Facing major capital expenditures to retrofit the primary data center Affinity for in-state deployment Results Analysis Assess deficiencies of existing facilities Assess mitigation strategies to buy time Evaluate regional markets Evaluate own vs. co-location Outcome Move primary DC to co-lo in a lower risk geography Repurpose existing DC to sub-production and DR Stabilize current environment Recommended best value alternative 27
Thank you for your time! Steve Miano Principal PlanNet Consulting 714.982.5820 smiano@plannet.com Gary Davis Principal PlanNet Consulting 714.982.5886 gdavis@plannet.com www.plannet.com 28