Data Center Dev Notes Flashcards

1
Q

What’s the typical dev cost of a data center?

A

$10 million per MW of load capacity

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the 3 types of revenue models / lease structures for data centers?

A

Wholesale, Colocation, Powered shell

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are the financial performance metrics of data centers?

A

Return on invested capital (8-12%) and IRR (12-15%)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What are operational metrics of data centers?

A

Power usage effectiveness (1.2.-1.5) and revenue per sq foot ($150-$500)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What are the primary risks in data center dev?

A

Tech obsolescence and Power procurement

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is AWS’s data center expansion strategy? (3 things)

A
  1. Focused on availability zones (AZ’s)
  2. Access to low-cost power and low-latency fiber
  3. Global expansion
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What are the priorities in AWS site selection? (4 things)

A
  1. Power availability and cost
  2. Fiber connectivity
  3. Land and zoning
  4. Environmental considerations
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What are AWS’s power and sustainability initiatives?

A
  1. 100% renewable energy by 2025
  2. Efficiency and cooling innovation
  3. Grid scale energy storage solutions
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is AWS’s development and construction process? (3 things)

A
  1. Speed (modular and prefab)
  2. Leasing or Building (AWS prefer to own and operate but do lease from colocation providers if necessary)
  3. Vendor and supply chain management (AWS has strategic partners to mitigate supply chain risks)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What are some key challenges and Industry Trends affecting AWS? (3 things)

A
  1. Power constraints
  2. Regulatory scrutiny
  3. AI & High density compute (require more performance and cooling)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is an AZ? What’s an example?

A

An availability zone is a location within an AWS region that consists of one or more separate data centers.

An example would be US-East-1 in Virginia

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

How do AZ’s work in AWS’s infrastructure? (4 things)

A
  1. Each AWS region has multiple AZ’s
  2. They are physically separated
  3. They have redundant power, cooling and networking
  4. Low latency connectivity between AZ’s
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Why are AZ’s so important to AWS? (4 things)

A

Because they meet the demands of cloud infrastructure requirements such as:

  1. Fault tolerance and disaster recovery
  2. Scalability and load distribution
  3. Compliance and data residency
  4. Network optimization
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

How do AZ’s affect AWS Site Selection and Development? What are they looking for? (4 things)

A
  1. Power Grid Independence (each AZ must have access to backup power)
  2. Network redundancy (AWS ensures that multiple fiber paths exist between AZ’s)
  3. Geographic separation (AZ’s are placed far enough apart to prevent a disaster from taking down multiple zones)
  4. Land and expansion space (to accommodate future development)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is a real world example of an AZ?

A

US-East-1 (Northern Virginia) is AWS largest region with 6+ locations and the highest density.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What are the core focus areas for AWS Site Selection? (4 things)

A
  1. Power availability and cost
  2. Fiber connectivity
  3. Zoning
  4. Environmental Compliance
17
Q

How does AWS design and engineer a site? (3 things)

A
  1. Modular Design
  2. Scalable power and cooling infrastructure
  3. Sustainable energy

AWS prioritizes flexibility in design, allowing for future retrofitting to accommodate AI and high-performance computing (HPC) workloads.

18
Q

How does AWS speed up the permitting and pre-con process?

A

AWS works with a network of global suppliers and pre-negotiates large-scale orders to speed up procurement.

19
Q

Describe the AWS Construction and Deployment Process

A
  1. Site Preparation (land is graded, foundations laid, and infrastructure for power, water and fiber is set up)
  2. Structural build out (modular components are assembled for rapid deployment)
  3. Power and cooling systems are installed
  4. Networking and security systems are installed
  5. Testing and commissioning is commenced to ensure reliability for customers
20
Q

What are some construction challenges and how does AWS address them?

A
  1. Power Constraints
    * Challenge: Power grid limitations in key regions (e.g., Northern Virginia, Phoenix).
    * Solution: AWS works directly with utilities to build new substations and invests in grid-scale battery storage.
  2. Supply Chain Delays
    * Challenge: Shortages of electrical transformers, cooling equipment, and steel impact build timelines.
    * Solution: AWS pre-orders materials in bulk and works with multiple vendors to secure alternative supplies.
  3. Local Regulations & Permitting Delays
    * Challenge: Complex zoning laws, environmental impact studies, and permitting delays can slow projects.
    * Solution: AWS has dedicated government relations teams that work with local regulators to streamline approvals.
  4. Sustainability & Water Usage Concerns
    * Challenge: Data centers require large amounts of electricity and, in some cases, water for cooling.
    * Solution: AWS is shifting to waterless cooling, low-carbon energy sources, and advanced energy-efficient chips to reduce power consumption.
21
Q

What’s one of the largest opex expenses for data centers?

A

Volumetric energy costs