Data Centre Power Consumption Models
Executive Summary
Key Takeaways
- ✓ Power consumption modelling forecasts actual electricity draw and cost, distinct from capacity planning, which governs how much power can be sold, and the two should be modelled as separate, linked disciplines.
- ✓ Load factor, the ratio of average actual power draw to contracted (peak) capacity, should be modelled explicitly, since utilities typically charge separately for demand (peak capacity) and consumption (actual usage), and a low load factor increases effective cost per unit of actual consumption.
- ✓ Utility tariff structure, demand charges, consumption charges, and any time-of-use pricing, should be modelled against the facility's actual load profile, not a single blended electricity rate.
- ✓ Power cost should be modelled as a function of both total facility power (including non-IT overhead captured by PUE) and the applicable utility tariff structure, not IT load alone.
Objective¶
This guide sets out how to model data centre power consumption and cost within Data Centre Financial Modelling, distinct from the capacity planning discipline that governs sellable capacity.
Power Consumption Versus Capacity Planning¶
Capacity planning governs how much power can be sold to tenants as billable critical IT load capacity. Power consumption modelling is a distinct, linked discipline forecasting the facility's actual electricity draw and cost, which depends on how much of that sold capacity is actually being utilised by tenants, plus the facility's own non-IT power overhead.
Load Factor¶
Load factor is the ratio of average actual power draw to contracted (peak) capacity. Utilities typically charge separately for demand, based on peak capacity, and consumption, based on actual usage, so a low load factor, actual average draw well below contracted peak capacity, increases the effective cost per unit of actual consumption, since the fixed demand charge is spread over less actual usage. Load factor should be modelled explicitly and tracked over time as tenant utilisation ramps.
Utility Tariff Structure¶
Power cost should be modelled against the facility's actual utility tariff structure, distinguishing demand charges, consumption charges, and any time-of-use pricing that varies the rate by time of day, rather than applying a single blended electricity rate. A blended rate can materially misstate cost if the facility's actual load profile does not match the assumptions implicit in that blended figure.
Total Facility Power as the Cost Base¶
Power cost should be modelled from total facility power, IT load plus non-IT overhead as captured by power usage effectiveness (PUE), since total facility power is what is actually metered and billed by the utility. Modelling power cost from IT load alone understates total consumption and cost by the PUE multiplier.
Common Construction Pitfalls¶
Power cost modelled from IT load alone. Understates total consumption and cost by omitting the PUE-driven non-IT overhead.
Single blended electricity rate applied regardless of tariff structure. Misstates cost where the facility's actual load profile diverges from the blended rate's implicit assumptions.
Load factor not modelled explicitly. Misses the cost impact of contracted capacity substantially exceeding actual tenant utilisation during a ramp-up period.
Recommended Practices¶
- Model power consumption and cost as a distinct, linked discipline from capacity planning.
- Track load factor explicitly, particularly during tenant ramp-up periods.
- Model utility tariff structure (demand, consumption, time-of-use) against the facility's actual load profile.
- Base power cost on total facility power (IT load times PUE), not IT load alone.
Continue Reading¶
Related Pillars¶
Related Technical Guides¶
Related Glossary¶
How OXXON tests thisRun a free structural check with FMAE
Frequently Asked Questions
How does power consumption modelling differ from capacity planning?
Capacity planning governs how much power can be sold to tenants as billable capacity. Power consumption modelling forecasts the facility's actual electricity draw and cost, which depends on how much of that sold capacity is actually being utilised, plus the facility's own non-IT power overhead.
What is load factor and why does it matter?
Load factor is the ratio of average actual power draw to contracted (peak) capacity. Utilities typically charge separately for demand (based on peak capacity) and consumption (based on actual usage), so a low load factor, where actual average draw is well below contracted peak capacity, increases the effective cost per unit of actual consumption, since the fixed demand charge is spread over less actual usage.
How should utility tariff structure be modelled?
Against the facility's actual load profile, distinguishing demand charges (based on peak capacity), consumption charges (based on actual usage), and any time-of-use pricing that varies rate by time of day, rather than a single blended electricity rate that can misstate cost if the facility's load profile does not match the tariff structure's assumptions.
Why should power cost be modelled from total facility power, not just IT load?
Because total facility power, IT load plus non-IT overhead such as cooling and power distribution losses captured by PUE, is what is actually metered and billed by the utility. Modelling power cost from IT load alone understates total consumption and cost by the PUE multiplier.
Related Articles
Data Centre Financial Modelling
Data centre financial modelling is the discipline of modelling a data centre operator's revenue, cost, and capital structure from its capacity-denominated drivers, power, space, and cooling capacity, rack density, and tenant contract structure, rather than the generic market-price and headcount-growth drivers used in most corporate models, or the pure occupancy-and-lease-term drivers of conventional commercial real estate. This page is the hub for the Knowledge Centre's data centre financial modelling content: how colocation, hyperscale, and enterprise business models each require a distinct model architecture, how rack revenue and occupancy are decomposed into their separable underlying drivers, and how capacity planning and financial KPIs tie the model together, as this domain expands to cover operations, revenue, investment, and governance practice across the sector.
Power Usage Effectiveness (PUE)
Power usage effectiveness (PUE) is calculated as total facility power divided by critical IT load power, with a value approaching 1.0 indicating that nearly all power consumed is delivered to IT equipment rather than lost to cooling, power distribution, and other non-IT overhead. PUE is the standard industry measure of data centre power efficiency, and because power is typically one of the largest operating cost categories, a facility's PUE directly drives its power cost per unit of billable capacity and, in turn, its profitability.
Data Centre Capacity Planning Models
Data centre capacity is jointly constrained by power, floor space, and cooling capability, and the binding constraint can shift as tenant rack density changes. This guide sets out how to model capacity planning across all three constraints simultaneously, how phased capacity delivery should be scheduled against demand, and why treating any single constraint as the sole capacity driver risks overstating achievable revenue.
Critical IT Load
Critical IT load is the amount of power a data centre facility delivers directly to IT equipment, servers, storage, and networking, and is the industry-standard unit for expressing a facility's billable and sellable capacity. It excludes the additional, non-IT power drawn by cooling and power distribution overhead, which is instead captured separately through power usage effectiveness (PUE). Critical IT load, in kW or MW, is the capacity figure that data centre revenue, capacity planning, and portfolio scale metrics are all built around.