Boosting a global tech and internet services provider’s data center cluster resilience

The data center challenge

A global leader in technology and internet services operates a vast network of data centers. It faced a significant challenge in assessing the risk of downtime, especially in scenarios where a single event could affect multiple data centers simultaneously. Traditional risk assessment tools were insufficient, as they did not account for interdependencies and the potential for widespread damage.

The business needed detailed insight into the vulnerabilities of its data center clusters to help it make informed decisions about operational planning and risk mitigation, as well as provide due diligence to their customers.

The tailored consulting and analytics solution

1. We developed a bespoke shared fate resilience assessment tool to identify and quantify the risk of downtime across multiple data centers within clusters. We analyzed the location data using advanced models, including our Global Peril Diagnostic and catastrophe models to assess current hazards, and Climate Diagnostic for potential impact of chronic hazards such as drought and heat stress to water resources, availability and utilities.
2. We then gathered essential information on building characteristics, mitigation measures, business continuity planning and utilities dependencies.
3. We evaluated the risk of four types of potential threats: natural catastrophes, utilities and power outages, proximity to high-risk locations, as well as geopolitical risks as an expanded scope.
4. Our solution delivered a tailored, structured and comprehensive assessment of the potential risks to the tech company’s operations to enable better strategic planning and a more effective response to interconnected and emerging threats.
5. We generated single numerical risk scores for each data center, making it easier to prioritize and allocate resources for risk mitigation, as well as cluster risk scores to help the business understand and globally compare the cumulative impact of a single event to each cluster. We also provided downtime estimates that made it easy to recognize and respond to imminent threats.

The impact for the data centers

By assessing and quantifying complex risks using sophisticated qualitative and quantitative frameworks and providing actionable insights, the business can better understand and manage the hazards and vulnerabilities of its data centers. Its data centers are now more likely to remain resilient, enabling greater uptime, even during a catastrophic event. With a tailored framework to consider interdependencies and the impact of widespread events, the business can make more informed strategic decisions on operations, planning and risk mitigation, as well as respond to imminent threats more impactfully.

For example, our exposure and vulnerability assessment helped the company consider whether to relocate some of their operations within a cluster to another colocation data center to avoid the shared fate and potential downtime due to flood risk.

Based on the initial work we carried out for existing data centers, the business asked us to expand the scope to evaluate the natural catastrophe and climate exposure of new data centers. We worked collaboratively with both the technology company and engineering design partners to inform design and construction requirements, as well as site selection.

We also proactively included geopolitical risks, such as civil unrest, terrorism, war and proximity to terrorist targets to help the organization consider the potential impact of previously unconsidered threats.

Ready to take control and get more value from your data center risk resiliency? Request a demo of our solutions or speak to our specialists today.