More than 500 hours of downtime have been recorded by 13 of the biggest cloud providers since 2007, according to a new report.
The research, carried out by the International Working Group on Cloud Computing Resiliency, found that the total economic impact of the downtime was $70 million.
The group, formed in March earlier this year by Telecom ParisTech and Paris 13 University, found that far from offering the five nines of reliability, on average availability was estimated to be 99.9 per cent or less.
It said that cloud service availability figures show an average of 7.5 hours unavailable per year. In comparison, the service average unavailability for electricity in a modern capital is less than 15 minutes per year.
The information for the report was gathered from press articles from a number of media outlets, including Cloud Pro. It studied press reports of outages at services provided by Twitter, Facebook, Amazon, Microsoft, Google, Yahoo and Paypal, among others.
It estimated the cost of outages varies from provider to provider with outage at travel service provider Amadeus running at $89,000 per hour up to $225,000 for PayPal. The researchers said that these figures are based on hourly costs accepted by the industry. It added that due to imperfect methodology, such gures are "most likely underestimated, since many events are not published in the press releases and the current procedure to collect events by IWGCR leaves a lot of room for missed outages."
Professor Christophe Crin at Paris 13 University and Coordinator of IWGCR said that the number of users hit by an outage was also not taken into account due to the "lack of public data."
"We encourage reading the report to understand the limitations of the current ranking and how we plan to improve it in the future," he said.
The group said it now intends to focus on improving its observations of cloud service availability and enhance measurement of the economic impact.
