At the date of simulation (July 2011), these were being advertised at a cost of D h = $0.085/hour (approximately $60 for a whole month of usage) for an on-demand instance.
The values in Table 1 differ slightly from those described in [1]; which states that the monthly cost of an on-demand instance is "approximately $60 for a whole month of usage" page 5, [1], and does not give absolute values for the monthly usage cost of reserved instances.
This will cost very little but will provide access to a resource should the infrastructure fail for less cost than that of an on-demand instance.
Once a forecast has been made, the broker must make a decision on whether to hedge the risk and invest in a reserved instance, or to wait until the next period and buy an on-demand instance.
In our simulation, the cost of an on-demand instance for the entire month is $60.
If not, the broker must purchase an on-demand instance and provide it to the client.
With Linux Amazon EC2 Reserved Instances, you could reduce the cost of your instance usage by up to 56% compared to an On-Demand instance.
With a cost factor C = 1 and on-demand price P D = 2, the cost of options from the broker (orange dotted line) is always cheaper than purchasing an on-demand instance directly from the provider (purple dotted line).
In [1], R&C assume that P M is the price of an on-demand instance purchased directly from the provider, P D. Using current AWS prices (Table 4), we have: P D = $43.833.
In R&C's original work, the model was bounded to ensure that options from the broker are always cheaper for users than an on-demand instance purchased directly from the provider.
This also means that in our system presented here, providers have a 12- or 36-month indication of market demand, rather than just the one month that was the case in Wu et al.'s original formulation of the WZH model, or no indication (as per the case of an on-demand instance).
