Model-Driven Application Refactoring To Minimize Deployment Costs In Preemptible Cloud Resources
收藏资源简介：
1. Attached files: This archive contains 1440 MATLAB files, each one containing the results of a single experiment.<br> The name of each file follows the following format: A_B_C_null_D_0.95_E_F.mat Where the fields A, B, C, D, E, and F are described as follows. A: number of users.<br> Considered values are: 2500, 5000, 10000, 20000, 40000. B: variation in the profile of the requests.<br> Considered values are: ref, var1, var2, var3, var4, var5.<br> ref -> reference experiment, no users are halved or doubled<br> var1 -> users in class 1 halved, other users doubled <br> var2 -> users in class 2 halved, other users doubled <br> var3 -> users in class 3 halved, other users doubled <br> var4 -> users in class 4 halved, other users doubled <br> var5 -> users in class 5 halved, other users doubled C: variation of the replaceability set of the application server.<br> Considered values are: ref, k1, k2, k3, k4, k5.<br> ref -> reference experiment, no rates are halved or doubled<br> k1 -> only possible substitution has rate k1 halved and other rates doubled<br> k2 -> only possible substitution has rate k2 halved and other rates doubled <br> k3 -> only possible substitution has rate k3 halved and other rates doubled <br> k4 -> only possible substitution has rate k4 halved and other rates doubled <br> k5 -> only possible substitution has rate k5 halved and other rates doubled D: variation of the design constraints.<br> Considered values are: none, 4, 34, 234.<br> none -> no components can be replicated<br> 4 -> only the application server can be replicated<br> 34 -> only the application server and the database server can be replicated<br> 234 -> all the components can be replicated E: Optimization algorithm.<br> Considered values are: norefactoring, replacement, reassignment, full<br> norefactoring -> experiment with no refactorings<br> replacement -> experiment with only replacement refactoring<br> reassignment -> experiment with only reassignment refactoring<br> full -> experiment with replacement and reassignment refactorings F: Experiment seed.<br> Considered values are from 1 to 20 2. Data format: MATLAB data format, can be loaded from MATLAB using the following command: results = load(filename); results is defined as a structure with the following fields: results.cost<br> Type: scalar, positive real number.<br> Desc: hourly cost in US dollars. <br> results.time<br> Type: scalar, positive real number.<br> Desc: total time (in seconds) needed by the algorithm to compute the solution. results.evaluations<br> Type: scalar, positive integer number.<br> Desc: number of constraints evaluations needed by the algorithm to compute the <br> solution. <br> results.d<br> Type: matrix, non negative positive real number. <br> Desc: association matrix between rented resources (columns) and application <br> components (rows). The sum of all the elements of this matrix is equal to<br> the ECUs used by the application.
