Autonomic Provisioning and Application Mapping on Spot Cloud Resources
Description
1. Attached files:
500_100_fmincon_0.95_1.mat
Experiment with 500 users, 100ms max response time, 95% availability, exact algorithm.
500_100_heuristic_0.95_1.mat
Experiment with 500 users, 100ms max response time, 95% availability, our algorithm.
2000_70_fmincon_0.95_1.mat
Experiment with 2000 users, 70ms max response time, 95% availability, exact algorithm.
2000_70_heuristic_0.95_1.mat
Experiment with 2000 users, 70ms max response time, 95% availability, our algorithm.
2000_100_fmincon_0.9_1.mat
Experiment with 2000 users, 100ms max response time, 90% availability, exact algorithm.
2000_100_heuristic_0.9_1.mat
Experiment with 2000 users, 100ms max response time, 90% availability, our algorithm.
2000_100_fmincon_0.95_1.mat
Experiment with 2000 users, 100ms max response time, 95% availability, exact algorithm.
2000_100_heuristic_0.95_1.mat
Experiment with 2000 users, 100ms max response time, 95% availability, our algorithm.
2000_100_fmincon_0.999_1.mat
Experiment with 2000 users, 100ms max response time, 99.9% availability, exact algorithm.
2000_100_heuristic_0.999_1.mat
Experiment with 2000 users, 100ms max response time, 99.9% availability, our algorithm.
2000_300_fmincon_0.95_1.mat
Experiment with 2000 users, 300ms max response time, 95% availability, exact algorithm.
2000_300_heuristic_0.95_1.mat
Experiment with 2000 users, 300ms max response time, 95% availability, our algorithm.
10000_100_fmincon_0.95_1.mat
Experiment with 10000 users, 100ms max response time, 95% availability, exact algorithm.
10000_100_heuristic_0.95_1.mat
Experiment with 10000 users, 100ms max response time, 95% availability, our algorithm.
2. Data format:
MATLAB data format, can be load from MATLAB using the following command:
results = load(filename);
results is defined as a structure with the following fields:
results.cost
Type: scalar, positive real number.
Desc: hourly cost in US dollars.
results.time
Type: scalar, positive real number.
Desc: total time (in seconds) needed by the algorithm to compute the solution.
results.evaluations
Type: scalar, positive integer number.
Desc: number of constraints evaluations needed by the algorithm to compute the
solution.
results.d
Type: matrix, non negative positive real number.
Desc: association matrix between rented resources (columns) and application
components (rows). The sum of all the elements of this matrix is equal to
the ECUs used by the application.
Files
dubois-iccac15-results.zip
Files
(372.3 kB)
Name | Size | Download all |
---|---|---|
md5:8d1172fc6b94b4246411640d6d9ba0bf
|
372.3 kB | Preview Download |
Additional details
Related works
- Is supplement to
- 10044/1/25102 (Handle)