├── GCD_VMs.tar.gz
└── README.md


/GCD_VMs.tar.gz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/HiPro-IT/CPU-and-Memory-resource-usage-from-Google-Cluster-Data/327b8ce301d43fd09e0a6b63279edca0728d1af8/GCD_VMs.tar.gz


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | This project contains the workload traces used in the simulations for the paper entitled "Virtual Machine Consolidation with Multiple Usage Prediction for Energy-Efficient Cloud Data Centers", which has been published to IEEE Transactions on Services Computing.
 2 | 
 3 | A set of the CPU and Memory utilization was created from the original Google Cluster Data (GCD) dataset (https://github.com/google/cluster-data). 
 4 | 
 5 | To create the CPU and the Memory utilization, the tasks of each job were aggregated by summing their CPU and Memory consumption every five minutes in a period of 24 hours. The dataset was extracted over the first ten days period (10 days May 2011) by filtering the utilization of CPU and memory from 5 to 90 percent, resulting in a total of 1,600 VMs.
 6 | 
 7 | Each txt file contains two columns:
 8 | - first column: CPU utilization (%)
 9 | - second column: Memory utilization (%)
10 | 
11 | Charactristics of the workload traces:
12 | - CPU: 
13 |     + Mean: 21.84
14 |     + St. dev: 13.62
15 |     + Median: 18
16 | - Memory:
17 |     + Mean: 19.55
18 |     + St. dev: 16.66
19 |     + Median: 12
20 | 
21 | When you use this dataset, please cite to the original Google cluster workload traces (https://github.com/google/cluster-data) and our paper mentioned above.
22 | 


--------------------------------------------------------------------------------