Introduction
-
(1) A thermal management-based resource scheduling method (TM-VMC) for the optimization of the total energy consumption of the data center. This method includes four algorithms in the process of VMC. TM-VMC can proactively avoid data center hot spots and minimize the total energy consumption of the data center while meeting SLAs (Service Level Agreements).
-
(2) An overload detection strategy (TU) based on host temperature and utilization. It determines whether a host is overloaded by detecting host temperature and utilization status in real time. It relocates redundant VMs away from the overloaded hosts, proactively avoiding data center hot spots.
-
(3) An underload host detection method (HOAVG) based on median average utilization. It selects underloaded hosts based on median average utilization and shuts them down, which avoids the overload problem caused by greedy server shutdown policies.
-
(4) A virtual machine selection policy (MMR) based on the memory allocated to the VMs. It migrates the virtual machines with the largest allocated memory, which reduces the frequent migration activities in the data center.
-
(5) An improved ant colony algorithm (UACO) used in the virtual machine placement stage. It includes a novel state transition rule and fitness function suitable for the thermal management resource scheduling problem. It also uses an improved pheromone update method to avoid the problem of easily falling into local optima in traditional Ant Colony Optimization algorithm (ACO), allowing the algorithm to find the optimal virtual machine placement solution in a short time.
abbreviation | Definition |
---|---|
VM | Virtual machine |
VMC | Virtual machine consolidation |
TM-VMC | A Thermal Management-based Virtual Machine Consolidation Method |
VMP | Virtual machine placement |
MMR | A virtual machine selection policy based on maximum migrated memory |
TU | An overload detection strategy based on host temperature and utilization |
HOAVG | an underload host detection method based on median average utilization |
SLA | Service Level Agreement |
CRAC | Computer Room Air Conditioning |
COP | Coefficient of Performance |
ACO | Ant Colony Optimization algorithm |
UACO | A virtual machine placement policy based on improved ant colony algorithm |
Related work
Overall architecture based on thermal management resource scheduling
Overall framework
Problem definition
Variable | Description |
---|---|
\({P}_{total}\) | Total data center power consumption |
\({P}_{IT}\) | Computing system power consumption |
\({P}_{CRAC}\) | Cooling system power consumption |
\({U}_{max}\) | Upper threshold of the host CPU utilization |
\({T}_{max}\) | Upper threshold for the CPU temperature of the host |
\({T}_{cpu}^{j}\) | CPU temperature of host j |
R | Server heat resistance |
C | Server heat capacity |
\({R}_{cpu}\) | CPU capacity |
\({R}_{mem}\) | Memory resource capacity |
\({U}_{cpu}^{j}\) | CPU utilization of host j |
\({R}_{bw}\) | Bandwidth resource capacity |
\({P}_{i}\) | Power consumption of a single node \(i\) |
\({T}_{sup}\) | CRAC air supply temperature |
Data center modeling
IT energy consumption model
Cooling system energy consumption model
Temperature model
Thermal management-based virtual machine consolidation
VM consolidation process
Host overload detection policy
Host underload detection policy
VM selection policy
VM placement policy
Initial pheromone and heuristic information
State transition rule
Pheromone update rule
Experiment setup and analysis of results
Experiment setup
Type | CPU Type | Frequency (GHz) | Core | RAM (GB) |
---|---|---|---|---|
IBM × 3550 M3 | Intel Xeon X5670 | 2.93 | 6 | 4 |
IBM × 3550 M3 | Intel Xeon X5675 | 3.07 | 6 | 4 |
Type | CPU frequency (MIPS) | RAM (MB) |
---|---|---|
Extra large instance | 2500 | 900 |
Large instance | 2000 | 1700 |
Small instance | 1000 | 1400 |
Micro instance | 500 | 600 |
Load instance | Date | Number of VMs | Average utilization rate(%) | The standard deviation(%) |
---|---|---|---|---|
P1 | 2011/03/03 | 1052 | 12.31 | 17.09 |
P2 | 2011/03/06 | 898 | 11.44 | 16.83 |
P3 | 2011/03/09 | 1061 | 10.70 | 15.57 |
P4 | 2011/03/22 | 1516 | 9.26 | 12.78 |
P5 | 2011/03/25 | 1078 | 10.56 | 14.14 |
P6 | 2011/04/03 | 1463 | 12.39 | 16.55 |
P7 | 2011/04/09 | 1358 | 11.12 | 15.09 |
P8 | 2011/04/11 | 1233 | 11.56 | 15.07 |
P9 | 2011/04/12 | 1054 | 11.54 | 15.15 |
P10 | 2011/04/20 | 1033 | 10.43 | 15.21 |
-
(1) Total Energy Consumption: reducing the total energy consumption of the data center is the primary goal of this paper. In this experiment, the total energy consumption is expressed as the sum of the energy consumption of the computing system and the cooling system.
-
(2) Number of Hot Spots: high server temperatures may affect the overall operational implementation of the data center, which can lead to server downtime with serious consequences. This metric indicates the number of times the host exceeds the temperature threshold throughout the simulation.
-
(3) SLA Violation Rate: this metric captures the system performance overhead due to dynamic consolidation, which mainly includes performance degradation due to full load in the data center \({SLA}_{TAH}\) and performance degradation due to virtual machine migration PDM, and is calculated by the following equation:$${SLA}_{violation}={SLA}_{TAH}\times PDM$$(21)Here, \({SLA}_{TAH}\) indicates the SLA violation time per host, calculated according to the following equation:where N is the total number of hosts, \({t}_{max}^{i}\) is the total time for \({Host}_{i}\) to reach full load state, and \({t}_{active}^{i}\) is the total active time of \({Host}_{i}\). In addition, the performance overhead PDM generated by VM migration is defined as:$${SLA}_{TAH}=\frac{1}{N}\sum_{i=1}^{N}\frac{{t}_{max}^{i}}{{t}_{active}^{i}}$$(22)$$PDM=\frac{1}{M}\sum_{j=1}^{M}\frac{{pdm}_{j}}{{C}_{{demand}_{j}}}$$(23)Among them, M is the total number of VMs, \({pdm}_{j}\) is the performance degradation due to the dynamic migration of \({VM}_{j}\), which is set to 10% in this experiment with reference to the suggestion of literature [43]. \({demand}_{j}\) indicates the total amount of CPU resources requested by \({VM}_{j}\) during its lifetime.
-
(4) Number of VM Migrations: it indicates the total number of migrations per scheduling cycle throughout the runtime. In enterprise-class data centers, VM migrations take a certain amount of time, consume a lot of resources, and lead to system performance degradation, so it is necessary to reduce the number of data center migrations.
-
(5) Number of Hosts Shut Down: the VMC method runs more workloads in a small number of physical machines to shut down underloaded hosts. The virtual machine scheduling method should bring more low-load hosts off to reduce energy consumption.
Results analysis
Algorithm | UACO | ACS_VMC | EVMCACS |
---|---|---|---|
Number of ants:\({N}_{ant}\) | 15 | 15 | 15 |
Number of iterations:\({N}_{c}\) | 10 | 10 | 10 |
Critical number:\({c}_{0}\) | 0.7 | 0.7 | 0.7 |
Local pheromone volatile factor:\(\rho\) | 0.3 | 0.3 | - |
Global pheromone volatile factor:\(\sigma\) | 0.4 | 0.4 | 0.4 |
Pheromone importance factor:\(\alpha\) | 0.9 | - | - |
Importance factor of heuristic information:\(\beta\) | 0.9 | 0.9 | 0.9 |
The maximum proportion of increase in pheromone concentration:\({\Delta \tau }_{max}\) | 1.5 | - | - |
Weight of power consumption in fitness function:\(\varepsilon\) | 0.5 | - | - |
Weight of the number of hosts closed in fitness function:\(\gamma\) | - | 5 | 5 |
Load | UACO | TAS | GRANITE | FFD | MBFD | ACS_VMC | EVMCACS |
---|---|---|---|---|---|---|---|
P1 | 774.12 | 348.19 | 25.86 | 24.27 | 22.65 | 936.58 | 799.90 |
P2 | 645.59 | 251.18 | 21.76 | 21.45 | 21.46 | 725.51 | 769.91 |
P3 | 822.37 | 284.53 | 28.59 | 25.14 | 24.16 | 859.57 | 852.55 |
P4 | 2502.77 | 610.95 | 30.92 | 33.78 | 27.07 | 2476.84 | 2275.82 |
P5 | 915.24 | 334.36 | 29.92 | 26.20 | 22.53 | 926.88 | 958.76 |
P6 | 1345.73 | 937.59 | 39.30 | 34.58 | 24.56 | 1538.69 | 1565.53 |
P7 | 2099.84 | 715.92 | 37.92 | 38.85 | 27.65 | 1940.80 | 1987.04 |
P8 | 2060.73 | 874.82 | 44.41 | 34.35 | 29. 98 | 2039.21 | 2110.68 |
P9 | 1229.14 | 745.14 | 28.81 | 32.50 | 23.72 | 1112.72 | 1164.21 |
P10 | 997.84 | 746.38 | 27.73 | 31.89 | 36.76 | 1013.06 | 1006.03 |