Advances, Systems and Applications
Table 1 Comparison of data centre RM approaches
From: Integrated resource management pipeline for dynamic resource-effective cloud data center
Authors | Architecture | Target | When to migrate | Performance Metric | Conclusion |
|---|---|---|---|---|---|
Nathuji and | Centralized | minimize power | - Periodic reallocation | - Power (W) | The overall energy |
Schwan [12] | Â | consumption without | Â | Â | consumption could be reduced significantly, up |
| Â | Â | performance penalties | Â | Â | to 34%, without appreciable losses in performance. |
Verma et al. [13] | Centralized | minimize power | - Periodic reallocation | - Power (watts) | pMapper was considered |
| Â | Â | consumption, | Â | - Energy (kilojoules) | an efficient solution to |
| Â | Â | considering the | Â | - Migration cost | minimize power |
| Â | Â | VM migration | Â | - Overall cost | consumption (less than |
| Â | Â | cost | Â | - Power savings (%) | 0.2% penalty). |
Zhu et al. [15] | De-centralized | improve | - Periodic reallocation | - Response time | The integration of node |
| Â | - Pod controllers | workload | - Threshold-based heuristics | (seconds) | and pod controllers |
| Â | - Node controllers | management to ensure efficient use of data center resources | Â | - Number of migrations | improved performance by 32% and 23% over fixed allocation and over non-integrated controllers, and reduced migrations for high priority workloads. |
Gmach et al. [16] | De-centralized | minimize power | - Periodic reallocation | - Migration overhead | The integration between |
| Â | - workload placement | consumption, | - Threshold-based heuristics | - CPU quality | reactive migration |
| Â | controller | taking into | Â | violations | controller and periodic |
| Â | - migration controller | account the Qos and the number of VM migrations | Â | - Power consumption | workload placement controller presented the best approach for power and SLA, but needs more migrations. |
VMware Distributed | Centralized | minimize power | - Fixed threshold heuristics | Â | Fixed threshold heuristics |
Power Management | Â | consumption | Â | Â | are unsuitable for real |
(DPM) [17] | Â | Â | Â | Â | systems with dynamic and unknown workloads. |
Li et al. [18] | Centralized | minimize power | - Dynamic threshold heuristics | - Energy | The double threshold with |
| Â | Â | consumption and QoS | Â | - Number of migrations | multi-resource utilization with the MPSO algorithm |
| Â | Â | guarantee | Â | - Number of active physical servers | reduces energy consumption and |
| Â | Â | Â | Â | - load balance degree | improves the QoS. |
Beloglazov et | Centralized | minimize power | - Fixed threshold heuristics | - Energy (kWh) | It is not a suitable decision |
al. [24] | Â | consumption, | Â | - SLAVs (%) | for keeping the utilization |
| Â | Â | taking into account QoS | Â | - Number of migrations | threshold constant as the workload is in continuous change. |
Beloglazov and | De-centralized | minimize power | - Decision based on statistical | - Energy (kWh) | The proposed LR |
Buyya [23] | Â | consumption, | analysis of historical data | - ESV | algorithm remarkably |
| Â | Â | taking into | Â | - SLAVs | outperformed other |
| Â | Â | account QoS | Â | - PDM (%) | dynamic VM consolidation |
| Â | Â | Â | Â | - Number of migrations | algorithms. |
Guenter et al. [21] | De-centralized | minimize power | - Decision based on statistical | - Power saving | Predicting demand was |
| Â | Â | consumption, | analysis of historical data | - normalized daily | used to switch on servers |
| Â | Â | considering the | Â | energy savings | before require and avoid |
| Â | Â | trade-off between cost, performance, | Â | (MWh) | switching on unnecessary servers. |
| Â | Â | and reliability | Â | Â | Â |
Bobroff et al. [22] | Centralized | minimize power | - Decision based on statistical | - Time-averaged | The proposed algorithm |
| Â | Â | consumption | analysis of historical data | number of servers | used decreased the |
| Â | Â | Â | Â | used | number of servers needed |
| Â | Â | Â | Â | - Capacity of overflow | to support a certain SLA by 50% compared to static consolidation. |
This work | De-centralized | minimize power | - Fixed threshold heuristics | - AITF (%) | Our combination of DES, |
| Â | Â | consumption, respect | - Decision based on statistical | - AOTF (%) | MMTMC 2, and MF |
|  |  | overall and end-user’s | analysis of historical data | - Number of migrations | algorithms improved |
| Â | Â | SLA, and eliminate | Â | - Energy saving (%) | performance in power |
| Â | Â | unnecessary migrations | Â | Â | saving, QoS, and network traffic. The number of migrations reduced by 49.44% compared to default algorithms. |