Virtual Machine Replica Placement Using a Multiobjective Genetic Algorithm

Table 1

A summary of the related work.

Ref.	VMP	VMR	Utilized technique	Objectives
[12]	✓	✗	Grey wolf optimization (GWO)	Minimize the number of active servers that are used to host the virtual machines (VMs)
[13]	✓	✗	Ant colony system (ACS)	Minimize the energy consumption
[15]	✓	✗	Microgenetic	Minimize energy consumption, VM migration, SLA violation, and number of server shutdown
[14]	✓	✗	NSGA-III	Minimize resource loss, energy consumption, and the number of active PM
[16]	✓	✗	Modified memetic algorithm (MA)	Minimize the energy cost and the cost of producing carbon dioxide
[17]	✓	✗	Combines the salp swarm and sine-cosine algorithms (MOSSASCA)	Maximize mean time before a PM shutdown (MTBHS) and minimize power consumption and SLA violations
[18]	✓	✓	Ant colony	Minimize SLA violation, minimize resource wasting, power consumption, and guarantee fault tolerance
[19]	✗	✓	Heuristic algorithms	Minimize the total power consumption and improve VM reliability and availability
[20]	✓	✓	Heuristic algorithms	Minimize the total power consumption and guarantee VM availability
[2]	✓	✓	Integer linear programming (ILP)-based algorithm	Minimize the number of PMs and guarantee fault-tolerant
[21]	✓	✗	Heuristic algorithms based on the maximum clique algorithm	Minimize the communication cost, latency between servers, and communication bandwidths
The proposed work	✓	✓	NSGA-III	Minimize the power consumption, performance degrading due to switching to a replica with specification lower than the user’s needs, and the distance between VM replicas