# A Survey of Swarm Intelligence Based Load Balancing Techniques in Cloud Computing Environment

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

#### 1.1. Objectives of the Research

- (a)
- To present the systematic literature review of SI based load balancing algorithms;
- (b)
- To present the algorithms along with the targeted issues and the areas of applications;
- (c)
- To present a comparative as well as quantitative analysis of some swarm intelligence algorithms used for balancing the load in cloud computing.

#### 1.2. Implications of the Research

#### 1.3. Motivation

## 2. Background and Design of Survey

#### 2.1. Research Questions

- (a)
- What is the need for and the importance of load balancing in cloud computing?
- (b)
- What is the main idea of SI?
- (c)
- How the occurring issues in Cloud Computing can be reformulated by SI?
- (d)
- How SI support load balancing in cloud computing?
- (e)
- What are the current and future challenges associated with load balancing in cloud computing?

#### 2.1.1. What Is the Need and Importance of Load Balancing in Cloud Computing?

#### 2.1.2. What Is the Main Idea of SI?

#### 2.1.3. How Can the Occurring Issues in Cloud Computing Be Reformulated by SI?

#### 2.1.4. How Does SI Support Load Balancing in Cloud Computing?

#### 2.1.5. What Are the Current and Future Challenges Associated with Load Balancing in Cloud Computing?

#### 2.2. Benchmark of Search

#### 2.3. Origin of Data

#### 2.4. Exploration Criteria

#### 2.5. Quality Evaluation

## 3. Literature Review

## 4. Load Balancing in Cloud Computing Using SI

#### 4.1. Traditional SI Algorithms for Load Balancing

- (a)
- Genetic Algorithms;
- (b)
- Particle Swarm Optimization;
- (c)
- Ant Colony Optimization;
- (d)
- Artificial Bee Colony;
- (e)
- Grey Wolf Optimization;
- (f)
- BAT Algorithm.

#### 4.1.1. Genetic Algorithm (GA)

Pseudocode of GA [42] |

1. Produce initial population “I” comprising chromosomes.2. Utilize fitness function to measure the value of fitness of each genetic code.3. Use the selection operator to pick the genetic codes that the next generation will make.4. Utilize these chromosomes to perform the crossover procedure.5. Now pick these chromosomes and execute the mutation process on them.6. Produce the fitness value of offspring known as these newly produced genetic codes.7. Improvise the population by changing irrelevant choices with genetic codes of better offspring.8. Go to step 3 and execute until 7 until the situation of termination is reached.The terminating scenario can be the last number of iterations possible or the fitness value of genetic code for all the possible runs is not able to update. 9. Return the best genetic code as a final result. |

#### GA and Its Variations

#### 4.1.2. Particle Swarm Optimization (PSO)

Pseudocode of PSO [54] |

1. Place vector and velocity vector initialization of each particle.2. Convert the continuous vector of position to a discrete vector.3. Calculate each particle’s fitness value using a fitness function.4. The “psobest” of each particle is given its best value of location until now. If the current fitness value of the particle is higher than the “psobest” of the particle, then substitute “psobest” with current position value.5. From all particles, pick the particle with the best fitness value as pobest.6. Using the following equations to change each particle’s vectors:Vj + 1 = qVj + i1n1 * (psobest − xj) + i2n2 * (pobest − xj), j is for iteration Xj + 1 = Xj + Vj + 1 where, q = interia i1, i2 =acceleration coefficients n1, n2 = Random numbers distributed arbitrary pobest = In a population, the best place of entire particles 7. Go to step 2 and loop till 6 until the situation for termination is met. The last number of iterations or when the fitness value of particles for the next iterations stops changing is the terminating condition.8. The best particle is created as the final solution. |

#### PSO and Its Variations

#### 4.1.3. Ant Colony Optimization (ACO)

Pseudocode of Ant Colony [62] |

1. Initialize the Ant Colony, targeted limitations, and the memory required for the source of food.2. Repeat steps 2–11 until stopping criteria not reached3. Allocate the starting position to each ant4. i = 15. For i<=ant perform the following operations6. Use the state transfer rule to pick the next node.7 Perform pheromone updations on each step8. i++9. End loop10. Before each ant has established a solution.11. Update the best one and perform updations on pheromone12. Output: Print Optimal solution |

#### ACO and Its Variations

#### 4.1.4. Artificial Bee Colony (ABC)

Pseudocode of ABC [70] |

1. Initialize the bat population and evaluate the fitness.2. Calculate the initial fitness value, f_init.3. Set the best solution, s_best.4. Set maximum no. of iterations, Noi.5. Set the population size, N.6. i = 17. Start loop end till iteration < Noi8. Generate a random solution for all no. of employed bees.9. Generate solution for all onlooker bees10. Apply a random structure on the selected bees, s_Changed.11. IF (s_best< s_Changed)12. Then s_Changed=s_best13. END IF14. Scout bees identify the abandoned source of food and ultimately replace it with new15. i ++16. End loop17. Output: the best solution |

#### ABC and Its Variations

- No. of tasks being processed by the VM < No. of tasks processing by other VMs;
- The deviation of the VM processing time from the average processing time of all VMs is less than the threshold. In this manner, the overall response times and data center processing times are successfully minimized (proved by simulations). As the algorithm intelligently focuses on distributing load to avoid under and overutilization of VMs, compared to other swarm algorithms i.e., ACO and ABC, the balancing performed by LBA_HB is more efficient.

#### 4.1.5. Grey Wolf Optimization (GWO)

Pseudocode of GWO [54] |

1. Select the max no. of iterations L.2. Initialization of the population X_{i} = (i = 1, 2, 3, 4, …, n)3. Initialization of r, N, D, & T = 1.3. Produce fitness of all the wolves (searching machines)4. Let, P = searching machine (best)5. Let, Q = searching machine (second best)6. Let, R = searching machine (third best)7. Start while (i < L) do 8.Repeat step 9 for every searching machine9. Change the position’s value of the recently available searching machine.10. Change the values of r, N, and D 11. Find the fitness of all searching machines 12. Update P, Q, and R 13. i ++14. end while 15.OUTPUT the best searching machine |

#### GWO and Its Variations

#### 4.1.6. BAT Algorithm

Pseudocode of BAT [88] |

1. Input: Population of searching machine Z, dimension of solutions n, upper and lower bounds of solutions [y_{1},…, y_{n}, L_{1}, …, L_{n}], Maximum iterationsOutput: The best searching machine P 1. Initialize the grey wolf population X _{i} = (x_{1}, x_{2}, …, x_{n})where (i ∈ [N]) and x _{j} ∈ [y_{j}, Lj] |∀ j ∈ [n]2. Initialize a, A, C, & i = 1.3. Find the fitness of each searching machine f(X_{i}), where (i ∈ [Z])4. Let, P = the best searching machine.5. Let, Q = the second-best searching machine6. Let, R = the third-best searching machine.7. while (i < Max iterations) do8. for each search agent do9. Change the position of the current searching machine accordingly10. end for11. Update a, A, and C12. Calculate the fitness of all searching machine13. Update P, Q, and R14. i++15. end while16. Output P as the best solution |

#### BAT and Its Variations

#### 4.2. Modern SI Algorithm for Load Balancing

#### 4.2.1. Whale Optimization Algorithm (WOA)

- Initialization phase: During this phase, the population is randomly created.
- Fitness calculation phase: In this phase, a fitness function is calculated. This is used to calculate the fitness function. Depending on the outcomes of the test, the best whale (agent) is selected.
- Encircling prey phase: The location of the prey is believed to be fixed during this process. Assuming that the current approach is the safest, the prey is covered by humpback whales. Other whales change their positions in accordance with the existing best agent. The exploration phase uses the following mathematical model (Equations (1) and (2)):$$SD=\left|C.{W}^{*}\left(i\right)-W\left(i\right)\right|$$$$W\left(i+1\right)=Wr\left(i\right)-A.SD$$

Pseudocode of Standard WO |

1. Initialize the population of whales (agents) “W” 2. Calculate the value of the fitness function. 3. Randomly pick the search agent W* 4. While i = 1 and t < MAX_LIMIT 5. Repeat for each search agent 6. if (probability < 0.5) 7. if (|A| <1) 8. Update the position of ith search agent by Eqution (1) 9. else if (probability < 0.5 AND |A| ≤ 1) 10. Update the position of ith search agent by Eqution (2) 11. end if 12. else if (probability ≥ 0.5) 13. Update the position of ith search agent by Eqution (3) 14. end if 15. End inner loop 16. Calculate the fitness of W(t + 1) and update W* 17. End Outer loop |

#### WOA and Its Variations

#### 4.2.2. Social Spider Algorithm (SSA)

Pseudocode of SSA [98] |

1. Inputs: Total count of spiders “T” Total No. of female spiders “T _{f}”Total No. of male spiders “T _{m}”2. Initialize the positions of male and female spiders 3. Ti = total no. of iterations 4. Output: The fitness value of the optimization problem and the optimal location of social spiders. 5. Process: while i ≤ Ti do 6. Determine the mating radius for female and male spiders. 7. Determine the weight of the spiders. 8. Based on female and male collective operators, determine the response of female and male spiders. 9. Accomplish a mating procedure with a dominant male and a dominant female. If the spider progenies are larger, then update the strategies. |

#### SSA and Its Variations

#### 4.2.3. Dragonfly Optimization Algorithm (DOA)

Pseudocode of Standard DAO [104] |

1. Initialization of data centers, host machines, and virtual machines 2. Demands for resource distribution are entered. 3. The demands are divided into several tasks. 4. Attempt to determine the number of VMs and the number of initial tasks to be executed 5. if (it is the end of the process) 6. Then (to balance the load) determine the execution requirements and resource time. 7. else 8. divide the activity between processors while maintaining load 9. Apply DFO for the scheduling of job while maintaining load 10. If (all VMs are active) 11. Then Go to step 4 12. else Go to Step 6 |

#### DOA and Its Variations

#### 4.2.4. Raven Roosting Optimization Algorithm (RROA)

Pseudocode of Standard RRA [108] |

1. Initialization of solutions and load of data centers 2. A proportion of the load is shifted to leave an overloaded VM and find the leading machine. 3. The arrived load searches for a VM for allocation as per the leading machine 4. if (i < the total number of VMs) 5. then 6. Search for the VM among the perception radius 7. Evaluate and reassign the ID 8. else 9. Evaluate and reassign the id if mandatory 10. if (terminating condition not meet) 11. then go to step 1 12. else 13. End the search process |

#### RROA and Its Variations

## 5. Summary of the Reviewed SI Algorithms

- GA has average time complexity and average solution quality, and ABC has the best solution quality despite having the worst time complexity.
- In addition, PSO looks to have the best time complexity, but the quality of its solution is not comparable to that of ABC.
- ACO has a good solution quality and a lower time complexity.
- BAT has the poorest solution quality but surpasses ABC in terms of convergence speed, whereas GWO’s convergence speed is more efficient in terms of ABC’s solution quality.
- In terms of recent SI algorithms, dragonfly and raven have significantly better performance based on time complexity and solution quality; however, the whale’s solution quality is below average with reduced time complexity.
- When compared to WWO, SSOs have an average time complexity and improved solution quality.

## 6. Comparative Performance Analysis of Various SI Algorithms Used for Load Balancing

#### 6.1. Comparative Performance Analysis of SI Algorithms in Cloud Computing

#### 6.1.1. Comparative Performance Analysis of Average Response Time (TRT) for Different User Bases (UB) and Data Centers (DC)

#### 6.1.2. Comparative Performance Analysis of Average Data Center Processing Time (DCPT) for Different User Bases (UB) and Data Centers (DC)

#### 6.1.3. Comparative Performance Analysis Based on Time and Cost to Complete Tasks

#### 6.1.4. Comparative Performance Analysis Based on Makespan

## 7. Future Directions

## 8. Conclusions

- For software or hardware maintenance, the complete network does not need to be taken down or offline;
- It can be performed on one server at a time while other servers’ services are still functioning;
- When more storage or processing capability is needed, businesses may simply ask their service provider to swiftly and seamlessly deploy additional servers to the connection;
- In the case of a catastrophe at the primary data center, distributed load balancing can provide disaster restoration services by diverting user connection requests in a disaster recovery data center;
- Massive enterprises with resource-intensive services, large amounts of constantly expanding data, and continual traffic want network connectivity, reliability, and flexibility in order to ensure that consumers can access their services or products at any location worldwide.

## Author Contributions

## Funding

## Conflicts of Interest

## References

- DeStefano, T.; Kneller, R.; Timmis, J. Cloud Computing and Firm Growth; 2020; p. 8306. Available online: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3618829 (accessed on 15 July 2021).
- Chen, Y.; Li, X.; Chen, F. Overview and analysis of cloud computing research and application. In Proceedings of the 2011 International Conference on E-Business and E-Government (ICEE), Shanghai, China, 6–8 May 2011. [Google Scholar]
- Shahid, M.A.; Islam, N.; Alam, M.M.; Mazliham, M.S.; Musa, S. Towards Resilient Method: An exhaustive survey of fault tolerance methods in the cloud computing environment. Comput. Sci. Rev.
**2021**, 40, 100398. [Google Scholar] [CrossRef] - Langmead, B.; Nellore, A. Cloud computing for genomic data analysis and collaboration. Nat. Rev. Genet.
**2018**, 19, 208–219. [Google Scholar] [CrossRef] [PubMed] - Velte, A.T.; Velte, T.J.; Elsenpeter, R. Cloud Computing: A Practical Approach. ISSN
**2019**, 2278, 0181. [Google Scholar] - Kumar, P.; Kumar, R. Issues and challenges of load balancing techniques in cloud computing: A survey. ACM Comput. Surv. (CSUR)
**2019**, 51, 1–35. [Google Scholar] [CrossRef] - Gutierrez-Garcia, J.O.; Ramirez-Nafarrate, A. Collaborative agents for distributed load management in cloud data centers using live migration of virtual machines. IEEE Trans. Serv. Comput.
**2015**, 8, 916–929. [Google Scholar] [CrossRef] - Chen, S.-L.; Chen, Y.-Y.; Kuo, S.-H. CLB: A novel load balancing architecture and algorithm for cloud services. Comput. Electr. Eng.
**2017**, 58, 154–160. [Google Scholar] [CrossRef] - Kaur, K.; Kumar, Y. Swarm Intelligence and its applications towards Various Computing: A Systematic Review. In Proceedings of the 2020 International Conference on Intelligent Engineering and Management (ICIEM), London, UK, 17–19 June 2020. [Google Scholar]
- Princess, G.A.P.; Radhamani, A. A Hybrid Meta-Heuristic for Optimal Load Balancing in Cloud Computing. J. Grid Comput.
**2021**, 19, 1–22. [Google Scholar] - Chien, N.K.; Son, N.H.; Loc, H.D. Load balancing algorithm based on estimating finish time of services in cloud computing. In Proceedings of the 2016 18th International Conference on Advanced Communication Technology (ICACT), Pyeongchang, Korea, 31 January–3 February 2016. [Google Scholar]
- Xavier, M.G.; Neves, M.V.; Rossi, F.D.; Ferreto, T.C.; Lange, T.; Rose, C.A.F. Performance evaluation of container-based virtualization for high performance computing environments. In Proceedings of the 2013 21st Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, Belfast, UK, 27 February–1 March 2013. [Google Scholar]
- Soltesz, S.; Pötzl, H.; Fiuczynski, M.E.; Bavier, A.; Peterson, L. Container-based operating system virtualization: A scalable, high-performance alternative to hypervisors. In Proceedings of the 2nd ACM SIGOPS/EuroSys European Conference on Computer Systems 2007, Lisbon, Portugal, 21–23 March 2007. [Google Scholar]
- Santos, J.; Wauters, T.; Volckaert, B.; Truck, F.D. Towards network-aware resource provisioning in Kubernetes for fog computing applications. In Proceedings of the 2019 IEEE Conference on Network Softwarization (NetSoft), Paris, France, 24–28 June 2019. [Google Scholar]
- Fazio, M.; Celesti, A.; Ranjan, R.; Liu, C.; Chen, L.; Villari, M. Open issues in scheduling microservices in the cloud. IEEE Cloud Comput.
**2016**, 3, 81–88. [Google Scholar] [CrossRef] - Burns, B.; Beda, J.; Hightower, K. Kubernetes: Up and Running: Dive into the Future of Infrastructure; O’Reilly Media: Sebastopol, CA, USA, 2019. [Google Scholar]
- Mishra, S.K.; Sahoo, B.; Parida, P.P. Load balancing in cloud computing: A big picture. J. King Saud Univ.-Comput. Inf. Sci.
**2020**, 32, 149–158. [Google Scholar] [CrossRef] - Makasarwala, H.A.; Hazari, P. Using genetic algorithm for load balancing in cloud computing. In Proceedings of the 2016 8th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Ploiesti, Romania, 30 June–2 July 2016. [Google Scholar]
- Elmagzoub, M.A.; Shaikh, A.; Alghamdi, A.; Rajab, K. A review on MIMO wireless signals over fibre for next generation fibre wireless (FiWi) broadband networks. Electronics
**2010**, 9, 2014. [Google Scholar] [CrossRef] - Mosa, M.A.; Anwar, A.S.; Hamouda, A. A survey of multiple types of text summarization with their satellite contents based on swarm intelligence optimization algorithms. Knowl.-Based Syst.
**2015**, 163, 518–532. [Google Scholar] [CrossRef] - Junaid, M.; Sohail, A.; Ahmed, A.; Baz, A.; Khan, I.A.; Alhakami, H. A hybrid model for load balancing in cloud using file type formatting. IEEE Access
**2020**, 8, 118135–118155. [Google Scholar] [CrossRef] - Gźsior, J.; Seredyński, F. Decentralized Job Scheduling In The Cloud Based On A Spatially Generalized Prisoner’s Dilemma Game. Int. J. Appl. Math. Comput. Sci.
**2015**, 25, 737–751. [Google Scholar] [CrossRef][Green Version] - Kennedy, J. Swarm Intelligence. In Handbook of Nature-Inspired and Innovative Computing; Springer: Boston, MA, USA, 2006; Volume 1, pp. 187–219. ISBN 978-0387-27705-9. [Google Scholar]
- Tan, Y.; Shi, Y.; Tuba, M. Advances in Swarm Intelligence, In Proceedings of the 11th International Conference ICSI 2020, Belgrade, Serbia, 14–20 July 2020; Springer Nature: Basingstoke, UK, 2020; Volume 12145. [Google Scholar]
- Fahad, M.; Aadil, F.; Khan, S.; Shah, P.A.; Muhammad, K.; Lloret, J.; Wang, H.; Lee, J.W.; Mehmood, I. Grey wolf optimization based clustering algorithm for vehicular ad-hoc networks. Comput. Electr. Eng.
**2018**, 70, 853–870. [Google Scholar] [CrossRef] - Sun, W.; Tang, M.; Zhang, L.; Huo, Z.; Shu, L. A survey of using swarm intelligence algorithms in IoT. Sensors
**2020**, 20, 1420. [Google Scholar] [CrossRef] [PubMed][Green Version] - Xu, M.; Tian, W.; Buyya, R. A survey on load balancing algorithms for virtual machines placement in cloud computing. Concurr. Comput. Pract. Exp.
**2017**, 29, e4123. [Google Scholar] [CrossRef][Green Version] - Chakraborty, T.; Datta, S.K. Application of swarm intelligence in internet of things. In Proceedings of the 2017 IEEE International Symposium on Consumer Electronics (ISCE), Kuala Lumpur, Malaysia, 14–15 November 2017. [Google Scholar]
- Houssein, E.H.; Gad, A.G.; Wazery, Y.M.; Suganthan, P.N. Task scheduling in cloud computing based on meta-heuristics: Review, taxonomy, open challenges, and future trends. Swarm Evol. Comput.
**2021**, 62, 100841. [Google Scholar] [CrossRef] - Ojha, V.K.; Abraham, A.; Snášel, V. Metaheuristic design of feedforward neural networks: A review of two decades of research. Eng. Appl. Artif. Intell.
**2017**, 60, 97–116. [Google Scholar] [CrossRef][Green Version] - Zhang, B.; Lin, C.; Huo, L.; Wang, Z.; Chan, C.K. A simple high-speed WDM PON utilizing a centralized supercontinuum broadband light source for colorless ONUs. In Proceedings of the 2006 Optical Fiber Communication Conference and the National Fiber Optic Engineers Conference, Anaheim, CA, USA, 5–10 March 2006. [Google Scholar]
- Buyya, R.; Srirama, S.N.; Casale, G.; Calheiros, R.; Simmhan, Y.; Varghese, B.; Gelenbe, E.; Javadi, B.; Vaquero, L.M.; Netto, M.A.; et al. A manifesto for future generation cloud computing: Research directions for the next decade. ACM Comput. Surv. (CSUR)
**2018**, 51, 1–38. [Google Scholar] [CrossRef][Green Version] - Ebadifard, F.; Babamir, S.M. Autonomic task scheduling algorithm for dynamic workloads through a load balancing technique for the cloud-computing environment. Clust. Comput.
**2021**, 24, 1075–1101. [Google Scholar] [CrossRef] - Singh, S.; Chana, I. A survey on resource scheduling in cloud computing: Issues and challenges. J. Grid Comput.
**2016**, 14, 217–264. [Google Scholar] [CrossRef] - Vakili, A.; Navimipour, N.J. Comprehensive and systematic review of the service composition mechanisms in the cloud environments. J. Netw. Comput. Appl.
**2017**, 81, 24–36. [Google Scholar] [CrossRef] - Hota, A.; Mohapatra, S.; Mohanty, S. Survey of different load balancing approach-based algorithms in cloud computing: A comprehensive review. Comput. Intell. Data Min.
**2019**, 711, 99–110. [Google Scholar] - Jyoti, A.; Shrimali, M.; Tiwari, S.; Singh, H.P. Cloud computing using load balancing and service broker policy for IT service: A taxonomy and survey. J. Ambient. Intell. Humaniz. Comput.
**2020**, 11, 4785–4814. [Google Scholar] [CrossRef] - Ghomi, E.J.; Rahmani, A.M.; Qader, N.N. Load-balancing algorithms in cloud computing: A survey. J. Netw. Comput. Appl.
**2017**, 88, 50–71. [Google Scholar] [CrossRef] - Sa, P.K.; Sahoo, M.N.; Murugappan, M.; Wu, Y.; Majhi, B. (Eds.) Progress in Intelligent Computing Techniques: Theory, Practice, and Applications: Proceedings of ICACNI 2016, Volume 2; Springer: Berlin/Heidelberg, Germany, 2017; Volume 719. [Google Scholar]
- Kabir, M.S.; Kabir, K.M.; Islam, D.R. Process of load balancing in cloud computing using genetic algorithm. Electr. Comput. Eng. Int. J. (ECIJ)
**2015**, 4, 57–65. [Google Scholar] [CrossRef][Green Version] - Shafiq, D.A.; Jhanjhi, N.; Abdullah, A. vLoad balancing techniques in cloud computing environment: A review. J. King Saud Univ. -Comput. Inf. Sci.
**2021**. [Google Scholar] [CrossRef] - Miao, Z.; Yong, P.; Mei, Y.; Quanjun, Y.; Xu, X. A discrete PSO-based static load balancing algorithm for distributed simulations in a cloud environment. Future Gener. Comput. Syst.
**2021**, 115, 497–516. [Google Scholar] [CrossRef] - Dam, S.; Mandal, G.; Dasgupta, K.; Dutta, P. Genetic algorithm and gravitational emulation based hybrid load balancing strategy in cloud computing. In Proceedings of the 2015 Third International Conference on Computer, Communication, Control and Information Technology (C3IT), Hooghly, India, 7–8 February 2015. [Google Scholar]
- Kaur, S.; Sengupta, J. Load balancing using improved genetic algorithm (iga) in cloud computing. Int. J. Adv. Res. Comput. Eng. Technol. (IJARCET)
**2017**, 6, 2278-1123. [Google Scholar] - Basu, S.; Kannayaram, G.; Ramasubbareddy, S.; Venkatasubbaiah, C. Improved Genetic Algorithm for Monitoring of Virtual Machines in Cloud Environment. In Smart Intelligent Computing and Applications; Springer: Berlin/Heidelberg, Germany, 2019; pp. 319–326. [Google Scholar]
- Saadat, A.; Masehian, E. Load Balancing in Cloud Computing Using Genetic Algorithm and Fuzzy Logic. In Proceedings of the 2019 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA, 5–7 December 2019. [Google Scholar]
- Goar, V.; Kuri, M.; Kumar, R.; Senjyu, T. Advances in Information Communication Technology and Computing; Springer: Berlin/Heidelberg, Germany, 2021. [Google Scholar]
- Jafarnejad Ghomi, E.; Masoud Rahmani, A.; Nasih Qader, N. Service load balancing, task scheduling and transportation optimisation in cloud manufacturing by applying queuing system. Enterp. Inf. Syst.
**2019**, 13, 865–894. [Google Scholar] [CrossRef] - Vidya, S.H.; Prakash, R.M. Response time analysis of dynamic load balancing algorithms in Cloud Computing. In Proceedings of the 2020 Fourth World Conference on Smart Trends in Systems, Security and Sustainability (WorldS4), London, UK, 27–28 July 2020. [Google Scholar]
- Dashti, S.E.; Rahmani, A.M. Dynamic VMs placement for energy efficiency by PSO in cloud computing. J. Exp. Theor. Artif. Intell.
**2016**, 28, 97–112. [Google Scholar] [CrossRef] - Mapetu, J.P.B.; Chen, Z.; Kong, L. Low-time complexity and low-cost binary particle swarm optimization algorithm for task scheduling and load balancing in cloud computing. Appl. Intell.
**2019**, 49, 3308–3330. [Google Scholar] [CrossRef] - Ebadifard, F.; Babamir, S.M. A PSO-based task scheduling algorithm improved using a load-balancing technique for the cloud computing environment. Concurr. Comput. Pract. Exp.
**2018**, 30, e4368. [Google Scholar] [CrossRef] - Singh, A.B.; Bhat, S.; Raju, R.; D’Souza, R. Survey on various load balancing techniques in cloud computing. Adv. Comput.
**2017**, 7, 28–34. [Google Scholar] - Gaidhane, P.J.; Nigam, M.J. A hybrid grey wolf optimizer and artificial bee colony algorithm for enhancing the performance of complex systems. J. Comput. Sci.
**2018**, 27, 284–302. [Google Scholar] [CrossRef] - Alguliyev, R.M.; Imamverdiyev, Y.N.; Abdullayeva, F.J. PSO-based load balancing method in cloud computing. Autom. Control. Comput. Sci.
**2019**, 53, 45–55. [Google Scholar] [CrossRef] - Agarwal, R.; Baghel, N.; Khan, M.A. Load balancing in cloud computing using mutation based particle swarm optimization. In Proceedings of the 2020 International Conference on Contemporary Computing and Applications (IC3A), Lucknow, India, 5–7 February 2020. [Google Scholar]
- Jordehi, A.R.; Jasni, J. Particle swarm optimisation for discrete optimisation problems: A review. Artif. Intell. Rev.
**2015**, 43, 243–258. [Google Scholar] [CrossRef] - Golchi, M.M.; Saraeian, S.; Heydari, M. A hybrid of firefly and improved particle swarm optimization algorithms for load balancing in cloud environments: Performance evaluation. Comput. Netw.
**2019**, 162, 106860. [Google Scholar] [CrossRef] - Pan, K.; Chen, J. Load balancing in cloud computing environment based on an improved particle swarm optimization. In Proceedings of the 2015 6th IEEE International Conference on Software Engineering and Service Science (ICSESS), Beijing, China, 23–25 September 2015. [Google Scholar]
- Ghumman, N.S.; Kaur, R. Dynamic combination of improved max-min and ant colony algorithm for load balancing in cloud system. In Proceedings of the 2015 6th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Dallas-Fortworth, TX, USA, 13–15 July 2015. [Google Scholar]
- Gao, R.; Wu, J. Dynamic load balancing strategy for cloud computing with ant colony optimization. Future Internet
**2015**, 7, 465–483. [Google Scholar] [CrossRef][Green Version] - Raj, B.; Ranjan, P.; Rizvi, N.; Pranav, P.; Paul, S. Improvised Bat Algorithm for Load Balancing-Based Task Scheduling. In Progress in Intelligent Computing Techniques: Theory, Practice, and Applications; Springer: Berlin/Heidelberg, Germany, 2018; pp. 521–530. [Google Scholar]
- Li, G.; Wu, Z. Ant colony optimization task scheduling algorithm for SWIM based on load balancing. Future Internet
**2019**, 11, 90. [Google Scholar] [CrossRef][Green Version] - Gupta, A.; Garg, R. Load balancing based task scheduling with ACO in cloud computing. In Proceedings of the 2017 International Conference on Computer and Applications (ICCA), Doha, Qatar, 6–7 September 2017. [Google Scholar]
- Ragmani, A.; Elomri, A.; Abghour, N.; Moussaid, K.; Rida, M. An improved hybrid fuzzy-ant colony algorithm applied to load balancing in cloud computing environment. Procedia Comput. Sci.
**2019**, 151, 519–526. [Google Scholar] [CrossRef] - Pourghaffari, A.; Barari, M.; Sedighian Kashi, S. An efficient method for allocating resources in a cloud computing environment with a load balancing approach. Concurr. Comput. Pract. Exp.
**2019**, 31, e5285. [Google Scholar] [CrossRef] - Tang, L.; Pan, J.S.; Hu, Y.; Ren, P.; Tian, Y.; Zhao, H. A novel load balance algorithm for cloud computing. In International Conference on Genetic and Evolutionary Computing; Springer: Berlin/Heidelberg, Germany, 2015. [Google Scholar]
- Kumar, A.; Kumar, D.; Jarial, S. A review on artificial bee colony algorithms and their applications to data clustering. Cybern. Inf. Technol.
**2017**, 17, 3–28. [Google Scholar] [CrossRef][Green Version] - Rajan, C.; Geetha, K.; Priya, C.R.; Sasikala, R. Investigation on bio-inspired population based metaheuristic algorithms for optimization problems in ad hoc networks. Int. J. Math. Comput. Phys. Electr. Comput. Eng.
**2015**, 9, 163–170. [Google Scholar] - Pruitt, J.N.; Avilés, L. Social spiders: Mildly successful social animals with much untapped research potential. Anim. Behav.
**2018**, 143, 155–165. [Google Scholar] [CrossRef] - Muthsamy, G.; Ravi Chandran, S. Task scheduling using artificial bee foraging optimization for load balancing in cloud data centers. Comput. Appl. Eng. Educ.
**2020**, 28, 769–778. [Google Scholar] [CrossRef] - Li, J.-Q.; Han, Y.-Q. A hybrid multi-objective artificial bee colony algorithm for flexible task scheduling problems in cloud computing system. Clust. Comput.
**2020**, 23, 2483–2499. [Google Scholar] [CrossRef] - Babu, K.R.; Samuel, P. Enhanced bee colony algorithm for efficient load balancing and scheduling in cloud. In Innovations in Bio-Inspired Computing and Applications; Springer: Berlin/Heidelberg, Germany, 2016; pp. 67–78. [Google Scholar]
- Hashem, W.; Nashaat, H.; Rizk, R. Honey bee based load balancing in cloud computing. KSII Trans. Internet Inf. Syst.
**2017**, 11, 5694–5711. [Google Scholar] - Patel, D.; Patra, M.K.; Sahoo, B. GWO Based Task Allocation for Load Balancing in Containerized Cloud. In Proceedings of the 2020 International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India, 26–28 February 2020. [Google Scholar]
- Abed-alguni, B.H.; Alawad, N.A. Distributed Grey Wolf Optimizer for scheduling of workflow applications in cloud environments. Appl. Soft Comput.
**2021**, 102, 107113. [Google Scholar] [CrossRef] - Mousavi, S.; Mosavi, A.; Varkonyi-Koczy, A.R.; Fazekas, G. Dynamic resource allocation in cloud computing. Acta Polytech. Hung.
**2017**, 14, 83–104. [Google Scholar] - Faris, H.; Aljarah, I.; Al-Betar, M.A.; Mirjalili, S. Grey wolf optimizer: A review of recent variants and applications. Neural Comput. Appl.
**2018**, 30, 413–435. [Google Scholar] [CrossRef] - Niu, P.; Niu, S.; Chang, L. The defect of the Grey Wolf optimization algorithm and its verification method. Knowl.-Based Syst.
**2019**, 171, 37–43. [Google Scholar] [CrossRef] - Natesan, G.; Chokkalingam, A. An improved grey wolf optimization algorithm based task scheduling in cloud computing environment. Int. Arab. J. Inf. Technol.
**2020**, 17, 73–81. [Google Scholar] [CrossRef] - Gohil, B.N.; Patel, D.R. A hybrid GWO-PSO algorithm for load balancing in cloud computing environment. In Proceedings of the 2018 Second International Conference on Green Computing and Internet of Things (ICGCIoT), Bangalore, India, 16–18 August 2018. [Google Scholar]
- Xingjun, L.; Zhiwei, S.; Hongping, C.; Mohammed, B.O. A new fuzzy-based method for load balancing in the cloud-based Internet of things using a grey wolf optimization algorithm. Int. J. Commun. Syst.
**2020**, 33, e4370. [Google Scholar] [CrossRef] - Ouhame, S.; Hadi, Y.; Arifullah, A. A hybrid grey wolf optimizer and artificial bee colony algorithm used for improvement in resource allocation system for cloud technology. Int. J. Online Biomed. Eng.
**2020**, 16, 4–17. [Google Scholar] [CrossRef] - Chételat, J.; Hickey, M.B.C.; Poulain, A.J.; Dastoor, A.; Ryjkov, A.; McAlpine, D.; Vanderwolf, K.; Jung, T.S.; Hale, L.; Cooke, E.L.; et al. Spatial variation of mercury bioaccumulation in bats of Canada linked to atmospheric mercury deposition. Sci. Total Environ.
**2018**, 626, 668–677. [Google Scholar] [CrossRef] - Ullah, A.; Nawi, N.M.; Khan, M.H. BAT algorithm used for load balancing purpose in cloud computing: An overview. Int. J. High Perform. Comput. Netw.
**2020**, 16, 43–54. [Google Scholar] [CrossRef] - Jayabarathi, T.; Raghunathan, T.; Gandomi, A. The bat algorithm, variants and some practical engineering applications: A review. In Nature-Inspired Algorithms and Applied Optimization; Springer: Berlin/Heidelberg, Germany, 2018; pp. 313–330. [Google Scholar]
- Kotteeswaran, R.; Sivakumar, L. A Novel Bat algorithm based re-tuning of PI controller of coal gasifier for optimum response. In Mining Intelligence and Knowledge Exploration; Springer: Berlin/Heidelberg, Germany, 2013; pp. 506–517. [Google Scholar]
- Kalra, M.; Singh, S. A review of metaheuristic scheduling techniques in cloud computing. Egypt. Inform. J.
**2015**, 16, 275–295. [Google Scholar] [CrossRef][Green Version] - Shaddad, R.Q.; Mohammad, A.B.; Al-Gailani, S.A.; Al-Hetar, A.M. Optical frequency upconversion technique for transmission of wireless MIMO-type signals over optical fiber. Sci. World J.
**2014**, 2014, 170471. [Google Scholar] [CrossRef] - Fahim, Y.; Rahhali, H.; Hanine, M.; Benlahmar, E.H.; Labriji, E.H.; Hanoune, M.; Eddaoui, A. Load balancing in cloud computing using meta-heuristic algorithm. J. Inf. Process. Syst.
**2018**, 14, 569–589. [Google Scholar] - Bhargavi, K.; Babu, B.S.; Pitt, J. Performance Modeling of Load Balancing Techniques in Cloud: Some of the Recent Competitive Swarm Artificial Intelligence-based. J. Intell. Syst.
**2021**, 30, 40–58. [Google Scholar] [CrossRef] - Mirjalili, S.; Lewis, A. The whale optimization algorithm. Adv. Eng. Softw.
**2016**, 95, 51–67. [Google Scholar] [CrossRef] - Strumberger, I.; Bacanin, N.; Tuba, M.; Tuba, E. Resource scheduling in cloud computing based on a hybridized whale optimization algorithm. Appl. Sci.
**2019**, 9, 4893. [Google Scholar] [CrossRef][Green Version] - Kaur, G.; Arora, S. Chaotic whale optimization algorithm. J. Comput. Des. Eng.
**2018**, 5, 275–284. [Google Scholar] [CrossRef] - Hemasian-Etefagh, F.; Safi-Esfahani, F. Dynamic scheduling applying new population grouping of whales meta-heuristic in cloud computing. J. Supercomput.
**2019**, 75, 6386–6450. [Google Scholar] [CrossRef] - Chen, X.; Cheng, L.; Liu, C.; Liu, Q.; Liu, J.; Mao, Y.; Murphy, J. A woa-based optimization approach for task scheduling in cloud computing systems. IEEE Syst. J.
**2020**, 14, 3117–3128. [Google Scholar] [CrossRef] - James, J.; Li, V.O. A social spider algorithm for global optimization. Appl. Soft Comput.
**2015**, 30, 614–627. [Google Scholar] - Evangeline, D.; Abirami, T. Social spider optimization algorithm: Theory and its applications. Int. J. Innov. Technol. Explor. Eng.
**2019**, 8, 327–332. [Google Scholar] - Usurelu, C.C.; Nita, M.C.; Istrate, R.; Pop, F.; Tapus, N. Spider mesh overlay for task load balancing in cloud computing. In Proceedings of the 2015 IEEE International Conference on Intelligent Computer Communication and Processing (ICCP), Cluj-Napoca, Romania, 3–5 September 2015. [Google Scholar]
- Mahato, D.P.; Singh, R.S. Balanced task allocation in the on-demand computing-based transaction processing system using social spider optimization. Concurr. Comput. Pract. Exp.
**2017**, 29, e4214. [Google Scholar] [CrossRef] - Xavier, V.A.; Annadurai, S. Chaotic social spider algorithm for load balance aware task scheduling in cloud computing. Clust. Comput.
**2019**, 22, 287–297. [Google Scholar] - Abrol, P.; Gupta, S.; Singh, S. QoS aware social spider cloud web algorithm: Analysis of resource placement approach. In Proceedings of the International Conference on Advancements in Computing & Management (ICACM), Jaipur, India, 13–14 April 2019. [Google Scholar]
- Rahman, C.M.; Rashid, T.A. Dragonfly algorithm and its applications in applied science survey. Comput. Intell. Neurosci.
**2019**, 2019, 9293617. [Google Scholar] [CrossRef] [PubMed] - Amini, Z.; Maeen, M.; Jahangir, M.R. Providing a load balancing method based on dragonfly optimization algorithm for resource allocation in cloud computing. Int. J. Netw. Distrib. Comput.
**2018**, 6, 35–42. [Google Scholar] [CrossRef][Green Version] - Polepally, V.; Chatrapati, K.S. Dragonfly optimization and constraint measure-based load balancing in cloud computing. Clust. Comput.
**2019**, 22, 1099–1111. [Google Scholar] [CrossRef] - Neelima, P.; Reddy, A.R.M. An efficient load balancing system using adaptive dragonfly algorithm in cloud computing. Clust. Comput.
**2020**, 23, 2891–2899. [Google Scholar] [CrossRef] - Brabazon, A.; Cui, W.; O’Neill, M. The raven roosting optimisation algorithm. Soft Comput.
**2016**, 20, 525–545. [Google Scholar] [CrossRef] - Torabi, S.; Safi-Esfahani, F. Improved raven roosting optimization algorithm (IRRO). Swarm Evol. Comput.
**2018**, 40, 144–154. [Google Scholar] [CrossRef] - Rani, E.; Kaur, H. Efficient Load Balancing Task Scheduling in Cloud Computing using Raven Roosting Optimization Algorithm. Int. J. Adv. Res. Comput. Sci.
**2017**, 8, 2419–2424. [Google Scholar] - Torabi, S.; Safi-Esfahani, F. A dynamic task scheduling framework based on chicken swarm and improved raven roosting optimization methods in cloud computing. J. Supercomput.
**2018**, 74, 2581–2626. [Google Scholar] [CrossRef] - Bhargavi, K.; Babu, B.S. Load Balancing Scheme for the Public Cloud using Reinforcement Learning with Raven Roosting Optimization Policy (RROP). In Proceedings of the 2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS), Bengaluru, India, 20–21 December 2019. [Google Scholar]
- Arulkumar, V.; Bhalaji, N. Performance analysis of nature inspired load balancing algorithm in cloud environment. J. Ambient. Intell. Humaniz. Comput.
**2021**, 12, 3735–3742. [Google Scholar] [CrossRef] - Li, Z.; Yi, L.; Zhang, Y.; Dong, Y.; Xiao, S.; Hu, W. Compatible TDM/WDM PON using a single tunable optical filter for both downstream wavelength selection and upstream wavelength generation. Photonics Technol. Lett. IEEE
**2012**, 24, 797–799. [Google Scholar] [CrossRef] - Valarmathi, R.; Sheela, T. Ranging and tuning based particle swarm optimization with bat algorithm for task scheduling in cloud computing. Clust. Comput.
**2019**, 22, 11975–11988. [Google Scholar] [CrossRef] - Al-Shargabi, M.A.; Shaikh, A.; Ismail, A.S. Enhancing the quality of service for real time traffic over Optical Burst Switching (OBS) networks with ensuring the fairness for other traffics. PLoS ONE
**2016**, 11, e0161873. [Google Scholar] [CrossRef][Green Version] - Sethi, S.; Sahu, A.; Jena, S.K. Efficient load balancing in cloud computing using fuzzy logic. IOSR J. Eng.
**2012**, 2, 65–71. [Google Scholar] [CrossRef] - Afzal, S.; Kavitha, G. Load balancing in cloud computing–A hierarchical taxonomical classification. J. Cloud Comput.
**2019**, 8, 1–24. [Google Scholar] [CrossRef][Green Version] - Dey, R.K.; Roy, S.; Bose, R.; Sarddar, D. Assessing Commercial Viability of Migrating On-Premise Mailing Infrastructure to Cloud. Int. J. Grid Distrib. Comput.
**2021**, 14, 1–10. [Google Scholar]

**Figure 5.**Genetic algorithm [41].

**Figure 6.**Particle swarm optimization flowchart [41].

**Figure 7.**Environment of ant colony optimization [41].

**Figure 8.**Artificial bee colony [69].

**Figure 9.**Gray wolf optimization algorithm [79].

**Figure 11.**Bubble net hunting strategy of whale optimization load balancing technique [91].

**Figure 12.**Behavior of social spider technique [91].

**Figure 13.**Behavior of dragonfly optimization algorithm [91].

**Figure 14.**Social roosting behavior of raven roosting load balancing technique [91].

Finding Engine | Address of Mentioned Search Engine |
---|---|

IEEE Xplore | https://ieeexplore.ieee.org/ (accessed on 5 June 2021) |

ACM | https://acm.org/ (accessed on 28 April 2021) |

Academia | https://academia.edu/ (accessed on 15 April 2021) |

Science Direct | https://sciencedirect.com (accessed on 10 May 2021) |

Taylor and Francis | https://www.taylorandfrancis.com (accessed on 18 July 2021) |

Springer | https://springer.com (accessed on 18 July 2021) |

Followed Rules of Research | |
---|---|

Inclusion | • A research paper that is designed by professionals. • A complete research analysis was performed in the sense of cloud computing. • A complete research analysis was performed in the sense of load balancing. • A research study was conducted in the context of swarm intelligence algorithms that target load balancing issues. • A research paper is presented in the English language. |

Exclusion | • A research study that did not focus on the load balancing issue in cloud computing. • A research paper that contains static algorithms. |

Algorithms | RT (ms) | FT (ms) | E (Joules) | C (Buffers) | N (in Numbers) |
---|---|---|---|---|---|

IGA [44] | 2.8 | 2.7 | 0.53 | 0.53 | 10 |

EIGA [47] | 2.5 | 2.25 | 0.5 | 0.44 | 7 |

Algorithm | Pros | Cons |
---|---|---|

GA | It makes greater use of resources and offers a better load balancing solution. | The numerous steps of computation add to computational complexity. When the search space is expanded, the efficiency suffers. It does not offer the same level of priority time. |

PSO | It has a higher utilization rate. The load is redistributed from an overburdened virtual machine to a physical machine. | The performance of the algorithm depends on the problem. |

ACO | Optimal resource usage through efficient load distribution among nodes. | Convergence takes a longer period time. |

ABC | Enhances the maximum throughput limit. | When utilized in a sequential process, the lack of supporting material causes the process to slow down, and the solution raises the computing cost. |

GWO | It is easier to use and converges more quickly due to less randomness and varied numbers of individuals assigned in global and local searching procedures. | The equal importance of the grey wolves’ positions, which is not consistent strictly with their social hierarchy. |

BAT | It boasts a high level of precision and efficiency. In terms of processing costs, it outperforms. | There is no mathematical analysis to link the parameters with convergence rates at an early stage; therefore, convergence occurs quickly. |

Algorithm | Pros | Cons |
---|---|---|

WOA | Increases the rate at which tasks are completed successfully. | It frequently fails during the initial iterative cycle, resulting in delayed convergence. |

SSA | Improves various QoS parameters by adopting the global best match. | As the number of comparable types of VMs expands, the rate of lucrative job execution falls. |

DOA | Provides fast convergence to the global optimum solution with high resource utilization. | In the lack of a nearby solution, overall response rates are shown to be ordinary rather than quick and fast. |

RROA | Efficiently prevents overloading and underloading. | Beginning iterations have a reduced rate of work completion. |

Algorithm | Authors | Main Objective | Area of Application | Targeted Issue(s) |
---|---|---|---|---|

Genetic algorithm (GA) | ||||

Genetic algorithm | Hussain A Makasarwala; Prasun Hazari, 2017 | Load balancing in cloud environments to achieve better response time. | Considers the priority to obtain real-world visualization. | To increase the range of request IDs through permutation encoding. Better response time is achieved. |

Genetic Algorithm and Gravitational Emulation | Santanu, Gopa Mandal, Dasgupta, and Paramartha Dutta, 2015 | Distribution of load among VMs. | Minimizes the makespan as well as reduces the number of VMs that are going to miss their deadlines | The combination of both strategies reduces the response time of VMs and guaranteed specifications for QoS. |

Fuzzy Logic-based Genetic Algorithm | Saadat, A., and Masehian, E, 2020 | Load Balancing in Cloud Computing. | Make output scheduling decisions correctly and based on efficient methods. | The objective function enables scheduling the order with the least possible delay. |

Multi-Agent Genetic Algorithm | Anant Kumar Jayswal, Prem Chand Saxena, 2020 | Efficient Load Balancing in Cloud Computing. | Minimizes makespan time and significantly improves the average throughput performance and resource load balancing on VMs. | Utilizes the resources efficiently and ensures QoS. |

Particle Swarm Optimization Algorithm (PSO) | ||||

Particle Swarm Optimization Algorithm | R.M.Al Guliyev, Y. N. Imamverdiyev, F. J. Abdullayeva, 2019 | Optimize the load. | Minimizes task execution and transfer time using target functions. | Time optimization for running and using energy. |

Hybrid Firefly iPSO Algorithm | Golchi, 2019 | Reach the better average load in a cloud environment. | Minimizes the makespan as well as increases the throughput. | Rapid convergence made it more effective and efficient. A high-speed response is achieved. |

Binary Particle Swarm Optimization Algorithm | Jean Buanga Mapetu, Zhen and Lingfu Kong, 2019 | Achievement of low-time complexity and low cost in load balancing. | Minimizes make-up, waiting for time, and degree of imbalance while minimizing scheduling time, cost of execution, and maximizing the use of resources. | It targets load balancing, cloud resource management task scheduling, and ensures device scalability. |

Particle Swarm Optimization Algorithm | Vidya, S. H., and Prakash, R. M. (2020). | Maintaining the load of infrastructure in Cloud. | Reduces the response time and balancing of load. | Exploit the capabilities of heterogeneous resources. |

Ant colony optimization algorithm (ACO) | ||||

Load balancing_ACO Algorithm | Gupta, A., and Garg, R., 2017 | Maintain load by task scheduling. | Meet users’ demands in terms of execution efficiency and increase resource utilization | Makespan optimization. |

Ant colony Optimization Algorithm | Gang Li, Zhijun Wu, 2019 | Optimize the load by task scheduling. | Maximize the load handling requirements of the system when efficiently completing the scheduling mission. | Better performance is achieved. |

Fuzzy-Ant Colony Algorithm | A. Ragmani, N. Abghour, and M. Rida, 2019 | Ensures neither the load is under or over-allocated. | Reduces the response and processing time up to 82% and 90%, respectively. | For handling complex networks. |

Ant colony algorithm with Support Vector Machine | Junaid, M., Sohail, A., Ahmed, A., Baz, A., Khan, I. A., and Alhakami, H, 2020. | Maintaining accuracy in load balancing. | Reduce violations, minimum migration time, high optimization, reduced makespan, and high response time. | Targets scalability and robustness in cloud environments. |

Artificial Bee Colony (ABC) | ||||

LBA_Honey Bee | W. Hashem, H. Nashaat, R. Rizk, 2017 | Maintaining load in a cloud-based environment. | Propose to avoid under and overutilization. | Reduces the execution time, reaction time, makespan, and load standard deviation. |

Artificial Bee Colony | Arif Ullah, Nazri, Jamal Uddin, Samad Baseer, Ansam Hadi Rashed, 2019 | Cloud Load Balancing with VM Strategy. | Convergence rates and global search efficiency are validated. | Fast convergence with high flexibility. |

Artificial bee foraging optimization | Geetha Muthsamy, Suganthe Ravi Chandran, 2020 | Managing the load of distributed systems. | Task preemption to reduce the tasks’ response and execution time. | Improves QoS metrics. |

Hybrid artificial bee colony algorithm with multi-objective | Jun-qing, Yun-qi, 2020. | Flexible task Scheduling in cloud computing. | Improves the rate of convergence with increased performance. | Enhances the exploitation process. |

Grey Wolf Optimization (GWO) | ||||

Simple GWO | Patel, D., Patra, M. K., and Sahoo, B.,2020 | Maintaining load in a cloud-based environment. | Propose resource allocation and load balancing. | Reduces the makespan. |

Hybrid GWO_PSO Algorithm | Gohil, B. N., and Patel, D. R., 2018 | Cloud Load Balancing with heterogeneous resources. | Convergence near the optimal solution. | Satisfy quality of service constraints. |

Fuzzy GWO | Xingjun, L., Zhiwei, S., Hongping, C., and Mohammed, 2020 | Managing the load on cloud-based IoT. | Ensures the utilization of resources efficiently. | Reduces response time and improves the degree of imbalancing. |

Hybrid GWO_ABC | Soukaina Ouhame, Youssef Hadi, 2020 | The resource allocation system is utilizing load balancing. | Improves 1.25% precision and reliability for cloud computing resource allocation systems in VM. | Improves efficiency, energy consumption, and the average time for network execution. |

Improved GWO | Gobalakrishnan Natesan, Arun Chokkalingam, 2020 | Optimize the Load by task scheduling and resource optimization. | In terms of make-up, cost, and the overall amount of work completed during the deadline, obtain the closest optimum schedule of tasks. | Improves the overall QoS. |

BAT Algorithm | ||||

iBAT Algorithm | Raj, Ranjan, Rizvi, Pranav, and Paul, 2017 | Managing the load on cloud-based IoT. | To achieve a desirable population (i.e., better utilization). | Optimized makespan is achieved. |

Micro BAT | Youssef, Hamza, Rahhali, Hanine, Benlahmar, Houssine, Mostafa, and Ahmed Eddaoui, 2018 | To avoid under and overloading the VMs. | Improve the resource allocation in series or parallel mode. | Load shifting to avoid overloaded or idle VMs. |

BAT Algorithm | Arif Ulah, Nazri Mohd, Mubashir Khan, 2020 | To improve load in a cloud-based environment. | Select VM optimally. | Satisfy QoS. |

IBO Algorithm | Vinothini, Balasubramanie, K. Arvind, 2020 | Provide load balancing in a multi-server environment. | Convergence near the optimal solution. | Better performance is achieved. |

Hybrid PSO and BAT Algorithm | Valarmathi, R., and Sheela, T., 2017 | Optimize task scheduling in the cloud to achieve load balancing. | Fast convergence. | Reduces makespan and improves resource utilization. |

Whale Optimization Algorithm (WOA) | ||||

Chaotic WOA | Kaur G and Arora S, 2018 | Balance workload and resource distribution. | Improve the convergence speed. | Reduces energy consumption with better performance. |

Hybrid WOA | Strumberger, I., Bacanin, N., Tuba, M., and Tuba, E. (2019) | Load balancing in the cloud environment. | Fast convergence. | The trade between exploitation and exploration in simple WO. |

Optimized WOA | FHemasian-Etefagh, F., and Safi-Esfahani, F., 2019 | Load balancing in the cloud with improved quality parameters. | Minimize the average execution time, response time, and throughput. | The early convergence issue. |

Improved WOA | Xuan Chen, Long Cheng, Cong Liu, Qingzhi Liu, Jinwei Liu, Ying Mao., 2020 | Cloud task scheduling | Optimizes the makespan, price, and load. | To boost the optimal solution exploration capability. |

Social Spider Algorithm (SSA) | ||||

Spider Mesh Overlay | Mahato, D. P., and Singh, R. S., 2017 | Load balancing pre-emptive jobs. | Improved fitness with fast convergence. | Enhance performance with improved efficiency of cloud-based environments. |

Chaotic SSA | Arul Xavier, V. M., and Annadurai, S., 2018 | To promote load transfer for effective scheduling. | Effective performance improvements. | To solve job planning problems in the cloud. |

SS Cloud Web Algorithm | Preeto Abrola, Savita Gupta, Sukhwinder Singh, 2019 | Load balancing non pre-emptive jobs. | Improve QoS requirements. | Create the population of tasks and resources with quality constraints. |

Dragonfly Optimization Algorithm (DOA) | ||||

Constraint Measure DOA | Polepally, V., and Shahu Chatrapati, K., 2017 | Load balancing in cloud. | Improve Performance. | Delegated job scheduling. |

Resource allocation based DOA | Zahra Amini, Mehrdad Maeen, Mohammad Reza Jahangir., 2018 | Resource Management to balance the load. | Substantial performance increase in scheduling tasks, balancing load, and allocating resources. | Task scheduling issues in data centers. |

Adaptive DOA | Neelima, P., and Reddy, A. R. M., 2020 | To avoid under and overutilization. | Optimal utilization of processing time. | The capability of minimization of execution time and cost. |

Raven Roosting Algorithm (RRO) | ||||

Basic RRO | E. Rani and H. Kaur., 2017 | Efficient task scheduling. | Improves makespan, average response, and waiting time. | To find the capacity of VMs. |

Improved RRO | Torabi, S., & Safi-Esfahani, F., 2018 | Effective load scheduling. | Improve performance, avg. response, and waiting time. | To resolve premature convergence. |

Hybrid IRRO | S. Torabi and F. Safi-Esfahani, 2018 | Improve the allocation of tasks. | The optimal solution for load balancing. | To overcome premature convergence and lacking performance. |

Reinforcement Learning with RRO Policy | Bhargavi, K., and Babu, B. S., 2019 | Load balancing in cloud | Proactive adjustment to the complex data center. | All the challenges and QoS parameters. |

Algorithms | Avg. TRT for 10 UB (ms) | Avg. TRT for 20 UB (ms) | Avg. TRT for 30 UB (ms) | Avg. TRT for 50 UB (ms) |
---|---|---|---|---|

GA | 48.4 | 49.2 | 52.3 | 56.4 |

ACO | 46.7 | 49 | 52.6 | 58.2 |

PSO | 45.6 | 47.2 | 50.3 | 53.2 |

Algorithms | Avg. TRT for 10 UB (ms) | Avg. TRT for 20 UB (ms) | Avg. TRT for 30 UB (ms) | Avg. TRT for 50 UB (ms) |
---|---|---|---|---|

GA | 45.6 | 46 | 48.4 | 52.8 |

ACO | 44.6 | 46.9 | 49 | 52.8 |

PSO | 43.2 | 45.2 | 47.8 | 50.8 |

Algorithms | Avg. TRT for 10 UB (ms) | Avg. TRT for 20 UB (ms) | Avg. TRT for 30 UB (ms) | Avg. TRT for 50 UB (ms) |
---|---|---|---|---|

GA | 42.1 | 43.2 | 45.8 | 47.9 |

ACO | 41.2 | 42.6 | 44 | 46.2 |

PSO | 40.2 | 42.2 | 44 | 47.6 |

Algorithms | Avg. TRT for 10 UB (ms) | Avg. TRT for 20 UB (ms) | Avg. TRT for 30 UB (ms) | Avg. TRT for 50 UB (ms) |
---|---|---|---|---|

GA | 39.6 | 41.3 | 43.9 | 46.4 |

ACO | 38.7 | 39.8 | 41.2 | 43.9 |

PSO | 37.8 | 38.4 | 39.8 | 41.2 |

Algorithms | Avg. DCPT for 10 UB (ms) | Avg. DCPT for 20 UB (ms) | Avg. DCPT for 30 UB (ms) | Avg. DCPT for 50 UB (ms) |
---|---|---|---|---|

GA | 6.4 | 6.1 | 6 | 5.6 |

ACO | 5.6 | 5.2 | 5.1 | 4.8 |

PSO | 5.9 | 5.1 | 4.9 | 4.6 |

Algorithms | Avg. DCPT for 10 UB (ms) | Avg. DCPT for 20 UB (ms) | Avg. DCPT for 30 UB (ms) | Avg. DCPT for 50 UB (ms) |
---|---|---|---|---|

GA | 5.8 | 5.6 | 5.5 | 5.2 |

ACO | 5.2 | 5 | 4.8 | 4.6 |

PSO | 5.4 | 4.8 | 4.6 | 4.3 |

Algorithms | Avg. DCPT for 10 UB (ms) | Avg. DCPT for 20 UB (ms) | Avg. DCPT for 30 UB (ms) | Avg. DCPT for 50 UB (ms) |
---|---|---|---|---|

GA | 5.6 | 5.3 | 5.1 | 4.7 |

ACO | 5 | 4.8 | 4.7 | 4.4 |

PSO | 5.1 | 4.6 | 4.5 | 4.2 |

Algorithms | Avg. DCPT for 10 UB (ms) | Avg. DCPT for 20 UB (ms) | Avg. DCPT for 30 UB (ms) | Avg. DCPT for 50 UB (ms) |
---|---|---|---|---|

GA | 5.3 | 5.1 | 4.9 | 4.5 |

ACO | 4.8 | 4.6 | 4.5 | 4.2 |

PSO | 4.9 | 4.5 | 4.3 | 4 |

No of Tasks | 3 | 4 | 5 | 6 |
---|---|---|---|---|

GA (time) | 2.1 | 3 | 5.75 | 6 |

PSO (time) | 1.5 | 2.5 | 5 | 5.5 |

No of Tasks | 3 | 4 | 5 | 6 |
---|---|---|---|---|

GA (cost) | 20 | 42 | 90 | 112 |

PSO (cost) | 10 | 25 | 80 | 100 |

Algorithms (with Reference) | RT | T | MS | EC | S | RU |
---|---|---|---|---|---|---|

GA (2017, [18,25]) | 🗴 | √ | √ | 🗴 | √ | 🗴 |

IGA (2017, [44]) | 🗴 | √ | √ | 🗴 | 🗴 | √ |

Fuzzy based GA (2020, [46]) | √ | √ | √ | 🗴 | 🗴 | √ |

Multi Agent GA (2020, [113]) | 🗴 | √ | √ | 🗴 | 🗴 | √ |

PSO (2019, [55]) | √ | 🗴 | 🗴 | 🗴 | 🗴 | √ |

IPSO (2019, [58]) | √ | 🗴 | √ | √ | 🗴 | √ |

Hybrid PSO (2017, [114]) | √ | 🗴 | √ | 🗴 | 🗴 | √ |

ACO (2015, [63]) | 🗴 | 🗴 | 🗴 | √ | √ | 🗴 |

Improved ACO (2016, [65]) | 🗴 | 🗴 | 🗴 | √ | √ | √ |

LBA_Honey Bee (2017, [74]) | √ | √ | √ | 🗴 | 🗴 | 🗴 |

Enhanced Bee colony (2016, [73]) | 🗴 | 🗴 | √ | 🗴 | 🗴 | √ |

ABC (2018, [20]) | 🗴 | 🗴 | √ | 🗴 | 🗴 | 🗴 |

Improved ABC (2020, [71]) | √ | 🗴 | √ | 🗴 | 🗴 | √ |

Fuzzy GWO (2017, [82]) | 🗴 | 🗴 | √ | 🗴 | 🗴 | √ |

GWO (2020, [81]) | √ | 🗴 | √ | 🗴 | 🗴 | 🗴 |

Improved GWO (2020, [80]) | √ | √ | √ | 🗴 | 🗴 | √ |

BAT (2016, [84]) | √ | 🗴 | 🗴 | 🗴 | 🗴 | √ |

iBAT (2017, [62]) | 🗴 | 🗴 | √ | 🗴 | 🗴 | √ |

microBAT (2018, [90]) | 🗴 | 🗴 | 🗴 | 🗴 | √ | √ |

Improved BAT (2020, [115]) | √ | √ | 🗴 | 🗴 | 🗴 | √ |

Chaotic WOA (2018, [94]) | √ | 🗴 | 🗴 | 🗴 | √ | 🗴 |

Hybrid WOA (2019, [93]) | √ | 🗴 | 🗴 | 🗴 | √ | 🗴 |

Optimized WOA (2019, [95]) | √ | √ | 🗴 | √ | √ | 🗴 |

Improved WOA (2020, [96]) | √ | √ | √ | √ | √ | 🗴 |

Spider Mesh Overlay (2017, [99]) | 🗴 | 🗴 | 🗴 | √ | √ | √ |

Chaotic SSA (2018, [101]) | 🗴 | 🗴 | 🗴 | √ | √ | √ |

SS Cloud Web Algorithm (2019, [102]) | √ | 🗴 | 🗴 | √ | √ | √ |

Constraint Measure DOA (2017, [105]) | √ | √ | 🗴 | √ | √ | √ |

Resource allocation based DOA (2018, [104]) | √ | 🗴 | 🗴 | √ | √ | √ |

Adaptive DOA (2020, [106]) | √ | 🗴 | 🗴 | √ | √ | √ |

Basic RRO (2017, [109]) | √ | √ | √ | 🗴 | 🗴 | √ |

Improved RRO (2018, [108]) | √ | √ | √ | √ | 🗴 | √ |

Hybrid IRRO (2017, [110]) | √ | √ | 🗴 | 🗴 | √ | √ |

Reinforcement Learning with RRO Policy (2019, [111]) | √ | √ | √ | 🗴 | 🗴 | √ |

Sr. No. | Challenges |
---|---|

1 | The backup program even system does not fail completely |

2 | Maintenance of system regularly |

3 | Resources must be used competently under load conditions |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Elmagzoub, M.A.; Syed, D.; Shaikh, A.; Islam, N.; Alghamdi, A.; Rizwan, S. A Survey of Swarm Intelligence Based Load Balancing Techniques in Cloud Computing Environment. *Electronics* **2021**, *10*, 2718.
https://doi.org/10.3390/electronics10212718

**AMA Style**

Elmagzoub MA, Syed D, Shaikh A, Islam N, Alghamdi A, Rizwan S. A Survey of Swarm Intelligence Based Load Balancing Techniques in Cloud Computing Environment. *Electronics*. 2021; 10(21):2718.
https://doi.org/10.3390/electronics10212718

**Chicago/Turabian Style**

Elmagzoub, M. A., Darakhshan Syed, Asadullah Shaikh, Noman Islam, Abdullah Alghamdi, and Syed Rizwan. 2021. "A Survey of Swarm Intelligence Based Load Balancing Techniques in Cloud Computing Environment" *Electronics* 10, no. 21: 2718.
https://doi.org/10.3390/electronics10212718