PHD Research Proposal for Load Balancing in Cloud Computing

Cloud computing is one the rapid-growing technique supports the computation by providing software applications as well as the hardware infrastructure over the Internet in the remote location. It allows us to run an application efficiently in the virtualized environment within the reduced cost. In Cloud computation, the utilization of Cloud resources should take place effectively, since it relates to an agreement between the user and the service provider, namely, Service-level agreement (SLA). The SLA violations occur while the resources get overloaded that is the utilization of the resources exceeds its capacity. The overloaded resources significantly increase the makespan, the CPU utilization rate that fails the resources.On the other hand, under-loaded resources reduce the makespan effectiveness; however, it increases power consumption. Hence, the effective utilization of the resource takes place within the balanced state is possible using the load-balancing technique [2]. The load-balancing is obtained using various techniques, for instance, migration, resource allocation, and task scheduling.
Various researchers effectively manage the load in specific resources using several systematic load-balancing algorithms. The existing research proposed a hybrid load balancing algorithm in [3] with the combination of two algorithms, namely, Teaching-Learning-Based Optimization (TLBO) and Grey Wolves Optimization algorithms (GWO) for maintaining the virtual machine (VM) over the multiple resources in the data center. This algorithm maintains the priority of the task, balances the load of the resources within the minimized makespan, and cost. In the specific research, they assign different algorithm for the dependent and independent tasks for maintaining the load in the resources using a hybrid task scheduling and load balancing scheme. This scheme uses three different algorithms. Namely, On-Demand scheduling, Querying and Migrating Task (QMT) and Staged Task Migration (STM) that are collectively known as the DeMS. This DeMS in [4] successfully minimizes the resource imbalance state by performing the effective scheduling of dependent and independent task. In some of the research work, they suggest an algorithm for estimating the completion time of the task in order to balance the workload in the certain resources of the data center. This load balancing algorithm effectively minimizes resource utilization, response time, and avoids the VM migration. Some of the researchers recommend the effective task scheduling algorithm [5] for the service providers that maintain the load in the resources. This algorithm distributes the available VM over the multiple resources in the data center; hence, it minimizes the power consumption, operational cost; and improves the response time, processing time.
Frequently, the existing algorithm faces difficulties in achieving the effective load-balancing since they cannot perform the load-balancing within the minimized response time and execution time. Furthermore, the performance of the existing algorithm gets degraded when the improper resource utilization, fault tolerance takes place. Notably, the resources in the data center face significant challenges to balance the load while executing the task based on its priority. Most of the existing algorithm tries to minimize the demerits mentioned above using the dynamic scheduling algorithm. However, the selection of the load, transferring the load, and selection of the target resources tend to increase the run-time overhead. Therefore, many of the researchers attempt to minimize the demerits in the existing static scheduling since these algorithms try to minimize the overall time consumption. Thus, the distribution of load across the multiple resources in the data center effectively minimizes the makespan, cost, and power consumption and achieves higher resource utilization.


  • [1] Moghaddam, Faraz Fatemi, Mohammad Ahmadi, Samira Sarvari, Mohammad Eslami, and Ali Golkar. “Cloud computing challenges and opportunities: A survey,” 1st IEEE International Conference on Telematics and Future Generation Networks (TAFGEN), pp.34-38, 2015.

  • [2] Ghomi, Einollah Jafarnejad, Amir Masoud Rahmani, and Nooruldeen Nasih Qader, “Load-balancing algorithms in cloud computing: a survey,” Journal of Network and Computer Applications, Vol.88, pp.50-71, 2017.

  • [3] Mousavi, Seyedmajid, Amir Mosavi, and Annamária R. Varkonyi-Koczy, “A load balancing algorithm for resource allocation in cloud computing,” International Conference on Global Research and Education, Springer, pp.289-296, 2017.

  • [4] Liu, Yu, Changjie Zhang, Bo Li, and Jianwei Niu, “DeMS: A hybrid scheme of task scheduling and load balancing in comp uting clusters,” Journal of Network and Computer Applications, Vol.83 pp. 213-220, 2017.

  • [5]Panwar, Reena, and Bhawna Mallick, “Load balancing in cloud computing using dynamic load management algorithm,” IEEE International Conference on Green Computing and Internet of Things (ICGCIoT), pp.773-778, 2015.

Leave Comment

Your email address will not be published. Required fields are marked *

clear formSubmit