Geographical Load Balancing for Online Service Applications in Distributed Datacenters

Abstract

-This work focuses on the load balancing problem for online service applications (which are response time-sensitive) considering a distributed cloud system comprised of geographically dispersed, heterogeneous datacenters. An offline solution based on force-directed scheduling is presented, which can determine the application placement for long periods of time. The solution is then extended to do online application placement and migration for geographically distributed datacenters based on predictions about the application lifetimes, workload intensities, dynamic energy prices, and renewable energy generation capacities at different datacenters in the cloud system. The simulation results demonstrate 27% to 40% improvement using the proposed algorithms with respect to the method that does not consider the geographical load balancing.

Quality-of-service in cloud computing: modeling techniques and their applications

“…A load balancer is presented in [50] to assign VMs among geographically-distributed data centers considering predictions on workload, energy prices, and renewable energy generation capacities. Two complementary methods are proposed: an offline deterministic optimization method to be used at design time and an online VM placement, migration and geographical load balancing algorithm for runtime.…”

“…In [48] the authors propose a resource provisioning approach of N-tier cloud web applications by modeling CPU as an M/G/1 PS queue. The M/M/1 open queue with FCFS scheduling has been used [49][50][51] to pose constraints on the mean response time of a cloud application. Heterogeneity in customer SLAs is handled in [52] with an M/M/k/k priority queue, which is a queue with exponentially distributed inter-arrival times and service times, k servers and no buffer.…”

Traffic-aware virtual machine placement in geographically distributed Clouds

“…In [11], the authors propose a Mixed Integer Linear Programming (MILP) formulation that aims to place VMs in large-scale Cloud system with the objective of minimum power consumption, they consider both inter and intra data center management constraints. In [12], the authors propose both an offline and an online solution based on scheduling techniques to solve the problem of energy efficiency and load balancing for a geographically distributed Cloud infrastructure. However, to reduce energy costs, most of the existent works focus on minimizing the power consumption, balancing thermal distribution or maximizing resource usage.…”

Improving Hadoop Service Provisioning in a Geographically Distributed Cloud

“…Using geographically load balancing, [7] investigates the opportunities of lowering the operational cost of each datacenter. [8,9,10] are working on evaluating and improving the performance of MapReduce jobs that are running on highly distributed data.…”