الفهرس 
Improving the Performance of Load Balancing Over Cloud Computing
Table Of ContentsOnly 14 pages are availabe for public view
 |  | from | 114 |  |  |
| | | from | 114 | | |
Abstract
Cloud computing is the present and the future. This is the internet era.
There is no field in which the internet doesn’t play an essential role. Cloud
computing has revolted the whole universe. Cloud computing is a rapidly
growing field in research and in business. Cloud computing provides three
types of services: SaaS, PaaS, and IaaS. With the improvement of cloud
computing technology, there are many opportunities for how applications
may be built. Via virtualization on the internet, various services can be
delivered to end users. Cloud service providers supply and offer largescaled computer infrastructure based on use, as well as services of
infrastructure that are extremely elastic.
One of the most important primary goals of cloud service providers is
to develop an efficient load balancing algorithm. Load balancing is
currently the most pressing issue in the cloud environment. Load
balancing is a method of spreading the workload across network
connections on multiple servers. It optimises throughput and minimizes
overall response time. The main purpose of load balancing is to prevent
overloading and possibly crashing any server. There are two types of load
balancing algorithms: static load balancing and dynamic load balancing.
This thesis presents three of the most common load balancing algorithms
Round Robin algorithm, Active Monitoring Load Balancing algorithm
(AMLB) and Throttled algorithm. we proposed new algorithm (Balanced
Throttled Load Balancing Algorithm (BTLB)) which consider a
modification on the throttled load balancing algorithm. Then the proposed
algorithm compared with the three algorithms using cloud analyst
xiii
simulator. Overall response time of Throttled Algorithm is less than
overall response time of Round Robin Algorithm and Active Monitoring
Algorithm. Cloud analyst simulator is used to evaluate the results. The
results of overall response time of the Balanced Throttled Load Balancing
Algorithm (BTLB) is less than the overall response time of the Throttled
Load Balancing algorithm (TLB) by 100 micro second. BTLB was
developed and tested using Java.