Efficient Load Forecasting Approach Using Historical Data of Customer Behaviour

  • Bingi Manorama Devi, Vanteru Sudha


Cloud computing is coming up into view as a new computing standard that is receiving great attention in both academic as well as business community. It provides pay-as-you-use model for accessing different services over the web that can be accessed from anywhere and at any time. Despite of so much of merits it also faces some challenges. One of the main key issues that needed to be taken care of is load balancing. Load balancing is basically about distributing the workload among all the nodes in an even manner such that it will have positive effect on the factors like resource utilization, scalability, fault tolerant etc. Many algorithms and methods have been proposed for this purpose. Due to advancement in technology and growth in human society, it is necessary to work in an environment that reduces cost, utilizes resources effectively, reduces man power and minimizes space utilization. This led to the development of Cloud Computing technology. Cloud computing is a kind of distributed computing with a collection of computing resources located in distributed data centers. It provides massively scalable IT related capabilities to multiple external customers on “pay per use” concept using internet technologies. The increase in the web traffic and different services day by day makes load balancing a critical research topic. Load balancing is one of the central issues in cloud computing. It is the process of distributing the load optimally and evenly among various servers. Proper load balancing in cloud improves the performance factors such as resource utilization, job response time, scalability, throughput, system stability and energy consumption. Many researchers have proposed various load balancing techniques Here, in this paper we are going to investigate some of these load balancing techniques and the latest approaches used for load balancing in order to provide efficient resource utilization, overall cost minimization etc.