چکیده (انگلیسی):

The distributed computations are broadly used in the current world for processing large scale jobs. For data
intensive applications with big data, it has recently received a very good attention. A simple programming
model that allows easy development of scalable parallel applications to process big data on large clusters
was required. In our proposed work the input files will be subjected to load balancing. In load balancing
process the files will be separated and are stored in the clouds. Load balancing is done to handle the big
data. Then the stored files will be subjected to map reduce process. In mapping process the files are mapped
and a key value will be assigned to the files and then the files are reduced. The map reduce process is to be
done by assigning mappers and reducers to the cloud servers. After the mapreduce process the files will be
optimized using genetic algorithm. If the node data size increases the efficiency reduces, for increasing the
efficiency we have optimized the node data size using genetic algorithm. The experimental results will
show the enhance in the node of the data size has done efficiently and the overall efficiency increased to
considerable level with the node increments. The proposed method implemented using JAVA.