With advancement in Recent technology, gradually mobile devices are replacing traditional personal computers. With gigabytes of memory and multi-core processors nowadays new generations of mobile devices are very powerful. These devices are high-end computing hardware and complex software applications that generate large amounts of data on the order of hundreds of megabytes. This data can vary from application raw data to images, audio, video or text files. With the fast hike in the number of mobile devices, big data processing on mobile devices has become a key emerging necessity for providing capabilities similar to those provided by traditional servers.
Recent mobile applications that can do massive computing tasks (big data processing) offload data and tasks to data centers or powerful servers in the cloud. For processing large datasets, there are numerous cloud services that provides computing infrastructure to end users. Hadoop MapReduce is one of the popular open source programming framework deployed in cloud for cloud computing applications. The framework splits the user job into smaller tasks and runs these tasks in parallel on different nodes, thus decreasing the overall execution time when compared with a sequential execution on a single node. In the case of military or disaster response operations this architecture however, fails in the absence of external network connectivity. This architecture is also not used in emergency response scenarios where there is limited connectivity to cloud, which leads to expensive data upload and download operations. In such scenarios, wireless mobile ad-hoc networks are typically deployed. The drawbacks of the traditional cloud computing motivate us to study the data processing problem in an infrastructure less and mobile environment. In which the internet is unavailable and all jobs are performed on mobile devices. The mobile devices in the vicinity are willing to share each other’s computational resources.
There are lots of challenges in bringing big data capabilities to the mobile environment:
Hadoop MapReduce framework over MDFS and evaluate its performance on a general heterogeneous cluster of devices. implementing the generic file system interface of Hadoop for MDFS. which makes system practical similar with other Hadoop frameworks like HBase. Since not requirement of any changes for existing HDFS applications to be deployed over MDFS. Hadoop MapReduce framework for mobile cloud that truly addresses the challenges of the dynamic network environment. The System provides a distributed computing model for processing of large datasets such as unstructured data like media files, text and sensor data in mobile environment while ensuring strong guarantees for energy efficiency, data reliability and security. Thus, system is a viable solution to meet the growing demands of data processing in mobile environment.
This essay has been submitted by a student. This is not an example of the work written by our professional essay writers. You can order our professional work here.