SAE: Toward Efficient Cloud Data Analysis Service for Large-Scale Social Networks

SAE: Toward Efficient Cloud Data Analysis Service for Large-Scale Social Networks

Abstract— SAE: Toward Efficient Cloud Data Analysis Service for Large-Scale Social Networks. Social network analysis is used to extract features of human communities and proves to be very instrumental in a variety of scientific domains. The dataset of a social network is often so large that a cloud data analysis service, in which the omputation is performed on a parallel platform in the could, becomes a good choice for researchers not experienced in parallel rogramming. In the cloud, a primary challenge to efficient data analysis is the computation and communication skew (i.e., load imbalance) among computers caused by humanity’s group behavior < Final Year Projects 2016 > e.g., bandwagon effect. Traditional load balancing echniques either require significant effort to re-balance loads on the nodes, or cannot well cope with stragglers. In this paper, e propose a general traggler-aware execution approach, SAE, to support the analysis service in the cloud. It offers a novel omputational decomposition method that factors straggling feature extraction processes into more fine-grained sub-processes, hich are then distributed over clusters of computers for parallel execution. Experimental results show that SAE can speed up he analysis by up to 1.77 times compared with state-of-the-art solutions.