In the era of big-data, the jobs submitted to the clouds exhibit complicated structures represented by graphs, where the nodes denote the sub-tasks each of which can be accommodated at a slot in a server, while the edges indicate the communication constraints among the sub-tasks. We develop a framework for efficient allocation of graph jobs in geo-distributed cloud networks (GDCNs), explicitly considering the power consumption of the datacenters (DCs). We address the following two challenges arising in graph job allocation: i) the allocation problem belongs to NP-hard nonlinear integer programming; ii) the allocation requires solving the NP-complete sub-graph isomorphism problem, which is particularly cumbersome in large-scale GDCNs. We develop a suite of efficient solutions for GDCNs of various scales. For small-scale GDCNs, we propose an analytical approach based on convex programming. For medium-scale GDCNs, we develop a distributed allocation algorithm exploiting the processing power of DCs in parallel. Afterward, we provide a novel low-complexity (decentralized) sub-graph extraction method, based on which we introduce cloud crawlers aiming to extract allocations of good potentials for large-scale GDCNs. Given these suggested strategies, we further investigate strategy selection under both fixed and adaptive DC pricing schemes, and propose an online learning algorithm for each.
The goal of opinion maximization is to maximize the positive view towards a product, an ideology or any entity among the individuals in social networks. So far, opinion maximization is mainly studied as finding a set of influential nodes for fast content dissemination in a social network. In this paper, we propose a novel approach to solve the problem, where opinion maximization is achieved through efficient information spreading. In our model, multiple sources inject information continuously into the network, while the regular nodes with heterogeneous social learning abilities spread the information to their acquaintances through gossip mechanism. One of the sources employs smart information spreading and the rest spread information randomly. We model the social interactions and evolution of opinions as a dynamic Bayesian network (DBN), using which the opinion maximization is formulated as a sequential decision problem. Since the problem is intractable, we develop multiple variants of centralized and decentralized learning algorithms to obtain approximate solutions. Through simulations in synthetic and real-world networks, we demonstrate two key results: 1) the proposed methods perform better than random spreading by a large margin, and 2) even though the smart source (that spreads the desired content) is unfavorably located in the network, it can outperform the contending random sources located at favorable positions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.