Abstract:The paper introduces a new direction in quality-of-service-aware networked sensing that designs communication protocols and scheduling policies for data delivery that are optimized specifically for decision needs. The work complements present decision monitoring and support tools and falls in the larger framework of decision-driven resource management. A hallmark of the new protocols is that they are aware of the inference structure used to arrive at decisions (from logical predicates), as well as the data (and data quality) that need to be furnished to successfully evaluate the unknowns on which these decisions are based. Such protocols can therefore anticipate and deliver precisely the right data, at the right level of quality, from the right sources, at the right time, to enable valid and timely decisions at minimum cost to the underlying network. This paper presents the decision model used and the protocol design philosophy, reviews the key recent results and describes a novel system, called Athena, that is the first to embody the aforementioned data delivery paradigm. Evaluation results are presented that compare the performance of decision-centric anticipatory information delivery to several baselines, demonstrating its various advantages in terms of decision timeliness, validity and network resources used. The paper concludes with a discussion of remaining future challenges in this emerging area.
The advent of social networks, mobile sensing, and the Internet of Things herald an age of data overload, where the amount of data generated and stored by various data services exceeds application consumption needs. In such an age, an increasingly important need of data clients will be one of data subsampling. This need calls for novel data dissemination protocols that allow clients to request from the network a representative sampling of data that matches a query. In this paper, we present the design of a new transport-layer dissemination protocol, called InfoMax, that allows applications to request such a data sampling. InfoMax exploits the recently proposed named-datanetworking (NDN) stack that makes networks aware of hierarchical data names, as opposed to IP addresses. Assuming that named objects with longer prefixes are semantically more similar, InfoMax has the property of minimizing semantic redundancy among delivered data items, hence offering the best coverage of the requested topic with the fewest bytes. The paper discusses the design of InfoMax, its experimental evaluation, and example applications.
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.