In recent years, most scientic research in both academia and industry has become increasingly data-driven. According to market estimates, spending related to supporting scientic data-intensive research is expected to increase to $5.8 billion by 2018 [1]. Particularly for

CONTENTS Introduction 3

What Is Science Big Data? 3 Networking for Science Big Data Movement 4 Demilitarized Zones for Science Big Data 4 Chapter Organization 6

Science Big Data Application Challenges 7 Nature of Science Big Data Applications 7 Traditional Campus Networking Issues 10

Transformation of Campus Infrastructure for Science DMZs 13 An “On-Ramp” to Science DMZ Infrastructure 13 Handling Policy Specications 14 Achieving Performance Visibility 16 Science DMZ Implementation Use Cases 17

Network-as-a-Service within Science DMZs 20 Concluding Remarks 22

What Have We Learned? 22 e Road Ahead and Open Problems 23

Summary 24 References 24

data-intensive scientic elds such as bioscience, or particle physics within academic environments, data storage/processing facilities, expert collaborators and specialized computing resources do not always reside within campus boundaries. With the growing trend of large collaborative partnerships involving researchers, expensive scientic instruments and high performance computing centers, experiments and simulations produce petabytes of data, namely, Big Data, that is likely to be shared and analyzed by scientists in multidisciplinary areas [2]. With the United States of America (USA) government initiating a multimillion dollar research agenda on Big Data topics including networking [3], funding agencies such as the National Science Foundation, Department of Energy, and Defense Advanced Research Projects Agency are encouraging and supporting cross-campus Big Data research collaborations globally.