A5073240021- Software-Defined Networks and 5G
- Distributed and Parallel Computing Systems
- Advanced Optical Network Technologies
- Cloud Computing and Resource Management
- Scientific Computing and Data Management
- Advanced Data Storage Technologies
- Caching and Content Delivery
- Peer-to-Peer Network Technologies
- Seismic Waves and Analysis
- Seismology and Earthquake Studies
- Optical Network Technologies
- Network Security and Intrusion Detection
- Quantum Computing Algorithms and Architecture
- Software System Performance and Reliability
- Quantum Mechanics and Applications
- Interconnection Networks and Systems
- IoT and Edge/Fog Computing
- Advanced Photonic Communication Systems
- Geophysics and Sensor Technology
- Advanced Fiber Optic Sensors
- Quantum Information and Cryptography
- Network Traffic and Congestion Control
- Research Data Management Practices
- Opportunistic and Delay-Tolerant Networks
- Graphite, nuclear technology, radiation studies
Energy Sciences Network
2015-2024
Lawrence Berkeley National Laboratory
2015-2024
Lawrence Livermore National Laboratory
2013
Nortel (Canada)
2004-2006
We present one of the first case studies demonstrating use distributed acoustic sensing deployed on regional unlit fiber-optic telecommunication infrastructure (dark fiber) for broadband seismic monitoring both near-surface soil properties and earthquake seismology. recorded 7 months passive data a 27 km section dark fiber stretching from West Sacramento, CA to Woodland, CA, densely sampled at 2 m spacing. This dataset was processed extract surface wave velocity information using ambient...
Sensor and smart phone technologies present opportunities for data explosion, streaming collecting from heterogeneous devices every second. Analyzing these large datasets can unlock multiple behaviors previously unknown, help optimize approaches to city wide applications or societal use cases. However, handling of massive presents challenges in how perform optimized online analysis `on-the-fly', as current are often limited by capability, expense resources. This a need developing new methods...
In this paper, we discuss building blocks that enable the exploitation of optical capacities beyond 100 Gb/s. Optical networks will benefit from more flexibility and agility in their network elements, especially coherent transceivers. To achieve 400 Gb/s more, transceivers operate at higher symbol rates. This be made possible with bandwidth components using new electro-optic technologies implemented indium phosphide silicon photonics. Digital signal processing algorithms. Multi-dimensional...
FABRIC is a unique national research infrastructure to enable cutting-edge and exploratory at-scale in networking, cybersecurity, distributed computing storage systems, machine learning, science applications. It an everywhere-programmable nationwide instrument comprised of novel extensible network elements equipped with large amounts compute storage, interconnected by high speed, dedicated optical links. will connect number specialized testbeds for cloud (NSF Cloud CloudLab Chameleon),...
University campuses, Supercomputer centers and R&E networks are challenged to architect, build support IT infrastructure deal effectively with the data deluge facing most science disciplines. Hybrid network architecture, multi-domain bandwidth reservations, performance monitoring GLIF Open Lightpath Exchanges (GOLE) examples of architectures that have been proposed, championed implemented successfully meet needs science. Most recently, Science DMZ, a campus design pattern bypasses...
ESnet, the Energy Sciences Network, has mission of providing network infrastructure to U.S. Department Energy's Office Science programs and facilities, which depend on large collaborations large-scale data sharing, enabling them accomplish their science. ESnet4 - a hybrid IP dynamic circuit designed in 2006 completed 2008 managed effectively satisfy networking needs science community, easily handling dramatic growth traffic requirements: around 80 percent year over 300 with Large Hadron...
Big data and insatiable consumer demand for broadband are driving a new generation of intelligent, programmable, energy-efficient networks—powered by optical switching—to support Internet services reaching terabit-per-second speeds.
New e-Science and grid applications require the coordination of geographically distributed scientific instruments along with data computing resources. Due to quality service requirements these applications, resources can be connected by a wavelength-routed optical network, allowing each application get dedicated bandwidth. These networks are referred as LambdaGrids. One important provided in is advance reservation. Applications need coordinate use both network. Advance reservation allows...
We present an architecture framework for the control and management of multilayer networks associated advanced network services. This material is identified as "architecture framework" to emphasize its role in providing guidance structure our subsequent detailed architecture, design, implementation activities. Our work motivated by requirements from Department Energy science application community real-time on-demand science-domain-specific services resource provisioning. also summarize...
Public and Private Enterprise clouds are changing the nature of WAN data center interconnects. Data interconnects today pre-allocated, static optical trunks high capacity. These pipes carry aggregated packet traffic originating from within centers while routing decisions made by devices at edges. In this paper, we propose a software-defined networking enabled transport architecture (Transport SDN) that meshes seamlessly with deployment SDN Centers. The proposed programmable abstracts core...
There have been a lot of proposals to unify the control and management packet circuit networks but none deployed widely. In this paper, we propose simple programmable architecture that abstracts core transport node into virtual switch, meshes well with software-defined network paradigm while leveraging OpenFlow protocol for control. A demonstration use-case an OpenFlow-enabled optical switch implementation managing small big-data applications is described. With appropriate extensions...
The Computing Models of the LHC experiments continue to evolve from simple hierarchical MONARC[2] model towards more agile models where data is exchanged among many Tier2 and Tier3 sites, relying on both large scale file transfers with strategic placement, an increased use remote access object collections caching through CMS's AAA, ATLAS' FAX ALICE's AliEn projects, for example. challenges presented by expanding needs CPU, storage network capacity as well rapid handling datasets have pointed...
We realize an open, programmable paradigm for application-driven network control by way of a novel plane - the "service plane" layered above legacy networks. The service bridges domains, establishes trust, and exposes to credited users/applications while preventing unauthorized access resource theft. authentication, authorization, accounting subsystem dynamic allocation controller are two defining building blocks our plane. In concert, they act upon interconnection request or restoration...
QUANT-NET is a three-node quantum network research testbed funded by the U.S. Department of Energy (DOE). The goal to establish this between two sites, Lawrence Berkeley National Lab (LBNL) and University California, Berkeley, connected with an entanglement swapping substrate over optical fiber managed protocol stack. On top team will implement most basic building blocks distributed computing repeater teleporting controlled-NOT gate far trapped-ion computation nodes. This paper presents...
Many companies deploy multiple data centers across the globe to satisfy dramatically increased computational demand. Wide area connectivity between such geographically distributed has an important role ensure both quality of service, and, as bandwidths increase 100Gbps and beyond, efficient way dynamically distribute computation. The energy cost transmission is dominated by router power consumption, which unfortunately not proportional. In this paper we only quantify performance benefits...
Wide area networks (WAN) forward traffic through a mix of packet and optical data planes, composed by variety devices from different vendors. Multiple forwarding technologies encapsulation methods are used for each plane (e.g. IP, MPLS, ATM, SONET, Wavelength Switching). Despite standards defined, the control planes these usually not interoperable, to manage segment independently Open Flow, TL-1, GMPLS). The result is lack coordination between layers inefficient resource usage. In this paper...
Big Data has emerged as a driving force for scientific discoveries. Large instruments (e.g., colliders, and telescopes) generate exponentially increasing volumes of data. To enable discovery, science data must be collected, indexed, archived, shared, analyzed, typically in widely distributed, highly collaborative manner. transfer is now an essential function discoveries, particularly within big environments. Although significant improvements have been made the area bulk transfer, currently...
Large community of high-energy physicists share their data all around world making it necessary to ship a large number files over wide- area networks. Regional disk caches such as the Southern California Petabyte Scale Cache have been deployed reduce access latency. We observe that about 94% requested volume were served from this cache, without remote transfers, between Sep. 2022 and July 2023. In paper, we show predictability resource utilization by exploring trends recent cache usage. The...