Publications from conferences, workshops, and journals are listed below. Please also see the NDN Technical Reports and Technical Presentations.
2022
Moll, Philipp; Patil, Varun; Wang, Lan; Zhang, Lixia
SoK: The Evolution of Distributed Dataset Synchronization Solutions in NDN Proceedings Article
In: Proceedings of the 9th ACM Conference on Information-Centric Networking, pp. 33–44, Association for Computing Machinery, Osaka, Japan, 2022, ISBN: 9781450392570.
Abstract | Links | BibTeX | Tags: NDN transport, Sync
@inproceedings{moll2022sok:,
title = {SoK: The Evolution of Distributed Dataset Synchronization Solutions in NDN},
author = {Philipp Moll and Varun Patil and Lan Wang and Lixia Zhang},
url = {https://doi.org/10.1145/3517212.3558092},
doi = {10.1145/3517212.3558092},
isbn = {9781450392570},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Proceedings of the 9th ACM Conference on Information-Centric Networking},
pages = {33–44},
publisher = {Association for Computing Machinery},
address = {Osaka, Japan},
series = {ICN '22},
abstract = {Distributed dataset synchronization, or Sync in short, plays the role of a transport service in the Named Data Networking (NDN) architecture. A number of NDN Sync protocols have been developed over the last decade. In this paper, we conduct a systematic examination of NDN Sync protocol designs, identify common design patterns, reveal insights behind different design approaches, and collect lessons learned over the years. We show that (i) each Sync protocol can be characterized by its design decisions on three basic components - dataset namespace representation, namespace encoding for sharing, and change notification mechanism, and (ii) two or three types of choices have been observed for each design component. Through analysis and experimental evaluation, we reveal how different design choices influence the latency, reliability, overhead, and security of dataset synchronization. We also discuss the relationship between transport and application naming, the implications of namespace encoding for Sync group scalability, and the fundamental reason behind the need for Sync Interest multicast.},
keywords = {NDN transport, Sync},
pubstate = {published},
tppubtype = {inproceedings}
}
Distributed dataset synchronization, or Sync in short, plays the role of a transport service in the Named Data Networking (NDN) architecture. A number of NDN Sync protocols have been developed over the last decade. In this paper, we conduct a systematic examination of NDN Sync protocol designs, identify common design patterns, reveal insights behind different design approaches, and collect lessons learned over the years. We show that (i) each Sync protocol can be characterized by its design decisions on three basic components - dataset namespace representation, namespace encoding for sharing, and change notification mechanism, and (ii) two or three types of choices have been observed for each design component. Through analysis and experimental evaluation, we reveal how different design choices influence the latency, reliability, overhead, and security of dataset synchronization. We also discuss the relationship between transport and application naming, the implications of namespace encoding for Sync group scalability, and the fundamental reason behind the need for Sync Interest multicast.
Moll, Philipp; Patil, Varun; Wang, Lan; Zhang, Lixia
SoK: The evolution of distributed dataset synchronization solutions in NDN Proceedings Article
In: Proceedings of the 9th ACM Conference on Information-Centric Networking, pp. 33–44, Association for Computing Machinery, New York, NY, USA, 2022, ISBN: 978-1-4503-9257-0.
Abstract | Links | BibTeX | Tags: distributed dataset synchronization, NDN transport, Sync, sync protocols
@inproceedings{moll_sok_2022,
title = {SoK: The evolution of distributed dataset synchronization solutions in NDN},
author = {Philipp Moll and Varun Patil and Lan Wang and Lixia Zhang},
url = {https://dl.acm.org/doi/10.1145/3517212.3558092},
doi = {10.1145/3517212.3558092},
isbn = {978-1-4503-9257-0},
year = {2022},
date = {2022-09-01},
urldate = {2022-09-01},
booktitle = {Proceedings of the 9th ACM Conference on Information-Centric Networking},
pages = {33–44},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
series = {ICN '22},
abstract = {Distributed dataset synchronization, or Sync in short, plays the role of a transport service in the Named Data Networking (NDN) architecture. A number of NDN Sync protocols have been developed over the last decade. In this paper, we conduct a systematic examination of NDN Sync protocol designs, identify common design patterns, reveal insights behind different design approaches, and collect lessons learned over the years. We show that (i) each Sync protocol can be characterized by its design decisions on three basic components - dataset namespace representation, namespace encoding for sharing, and change notification mechanism, and (ii) two or three types of choices have been observed for each design component. Through analysis and experimental evaluation, we reveal how different design choices influence the latency, reliability, overhead, and security of dataset synchronization. We also discuss the relationship between transport and application naming, the implications of namespace encoding for Sync group scalability, and the fundamental reason behind the need for Sync Interest multicast.},
keywords = {distributed dataset synchronization, NDN transport, Sync, sync protocols},
pubstate = {published},
tppubtype = {inproceedings}
}
Distributed dataset synchronization, or Sync in short, plays the role of a transport service in the Named Data Networking (NDN) architecture. A number of NDN Sync protocols have been developed over the last decade. In this paper, we conduct a systematic examination of NDN Sync protocol designs, identify common design patterns, reveal insights behind different design approaches, and collect lessons learned over the years. We show that (i) each Sync protocol can be characterized by its design decisions on three basic components - dataset namespace representation, namespace encoding for sharing, and change notification mechanism, and (ii) two or three types of choices have been observed for each design component. Through analysis and experimental evaluation, we reveal how different design choices influence the latency, reliability, overhead, and security of dataset synchronization. We also discuss the relationship between transport and application naming, the implications of namespace encoding for Sync group scalability, and the fundamental reason behind the need for Sync Interest multicast.
Patil, Varun; Song, Sichen; Xiao, Guorui; Zhang, Lixia
Scaling state vector sync Proceedings Article
In: Proceedings of the 9th ACM Conference on Information-Centric Networking, pp. 168–170, Association for Computing Machinery, New York, NY, USA, 2022, ISBN: 978-1-4503-9257-0.
Abstract | Links | BibTeX | Tags: distributed dataset synchronization, NDN transport, state vector sync, Sync
@inproceedings{patil_scaling_2022,
title = {Scaling state vector sync},
author = {Varun Patil and Sichen Song and Guorui Xiao and Lixia Zhang},
url = {https://doi.org/10.1145/3517212.3559485},
doi = {10.1145/3517212.3559485},
isbn = {978-1-4503-9257-0},
year = {2022},
date = {2022-09-01},
urldate = {2022-09-01},
booktitle = {Proceedings of the 9th ACM Conference on Information-Centric Networking},
pages = {168–170},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
series = {ICN '22},
abstract = {State Vector Sync (SVS) is a Distributed Dataset Synchronization (Sync) protocol designed to support distributed applications running over NDN. SVS encodes raw dataset state in its messages to achieve resilient synchronization with low latency. As a result, the SVS message size grows linearly with the number of data producers in the same communication group, raising concerns about its scalability. This poster proposes a solution to improve SVS's scalability through the use of partial state vectors (p-SVS), and presents the results from our preliminary evaluation. Our results show that p-SVS has similar performance to vanilla SVS with improved scalability.},
keywords = {distributed dataset synchronization, NDN transport, state vector sync, Sync},
pubstate = {published},
tppubtype = {inproceedings}
}
State Vector Sync (SVS) is a Distributed Dataset Synchronization (Sync) protocol designed to support distributed applications running over NDN. SVS encodes raw dataset state in its messages to achieve resilient synchronization with low latency. As a result, the SVS message size grows linearly with the number of data producers in the same communication group, raising concerns about its scalability. This poster proposes a solution to improve SVS's scalability through the use of partial state vectors (p-SVS), and presents the results from our preliminary evaluation. Our results show that p-SVS has similar performance to vanilla SVS with improved scalability.