Respawn: A Distributed Multi-resolution Time-series Datastore
Maxim Buevich, Anthony Rowe

Citation
Maxim Buevich, Anthony Rowe. "Respawn: A Distributed Multi-resolution Time-series Datastore". IEEE Real-Time Systems Symposium (RTSS), 3, December, 2013.

Abstract
As sensor networks gain traction and begin to scale, we will be increasingly faced with challenges associated with managing large-scale time-series data. In this paper, we present a cloud-to-edge partitioned architecture called Respawn that is capable of serving large amounts of time-series data from a continuously updating datastore with access latencies low enough to support interactive real-time visualization. Respawn targets sensing systems where resource-constrained edge node gateway devices may only have limited or intermittent network connections linking them to a cloud-backend. The cloud-backend provides aggregate storage and transparent dispatching of data queries to edge node devices. Data is downsampled as it enters the system creating a multi-resolution representation capable of low-latency range-base queries. Lower-resolution aggregate data is automatically migrated from edge nodes to the cloud-backend both for improved consistency and caching. In order to further mask latency from users, edge nodes attempt to automatically identify and migrate blocks of data that contain statistically interesting features. We show through simulation and micro-benchmarking that Respawn is able to run on ARM-based edge node devices connected to a cloud-backend with the ability to serve thousands of clients and terabytes of data with sub-second latencies.

Electronic downloads

Internal. This publication has been marked by the author for TerraSwarm-only distribution, so electronic downloads are not available without logging in.

Citation formats

• HTML

  Maxim Buevich, Anthony Rowe. <a
  href="http://www.terraswarm.org/pubs/97.html"
  >Respawn: A Distributed Multi-resolution Time-series
  Datastore</a>, IEEE Real-Time Systems Symposium
  (RTSS), 3, December, 2013.

• Plain text

  Maxim Buevich, Anthony Rowe. "Respawn: A Distributed
  Multi-resolution Time-series Datastore". IEEE Real-Time
  Systems Symposium (RTSS), 3, December, 2013.

• BibTeX

  @inproceedings{BuevichRowe13_RespawnDistributedMultiresolutionTimeseriesDatastore,
      author = {Maxim Buevich and Anthony Rowe},
      title = {Respawn: A Distributed Multi-resolution
                Time-series Datastore},
      booktitle = {IEEE Real-Time Systems Symposium (RTSS)},
      day = {3},
      month = {December},
      year = {2013},
      abstract = {As sensor networks gain traction and begin to
                scale, we will be increasingly faced with
                challenges associated with managing large-scale
                time-series data. In this paper, we present a
                cloud-to-edge partitioned architecture called
                Respawn that is capable of serving large amounts
                of time-series data from a continuously updating
                datastore with access latencies low enough to
                support interactive real-time visualization.
                Respawn targets sensing systems where
                resource-constrained edge node gateway devices may
                only have limited or intermittent network
                connections linking them to a cloud-backend. The
                cloud-backend provides aggregate storage and
                transparent dispatching of data queries to edge
                node devices. Data is downsampled as it enters the
                system creating a multi-resolution representation
                capable of low-latency range-base queries.
                Lower-resolution aggregate data is automatically
                migrated from edge nodes to the cloud-backend both
                for improved consistency and caching. In order to
                further mask latency from users, edge nodes
                attempt to automatically identify and migrate
                blocks of data that contain statistically
                interesting features. We show through simulation
                and micro-benchmarking that Respawn is able to run
                on ARM-based edge node devices connected to a
                cloud-backend with the ability to serve thousands
                of clients and terabytes of data with sub-second
                latencies. },
      URL = {http://terraswarm.org/pubs/97.html}
  }
  

Posted by Anthony Rowe on 14 Aug 2013.