Lamps: Location-Aware Moving Top-k Pub/Sub

Nishio, Shunya; Amagata, Daichi; Hara, Takahiro

doi:10.1109/tkde.2020.2979176

Cited by 18 publications

(8 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some studies [10,28,29,33] also tackled the problem of spatiotextual 𝑘NN (or top-k) monitoring. [10] considers a decay model for streaming data, while [29,33] do a sliding-window model.…”

Section: Related Workmentioning

confidence: 99%

“…Due to the recent prevalence of GPS-enabled devices, many applications have been generating objects that contain location information and keywords [15,27]. They often provide services that retrieve objects useful to users from the generated ones, based on a locationaware publish/subscribe (Pub/Sub) model [22,23,29,33,34]. In this model, users register queries that specify query locations and keywords as their subscriptions on a Pub/Sub system, and this system delivers appropriate objects generated by publishers (e.g., Point of Interests) to subscriptions based on their query locations and keywords.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Distributed Spatial-Keyword kNN Monitoring for Location-aware Pub/Sub

Tsuruoka

Amagata

Nishio

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recent applications employ publish/subscribe (Pub/Sub) systems so that publishers can easily receive attentions of customers and subscribers can monitor useful information generated by publishers. Due to the prevalence of smart devices and social networking services, a large number of objects that contain both spatial and keyword information have been generated continuously, and the number of subscribers also continues to increase. This poses a challenge to Pub/Sub systems: they need to continuously extract useful information from massive objects for each subscriber in real time.In this paper, we address the problem of 𝑘 nearest neighbor monitoring on a spatial-keyword data stream for a large number of subscriptions. To scale well to massive objects and subscriptions, we propose a distributed solution, namely D𝑘M-SKS. Given 𝑚 workers, D𝑘M-SKS divides a set of subscriptions into 𝑚 disjoint subsets based on a cost model so that each worker has almost the same 𝑘NN-update cost, to maintain load balancing. D𝑘M-SKS allows an arbitrary approach to updating 𝑘NN of each subscription, so with a suitable in-memory index, D𝑘M-SKS can accelerate update efficiency by pruning irrelevant subscriptions for a given new object. We conduct experiments on real datasets, and the results demonstrate the efficiency and scalability of D𝑘M-SKS.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Distributed Spatial-Keyword kNN Monitoring for Location-aware Pub/Sub

Tsuruoka

Amagata

Nishio

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In traditional pub/sub middlewares [13], [35], clients are divided into publishers and subscribers. In our SDN-like pub/sub middleware, publishers are further decoupled into producers and advertisers; subscribers are further decoupled into consumers and interest managers.…”

Section: A Sdn-like Publish/subscribe Middleware Architecturementioning

confidence: 99%

“…Software Defined Networking (SDN) [6]- [11] is used to solve the difficult problem of Quality of Service (QoS) guarantees of delivering events from publishers to subscribers in IoT. For traditional IP-based pub/sub middlewares [12], [13], event matching with defined filters takes more latency owing to a detour to broker network. However, event matching and forwarding can become more efficient in SDN-based pub/sub middlewares [14], [15] because these processes can be executed directly…”

Section: Introductionmentioning

confidence: 99%

Topic-Oriented Bucket-Based Fast Multicast Routing in SDN-Like Publish/Subscribe Middleware

et al. 2020

View full text Add to dashboard Cite

In traditional IP-based publish/subscribe middlewares, a detour to overlay network is demanded to match events with defined filters, which introduces more latency overhead for delivering events from publishers to subscribers. The emerging Software Defined Networking (SDN) creates boundless possibilities to improve the efficiency of event delivery because of its centralized control and customized programmability. In this paper, we propose a topic-oriented bucket-based fast multicast routing to improve the efficiency of delivering events in SDN-like publish/subscribe middlewares. First, we design an SDN-like publish/subscribe middleware hierarchical architecture with an implementation framework in SDN controller to deliver events. Topic encoding, topic prefix matching, and the subscription coverage relationships between topics are considered to reduce the number of flow entries and improve the matching abilities of SDN switches. Then, a topic-oriented multicast tree construction algorithm is proposed to build publish/subscribe overlay networks with the minimal total link delay of event transmission and minimal switches in SDN controllers to deliver events fast. A topic-oriented bucket-based multicast forwarding algorithm is designed to achieve efficient multicast forwarding in SDN switches. Finally, experiments are conducted to verify that our construction algorithm has the minimal total delay of event transmission and our bucket-based multicast forwarding algorithm is effective.

show abstract

“…Due to the recent prevalence of GPS-enabled devices, many applications have been generating objects that contain location information and keywords [8,13]. They often provide services that retrieve objects useful to users from the generated ones, based on a locationaware publish/subscribe (Pub/Sub) model [10,11,14,15,18,19]. It is well known that range and nearest neighbor ( NN) queries support location-aware Pub/Sub systems.…”

Section: Introductionmentioning

confidence: 99%

Distributed Spatial-Keyword kNN Monitoring for Location-aware Pub/Sub

Tsuruoka

Amagata

Nishio

et al. 2020

Proceedings of the 28th International Conference on Advances in Geographic Information Systems

Self Cite

View full text Add to dashboard Cite

Recent applications employ publish/subscribe (Pub/Sub) systems so that publishers can easily receive attentions of customers and subscribers can monitor useful information generated by publishers. Due to the prevalence of smart devices and social networking services, a large number of objects that contain both spatial and keyword information have been generated continuously, and the number of subscribers also continues to increase. This poses a challenge to Pub/Sub systems: they need to continuously extract useful information from massive objects for each subscriber in real time. In this paper, we address the problem of nearest neighbor monitoring on a spatial-keyword data stream for a large number of subscriptions. To scale well to massive objects and subscriptions, we propose a distributed solution. Given workers, we divide a set of subscriptions into disjoint subsets based on a cost model so that each worker has almost the same NN-update cost, to maintain load balancing. We allow an arbitrary approach to updating NN of each subscription, so with a suitable in-memory index, our solution can accelerate update efficiency by pruning irrelevant subscriptions for a given new object. We conduct experiments on real datasets, and the results demonstrate the efficiency and scalability of our solution.

show abstract

Lamps: Location-Aware Moving Top-k Pub/Sub

Cited by 18 publications

References 34 publications

Distributed Spatial-Keyword kNN Monitoring for Location-aware Pub/Sub

Distributed Spatial-Keyword kNN Monitoring for Location-aware Pub/Sub

Topic-Oriented Bucket-Based Fast Multicast Routing in SDN-Like Publish/Subscribe Middleware

Distributed Spatial-Keyword kNN Monitoring for Location-aware Pub/Sub

Contact Info

Product

Resources

About