A bottom-up approach to real-time search in large networks and clouds

Uddin, Misbah; Stadler, Rolf

doi:10.1109/noms.2016.7502937

Cited by 3 publications

(2 citation statements)

References 93 publications

(174 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Learning based search in large networks [7] is also studied for large Clouds where network and data links [8] make the network connexions more complex. Search for objects which are hard to find has been addressed in robotics for dangerous environments [9]- [11] but this still remains an area that relies heavily on human guidance and intuition.…”

Section: A Prior Workmentioning

confidence: 99%

Search in the universe of big networks and data

Gelenbe

Abdelrahman

2014

IEEE Network

View full text Add to dashboard Cite

Searching in the Internet for some object characterised by its attributes in the form of data, such as a hotel in a certain city whose price is less than something, is one of our most common activities when we access the Web. We discuss this problem in a general setting, and compute the average amount of time and the energy it takes to find an object in an infinitely large search space. We consider the use of N search agents which act concurrently. Both the case where the search agent knows which way it needs to go to find the object, and the case where the search agent is perfectly ignorant and may even head away from the object being sought. We show that under mild conditions regarding the randomness of the search and the use of a time-out, the search agent will always find the object despite the fact that the search space is infinite. We obtain a formula for the average search time and the average energy expended by N search agents acting concurrently and independently of each other. We see that the time-out itself can be used to minimise the search time and the amount of energy that is consumed to find an object. An approximate formula is derived for the number of search agents that can help us guarantee that an object is found in a given time, and we discuss how the competition between search agents and other agents that try to hide the data object, can be used by opposing parties to guarantee their own success.

show abstract

Section: A Prior Workmentioning

confidence: 99%

Search in the universe of big networks and data

Gelenbe

Abdelrahman

2014

IEEE Network

View full text Add to dashboard Cite

show abstract

“…Address of a node is efficiently retrievable in a fully decentralized manner by searching for either of its identifiers. The ability to perform efficient, fully decentralized and concurrent search operations in a scalable manner accompanied with the flexibility in the connectivity patterns of nodes based on the name IDs emerge Skip Graph as the routing infrastructure in many P2P applications including P2P storage systems [5]- [8]. Likewise, Skip Graph can be used as an alternative of other DHTs like Chord [9] in various P2P applications.…”

Section: Introductionmentioning

confidence: 99%

Decentralized and locality aware replication method for DHT-based P2P storage systems

Hassanzadeh-Nazarabadi

Küpçü

Özkasap

2018

Future Generation Computer Systems

View full text Add to dashboard Cite

Skip Graph, a type of DHT, plays an important role in P2P cloud storage applications, where nodes publicly or privately store, share, and access data. Nowadays P2P storage systems are widely using replication to support data availability, reliability, and maintainability. With replication, the main consideration is determining peers to replicate the data. Traditional replication algorithms are partially randomized and employ rigid assumptions about nodes' distribution. This results in high access delay between nodes and their closest replicas, which degrades the system performance. We propose GLARAS, a dynamic and fully decentralized locality aware replication method for Skip Graph. In contrast to the traditional algorithms, which replicate based on strict assumptions about the distribution of nodes, GLARAS aims to approximate the underlying distribution by interacting with a very small subset of nodes and minimize the average access delay of replication accordingly. To ensure GLARAS performs at its best, we also propose a dynamic fully decentralized landmark-based locality aware name ID assignment namely LANS. This ensures that the nodes' distances in the overlay and the underlying network are consistent with each other. Our extensive experiments and analysis results demonstrate that compared to the best existing decentralized locality aware replication, GLARAS improves the average access delay of public and private replications by about 13% and 17%, respectively. Likewise, in comparison to the best existing decentralized locality aware name ID assignment, LANS improves the locality awareness of name IDs and the end-to-end latency of search queries in Skip Graph with the gains of about 19% and 8%, respectively. The average replication's access delay of a Skip Graph-based P2P storage system that employs GLARAS and LANS has an improvement gain of about 2.7 over the best state-of-the-art algorithms. Since Skip Graph is a DHT, any other DHT-based P2P storage service would benefit from our solution.

show abstract