6533b7d8fe1ef96bd126b6c2

RESEARCH PRODUCT

DSMAV: An improved solution for multi-attribute search based on load capacities

Claudiu Vasile KiforHoai Son NguyenThanh-dat Nguyen

subject

Computer sciencebusiness.industryDistributed computingScalability0202 electrical engineering electronic engineering information engineering020206 networking & telecommunications020201 artificial intelligence & image processing02 engineering and technologyLoad balancing (computing)Chord (peer-to-peer)businessComputer networkDistributed hash table

description

DHT (Distributed Hash Table) such as CHORD or PARTRY facilitates information searching in scalable systems. Two popular DHT-based approaches for range or multi-attribute search are to rely on attribute-value tree and a combination of attributes and values. However, tradeoff between a load balancing mechanism and query efficiency is a challenging task for such information searching systems. In this paper, we propose improved algorithms for a system called DSMAV in which information resources are distributed fairly among nodes and found based on multi-attribute queries in a small number of hop counts. Our system creates identifiers from resource names, each of which is a combination of attribute-value pairs (AV pairs). In order to overcome problem of load imbalance among nodes because of frequent appearance of AV pairs in many resource names, we control the quantity of information resources distributed to a node based on load capacity of each node. Moreover, periodical updating processes on a node enable our load balancing mechanism to be maintained accurately. As a result, our improvement evaluated by simulated results depicts a good degree of load balance as well as query efficiency.

yearjournalcountryeditionlanguage
2016-07-012016 IEEE Sixth International Conference on Communications and Electronics (ICCE)
https://doi.org/10.1109/cce.2016.7562605