Skyline Recommendation in Distributed
Networks
Zhenhua Huang1, Jiawen
Zhang1, Zheng Liu1, Bo Zhang2, and Dong Wang3
1School of Electronics and
Information, Tongji University, China
2College of Information Mechanical
and Electrical Engineering, Shanghai Normal University, China
3College of Computer
Science and
Information Engineering, Shanghai Institute of Technology, China
Abstract: Skyline recommendation technology has recently
received a lot of attention in the database community. However, the existing works
mostly focus on how to obtain skyline objects from fine-grained data in
centralized environments. And the time cost of skyline recommendation will increase
exponentially as the number of data and skyline recommendation instructions increases, which will seriously influence the
recommendation efficiency. Motivated by the above fact, this paper proposes an efficient algorithm Skyline Recommendation
Algorithm in Distributed Networks (SRADN) in Super-Peer Architecture (SPA) distributed networks to handle multiple
subspace skyline
recommendations by prestoring the set of skyline snapshots under the cost
constraint of maintenance and communication. The proposed SRADN algorithm fully considers the characteristic of
storage and communication of SPA networks, and uses the map/reduce distributed
computation model. The SRADN algorithm
can quickly produce
the optimal set of skyline
snapshots through the following two phases: Heuristically constructing the initial set
of snapshots, and adjusting the set of snapshots based on the genetic
algorithm. The detailed theoretical analyses and extensive experiments
demonstrate that the proposed SRADN algorithm is both efficient and effective.
Keywords: Skyline
recommendation, distributed networks, map/reduce, genetic algorithm.
Received August 30, 2014; accepted December
16, 2014