Range Query Operations Research Articles

Enabling Privacy-Preserving Geographic Range Query in Fog-Enhanced IoT Services

The explosive growth of the Internet of Things (IoT) is pushing forward the paradigm of fog computing services today. An important service for most fog-enhanced applications is geographic range-match, which means the fog-nodes can accurately collect sensed data from IoT devices based on their location distances. However, due to the increasing attacking surfaces, outsourcing range query operations to untrusted fog-nodes inevitably raises new privacy concerns about query content and device location exposure. In this article, we devise a new geographic range-match scheme for fog-enhanced services, which allows fog-nodes to securely collect range-based sensed data while protecting the location privacy of IoT devices. Our main idea is to formulate the problem of encrypted geographic queries as range-based pattern matching and carefully craft security schemes to enable efficient range queries in the ciphertext domain. The proposed range-match scheme is provably secure and can reduce accessible information during distance comparisons. We formally analyze the security strengths and complete the prototype implementation. The comprehensive experimental results demonstrate the practicality of our designs.

Towards the design of efficient hash-based indexing scheme for growing databases on non-volatile memory

The index is a fundamental component in data intensive systems to accelerate data retrieval operations. In the design of Non-Volatile Memory (NVM) based indexes, the hash-based structure is one of the most promising candidates since it can take full advantages of byte-addressable property of NVM to perform query operations with constant time complexity. However, we found that the basic operation, “rehash operation”, may incur a large number of write activities on NVM, which is harmful to the endurance of NVM, and will cause drastic performance degradation. Additionally, range query operations cannot be efficiently conducted on hash-based indexes. In this paper, we first investigate how to design an NVM-friendly hash-based structure with the considerations of endurance and performance issues. Then, we propose a novel indexing scheme called “Bucket Hash”, which can significantly reduce the overhead caused by rehash operations and range query operations. We evaluate the proposed Bucket Hash using YCSB workloads. Compared with existing indexes, Bucket Hash achieves 40% reduction on average in the number of NVM writes, meanwhile gaining 30% improvement on timing performance.

Harnessing epoch-based reclamation for efficient range queries

Concurrent sets with range query operations are highly desirable in applications such as in-memory databases. However, few set implementations offer range queries. Known techniques for augmenting data structures with range queries (or operations that can be used to build range queries) have numerous problems that limit their usefulness. For example, they impose high overhead or rely heavily on garbage collection. In this work, we show how to augment data structures with highly efficient range queries, without relying on garbage collection. We identify a property of epoch-based memory reclamation algorithms that makes them ideal for implementing range queries, and produce three algorithms, which use locks, transactional memory and lock-free techniques, respectively. Our algorithms are applicable to more data structures than previous work, and are shown to be highly efficient on a large scale Intel system.

GPU를 이용한 R-tree에서의 범위 질의의 병렬 처리

R-tree는 데이터베이스 시스템에서 가장 많이 사용되는 색인 구조로 다차원의 데이터를 관리하는데 매우 효율적이다. 하지만 데이터베이스 시스템이 처리해야 하는 데이터의 용량이 증가함에 따라, 기존의 R-tree에서의 범위 질의의 처리는 디스크의 접근 지연 등의 이유로 인하여 수행 시간이 증가하게 되었다. 이러한 문제들을 해결하기 위하여 버퍼를 사용하거나 혹은 다수의 디스크와 프로세서를 사용하여 병렬로 질의를 수행하고자 하는 많은 연구들이 진행되었다. 이러한 연구들의 일환으로 최근 Graphics Processing Unit(GPU)을 이용한 병렬화 기법들에 대한 연구들이 진행되고 있다. 이러한 GPU의 적용을 통한 병렬화는 계산 속도의 증가와 디스크 접근 횟수의 감소를 통하여 수행 속도의 개선을 가능하게 하지만 GPU와 CPU사이의 메모리 교환 및 GPU 메모리의 접근 지연 등에 의한 오버헤드를 발생시킨다. 본 논문에서는 이러한 오버헤드를 해결하고 효과적으로 GPU를 적용하기 위하여 GPU를 버퍼로 사용하여 범위 질의를 병렬화하는 기법을 제안하였다. 버퍼 알고리즘을 통하여 메모리 교환 횟수를 줄이고, 동시 접근 가능한 메모리의 용량을 증가시켜 메모리의 접근 지연을 최소화 할 수 있었다. 제안 기법과 기존의 인덱스의 비교 실험에서 최대의 경우 5배 정도의 성능이 개선되는 것을 확인 할 수 있었다. R-trees are widely used in various areas such as geographical information systems, CAD systems and spatial databases in order to efficiently index multi-dimensional data. As data sets used in these areas grow in size and complexity, however, range query operations on R-tree are needed to be further faster to meet the area-specific constraints. To address this problem, there have been various research efforts to develop strategies for acceleration query processing on R-tree by using the buffer mechanism or parallelizing the query processing on R-tree through multiple disks and processors. As a part of the strategies, approaches which parallelize query processing on R-tree through Graphics Processor Units(GPUs) have been explored. The use of GPUs may guarantee improved performances resulting from faster calculations and reduced disk accesses but may cause additional overhead costs caused by high memory access latencies and low data exchange rate between GPUs and the CPU. In this paper, to address the overhead problems and to adapt GPUs efficiently, we propose a novel approach which uses a GPU as a buffer to parallelize query processing on R-tree. The use of buffer algorithm can give improved performance by reducing the number of disk access and maximizing coalesced memory access resulting in minimizing GPU memory access latencies. Through the extensive performance studies, we observed that the proposed approach achieved up to 5 times higher query performance than the original CPU-based R-trees.

Scalable distributed compact trie hashing (CTH*)

This last decade, a new class of data structures named Scalable Distributed Data Structures (SDDSs), is appeared completely dedicated to a distributed environment. This type of data structures opened an important axis of research, considering that the data management in a transparent manner is fundamental in a computer network. All the existing methods are mainly based on Linear hashing (LH*) and Range-partitioning (RP*). In this paper, we propose a new method with the constraints of the SDDS. Our approach is an adaptation of the well-known method Trie hashing (TH) for a distributed environment, i.e. a network of interconnected computers. The latter uses a digital tree (trie) as access function. Our major objective is the distribution of file buckets and the tree representing the hashing function. We have considered TH with the tree represented in compact form (CTH) because this option is probably more interesting for the reduction of the message size circulating on the network. Contrary to the majority of the existing methods, the proposed one provides the order of distributed files, then facilitates both the range query operations and the ordered traversal of files. Moreover, the following properties make our method a promising opening towards a new class of SDDS: (a) preservation of the order of records, (b) works without multicast (c) three bytes are sufficient to address a server, (d) the transfer of some bytes is enough for the update of the client trees. The access performances should exceed the ones of traditional files and some competitive scalable and distributed data structures.

Spatial indexing of large volume swath data sets

This paper introduces a new hierarchical data structure that supports efficient insertion, deletion and two-dimensional range query operations on swath data. Three different spatial indexing methods were designed, implemented and compared on a large swath data set. Two of the methods are based on the Morton code sequence, and the third uses an R-tree for the index. A relational database management system (RDBMS) was used to build one of the Morton code sequence indexing methods. Experiments with the large scale data set show that R-tree indexing is superior to Morton sequence indexing by providing two to nine times faster two dimensional range search speed, occupying slightly less disk space, and supporting the range deletion operation. Time and space requirements for spatial indexing with the RDBMS were shown experimentally to be significantly worse than for the direct C code implementation of the Morton code sequence indexing.