Cache management for shared sequential data access

As one of the main characteristics of ICN (Information Centric Networking), in-network caching had played a huge role in reducing network traffic. How to make reasonable use of the limited cache space in order to improve the cache hit ratio and reduce the network traffic had become the focus of the cache management in ICN. Considering users had different preferences in different data types, and the impact of data popularity on the data access rates, a new cache management scheme was proposed for ICN. In the proposed scheme, data were classified into different categories based on their semantic information, and the interest vector of nodes was defined according to the corresponding user preferences in different categories of data in order to address replica placement. Meantime, data popularity was introduced to solve the problem of cache replacement. Simulation results show that the proposed scheme was both feasible and effective in saving the cache space, improving the cache hit ratio and reducing network traffic load.

Download Full-text

Sequential data access with Oracle and Hadoop: a performance comparison

Journal of Physics Conference Series ◽

10.1088/1742-6596/513/4/042001 ◽

2014 ◽

Vol 513 (4) ◽

pp. 042001

Author(s):

Zbigniew Baranowski ◽

Luca Canali ◽

Eric Grancher

Keyword(s):

Data Access ◽

Performance Comparison ◽

Sequential Data ◽

A Performance

Download Full-text

Multi-level cache management of quantitative trading platform

Applied Mathematics and Nonlinear Sciences ◽

10.2478/amns.2021.2.00045 ◽

2021 ◽

Vol 0 (0) ◽

Author(s):

Zou Lida ◽

Hassan A. Alterazi ◽

Roaya Hdeib

Keyword(s):

User Experience ◽

Time Series Data ◽

Rapid Development ◽

Research Work ◽

Data Access ◽

Series Data ◽

Access Time ◽

Management Approach ◽

Cache Management ◽

Multi Level

Abstract With the rapid development of quantitative trading business in the field of investment, quantitative trading platform is becoming an important tool for numerous investing users to participate in quantitative trading. In using the platform, return time of backtesting historical data is a key factor that influences user experience. In the aspect of optimising data access time, cache management is a critical link. Research work on cache management has achieved many referential results. However, quantitative trading platform has its special demands. (1) Data access of users has overlapping characteristics for time-series data. (2) This platform uses a wide variety of caching devices with heterogeneous performance. To address the above problems, a cache management approach adapting quantitative trading platform is proposed. It not only merges the overlapping data in the cache to save space but also places data into multi-level caching devices driven by user experience. Our extensive experiments demonstrate that the proposed approach could improve user experience up to >50% compared with the benchmark algorithms.

Download Full-text

Index Structures for Data Warehousing and Big Data Analytics

Emerging Perspectives in Big Data Warehousing - Advances in Data Mining and Database Management ◽

10.4018/978-1-5225-5516-2.ch008 ◽

2019 ◽

pp. 182-197

Author(s):

Veit Köppen ◽

Martin Schäler ◽

David Broneske

Keyword(s):

Data Mining ◽

Big Data Analytics ◽

Data Access ◽

Main Memory ◽

Multidimensional Data ◽

Sequential Data ◽

Access Methods ◽

Data Mining Techniques ◽

Efficient Data ◽

Database Operations

With the ongoing increasing amount of data, these data have to be processed to gain new insights. Data mining techniques and user-driven OLAP are used to identify patterns or rules. Typical OLAP queries require database operations such as selections on ranges or projections. Similarly, data mining techniques require efficient support of these operations. One particularly challenging, yet important property, that an efficient data access has to support is multi-dimensionality. New techniques have been developed taking advantage of novel hardware environments including SIMD or main-memory usage. This includes sequential data access methods such SIMD, BitWeaving, or Column Imprints. New data structures have been also developed, including Sorted Projections or Elf, to address the features of modern hardware and multi-dimensional data access. In the context of multidimensional data access, the influence of modern hardware, including main-memory data access and SIMD instructions lead to new data access techniques. This chapter gives an overview on existing techniques and open potentials.

Download Full-text

Cooperative Caching in Mobile Ad Hoc Networks Based on Data Utility

Mobile Information Systems ◽

10.1155/2007/193641 ◽

2007 ◽

Vol 3 (1) ◽

pp. 19-37 ◽

Cited By ~ 31

Author(s):

Narottam Chand ◽

R. C. Joshi ◽

Manoj Misra

Keyword(s):

Ad Hoc Networks ◽

Mobile Ad Hoc Networks ◽

Ad Hoc ◽

Data Access ◽

Data Availability ◽

Replacement Policy ◽

Cache Management ◽

Cooperative Caching ◽

Mobile Ad Hoc ◽

Hoc Networks

Cooperative caching, which allows sharing and coordination of cached data among clients, is a potential technique to improve the data access performance and availability in mobile ad hoc networks. However, variable data sizes, frequent data updates, limited client resources, insufficient wireless bandwidth and client's mobility make cache management a challenge. In this paper, we propose a utility based cache replacement policy, least utility value (LUV), to improve the data availability and reduce the local cache miss ratio. LUV considers several factors that affect cache performance, namely access probability, distance between the requester and data source/cache, coherency and data size. A cooperative cache management strategy, Zone Cooperative (ZC), is developed that employs LUV as replacement policy. In ZC one-hop neighbors of a client form a cooperation zone since the cost for communication with them is low both in terms of energy consumption and message exchange. Simulation experiments have been conducted to evaluate the performance of LUV based ZC caching strategy. The simulation results show that, LUV replacement policy substantially outperforms the LRU policy.

Download Full-text