• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04a
• /
• pp.466-468
• /
• 2002

본 논문에서는 가상의 HLR agent database를 이용해서 다양한 CM을 가지는 단말들에 대해 적용할 수 있는 위치관리 기법을 제안한다. 기존에 제안된 방법들은 단말의 CMR을 특정범위로 제한하고 있다. 표적으로 AS(Anchor Strategy)는 CMR이 낮을 경우 위치등록 용을, caching은 CMR이 높을 경우 호 설정 비용을 줄이는 기법이다. 그러나 현실적으로는 단말의 이동과 호 수신 패턴은 일정치 않다. 기존 기법과 본 논문에서 제안하는 기법간에 성능평가를 위해 다양한 CMR을 가지는 단말들에 대한 시뮬레이션을 수행한 결과, 제안기법은 데이터베이스 접근비용이 다소 증가하지만 전체적으로 15%~20%의 성능향상을 가져올 수 있었다.

• Journal of Platform Technology
• /
• v.11 no.4
• /
• pp.71-79
• /
• 2023

In this paper, we analyze the characteristics of machine learning workloads and, based on them, propose a distributed in-memory caching technique to improve the performance of machine learning workloads. The core of machine learning workload is model training, and model training is a computationally intensive task. Performing machine learning workloads in a Kubernetes-based cloud environment in which the computing framework and storage are separated can effectively allocate resources, but delays can occur because IO must be performed through network communication. In this paper, we propose a distributed in-memory caching technique to improve the performance of machine learning workloads performed in such an environment. In particular, we propose a new method of precaching data required for machine learning workloads into the distributed in-memory cache by considering Kubflow pipelines, a Kubernetes-based machine learning pipeline management tool.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.13 no.3
• /
• pp.109-116
• /
• 2018

SSDs that are not allowed in-place update within the allocated page cause another allocation of a new page that will replace the previous page at the moment data modification occurs. This intrinsic characteristic of SSDs requires many changes to the existing HDD-based IO theory. In this paper, we conduct a performance comparison of FTL caching strategy in perspective of cache hashing (Global vs. grouped) and caching algorithm (LRU vs. NUR) through a simulation. Experimental results show that in terms of energy consumption for flash operation the grouped management of cache is not suitable and NUR algorithm is superior to LRU algorithm. In particular, we found that the cache hit ratio of LRU algorithm is about 10% point higher than that of NUR algorithm while the energy consumption of LRU algorithm is about 32% high.

• The KIPS Transactions:PartC
• /
• v.9C no.6
• /
• pp.961-968
• /
• 2002

This paper proposes a new access method which is to considered the high variability in World Wide Web and manage the web cache space. Instead of using a single cache, we divide a cache and store all documents according to their file types. Proposed method was compares with current cache management policies using LFU, LRU and SIZE base algorithm. Using two different workload, we show the improvement hitting ratio and byte hitting ratio through simulating on the file type caching.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.4
• /
• pp.32-39
• /
• 1999

Video-On-Demand servers have to provide timely processing guarantees and reduce the storage and reduce the storage and bandwidth requirements for continuous media However, compression techniques used in Video-On-Demand servers make the bit rates of compressed video data significantly variable from frame to frame Consequently, most pervious Video-On-Demand servers which use constant bit rate retrieval to guarantee deterministic service under-utilize the system resources and restrict the number of clients. In this paper, I propose a buffer management scheme called CAP(Caching And Prefetching) for Video-On-Demand server using variable bit rate continuous media. By caching and prefetching the data CAP reduces the variation of the compressed data and increases the number of clients simultaneously served and maximizes the utilization of system resources. Results of trace-driven simulations show the effectiveness of the scheme.

• Journal of KIISE:Databases
• /
• v.32 no.1
• /
• pp.56-70
• /
• 2005

The results of location-dependent queries(LDQ) generally depend on the current locations of query issuers. Many mechanisms, e.g. broadcast scheme, hoarding, or racking policy, have been developed to improve the system peformance and provide better services, which are specialized for LDQs. Considering geographical adjacency of data and characteristics oi target area, caching policy and broadcast scheme affect the overall performance in LDQ. For this reason, we propose both the caching policy and broadcast scheme, which these features are reflected in. Based on the adjacency of data in LDQ, our broadcast scheme use Hilbert curve to cluster data. Moreover, in order to develop the caching policy suitable for LDQ on urban area, we apply the moving distance of a MH(Mobile Host) to our caching policy We evaluate the performance of the caching policy measuring the workload of MHs and the correctness of LDQ results and the performance of the broadcast scheme measuring the average setup-time of MHs in our experiments. Finally, we expect that our caching policy Provides more correct answers when executing LDQ in focal cache and leads significant improvement of the performance of MHs. It also seems quite probable that our broadcast scheme leads improvement of battery life of the MH.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.6B
• /
• pp.867-874
• /
• 2010

Since high packet losses occur in multi-hop transmission of wireless sensor networks, reliable data transmission is required. Especially, in case of event-driven data, a loss recovery mechanism should be provided for lost packets. Because retransmission for lost packets is requested to a node that caches the packets, the caching node should maintains all of data for transmission in its buffer. However, nodes of wireless sensor networks have limited resources. Thus, both a loss recovery mechanism and a buffer management technique are provided for reliable data transmission in wireless sensor networks. In this paper, we propose a buffer management technique at a caching position determined by a loss recovery mechanism. The caching position of data is determined according to desirable reliability for the data. In addition, we validate the performance of the proposed method through computer simulations.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.6
• /
• pp.1696-1704
• /
• 2008

The conventional hard disk has been the dominant database storage system for over 25 years. Recently, hybrid systems which incorporate the advantages of flash memory into the conventional hard disks are considered to be the next dominant storage systems. Their features are satisfying the requirements like enhanced data I/O, energy consumption and reduced boot time, and they are sufficient to hybrid storage systems as major database storages. However, we need to improve traditional index management schemes based on B-Tree due to the relatively slow characteristics of hard disk operations, as compared to flashmemory. In order to achieve this goal, we propose a new index management scheme called FNC-Tree. FNC-Tree-based index management enhanced search and update performance by caching data objects in unused free area of flash leaf nodes to reduce slow hard disk I/Os in index access processes. Based on the results of the performance evaluation, we conclude that our scheme outperforms the traditional index management schemes.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.9 no.3
• /
• pp.91-98
• /
• 2013

Node which plays the role of cache server does not exist in the wireless ad-hoc network consisting of only mobile nodes. Even if it exists, it is difficult to provide cache services due to the movement of nodes. Therefore, the cooperative cache technique is necessary in order to improve the efficiency of information access by reducing data access time and use of bandwidth in the wireless ad-hoc network. In this paper, the whole network is divided into zones which don't overlap and master node of each zone is elected. General node of each zone has ZICT and manages cache data to cooperative cache and gateway node use NZCT to manage cache information of neighbor zone. We proposed security structure which can accomplish send and receive in the only node issued id key in the elected master node in order to prepare for cache consistent attack which is vulnerability of distributed caching techniques. The performance of the proposed method in this paper could confirm the excellent performance through comparative experiments of GCC and GC techniques.

• Journal of Communications and Networks
• /
• v.17 no.1
• /
• pp.40-46
• /
• 2015

In a mobile ad hoc network (MANET), communication between mobile nodes occurs without centralized control. In this environment the mobility of a node is unpredictable; this is considered as a characteristic of wireless networks. Because of faulty or malicious nodes, the network is vulnerable to routing misbehavior. The resource constrained characteristics of MANETs leads to increased query delay at the time of data access. In this paper, AntHocNet+ Security (ANTSEC) framework is proposed that includes an enhanced cooperative caching scheme embedded with artificial immune system. This framework improves security by injecting immunity into the data packets, improves the packet delivery ratio and reduces end-to-end delay using cross layer design. The issues of node failure and node malfunction are addressed in the cache management.