• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06a
• /
• pp.265-267
• /
• 2012

최근 들어, 하드웨어 플랫폼은 다수의 코어 아키텍처의 메모리 대역폭을 유지하기 위해 NUMA 구조로 설계되고 있다. 이러한 NUMA 시스템 구조에서 다른 노드의 메모리에 접근할 경우, 더 많은 시간과 비용이 소모된다. 따라서 이를 고려한 스케줄링 기법들이 가상화 혹은 가상화되지 않은 시스템 환경에서 연구되고 있다. 하지만, 아직까지 NUMA 시스템 가상화 환경에서 리모트 접근을 제거함과 동시에 이에 따른 오버헤드를 최소화하는 연구는 없었다. 따라서 본 논문에서는 이러한 환경에서 메모리 접근 지연을 줄이기 위한 VCPU 스케줄링 기법을 제안한다. 본 기법은 노드별 페이지 테이블 관리, LRU 기반 게스트 스케줄러, 캐시 오염 태스크 전용 버퍼 관리 기술을 이용한다. 다른 기법들과의 비교 및 분석 결과에서 알 수 있듯이, 본 기법을 적용할 경우 NUMA 시스템 노드 간 리모트 접근을 없애고, 이에 따른 오버헤드를 최소화하며, 주어진 하드웨어 캐시를 효율적으로 사용할 수 있다.

• ETRI Journal
• /
• v.42 no.4
• /
• pp.585-595
• /
• 2020

Integration of multiple communication technologies in a smart grid (SG) enables employing cognitive radio (CR) technology for improving reliability and security with low latency by adaptively and effectively allocating spectral resources. The versatile features of the CR enable the smart meter to select either the unlicensed or the licensed band for transmitting data to the utility company, thus reducing communication outage. Demand response management is regarded as the control unit of the SG that balances the load by regulating the real-time price that benefits both the utility company and consumers. In this study, joint allocation of the transmission power to the smart meter and consumer's demand is formulated as a two stage multi-armed bandit game in which the players select their optimal strategies noncooperatively without having any prior information about the media. Furthermore, based on historical rewards of the player, a real-time pricing adaptation method is proposed. The latter is validated through numerical results.

• Proceedings of the IEEK Conference
• /
• 2004.06b
• /
• pp.589-592
• /
• 2004

The CORDIC algorithm can be implemented very simple H/W, but needs a lot of latency to compute trigonometric function. The RA(Redundant Arithmetic) resolves this problem, but also has difficulty to determine the directions of micro-rotations. The pre-computed direction of micro-rotation algorithm relieves the RA of this matter. In this paper, we proposed the modified the pre-computed algorithm adopted with a table-lookup. Instead of reducing H/W complexity, its performance and calculation errors are improved.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.707-710
• /
• 2005

In this paper, we propose a new communication network for on-chip communication. The network is based on a direct sequence code division multiple access (DS-CDMA) technique. The new communication network is suitable for a parallel processing system and also drastically reduces the I/O pin count. Our network architecture is mainly divided into a CDMA-based network interface (CNI), a communication channel, a synchronizer. The network includes a reverse communication channel for reducing latency. The network decouples computation task from communication task by the CNI. An extreme truncation is considered to simplify the communication link. For the scalability of the network, we use a PN-code reuse method and a hierarchical structure. The network elements have a modular architecture. The communication network is done using fully synthesizable Verilog HDL to enhance the portability between process technologies.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.7 no.6
• /
• pp.331-338
• /
• 2012

This paper presents a wireless sensor network protocol aimed for artificial structure monitoring. The proposed protocol enables the sensor network to operate at a low duty cycle for reducing power consumption with a high degree of synchronization accuracy. It also enables event-triggered measurement of environmental information with a high sampling rate and the transmission of the measured data with a low latency. The feasibility of the proposed protocol is demonstrated through experiments involving three sensor nodes and a sink node. Though a tunnel health monitoring was considered in the paper, the proposed protocol can be easily adopted in other areas.

• Journal of information and communication convergence engineering
• /
• v.8 no.1
• /
• pp.71-76
• /
• 2010

Scalable video coding (SVC) has been standardized as an extension of the H.264/AVC standard. SVC allows straightforward adaptation of video streams by providing layered bit streams. In this paper, we propose a SVC video-based multicasting system preserving scalable security which is able to provide a SVC video service while maintaining information security. In order to maintain information security between a server and a client during all transmission time, the proposed system immediately performs a packet filtering process without decoding with respect to encrypted data received in a routing device, thereby reducing an amount of calculations and latency.

• Journal of Computing Science and Engineering
• /
• v.9 no.3
• /
• pp.134-141
• /
• 2015

In on-demand multimedia streaming systems, streaming techniques are usually combined with proxy caching to obtain better performance. The patch streaming technique has no start-up latency inherent to it, but requires extra bandwidth to deliver the media data in patch streams. This paper proposes a proxy caching technique which aims at reducing the bandwidth cost of the patch streaming technique. The proposed approach determines media prefixes with high patching cost and caches the appropriate media prefix at the proxy/local server. Herein the scheme is evaluated using a synthetically generated media access workload and its performance is compared with that of the popularity and prefix-aware interval caching scheme (the prefix part) and with that of patch streaming with no caching. The bandwidth saving, hit ratio and concurrent number of clients are used to compare the performance, and the proposed scheme is found to perform better for different caching capacities of the proxy server.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.5
• /
• pp.303-309
• /
• 2016

This paper presents a channel-adaptive rate control algorithm for low delay video coding. The main goal of the proposed method is to adaptively use the unknown available channel bandwidth while reducing the end-to-end delay between encoder and decoder. The key idea of the proposed algorithm is for the status of the encoder buffer to indirectly reflect the mismatch between the available channel bandwidth and the generated bitrate. Hence, the proposed method fully utilizes the unknown available channel bandwidth by monitoring the encoder buffer status. Simulation results show that although the target bitrate mismatches the available channel bandwidth, the encoder efficiently adapts the given available bandwidth to improve the peak signal-to-noise ratio.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.2
• /
• pp.117-123
• /
• 2016

In general, PCM (Phase Change Memory) is unsuitable as a main memory because it has limitations: high read/write latency and low endurance. However, the DRAM&PCM hybrid memory with the same level is one of the effective structures for a next generation main memory because it can utilize an advantage of both DRAM and PCM. Therefore, it needs an effective page management method for exploiting each memory characteristics dynamically and adaptively. So we aim reducing an access time and write count of PCM by using an effective page replacement. According to our simulation, the proposed algorithm for the DRAM&PCM hybrid can reduce the PCM access count by around 60% and the PCM write count by 42% given the same PCM size, compared with Clock-DWF algorithm.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.101-104
• /
• 2007

Efficient Query processing and optimization are critical for reducing network traffic and decreasing latency of query when accessing and manipulating sensor data of large-scale sensor networks. Currently it has been studied in sensor database projects. These works have mainly focused on in-network query processing for sensor networks and assumes homogeneous sensor networks, where each sensor network has same hardware and software configuration. In this paper, we present a framework for efficient query processing over heterogeneous sensor networks. Our proposed framework introduces query processing paradigm considering two heterogeneous characteristics of sensor networks: (1) data dissemination approach such as push, pull, and hybrid; (2) query processing capability of sensor networks if they may support in-network aggregation, spatial, periodic and conditional operators. Additionally, we propose multi-query optimization strategies supporting cross-translation between data acquisition query and data stream query to minimize total cost of multiple queries. It has been implemented in WSN middleware, COSMOS, developed by ETRI.