Abstract As an effective traffic control mechanism of the asynchronous transfer mode (ATM) local area network (LAN) which has been getting attention as the next‐generation high‐speed LAN, the reactive congestion control is considered. In this paper, to obtain such a traffic control mechanism, a scheme to add the function of backpressure to an ATM switch having buffers in both the input side and the output side is evaluated. Also in this paper, the maximum throughput of an ATM switch with backpressure function for burst traffic is analyzed mathematically. Further, a uniform traffic load and a mixture of such traffic occupying the bandwidth in a peak rate as voice and video are analyzed. Moreover, with some numerical data examples, the effect of the output buffer size and the burstiness of the arriving traffic on the system performance is analyzed.
A feedback-based congestion control mechanism is essential to realize an efficient best-effort service in high-speed networks. A window-based flow control mechanism called TCP (Transmission Control Protocol), which a sort of feedback-based congestion control mechanism, has been widely used in the current Internet. Recently-proposed TCP Vegas is another version of TCP mechanism, and can achieve better performance than the current TCP Reno. In our previous works, we have analyzed stability of a window-based flow control mechanism based on TCP Vegas in both homogeneous and heterogeneous networks. In this paper, using our analytic results, we invesitigate how the dynamics of the window-based flow control mechanism based on TCP Vegas is affected by the difference in propagation delays of TCP connections. We also investigate the effect of various system parameters on transient performance of the window-based flow control mechanism.
In this paper, we propose a delivery control method of floating contents called PFCS (Proportional control for Floating Content Sharing) and investigate its properties through stability analysis. By intentionally limiting the coverage and the lifetime of epidemic broadcasting, floating contents can be shared among mobile nodes without dedicated infrastructure. Information sharing with floating contents is realized by (1) embedding the usable area (i.e., anchor zone) and the lifetime (i.e., TTL (Time-to-Live)) in a message, (2) forwarding the message among mobile nodes only in its anchor zone, (3) deleting the message if it expires, and (4) deleting the message, if necessary, once the mobile node carrying the message leaves the anchor zone. Hence, if message forwarding among mobile nodes is discontinued or some messages are lost due to buffer overflow of a mobile node, floating contents may be vanished. Such a limitation becomes more problematic when the anchor zone accommodates a number of floating contents. In this paper, we therefore propose a delivery control method of floating contents called PFCS, which controls the message possession ratio (i.e., the fraction of mobile nodes carrying a message in the anchor zone). We also perform stability analysis of PFCS to investigate fundamental properties of PFCS. Through numerical examples and simulation results, we demonstrate the effectiveness of PFCS as well as the validity of our approximate analysis.
It has been pointed out by many researchers that network traffic in LAN and WAN environments have self-similarity. However, it has not been clear why self-similarity is observed in the network traffic. Also, its impact on network performance has not been fully investigated. In this paper, we investigate the cause of traffic self-similarity in a network employing TCP/IP as its upper-layer protocol through simulation experiments. We further investigate effect of the TCP mechanism on the self-similarity of the network traffic and the effect of the self-similarity of the network traffic on the users' quality of service (QoS).
We propose a novel problem called influence maximization for unknown graphs, and propose a heuristic algorithm for the problem. Influence maximization is the problem of detecting a set of influential nodes in a social network, which represents social relationships among individuals. Influence maximization has been actively studied, and several algorithms have been proposed in the literature. The existing algorithms use the entire topological structure of a social network. In practice, however, complete knowledge of the topological structure of a social network is typically difficult to obtain. We therefore tackle an influence maximization problem for unknown graphs. As a solution for this problem, we propose a heuristic algorithm, which we call IMUG (Influence Maximization for Unknown Graphs). Through extensive simulations, we show that the proposed algorithm achieves 60--90% of the influence spread of the algorithms using the entire social network topology, even when only 1--10% of the social network topology is known. These results indicate that we can achieve a reasonable influence spread even when knowledge of the social network topology is severely limited.
In this paper we propose Block Device Layer with Automatic Parallelism Tuning (BDL-APT), a mechanism that maximizes the goodput of heterogeneous IP-based Storage Area Network (IP-SAN) protocols in long-fat networks. BDL-APT parallelizes data transfer using multiple IP-SAN sessions at a block device layer on an IP-SAN client, automatically optimizing the number of active IP-SAN sessions according to network status. A block device layer is a layer that receives read/write requests from an application or a file system, and relays those requests to a storage device. BDL-APT parallelizes data transfer by dividing aggregated read/write requests into multiple chunks, then transferring a chunk of requests on every IP-SAN session in parallel. BDL-APT automatically optimizes the number of active IP-SAN sessions based on the monitored network status using our parallelism tuning mechanism. We evaluate the performance of BDL-APT with heterogeneous IP-SAN protocols (NBD, GNBD and iSCSI) in a long-fat network. We implement BDL-APT as a layer of the Multiple Device driver, one of major software RAID implementations included in the Linux kernel. Through experiments, we demonstrate the effectiveness of BDL-APT with heterogeneous IP-SAN protocols in long-fat networks regardless of protocol specifics.
Abstract Introduction Competency is used to channel abilities into successful processes and is employed in the medical field. Worldwide, many laboratory competencies are available, but little evidence-based information about the competency of novice medical laboratory scientists exists in Japan. This study aimed to clarify competencies by various expert opinions around Japan. Methods The Delphi method was used to achieve an expert consensus on the competencies of novice medical laboratory scientists. We asked the participants to evaluate the importance of each item using the Likert scale and set 70% as the final consensus rate. The participants comprised medical laboratory scientists who met the following inclusion criteria: (1) qualified Japanese national medical laboratory scientists, (2) practised with >10 years of experience and (3) were heads of medical laboratory scientists in a clinical setting. Results We obtained 106 responses from 400 (26.5%) participants in round one and 95 from 106 (89.6%) participants in round two. Their professional experience mean ± standard deviation was 32.4 ± 6.0 years (range: 13–41). The average of each category consensus rate was >99.1%. The opinions of 95 experts converged, who agreed that competency comprised 8 categories and 54 items. Discussion Here, Japanese novice medical laboratory scientists required not only basic laboratory competencies but also other competencies, such as ‘medical safety management’, ‘interpersonal relationships’, ‘professional development’ and ‘ethics’, and some items were characteristic of Japan. Further research is warranted to explore assessments tools through the scale development of competencies, thus helping clarify the differences between ability and correlated factors.
