Ching Fang Hsu

Performance analysis of deflection routing in optical burst-switched networks

This paper concerns itself with the performance of deflection routing in optical burst-switched networks based on just-enough-time (JET) signaling. Generally speaking, buffer requirement is not vital for JET-based optical burst switching (OBS). However, if deflection routing is enabled, optical buffers are necessary to solve the insufficient offset time problem. A variant of priority queuing model is proposed to approximate burst loss probability and the results show that the model provides an accurate estimation. We also evaluate the performance of deflection routing in Arpanet-2 topology. Simulation results indicate that deflection routing evidently brings significant blocking performance gain, especially with fewer wavelengths and under lighter load. In addition, we notice that excessive deflection will cause longer end-to-end delay and reduce the blocking performance. Therefore, it is necessary to control the maximum allowed deflection occurrences of a burst.

On the deflection routing in QoS supported optical burst-switched networks

Generally speaking, buffer requirement is not vital for JET-based optical burst switching (OBS). However, if deflection routing is enabled, optical buffers are necessary to solve the insufficient offset time problem. Another solution, which can alleviate buffering, is to lengthen offset time in the beginning. As previous work indicated, a burst with extra offset time has higher priority than that without extra offset time and quality of service (QoS) can be accomplished in this way. Therefore, we investigate the performance of deflection routing in prioritized JET-based optical burst-switched networks. A queuing model is proposed to approximate loss probability. We also evaluate the impact of deflection routing in Arpanet-2 topology by simulation.

Performance of adaptive routing strategies in wavelength-routed networks

As the trend of increased reconfigurability emerges in wavelength division multiplexing (WDM) networks, lightpath establishment would be moved from static toward dynamic regimes. Therefore our interest is in real-time traffic where connection requests arrive dynamically and last for a random holding time if granted. We are concerned with the performance of adaptive routing algorithms in wavelength-routed networks with wavelength conversion capability. We first investigate several adaptive routing strategies, including the shortest path strategy, the least-loaded path strategy, and the proposed weighted-shortest path strategy . We then develop an analytical model to estimate blocking performance and compare the analyses with simulations. The numerical results show that the weighted-shortest path strategy can enhance blocking performance and fairly distribute load among the links.

On the fairness improvement of channel scheduling in optical burst-switched networks

In the past years, several signaling protocols were proposed for OBS networks and the most popular one is the Just-Enough-Time (JET) protocol. JET not only efficiently utilizes the network capacity, but also effectively reduces the end-to-end transmission delay. However, the most critical defect of JET is its intrinsic deficiency: Fairness. The fairness problem is a traditional problem common to various kinds of networks. It results in a phenomenon that bursts with a shorter number of hops are generally favorized and hence deteriorates the network utilization as well. In this article, we investigate this problem and propose a fair channel scheduling algorithm as a solution. Usually there is a tradeoff between fairness and blocking performance. Accordingly, the objective of our scheme is to achieve a balance between the two conflicting metrics as much as possible. In our scheme, each burst is associated with a dynamic priority which is defined by several characteristics of the burst. When contention occurs, the proposed scheme picks the preferable burst and drops the other one according to their priorities. From simulation results, we observed that the proposed scheme could improve fairness without causing significant reduction in dropping performance. Furthermore, it increases the effective link utilization as well.

An Adaptive Interpiconet Scheduling Algorithm Based on HOLD Mode in Bluetooth Scatternets

To efficiently relay packets between associated piconets in an arbitrary-sized scatternet, an adaptive interpiconet scheduling algorithm is a requisite in a bridge. In this paper, we proposed a new interpiconet scheduling algorithm based on the HOLD mode - a power-saving mode of Bluetooth - to reduce the average interpiconet packet delay while increasing the utilization of a bridge. Generally speaking, interpiconet packet delay mainly results from the phenomenon that a bridge stays in one piconet without any interpiconet transmission activity in progress while other associated piconets are waiting for the bridge to deal with interpiconet packets. Thus, our proposed scheme estimates the time duration for which the bridge should stay in each piconet according to the traffic pattern so that the bridge can avoid being idle as possible. In particular, neither Bluetooth specification modifications nor any extra devices are needed to integrate our proposed interpiconet scheduling algorithm. Finally, the simulation results show the superiority of our proposed scheme, including low average delay, high throughput, and remarkable scalability.

Performance of Adaptive Routing in Wavelength-Routed Networks with Wavelength Conversion Capability

This paper concerns itself with the performance of adaptive routing in wavelength-routed networks with wavelength conversion capability. Exploiting the concept of load balancing, we propose an adaptive weighted-shortest-cost-path (WSCP) routing strategy. The salient feature of WSCP is that it seeks the path that minimizes the resource cost while simultaneously maintaining the traffic load among the links as balanced as possible. In our simulation, we compare the blocking probability, average hops and link utilization of WSCP with traditional shortest-cost-path (SCP) strategy, fixed routing and alternate routing. The numerical results show that WSCP can enhance blocking performance and just lengthen hop distances a little longer. The improvement is more significant in denser networks or with more wavelengths. We also develop an analytical model to estimate blocking performance of WSCP and compare analyses with simulations. Because of the benefit from load balancing, the proposed WSCP strategy can be used as a path selection algorithm in traffic engineering.

An adaptive routing strategy for wavelength-routed networks with wavelength conversion capability

We investigate adaptive routing in wavelength-routed networks. Exploiting the concept of load balancing, we propose an adaptive routing strategy named weighted-shortest-cost-path (WSCP). The salient feature of WSCP is that it seeks the path that minimizes the resource cost while simultaneously maintaining the traffic load as balanced as possible. We compare the blocking probability and average hops of WSCP with those of the traditional shortest-cost-path (SCP) strategy, fixed routing, and alternate routing. The numerical results show that WSCP can enhance blocking performance and lengthen hop distances just a little. The improvement is more significant in denser networks or with more wavelengths. We also develop an analytical model to estimate blocking performance of WSCP.

Multicast QoS traffic scheduling with arbitrary tuning latencies in single-hop WDM networks

To accommodate the demands of QoS and multicast applications, a multicast QoS traffic scheduling algorithm with tuning latency consideration in a WDM star-coupled network is provided in this paper. We define the slot scanning problem in the connection setup process as the maximum assignable slots (MAS) problem. We prove that the optimal solution of the MAS problem can be obtained in polynomial time. Owing to its high-order time-complexity, we also propose two heuristics for the MAS problem. The performance of these strategies is evaluated and compared by simulations under different system parameters, such as traffic load and tuning latency.

An Efficient Dynamic Bandwidth Allocation Algorithm with Two-Round Deliberation in Light-Trail Networks

Light-trail is a new technique, which is generalized from the concept of light path. It possesses two major advantages; one is bandwidth sharing and the other one is efficient bandwidth utilization. While a lot of literature investigate the design of routing algorithms, however, the performance of light-trail networks relies on the efficiency of dynamic bandwidth allocation schemes. In this paper, we proposed an efficient dynamic bandwidth allocation scheme named Demand and Delay latency-aware with Two-round Evaluation (DDTE). With a double-check mechanism, DDTE can allocate bandwidth more accurately and efficiently in light-trail networks. In addition to the bandwidth allocation scheme, we proposed a setup/release scheme as well. To demonstrate the superiority of DDTE, we developed a simulation suite composed of four topologies with four scenarios and gathered comparisons between DDTE and the previously proposed Dual Auction algorithm. From simulation results we can observe the significant improvement achieved by DDTE and the setup/release mechanism in both of blocking and delay performance.

An Adaptive Traffic-Aware Polling and Scheduling Algorithm for Bluetooth Piconets

According to Bluetooth specifications, communications between slave devices within a piconet are controlled by its master node. In other words, a master node has to be involved in all packet exchange activities in its associated piconet. Consequently, how to determine the polling sequence and how to estimate service time for individual slave nodes are two critical intrapiconet missions to a master and are usually categorized as the intrapiconet polling and scheduling problem. Obviously, a good polling sequence can reduce the average packet delay, whereas accurate service time estimation would result in better throughput performance. Furthermore, the packet delay of intrapiconet transmission is mostly caused by the inadequate behavior in which the master node polls an idle slave since other nonidle slaves belonging to the same piconet have to wait for the completion of such POLL/NULL packet transmissions. Certainly, unnecessary pollings would cause bandwidth utilization reduction as well. Therefore, the adaptability to traffic pattern is a necessary condition to a good intrapiconet polling and scheduling algorithm. In this paper, we proposed a traffic-aware algorithm to deal with the polling and scheduling issue within a piconet. The objective of our work is to maximize the throughput performance and to reduce the average intrapiconet packet delay as simultaneously as possible. As expected, the simulation results verify that our work designs an intrapiconet scheduling scheme with low delay and high throughput, which is adaptive to various traffic scenarios as well.