With the rapid growth of wearable devices and the Internet of Things (IoT), users increasingly rely on smartwatches and fitness trackers for services in connected environments. These devices collect sensitive physiological and behavioral data, requiring reliable user authentication to ensure secure access by authorized users. However, few-shot scenarios with significant intra-class variability and limited training data make it challenging for models to capture complex feature interactions. In this paper, we propose a Ratio-Enhanced Feature Interaction (RE-FI) framework designed for wearable running data. RE-FI systematically constructs pairwise product and ratio-based cross features to explicitly model second-order interactions and applies information gain–based feature selection to retain the most discriminative features. We provide theoretical justification for these design choices across linear models, tree-based classifiers, and deep neural networks. We validate RE-FI on real-world running data using nine representative classifiers. Results show that RE-FI consistently outperforms the baseline feature set across all classifiers, achieving an average accuracy improvement of 4.2% and up to 6.2% in F1-score. In extreme few-shot settings with only five samples per user, RE-FI maintains robust performance, with Random Forest achieving an average accuracy of 86%. Overall, this work offers a computationally simple feature-interaction solution that is compatible with diverse supervised models on session-level wearable statistical features and provides a principled approach for wearable security and personalized health monitoring in IoT applications.

Technologies such as intelligent reflective surface (IRS)-assisted free-space optics (FSO) systems, are capable of providing connectivity with varied bandwidth through flexibly allocating resources on a planer panel. This flexibility provides new opportunities in handling inter-rack traffic that is often unevenly distributed in space and time. In this paper, we explore a new type of resource allocation scheme by taking full advantage of this flexibility. The key ideas include: (1) dynamically divide the resource on the planar panel into two planes, such that the small and large flows can be handled separately; (2) in the plane serving small flows, use multi-hop routing with variable bandwidth connections to handle skewed traffic between source-destination pairs; (3) in the plane serving large flows, use direct links with variable bandwidth to schedule unevenly distributed demand. In essence, through flexible resource allocation in and between the two planes, this scheme is able to make more efficient use of resources. We theoretically analyze the capacities of the proposed scheme, where the effectiveness conditions and performance bounds for dynamic resource adaptation are derived and the traffic scheduling with flexible bandwidth in two planes is proved to be able to achieve constant factor approximation to the ideally optimal performance. We then propose a set of lightweight algorithms with performance guarantees in each of two planes, collectively calledFlexAlloc, to realize the flexibility and adaptivity of the proposed scheme, and discuss an example of this scheme in the context of IRS-assisted FSO systems. Our simulation results show thatFlexAllocexhibits significant superiority over existing schemes for unevenly distributed traffic at low computational complexity, and can reduce the average flow completion time by 56-81%.

Recommendation systems are essential tools in modern e-commerce, facilitating personalized user experiences by suggesting relevant products. Recent advancements in generative models have demonstrated potential in enhancing recommendation systems; however, these models often exhibit limitations in optimizing retrieval tasks, primarily due to their reliance on autoregressive generation mechanisms. Conventional approaches introduce sequential dependencies that impede efficient retrieval, as they are inherently unsuitable for generating multiple items without positional constraints within a single request session. To address these limitations, we propose TBGRecall, a framework integrating Next Session Prediction (NSP), designed to enhance generative retrieval models for e-commerce applications. Our framework reformulation involves partitioning input samples into multi-session sequences, where each sequence comprises a session token followed by a set of item tokens, and then further incorporate multiple optimizations tailored to the generative task in retrieval scenarios. In terms of training methodology, our pipeline integrates limited historical data pre-training with stochastic partial incremental training, significantly improving training efficiency and emphasizing the superiority of data recency over sheer data volume. Our extensive experiments, conducted on public benchmarks alongside a large-scale industrial dataset from TaoBao, show TBGRecall outperforms the state-of-the-art recommendation methods, and exhibits a clear scaling law trend. Ultimately, NSP represents a significant advancement in the effectiveness of generative recommendation systems for e-commerce applications.

When optical switching is deployed in Data Center Networks (DCNs), the reconfiguration of the optical switching matrix leads to substantially longer overheads, posing a significant impact on the system performance. Despite the extensive studies on the scheduling algorithms based on demand matrix decomposition (DMD), the stateful and irregular nature of the scheduling processes hinders the development of quantitative models, thereby limiting our understanding of resource scheduling in optical switching DCNs based on DMD. In this paper, we model the DMD based resource scheduling process under a bursty and skewed traffic pattern and derive closed-form equations for the burst completion time. Our study shows that an increased reconfiguration delay will lead to an approximate linear increase in the burst completion time. Our study also demonstrates that the size of the slot and the maximum allowed duration of one match are approximately inversely proportional to the burst completion time, with diminishing marginal returns.

The growing threat of physical inactivity to human health has highlighted the rising importance of community sports organizations, which play a crucial role in promoting physical activity and improving overall public health. However, the limited understanding of human behavior leads to suboptimal resource utilization, highlighting the necessity for a scientific understanding of human behavior within such social systems to optimize resource allocation, enhance participation levels, and improve public health. In this study, we aim to gain insights into the possible mechanisms behind user participation in community sports activities and reveal the role of external incentives on individual engagement. We study the participation behavior of 2,956 members over a 6-year period in a community sports organization, and demonstrate that the participation frequency adheres to a power-law distribution. We then propose a mathematical model called habit formation and behavioral inertia (HFBI), and through experiments, we demonstrate that the data generated by the model shows a robust fit to the distribution of empirical data. We also analyze the effects of different types of activities, and find that periods of high activity participation often begin with rewarded activities, suggesting the importance of incentives to sustain long-term participation. Our study provides a scientific foundation for developing optimized strategies to enhance community sports participation. The HFBI model may also be used to understand data exhibiting power-law distributions beyond the domain of community sports.

Intelligent reflective surface (IRS)-assisted free-space optics (FSO) systems allow allocation of different number of IRS elements between communication end-points. It thus can provide connectivity with variable bandwidth in data centers, where the traffic between top-of-rack switches is often unevenly distributed in space and time. In this paper, we propose a novel traffic scheduling technique that allows variable bandwidth in the context of IRS-assisted FSO systems in data center networks (DCNs). We formalize the problem of scheduling with variable bandwidth, explore the performance space for designing scheduling algorithms, and provide insights on how to use heuristics in practice. Then, we propose a low-complexity and performance-guaranteed parallel scheduling algorithm,pVarband, that takes advantage of variable bandwidth to avoid the time-consuming maximum weight matching and can run at a complexity of$\mathcal {O}(N\log N)$in a DCN withNracks. We theoretically demonstrate that scheduling with variable bandwidth requires at most$\mathcal {O}(\log (1/\epsilon))$reconfigurations to obtain an$\epsilon $-approximate decomposition for an arbitrary traffic matrix. Also, we provide insights for design and deployment of an IRS-assisted FSO system to achieve performance saturation. Our results show that scheduling allowing variable bandwidth can achieve almost optimal performance for unevenly distributed traffic, and also outperforms its fixed bandwidth counterpart in terms of running time and decomposition error. Our work also provides useful insights for scheduling with variable bandwidth in contexts other than IRS-assisted FSO systems.

Steerable free-space optics (FSO) communications are flexible in link reconfiguration (LR), and easy to deploy, especially when the available physical space is limited. Thus it is considered as a good complement to the wired network in data centers. In this paper, we are interested in understanding the role of FSO when used as a hotspot offloading technique in data center networks. We aim to quantify the performance of FSO-based hotspot offloading, in the presence of link impairment, failed negotiations and reconfiguration overhead. We model this steerable FSO-based traffic offloading process as a vacation queueing system with limited service discipline. A general expression for the average delay is derived, and then equations for three different hybrid automatic repeat request (HARQ) protocols are separately derived. To overcome the inherent difficulty of calculating the average delay with limited service, efficient low-complexity approximations are developed. We then show that the system delay increases approximately linearly with the traffic rate until a point, beyond which it grows rapidly. Further, we analyze the effect of various factors on the delay performance and offer insights for the design configurations to achieve the desired performance. The simulation results verify the validity of the theoretical analysis.

As an accurate measurement of physical activity, step counts data can be collected expediently by smartphones and wearable devices. Complete and high time-resolution step counts data record the time and intensity of individuals’ physical activity in a day, and can be used to mine activity habits or to recommend customized workout plans. However, sparse step counts data are common in practice due to hardware and software limitations. Understanding the value of sparse step counts data can contribute to its application in healthcare, and also can help us design cost-effective hardware and software. In this article, we aim to infer activity patterns from sparse step counts data. We design a deep learning model based on recurrent neural networks, namely MLP-GRU, which considers bidirectional short-term dependency and long-term regularity of sparse step counts data, and implements data-driven imputation and classification. We also develop an interpretable and elastic method to obtain sparse step counts data labeled with multi-granular activity patterns to train MLP-GRU. Evaluations on real-world datasets reveal that MLP-GRU outperforms other strong baseline methods. The results also show that activity patterns can be inferred from extremely sparse step counts data with high accuracy, provided that proper granularity is used for data of different sparsity.

The data center markets in emerging economies are being built at a furious pace. When high availability is required, as it always is in the modern digital economy, the placement of geo-distributed data centers may be influenced by factors such as technician shortage and under-developed infrastructure, both of which are typical in emerging economies. Although the data center availability subject in general has been well studied, it remains unclear how rapid and unbalanced economic development in emerging economies may affect the availability of geo-distributed data centers and their cost of ownership. In this paper, we incorporate the unbalanced availability of infrastructure and technician into the data center placement. The problem is first formulated as a mixed integer nonlinear program (MINLP).To solve this potentially large scale problem, we transform it into a QCQP, capable of handling heterogeneous workloads. The resulting problem can then be efficiently solved by off-the-shelf optimization toolboxes. With real-life data in China, we show how unbalanced development of infrastructure and technician shortage may affect the placement of data centers, and analyze the tradeoff between cost and availability. Our results indicate that technician shortage and unbalanced network infrastructure will lead to increased cost and distinct data center placement strategies.

The increasing demand of bulk data transfer imposes significant challenges in inter-datacenter networks that span multiple domains. Storing data temporarily at domain borders and forward it at later off-peak hours (SnF) can reduce congestion and improve network utilization. However, performance gains from SnF transfer still requires further quantitative study. In this paper, we model deadline-constrained SnF transfers in networks with congested inter-domain links, where traffic has slightly varying peak hour and diurnal patterns. A closed-form estimation for the two-links case is derived to quantify the performance gain of intermediate storage (IS) and edge storage (ES). Our study shows that if bulk data transfer requests arrive with equal probability in a day, increase the allowed waiting time will increase the successful transfer probability linearly. Increasing the aggregated network load, defined as the summed duration of the background traffic peak-hour and data transfer, will result in linear decrease in successful transfer probability, when the network is moderately loaded. Our research also shows that IS has significant advantages over ES under heavy network load, and the maximum benefit occurs when the allowed waiting time is two times the aggregated network load.

As people become more health-conscious, more community sports organizations (CSOs) are emerging in society. The development of CSOs is often subject to very limited resources, and understanding its underlining principles is critical to maximizing the utility of available resources. Existing studies of CSOs are often empirical and adopt top-down methods of organizational management. This is partly because the inputs needed for such studies, for example, the interactions between community members, are often difficult to record. In this article, we perform an objective social network analysis on a real CSO with 2073 active members, with data collected over a five-year span on a mobile platform. Our study shows that the CSO members’ network has a low density and weak densification and is assortative and obvious in community structure. With a classification algorithm called SC-CEE, we observe that the development of the CSO can be robustly divided into stages. We further observe that the relationship between specific stimulus and community evolution varies across development stages, implying that an organization’s response strategy to change should be aligned with its stage of development. We then give practical guidance on the developmental priorities and response strategy of CSOs at different stages.

This article investigates an unmanned aerial vehicle (UAV)-assisted wireless-powered mobile-edge computing (MEC) system, where the UAV powers the mobile terminals by wireless power transfer (WPT) and provides computation service for them. We aim to maximize the computation bits of terminals while ensuring fairness among them. Considering the random trajectories of mobile terminals, we propose a soft actor–critic (SAC)-based UAV trajectory planning and resource allocation (SAC-TR) algorithm, which combines off-policy and maximum entropy reinforcement learning to improve the convergence of the algorithm. We design the reward as a heterogeneous function of computation bits, fairness, and destination. Simulation results show that SAC-TR can quickly adapt to varying network environments and outperform representative benchmarks in various situations.

Emerging online services have fueled unprecedented demands for multicast transfers across geo-distributed datacenterse However, the time- and space-varying nature of background traffic in inter-datacenter networks (inter-DCNs) makes conventional multicast trees difficult to fully utilize the residual bandwidth in the inter-DCNs. In this paper, we introduce datacenter storage into multicast transfers, and propose Store-and-Forward-Tree (SnFTree) scheduling method for multicast transfers in the software-defined optical network. Compared to the conventional multicast scheduling methods, the advantages of SnFTree are as follows: (i) by enabling temporary storage at intermediate sites, SnFTree can segment the conventional multicast tree into independent subtrees, which maximizes the flexibility of provisioning; (ii) by introducing load-balancing routing into the tree computation, SnFTree can balance the traffic load across network efficiently; (iii) benefiting from optical multicast, storing, forwarding and reception can be simultaneously implemented on a site with negligible processing delay; (iv) by formulating the multicast scheduling problem into a routing problem, SnFTree greatly simplifies the problem for dynamic traffic. Simulations demonstrate that compared to conventional scheduling methods, SnFTree obtains lower blocking probability and requires fewer OpenFlow Agent Updates.

Traffic fluctuations make conventional multicast tree difficult to fully utilize the residual bandwidth in the inter-datacenter networks. In this paper, we introduce datacenter storage into the provisioning process of multicast transfers. A scheduling method, named Store-and-Forward-Tree (SnFTree), is proposed for multicast transfers in the software-defined inter-datacenter optical network. By leveraging temporary storage at intermediate sites, a multicast tree can be segmented into time-independent subtrees when provisioning an entire light-tree fails. Benefiting from the broadcast nature of optical multicast, intermediate sites can provide cut-through routing and temporary storage simultaneously with negligible processing delay. By using load-balancing tree computation, traffic can be balanced across the network efficiently. Simulations show that SnFTree provides extra provisioning flexibility and hence outperforms the state-of-the-art scheduling methods in terms of blocking probability and the number of OpenFlow Agent updates.

In recent years, connection-based slotted-Aloha (CS-Aloha) has been proposed to improve the performance of random access networks. In this protocol, each node attempts to send a request to the access point (AP) before packet transmission. Once this attempt is successful, the node can transmit up to M packets to the AP. Previous works indicated that the CS-Aloha can achieve a higher throughput than the classical slotted Aloha (S-Aloha), if M is large enough. However, the impact of M on the delay performance and stability is still unknown. To solve this problem, we model each node of the CS-Aloha as a vacation queueing system with limited service discipline, where we consider each batch of packet transmissions as a busy period, and the attempt process between two successive busy periods as a vacation period. We derive the delay distribution, which is turned out to be a geometric distribution. From this result, we further obtain the mean delay, the delay jitter, and the bounded delay region. Our analysis shows that increasing M can accelerate the clean-up of the buffer in each node and thus decrease the attempt rate, which can reduce the average time needed by a node to make a successful attempt. As a result, a large M can decrease the mean delay and the delay jitter, and enlarge the bounded delay region. Also, we obtain the condition to achieve the minimum mean delay under different values of M .

The time- and space-varying nature of residual bandwidth in inter-datacenter networks (inter-DCNs) makes conventional end-to-end connections difficult to fully utilize the residual bandwidth. A promising solution is to introduce datacenter storage into data-plane paths. Delay-tolerant bulk data can be temporarily stored at intermediate sites and forwarded (SnF) at a later time when inter-DCN is less congested. However, the conventional methods attempt to involve multi-dimensional state information of the entire network in scheduling, which results in high computational complexity. In this paper, our studies reveal that there exist redundant states in scheduling, which cannot provide any performance benefit while imposing extra computational burden. Inspired by this finding, we propose a state-merging scheduling (SMS) method. By merging the state information of the pre-selected links, the SMS method naturally reduces the redundant states involved, which greatly improves the efficiency of SnF scheduling. Simulations demonstrate that the SMS method can outperform the conventional scheduling method, given a limit of the computational cost.

BACKGROUND: The human leukocyte antigen (HLA) gene family plays a key role in the immune response and thus is crucial in many biomedical and clinical settings. Utilizing Sanger sequencing, the golden standard technology for HLA typing enables accurate identification of HLA alleles in high-resolution. However, only the commercial software, such as uTYPE, SBT-Assign, and SBTEngine, and very few open-source tools could be applied to perform HLA typing based on Sanger sequencing. RESULTS: We developed a user-friendly, cross-platform and open-source desktop application, known as SOAPTyping, for Sanger-based typing in HLA class I and II alleles. SOAPTyping can produce accurate results with a comprehensible protocol and featured functions. Moreover, SOAPTyping supports a more advanced group-specific sequencing primers (GSSP) module to solve the ambiguous typing results. We used SOAPTyping to analyze 36 samples with known HLA typing from the University of California Los Angeles (UCLA) International HLA DNA Exchange platform and 100 anonymous clinical samples, and the HLA typing results from SOAPTyping are identical to the golden results and 5.5 times faster than commercial software uTYPE, which shows the usability of SOAPTyping. CONCLUSIONS: We introduce the SOAPTyping as the first open-source and cross-platform HLA typing software with the capability of producing high-resolution HLA typing predictions from Sanger sequence data.

Existing data center networks (DCNs) based on only electronic packet or all-optical switching still pose an exponential increase in power consumption and cost due to the current high demand for digital data and sustainability issues. The recent development of hybrid DCN prototypes is a promising solution offering relatively higher data throughput, low latency, reduction in cost and energy consumption. This paper explores the frontier of hybrid DCN with a special focus on energy consumption and cost. We evaluate the energy consumption per bit and the greenhouse gas (GHG) emission per year of three hybrid switching systems as compared with an optical point to point (ptp) network, results show that the hybrid switching systems will consume less energy per bit and are likely to emit less GHG annually. We present feasibility analysis on the energy consumption and cost of some hybrid DCN prototypes. Evaluation results show that Helios-like and Hybrid Optical Switching-like prototypes achieve a power usage effectiveness (PUE) value lower than 1.2, an index which represents a very efficient level of energy performance in a data center network.

Increasingly bulk data transfers impose an unprecedented challenge on inter-datacenter (DC) wide area networks (WANs). To overcome this challenge, DC storage is exploited and introduced into the data-plane path so that delay-tolerant bulk data can be temporarily stored and forwarded (SnF) at a later time when network is less congested. However, the use of storage introduces additional complexity into the transfer process. In this paper, we evaluate the computational complexity of the SNF scheduling problem. Studies show that desirable performance can be attained by considering only a few alternate routes rather than dynamically routing over the entire network topology. Inspired by this finding, we propose a time-space decoupled (TSD) SNF scheduling method. By decoupling the problem into its spatial and temporal components and solving these components separately, the TSD method obtains good performance while maintaining low complexity. Simulations show that the TSD method can outperform the conventional joint method when the traffic load is medium or higher.

Rapid growth of traffic leads to bottlenecks on inter-domain links, and the residual bandwidth on such links exhibits temporal and spatial variations. There may not be sufficient bandwidth for end-to-end cross domain transmission upon the arrival of bulk data requests. Storage can be introduced into the forwarding path so that the delay tolerant data can be temporarily stored and forwarded when network links become less congested. In this paper, we study the Store-and-Forward (SnF) problem in a multi-domain environment. We present a routing scheme based on a framework named TS-MLG (time-shifted multilayer graph) to perform inter-domain bulk data transfer by taking both spatial and temporal aspects into consideration. With this scheme, the cross-domain routing path, as well as the storage points and the time of transmission, can be determined through conventional routing computations. An updating strategy is proposed to realize temporal bandwidth information exchange between physical and logical layers. Numerical simulations reveal that SnF can improve the inter-domain bandwidth utilization and optimize the network performance at the practical cost of network states maintenance overhead and computational complexity. Since the multi-domain routing is sensitive to the burden of the control plane, we also studied factors that affect computational complexity.

WAN provider links are often operated at low utilization levels, which leaves large unused capacity (headroom). In this paper, we propose using Software Defined Networking (SDN) controllers to support novel Static Headroom (SH) and Dynamic Headroom (DH) services to allow customers to fill this headroom with Elephant Flows (EFs) without adversely affecting the provider's ability to meet its Best-Effort (BE) service-level agreements, and ability to absorb extra traffic load created during failure recovery periods. Our solution calls for the use of lower-priority service for EFs. We use simulations to compare SH service with BE service, and DH service with SH service. When EFs are sent on BE service, they could cause packet losses in general-purpose IP traffic, especially when the burstiness of the latter is high, while with SH service, this packet loss rate is reduced to 0. While DH service requires the added complexity of a provider SDN controller, the ability to dynamically route EFs on lower-utilized links results in higher average EF throughput. The higher the non-uniformity (from a node-pair perspective) in network traffic, the greater the DH gain factor.

Increasing bulk data transfers have been overwhelming the Internet. To overcome this, optical circuit-switched (OCS) networks are equipped with assistive storage, so that bulk data that are delay tolerant can be temporarily stored at intermediate nodes and forwarded at later times. But, the use of storage greatly complicates the routing problem, since data storage must be incorporated into routing. This motivates us to simplify this issue by applying slotted operations for the network. Intuitively, the slotted network suffers from degraded network performance due to the inefficient utilization incurred by the slot constraint. However, our simulation shows that when the slot size equals to half the mean duration, the blocking probability is reduced from 0.076 to 8.5×10-5, and the number of network reconfigurations is reduced by a factor of 5, compared to the unslotted case. We reveal that in spite of the inefficient utilization, the slotted operations mitigate bandwidth fragmentation. This suggests in the slotted case, more bandwidth gaps on the links are available for accommodating other requests, and they are aligned with each other in time. Requests hence are delivered with less store-and-forward (SnF) operations being performed. Thus, when the number of SnF allowed for routing each request is limited (in order to reduce the computational complexity of routing), requests are more easily served in the slotted than in the unslotted cases. Our research provides clue for designing scalable slotted OCS networks with assistive storage.

5G backhaul requires high bandwidth and hybrid Radio Frequency/ Free Space Optical (RF/FSO) Communication offers Gbps links. The weather affects availability of both mmW RF and FSO links. Below cloud ceiling, the availability of hybrid RF/FSO link is above 85.7% and it can only be used for deadline-constrained large data transfers. At 17-22km above ground, the bit error rate of FSO links reaches below 10-3and it can be used for delay-sensitive packet transfers. In this work, first, we propose a method to determine the required number of wavelengths and storage size for large data transfers and second, we propose a distributed implementation of automatic repeat request protocol to support 10Gbps bandwidth and millisecond delay for delay-sensitive packet transfers. The simulation results show the following: With link availability of 0.85, blocking rate of 0.05 can be achieved for large data transfers, which indicates 0.05 of the cost of transferring data over 5G dmW spectrum is necessary to guarantee deadline. The distributed implementation of automatic repeat request has similar performance with selective repeat. Both theoretical and simulation results show if load exceeds 0.9 of maximum load allowed by packet error probability, delay increases about 20% drastically.

For large data transfers, the Store-and-Transfer WDM Network (STWN) provides storage and lightpaths jointly. Constrained delays of the transfers restrict the number of waiting requests, thus the storage size can be limited. For dimensioning of STWN, we propose a method to determine the number of wavelengths and storage size required to satisfy the demand. The demand is given as a load matrix with a common deadline and blocking, then we express the load matrix as a base load multiplying an integer matrix consisting of mutually prime elements. The dimensioning process has two steps. 1) We model STWN as TDM network and analyse channels of the TDM system as M/G/1 subsystems. We calculate approximate performance of source-destination pairs and minimize the service rate provisioned for the demand with linear search to find the maximum allowed number of time-slots. 2) With the number of time-slots fixed, we optimize routing and wavelength and time-slot assignment to minimize the number of wavelengths required to accept the integer matrix. In step 1, the approximate performance calculated includes turnout, distribution of delay and storage size. Numerical results show how to drastically decrease the required resources.

In this paper, we propose a mathematical model for calculating the steady state performance of congested networks with large number of TCP flows. Marking probability, average queue length, bandwidth and RTT are connected by a group of nonlinear equations. We transform these equations into a constrained optimization problem, which is then solved by SQP algorithm, a robust method for the optimization with inequality constraints. Numerical results with Matlab and simulation results with NS-2 are given to validate the accuracy of the model and algorithm. We study the relationship between the calculation time and congestion network parameters, and provide a good estimation of calculation time at different network scale. It is helpful for network pricing system.

In Ethernet Passive Optical Networks (EPONs) with offline Dynamic Bandwidth Allocation (DBA) framework, the Optical Line Terminal (OLT) will first collect bandwidth requests from all Optical Network Units (ONUs), and then make bandwidth allocation and scheduling decisions for the shared upstream channel. Due to varying Round-Trip Time (RTT) and grant window sizes, the transmission order of ONUs will greatly affect the mean packet delay. In this paper, we address this grant scheduling problem aiming at minimizing the mean packet delay. We prove several theorems which could determine the ONU to transmit first which will minimize the mean packet delay. And then, by iteratively using these theorems, we propose an Integrated Grant Scheduling (IGS) algorithm to determine the optimal transmission order to minimize the mean packet delay. We then conduct simulations to evaluate the performance of our algorithm, and find that the performance of our algorithm is better compared with other algorithms under various conditions.

Bulk data transfers, which require reliable and efficient transfer of terabits or even petabits of data for data-intensive applications, have been extensively studied. In these applications, usually, a specified amount of data needs to be transferred within strict deadline. Previous researches mainly focus on routing deadline-constrained bulk data transfers to improve the utilization of network resources for guarantying deadline requirements, without considering network failures. This paper proposes novel routing algorithm for deadline-constrained bulk data transfers based on Transfer Failure Probability using continuous-time Markov model. The goal of the novel algorithm is to guarantee the deadline requirement by decreasing the failure probability of data transfer request under network failure settings. Simulation evaluates the performance and demonstrates the effectiveness of our algorithm in terms of deadline violation ratio and service blocking ratio under network failures.

Multi-channel delivery is one competitive solution to reduce channel change time in IPTV. We presented the performance analysis on finite duration multi-channel delivery method in our previous work, when channel changes are sequential and adjacent. In this paper, we develop mathematical models to evaluate the performance of this method when channel change happens randomly. This in fact generalizes the previous model. We find that, in typical setup, a delivery duration of 20 seconds is enough to reduce the channel change time by 47.5%, yet the peak bandwidth increase on carrier's uplink is 66.7%. This indicates that the finite duration multi-channel delivery method can improve viewers' experience effectively when channel changes are random.

In this paper, we study the efficiency of inter-domain state advertising in multi-domain networks, in which the intra-domain topology is substituted with a full-mesh topology of abstract links interconnecting the border nodes of the domain. The advertising trigger rate of individual abstract link is taken as the metric of efficiency. We present an analytical model that reveals the contributions of different physical links to the advertising trigger rate of individual abstract links. According to the model, we propose a state based advertising mechanism, called partial link based advertising (PLA) which can discern and advertise the state variation of individual abstract link by monitoring only a portion of physical links. We formulate the problem of how to optimally selecting physical links to monitor, and provide a heuristic algorithm for link selection. Results show that the PLA performs more efficiently than existing mechanisms in terms of advertising trigger rate and blocking probability.

The optical network based distributed computing system has been thought as a promising technology to support large-scale data-intensive distributed applications. For such a system with so many heterogeneous resources and middlewares involved, faults seem to be inevitable. However, for those applications that need to be finished before the given deadline, a fault in the system will lead to the failure of the application. Therefore, fault-tolerant policy is necessary to improve the performance of the system when faults could happen. In this paper, we address to the fault-tolerant problem for the optical network based distributed computing system. We first propose an overlay approach which applies the existing fault-tolerant policies for distributed computing and optical network. Then we present a joint fault-tolerant policy which takes into account the fault tolerance for computing resource and network resource in the same time. We compare the performances of different polices by simulation. The simulation results show that the joint fault-tolerant policy achieves much better performances compared to overlay approaches.

In this paper, we investigated designing multicast-capable optical cross-connects (MC-OXCs) on a basis of the 4- stage multicast network. Firstly, we derive the sufficient wide- sense nonblocking (WSNB) and rearrangeable nonblocking (RNB) conditions for the 4-stage multicast network with only two (the second and output) stages being multicast-capable. Both WSNB and RNB 4-stage multicast networks need 0(N3/2) crosspoints. Then MC-OXCs empoying the WSNB and RNB 4-stage multicast network are proposed and proven to be power efficient in reducing the total power loss caused by light splitting.

It is widely believed that IP over optical networks will be a major component of the next generation Internet However, it is not efficient to map a single multicast IP flow into one light-tree, since the bandwidth of an IP flow required is usually much less than that of a light-tree. In this paper, we study the problem of multicast flow aggregation (MFA) in the IP over optical two-layered networks under the overlay model, which can be defined as follows: given a set of head ends (i.e. optical multicasting sources), each of which can provide a set of contents (i.e. multicast IP flows) with different required transmission bandwidth, and a set of requested content at the access routers (i.e. optical multicasting destinations), find a set of light-trees as well as the optimal aggregation of multicast IP flows in each light-tree. We model MFA by a tri-partite graph with multiple criteria and show that the problem is NP-complete. Optimal solutions are designed by exploiting MFA to formulate an integer linear programming (ILP), with two parameters: the multicast receiving index alpha and the redundant transmitting index beta. We also propose a heuristic algorithm. Finally, we compare the performance of MFA for different combination of alpha and beta via experiments and show our heuristic algorithm is effective for large-scale network in numerical results

To support large-scale IP-TV signal delivering, a new multicast-IP over light-tree network model was proposed in W. Sun et al. In this paper, we study the problem of topology-independent IP group aggregation in the multicast capable optical network. We first use a tri-partite graph to describe the problem, and then formulate the problem by a mixed integer linear programming (MILP) model. Finally, we propose a pre-estimation for the number of light-trees to reduce the searching space, which significantly saves solving time of MILP