In hierarchical federated learning, client selection is typically performed at edge servers and the central server. Edge servers perform intermediate model aggregation before transmitting updates to the central server, which aggregates the local models’ parameters. One of the challenges in federated learning is coping with the heterogeneity of clients’ resources and datasets, which can lead to slow global model convergence and poor performance. This paper introduces a client selection algorithm to address heterogeneity and scalability challenges in hierarchical scenarios. Our algorithm ranks client clusters based on a scoring function that incorporates resource availability, communication quality, and data-related attributes. Then, clients are selected from the top-ranked cluster. The proposed method is formulated as a combinatorial optimization problem and evaluated via emulation using the MNIST and CIFAR-10 datasets under heterogeneous scenarios. Experimental results show that, compared to existing clustering-based baselines, our method reduces CPU utilization by up to 42%, memory usage by 58%, and energy consumption by 48%. These improvements are obtained with negligible loss in model accuracy on MNIST and a slightly higher reduction in accuracy on CIFAR-10, consistent with its higher task complexity.

Hierarchical federated learning (HFL) improves scalability and communication efficiency through intermediate edge servers, yet energy and network constraints remain critical in heterogeneous settings. We propose two energy-aware client-selection methods: HEPS-ML, a supervised approach enabling autonomous participation based on energy, resources, performance, and data features; and HEPS-SCA, which leverages the sine cosine algorithm to balance accuracy, energy, and latency. Edge-server selection is handled by a central MAB using historical and network information. Evaluations on CIFAR-10 and MNIST, including calibrated energy modeling and ablation of MAB-based server selection, show 65–80% energy savings over baselines while preserving accuracy under non-IID distributions.

This paper addresses the optimal placement of Multi-Access Edge Computing (MEC) nodes in 5G networks, aiming to meet stringent performance requirements while minimizing cost. It explores the impact of various Virtual Network Function (VNF) distribution strategies on overall network cost, specifically examining the 1:1, 1:N, and 1:N:K protection schemes. To tackle the MEC location problem, bi-objective nonlinear mathematical models are employed for exact solutions in small-scale networks, while the Non-dominated Sorting Genetic Algorithm II (NSGA-II) is applied for larger networks. The results reveal that VNF distribution can significantly escalate network costs, with fully distributed VNFs incurring the highest expenses. However, the enhanced protection scheme demonstrates improved cost-efficiency. These findings highlight the critical role of strategic MEC placement and intelligent resource allocation in building scalable, resilient, cost-effective 5G infrastructures.

Driven by emerging distributed computing and cloud-edge collaborative applications, metro and regional networks have experienced continuous surges in hub-and-spoke (H&S) traffic, posing great challenges to existing point-to-point network infrastructures. While coherent point-to-multipoint optical transceivers (P2MP-TRXs) present a more cost-effective solution for accommodating H&S traffic, existing P2MP networking paradigms fail to address the dynamic and asymmetric nature of traffic prevalent in such networks, and consequently, could lead to subpar resource utilization. In this paper, we fill this gap by investigating dynamic asymmetric subcarrier allocation and reconfiguration in drop-and-continue (D&C) optical networks. In particular, our approach aims at minimizing the operational cost of service provisioning by invoking reactive and coordinated connection consolidation as a remedy for the inability to accommodate traffic demands with in-service or newly activated P2MP-TRXs. We first devise an integer linear programming (ILP) model to solve the multi-objective optimization problem exactly. As the problem is proved to beNP-hard, we further develop a column generation (CG)-based approximation algorithm that can offer guaranteed optimality bounds within reasonable time, as well as a polynomial-time heuristic framework employing priority-queue-based progressive search. Extensive simulations verify the effectiveness of our proposal, demonstrating up to 43.3% reduction in bandwidth blocking ratio and 2.9% improvement in spectrum utilization compared with the state of the art.

Detecting sedentary behavior has increasing attention due to its significant health implications. However, distinguishing these low-intensity activities in federated learning scenarios is notably more complex than general human activity recognition. This complexity comes from heterogeneous feature distributions that can arise even for the same labeled activity, e.g., running and playing soccer, which may exhibit different sensor patterns despite both representing high-intensity activities. This paper proposes a robust personalized federated learning approach for sedentary behavior classification under adversarial conditions. Our method leverages ordinal pattern descriptors to extract meaningful symbolic representations from wearable sensor time series, then applies a meta-learning framework with Siamese Neural Networks to rapidly adapt across clients. Next, a reputation mechanism further safeguards the global model by penalizing malicious updates. Experiments on multiple public datasets show that our method achieves high F1-scores compared to baselines, affirming its ability to maintain robust performance in privacy-sensitive and adversarial environments.

Optimal code-expanded random access (OptCeRA) is a promising random access (RA) technique for supporting massive Internet of Things (MIoT) in mobile networks. It allows devices to employ, as contention resources, codewords formed by the transmission of preambles in consecutive RA slots and selected from a maximum average distance code. This paper introduces the adaptive version of the OptCeRA scheme to cope with substantial random access channel (RACH) demands, which is particularly relevant for supporting MIoT scenarios in such networks. A practical algorithm to dynamically adjust the OptCeRA scheme parameters to the RA channel load based on optimizing the RA success probability is proposed. Numerical results show that the proposal significantly increases the capacity of the networks in terms of the number of simultaneous random access attempts compared to the state-of-the-art RA schemes.

The support of Mobile Fronthaul (MFH) over Passive Optical Networks (PONs) poses significant challenges due to the stringent latency and bandwidth requirements of Functional Splitting (FS). This paper addresses the problem of Quality of Service (QoS) provisioning in next-generation Ethernet PON (NG-EPON) for the transport of traffic generated by multiple different FS options. We propose a PON bandwidth allocation algorithm that distributes the resources for the Optical Network Units (ONUs) serving Functional Split (FS) options based on their bandwidth and latency requirements in networks with customers renting/owning more than one ONU (multi-ONU customers). Simulation results show that our proposal significantly improves network resource utilization for multi-ONU customers, meeting the latency requirements of the different FS options while reducing the required bandwidth.

This paper introduces a novel hierarchical federated learning model, Sedentary-SMELL, for classifying sedentary behavior using wearable device data. Our methodology involves transforming sensor data into Ordinal Patterns (OP) for efficient representation, training a federated autoencoder to capture standard features, and clustering users based on similar activity patterns. We employ meta-learning within clusters for enhanced pattern comparison and conclude with personalized model finetuning, adapting to individual user variations for accurate sedentary detection. Extensive testing on various datasets, including BaSA and Har UML 20, demonstrates the model’s superiority over traditional personalized methods, achieving remarkable F1scores of 0.9958 and 0.9124, respectively. Integrating a personalizing step further refines the model, tailoring it to individual user characteristics while retaining the core structure learned from meta-learning, surpassing the median performance of centralized models across all datasets.

Characterizing and monitoring patient activities through time series data is critical for identifying lifestyle patterns that may impact health outcomes. Sedentary behavior is a significant concern due to its association with various health risks. This study introduces a lightweight supervised classifier for healthcare applications based on ordinal pattern (OP) transformation to detect sedentary behavior in federated learning (FL) scenarios. Our hypothesis is grounded on the idea that sedentary behavior exhibits distinct dynamics compared to other activities, and information descriptors derived from the transformation of OPs effectively capture these differences. Next, we proceed with the FL training. We train a neural network (NN)-based encoder locally and send the local models to a server. The FL process updates the encoder weights based on the encoded representations of the clients’ data, enabling the model to learn from different participants. Finally, we personalize the model for the specific task of classifying sedentary behavior. Our approach utilizes a meta-learning framework, incorporating a Siamese NN to learn a similarity space. We fine-tune the model in this step by further training the last NN layer. This fine-tuning allows the model to adapt and specialize in accurately classifying sedentary behavior. We carry out a comprehensive analysis to support our hypothesis. We also extensively validated our proposal by comparing it with other methods over five different data sets. We obtain the best results using a smaller machine learning model compared with the best approaches in the literature. Specifically, our model has 78.73% times fewer parameters and consumes 48.67% times less energy than the best result in the literature.

Federated Learning is a promising technique for providing distributed learning without clients disclosing their private data. In Hierarchical Federated Learning, edge servers partially aggregate the parameters of their connected clients’ models, improving scalability and reducing computational overhead on the central server. To speed up the convergence of the global model, only those clients with potential contributions to the model performance will participate in model training. This paper introduces a two-step client selection approach for hierarchical federated learning and three novel algorithms, which consider a large set of features in this selection and the client’s contributions to the model performance. Compared to selected baseline algorithms, the proposed client selection algorithms reduce CPU utilization by more than 50%, memory usage by 80%, and energy consumption by 50%.

Accurate modeling of realistic network topologies is essential for evaluating novel Internet solutions. Numerous investigations have used topologies generated by graph generators employing scale-free-based models. Although scale-free networks accurately encode node degree distribution, they overlook crucial graph properties, such as betweenness, clustering, and assortativity. The limitations of existing generators pose challenges for evaluating network mechanisms and protocols, such as routing. This paper introduces a novel deep learning-based generator of synthetic graphs representing intra-autonomous on the Internet, named Deep-Generative Graphs for the Internet (DGGI). It also presents a massive new dataset of real intra-AS graphs extracted from the project Internet Topology Data Kit (ITDK), called Internet Graphs (IGraphs). DGGI creates synthetic graphs that accurately reproduce the properties of centrality, clustering, assortativity, and node degree. DGGI overperforms existing Internet topology generators. On average, DGGI improves the Maximum Mean Discrepancy (MMD) metric by 84.4%, 95.1%, 97.9%, and 94.7% for assortativity, betweenness, clustering, and node degree, respectively.

Data plane programmable (PDP) switches are becoming increasingly popular for network function virtualization (NFV), for their programmability and high packet processing performance. However, the inherent limitations of PDP switches, such as limited memory space, make it challenging to implement certain types of network functions (NFs) (i.e., the stateful ones) on them. This paper proposes SFCache, which combines PDP switches and commodity servers to achieve self-adaptive SFC deployment. SFCache aims to exploit the high packet processing performance of PDP switches while supporting the flexible deployment of a wide range of SFCs (including the stateful ones) with servers. Specifically, SFCache can dynamically improve the packet processing performance of the SFCs that were deployed on servers by selectively caching SFC-level packet processing rules on PDP switches. We design a few key components to facilitate SFCache, including an NF-destructed P4 pipeline that allows customizing packet processing rules in a match-rewrite pattern, a runtime NF synthesis method that can transform a set of NF-level match-rewrite rules into an equivalent SFC-level rule, and a count-min selection strategy to choose the best synthesized rule for being cached in PDP switch pipeline. We prototype SFCache with a PDP switch based on Tofino ASIC and a server, and demonstrate the effectiveness of our proposal experimentally.

Self-adaptation of service function chains (SFCs) has been considered as an important attribute to ensure the resource-efficiency and reliability of network function virtualization (NFV) systems. In this work, we leverage the idea of integrating segment routing over IPv6 (SRv6) and in-band network telemetry (INT) seamlessly to realize SRv6-INT and explore the mutual benefits of SRv6 and INT for achieving self-adaptive SFC deployment. Specifically, we design and experimentally demonstrate a self-adaptive SRv6-INT-driven SFC deployment system that orchestrates network and IT resources timely to adapt to bursty traffic and network changes. We first enhance our previous design of SRv6-INT to better use it for self-adaptive SFC deployment, and then propose an IT resource management technique for Kubernetes (K8s) to accomplish resource allocation and contention resolution without offline virtual network function (vNF) profiling. Next, a closed-loop system is designed to manage SFCs in both the local and global ways. As for the local way, we let servers make local decisions based on the INT data encoded in packets to scale the vNFs running on them vertically. The global way involves the control plane, which oversees the SFC deployment in the whole network to change the number and placement of vNFs and the traffic routing through them. Finally, we prototype our proposal with commodity servers and hardware PDP switches based on Tofino ASICs, and experimentally demonstrate its effectiveness.

Fog nodes usually belong to fixed infrastructures that, once deployed, cannot be easily moved. Despite the easy management of these infrastructures, they are limited in dealing with variations in the demand of mobile users. To cope with that, fog nodes can be mounted on unmanned aerial vehicles (UAVs), which can be quickly deployed, staying close to those users requiring low latency services. The location and period of operation of UAVs must be determined to maximize the number of requests processed and reduce the latency in accessing the infrastructure. This paper proposes a solution to the fog node location problem with rotary-wing UAVs that considers variable demands. We have modeled the problem with an integer linear programming formulation and have proposed the Sequential UAV Fog Node Location algorithm to deal with large scenarios. The results derived using real traces show that low delay applications can be supported. It is, however, essential to plan the deployment of UAVs so that the operational time of battery-constrained UAVs can be extended.

On behalf of the Organizing Committee, we have been delighted to welcome you to the IEEE Global Telecommunications Conference (GLOBECOM 2022). The conference was held in Rio de Janeiro, Brazil from 4 to 8 December 2022. IEEE GLOBECOM is one of the two flagship conferences of the IEEE Communications Society (IEEE ComSoc). It is a premium event that brings together the best researchers and professionals from academic, industry and government to exchange novel ideas that will shape future generations of communication technologies. IEEE Globecom 2022 featured striking advances in communications research and industry development, which will certainly lead to new systems and networks and bring humanity to a new World, still unimaginable. The theme of Globecom 2022 “Accelerating the Digital Transformation through Smart Communications” reflects the fundamental role of intelligent communications in enabling dynamically adaptive societal systems.

In this paper, we propose three multi-objective task scheduling algorithms for the cloud-fog continuum, that minimize both the makes pan and processing cost of workflows, considering the QoS requirements of the applications. Numerical results show that the scheduler based on Reinforcement Learning outperforms those based on classical optimization.

This paper introduces a batch grooming algorithm for establishing connections with different deadlines to be torn down for Elastic Optical Networks with Space-Division Multiplexing (EON-SDM). The proposed algorithm creates batches of requests for lightpath establishment and postpones their establishment to groom the highest possible number of lightpaths. Each batch comprises a set of requests that can be allocated as a single request without guard bands separating their lightpaths and using only one transponder per batch, which leads to higher spectrum efficiency and lower energy consumption. Results show that the algorithm produces lower blocking and higher energy efficiency than the existing algorithms.

Traditional routing protocols employ limited information to make routing decisions, which leads to slow adaptation to traffic variability and restricted support to the quality of service requirements of applications. To address these shortcomings, in previous work, we proposed RSIR, a routing solution based on Reinforcement Learning (RL) in Software-Defined Networking (SDN). However, RL-based solutions usually suffer an increase in time during the learning process when dealing with large action and state spaces. This paper introduces a different routing approach, called Deep Reinforcement Learning and Software-Defined Networking Intelligent Routing (DRSIR). DRSIR defines a routing algorithm based on Deep RL (DRL) in SDN that overcomes the limitations of RL-based solutions. DRSIR considers path-state metrics to produce proactive, efficient, and intelligent routing that adapts to dynamic traffic changes. DRSIR was evaluated by emulation using real and synthetic traffic matrices. The results show that this solution outperforms the routing algorithms based on Dijkstra’s algorithm and RSIR in relation to stretch, packet loss, and delay. Moreover, the results obtained demonstrate that DRSIR provides a practical and feasible solution for routing in SDN.

With the advent of 5G networks, telecommunications infrastructure providers (InP) have faced numerous challenges as they attempt to meet the stringent quality of service requirements. The placement of applications at the edge of the mobile network in Multi-access Edge Computing (MEC) and slicing techniques have provided powerful tools to enable networks to support these requirements. This paper studies the problem of locating MECs and slices in a 5G infrastructure protected by a 1:${N}$:${K}$protection scheme. The aim is to support high reliability and low latency requirements at a minimum cost. A bi-objective non-linear formulation is proposed, and a solution is derived by employing the non-dominated sorting genetic algorithm (NSGA)-II. Results show that the enhanced 1:${N}$:${K}$scheme is cost-effective. The proposal is evaluated on the basis of various levels of reliability, latency requirements, and probability of failure.

As a promising technology, Flex Ethernet (FlexE) helps to realize deterministic and ultra-low latency in metro and transport networks. Meanwhile, previous studies have confirmed the advantages of the symbiosis of FlexE and elastic optical network (EON) (i.e., a FlexE-over-EON) on resource utilization and cost-effectiveness. In this paper, we consider the cross-layer restoration (CLR) in FlexE-over-EONs based on the FlexE-aware architecture. Specifically, we address the situation where an outage happened on one FlexE switch in the packet layer to bring it offline temporarily and then the affected client flows need to be recovered quickly and proactively. Three CLR strategies are first proposed to fully explore the flexibility of FlexE-over-EON for restoring the affected flows. Then, with the strategies, we formulate an integer linear programming (ILP) model and design an auxiliary graph (AG) based algorithm to reroute the affected flows as well as minimize the additional operational expense (OPEX) incurred during the CLR. Extensive simulations verify the effectiveness of our proposed CLR algorithms.

The demographic growth in cities has increased carbon dioxide (CO2) emissions, a significant problem that challenges societies worldwide. The CO2 emission raises the pollution levels causing health risks for the people and contributes to climate change. Moreover, the transportation sector is responsible for 20.6% of CO2 emissions. Thus, it is necessary to reduce vehicle fuel consumption to minimize CO2 emissions. This paper proposes a system based on artificial intelligence techniques: a fuzzy controller and a neural network to find the instantaneous speed, which reduces vehicle fuel consumption. The proposed system employs only vehicle and highway information, which means communication between vehicles is not required. The simulation scenario comprises a loaded truck traveling through a highway with slopes based on a data set. Results derived from simulation show that both techniques produce a lower fuel consumption than the standard Simulation of Urban MObility (SUMO) algorithm.

Traditional routing protocols employ limited information to make routing decisions, which can lead to a slow adaptation to traffic variability, as well as restricted support to the Quality of Service (QoS) requirements of applications. This article introduces a novel approach for routing in Software-defined networking (SDN), called Reinforcement Learning and Software-Defined Networking Intelligent Routing (RSIR). RSIR adds a Knowledge Plane to SDN and defines a routing algorithm based on Reinforcement Learning (RL) that takes into account link-state information to make routing decisions. This algorithm capitalizes on the interaction with the environment, the intelligence provided by RL and the global view and control of the network furnished by SDN, to compute and install, in advance, optimal routes in the forwarding devices. RSIR was extensively evaluated by emulation using real traffic matrices. Results show RSIR outperforms the Dijkstra's algorithm in relation to the stretch, link throughput, packet loss, and delay when available bandwidth, delay, and loss are considered individually or jointly for the computation of optimal paths. The results demonstrate that RSIR is an attractive solution for intelligent routing in SDN.

Although network function virtualization (NFV) has been proven to be beneficial in terms of equipment cost, service delivery flexibility, and time-to-market, most of the studies in this area only addressed homogeneous NFV platforms (e.g., with virtual machines (VMs) only). In this work, we argue that by leveraging heterogeneous NFV platforms such as VMs, docker containers, and programmable hardware accelerators (e.g., SmartNICs), one could achieve better flexibility and cost-effectiveness to support virtual network function service chains (vNF-SCs) with various quality-of-service (QoS) requirements. Therefore, we study application-driven provisioning of vNF-SCs over heterogeneous NFV platforms, and design a polynomial-time approximation algorithm to tackle the problem for near-optimal solutions. We first introduce a layered auxiliary graph (LAG) based approach to model the problem of vNF-SC provisioning, and then formulate a novel integer linear programming (ILP) model based on it. Specifically, the ILP model minimizes the total cost of vNF-SC deployment while ensuring that the QoS requirements of all the vNF-SCs are satisfied. To solve the ILP time-efficiently, we propose an approximation algorithm based on linear programming (LP) relaxation and randomized rounding. Extensive simulations confirm that with significantly improved time-efficiency, our proposed algorithm can provide near-optimal solutions whose gaps to the exact ones are bounded.

This article studies the cross-layer network planning that tries to combine flexible Ethernet (FlexE) and elastic optical networks (EONs), for FlexE-over-EONs. We focus our investigation on the most challenging setting, i.e., the FlexE-over-EONs based on the FlexE-aware architecture, and consider both single-hop and multi-hop scenarios for the cross-layer planning. For the single-hop scenario, we assume that all the client flows are routed over end-to-end lightpaths in the EON. We formulate a mixed integer linear programming (MILP) model for this problem, transform it into the class constrained bin packing problem (CCBP), and leverage the primal-dual interior-point (PDIP) method to propose a polynomial-time approximation algorithm for it. Then, for the multi-hop scenario, we use a more realistic assumption that each client flow can be routed over multiple lightpaths in the EON. We show that after solving the virtual topology design, the cross-layer planning in this scenario can be transformed into that in the single-hop scenario. Therefore, an integer linear programming (ILP) model is formulated to tackle the virtual topology design, and we design a polynomial-time approximation algorithm for it by modifying the well-known branch-and-bond method. To evaluate the performance of our two-step method for the multi-hop scenario, we also propose a heuristic algorithm. Extensive simulations verify that regarding large-scale cross-layer planning for FlexE-over-EONs, our approximation algorithms are significantly more time-efficient than the ILP/MILP models, and their solutions have bounded gaps to the optimal ones and are much better than those of the heuristic.

Infrastructure service providers (InPs) can employ bandwidth sharing to offer new services and business models to their customers. In this paper, we introduce a dynamic bandwidth allocation (DBA) algorithm which allows cooperation among Ethernet PON (EPON) customers so that they can share unused bandwidth among themselves without affecting their guaranteed bandwidth. Simulation results show that our proposal increases the throughput and decreases the delay for cooperative customers.

In Elastic Optical Networks with Space-Division Multiplexing (EON-SDM), dynamic allocation and deallocation of the spectrum can cause spectrum fragmentation. A possible solution is the use of proactive techniques to reduce the occurrence of fragmentation. In this paper, we propose a proactive algorithm for EON-SDM networks using Multi-Core Fibers (MCFs), which employs a core prioritization and quadrant ordering to allocate requests. Results show that our algorithm can effectively reduce the blocking of requests for connection establishment.

The support of stringent requirements such as ultra-low latency and ultra-reliability of the forthcoming 5G services poses several challenges to telecommunications infrastructure providers. Network Function Virtualization, multi-access edge computing (MEC), and network slicing capabilities can help the support of such requirements. However, a trade-off between the cost of resource deployment and the support of service requirements needs to be taken into account in the design of NFV-based 5G networks. In this paper, we investigate the MEC location problem, which aims at selecting locations to place MECs hosting protected slices. We propose a MEC location problem enhanced with 1: 1 and 1:Nprotection schemes for the provisioning of protected slices. In the 1: 1 scheme, protection is assured by reserving a backup slice for each tenant, whereas in the 1:Nscheme, a backup slice is shared amongNtenants. The problem is modeled as a multi-criteria optimization problem and solved by the employment of a multi-objective evolutionary non-dominated sorting genetic algorithm. A comparison between the 1: 1 and 1:Nprotection schemes is carried out in the context of 5G network slicing. Results show that the protection scheme 1: 1 can reduce the response time, at a higher deployment cost when compared to the 1:Nscheme.

The processing of big data generated by the Industrial Internet of Things (IIoT) calls for the support of processing at the edge of the network, as well as at the cloud data centers. The equal-cost multipath, which is the default routing technique in the cloud data centers, can degrade the network performance when handling mouse and elephant flows. Such degradation of performance can compromise the support of the strict quality of service requirements of the IIoT over 5G networks. Novel techniques for scheduling the elephant flows can alleviate this problem. Recently, several approaches have incorporated machine learning techniques at the controller-side in software-defined data center networks (SDDCNs) to detect elephant flows. However, these approaches can produce heavy traffic overhead, low scalability, low accuracy, and high detection time. This article introduces the Network Elephants Learner and anaLYzer (NELLY), a novel and efficient method for applying incremental learning at the server side of SDDCNs to accurately and timely identify elephant flows with low traffic overhead. Incremental learning enables NELLY to adapt to varying network traffic conditions and perform continuous learning with limited memory resources. NELLY has been extensively evaluated using real traces and various incremental learning algorithms. Results show that NELLY is accurate and supports low classification time when using adaptive decision trees algorithms.

Fog computing brings the advantages and power of cloud computing to the edge of the network. Software-Defined Networking (SDN) has been considered as a feasible solution to cope with the complexity of the orchestration of fog devices. Nevertheless, the use of an SDN controller introduces delays into the transport of packet flows in the fog layer, which may impact on the Quality of Service (QoS) of applications in the continuum IoT-Fog-Cloud. In this paper, we propose a regression model for predicting delay values in an SDN-based fog layer. To build up the regression model, we constructed a dataset, performed data cleaning, carried out feature selection, and applied different Machine Learning (ML) techniques. Our evaluation results reveal that the Random Forest (RF) technique overperforms Decision Tree (DT) and Neural Network (NN) techniques on predicting the delay in an SDN-based fog layer. Furthermore, the predicted delay values reinforce that a fog layer based on SDN can support different latency-sensitive applications.

The adoption ofSpace division multiplexing (SDM) in elastic optical networks brings new challenges for spectrum allocation. This paper proposes an algorithm for routing, spectrum and core allocation based on single/multipath routing for providing path protection. The proposed solution has the advantage of using small contiguous bands divided into several paths to provide the request protected bandwidth, allowing the increase in the number of requests accepted. Results show that the proposed algorithm can decrease the blocking ratio by three orders of magnitude when compared with other existing algorithms.

A significant problem affecting the overall performance of Data Center Networks (DCNs) based on Software-Defined Networking (SDN) is the delay introduced by controllers to mice flows. In the literature, there exist approaches facing this problem by compiling and installing paths for mice and elephants dynamically. However, such approaches have shortcomings related to the large number of routing rules that the switches must handle, which may also lead to extensive delays to mice flows. In this paper, we propose MiceDCER, an algorithm that efficiently routes mice flows in SDN-based DCNs by assigning internal Pseudo-MAC (PMAC) addresses to the edge switches and hosts. Aiming at reducing the number of routing rules, MiceDCER installs wildcard rules based on the information carried by the Address Resolution Protocol (ARP) packets. Our evaluation reveals MiceDCER significantly reduces the number of rules installed in switches and, therefore, contributes to reducing the delay in SDN-based DCNs.

Mobile fronthaul networks can benefit from TWDM-PON systems, such as NG-EPON, by employing an efficient DWBA scheme to fulfill CPRI requirements. This paper introduces a prediction-based DWBA algorithm to meet the bandwidth and delay requirements of the CPRI traffic regardless of the used line bit rate. The central idea is to provide for each ONU multiple time slots in one or more wavelengths. Moreover, a prediction method is employed to determine the number of time slots required for each ONU in future cycles. To the best of our knowledge, this is the first NG-EPON's DWBA algorithm focused in C-RAN architectures. Numerical results show that the proposed strategy decreases the number of active wavelengths, while improves time slot utilization and throughput rate without violating the fronthaul delay requirements, when compared with the state-of-the-art algorithms.

The collision of multiple MSG3transmissions due to the selection of the same preamble sequence in the Long Term Evolution (LTE) Random Access procedure is an important problem which can impact on the performance of cellular Internet of Things (IoT) networks. In this paper, we propose a standard-compatible probabilistic retransmission approach to reduce the number of collisions of MSG3messages in cellular IoT technologies. In our proposal, every Machine-Type Communications (MTC) device with an uplink grant for retransmitting an MSG3message uses a probability value to decide whether or not to transmit. Two retransmission policies were proposed to reduce the number of simultaneous MSG3messages received at the base station. To apply these policies, the estimation of the number of MTC devices trying random access in a given Random Access Opportunity is required. A novel method to estimate this value at the device side is proposed based on Random Access Response (RAR) message counting and the Access Class Barring (ACB) barring probability. Results derived via simulations show that the proposed approach decreases the number of collisions of MSG3messages, reducing the access delay and energy consumption, as well as decreasing the utilization of the Packet Uplink Shared Channel (PUSCH) when compared to conventional LTE Random Access scheme.

The use of protection in elastic optical networks (EONs) with spatial division multiplexing (SDM) can lead to under-utilization of the spectrum, since a high number of resources is reserved for protection. In this paper, we propose an algorithm that employs minimum interference routing, FIPP p-cycle, optical traffic grooming, and spectrum overlap to increase the efficiency in spectrum utilization in protected EONs-SDM. Extensive simulation results show that the proposed algorithm prevents the formation of network bottlenecks and reduces the resources used for protection.

Spatial division multiplexing is a promising solution proposed for elastic optical networks to cope with the expected depletion of the capacity of single core networks. The introduction of space division multiplexing in optical networks brings new challenges for network protection since a lightpath can span high capacity and transmit data at different rates. In addition, there is a great need for protection mechanisms against failure due to the high volume of traffic carried in these networks. Moreover, these networks suffer from the fragmentation of the spectrum that hampers the contiguity and continuity constraints and therefore increase blocking. To address these problems, in this paper, we propose a protection algorithm for elastic optical networks with spatial division multiplexing using hybrid routing and FIPP pcycle. The proposed algorithm prioritizes the use of single path routing, and uses multipath when no single path can be found to accommodate the requested bandwidth. The proposed algorithm is compared to four other algorithms that use single path routing. Results indicate that 100% protection for single failures with low overhead can be provided by the proposed algorithm.

In Elastic Optical Networks with Space-Division Multiplexing (EON-SDM), dynamic allocation and de-allocation can generate spectrum fragmentation, increasing the blocking probability. Proactive solutions attempt to minimize or prevent future fragmentation occurrence by trying to find paths and blocks of slots to allocate. These solutions increase the chances of future connection requests to be allocated. This paper presents two proactive algorithms to avoid spectrum fragmentation in EON-SDMs. The proposed algorithms take into consideration the fragmentation state of the spectrum as well as potential bottleneck formation. Results demonstrate that our algorithms can reduce significantly the blocking probability while respecting the inter-core cross-talk constraint in Multi-Core Fiber (MCF).

In hybrid clouds, inter-cloud links play a key role in the execution of jobs with data dependencies. Insufficient available bandwidth in inter-cloud links can increase the makespan and the monetary cost to execute the application on public clouds. Imprecise information about the available bandwidth can lead to inefficient scheduling decisions. This paper attempts to evaluate the impact of imprecise information about the available bandwidth in inter-cloud links on workflow schedules, and it proposes a mechanism to cope with imprecise information about the available bandwidth and its impact on the makespan and cost estimates. The proposed mechanism applies a deflating factor on the available bandwidth value furnished as input to the scheduler. Simulation results showed that the mechanism is able to increase the number of solutions with makespans that are shorter than the defined deadline and reduce the underestimations of the makespan and cost provided by workflow schedulers.

In the Internet of Things (IoT), it is desirable that every IoT device will be capable to communicate with the network at any time. Among various technologies to enable network connectivity, the Long Term Evolution (LTE) is by far the most ubiquitous technology to provide large coverage of IoT devices. Machine-Type Communications (MTC) is seen as a major service in the next generation cellular mobile networks for IoT. However, the predicted large number of MTC devices will overload the Radio Access Network (RAN), with impact on non-MTC devices. In this work, we propose a design of a RAN overload control mechanism based in clustering that is exclusively engineered for delay-tolerant MTC devices. The proposed solution is intended for delay-tolerant MTC devices with a Radio Resource Control (RRC) context (have a Cell Radio Network Temporary Identity (C-RNTI)) but without being synchronized with the network. By simulation, we show that the proposed scheme leads to acceptable collision levels, besides ameliorating the energy efficiency.

Video on Demand (VoD) allows subscribers to choose videos and watch them remotely. Currently, Infrastructure as a Service (IaaS) offers "pay as you go" type of service, which allows the increase of the computation capacity of a service provider. However, challenges include the distribution of content among geographically distributed data centers. In this paper, we propose heuristics to select a server to stream a requested video as well as where to dynamically allocate the server.

The Space division multiplexing (SDM) in elastic optical networks brings new challenges for protection of networks since a lightpath can span multiple cores. Although previous studies have studied protection in SDM elastic optical networks (EON), no work has considered the joint use of p-cycle, traffic grooming and spectrum overlap for these networks. In this paper, we investigate the problem of protection in space division multiplexing elastic optical networks, generating primary paths and p-cycles. The proposed solution allows a more efficient use of network, keeping crosstalk acceptable. Results derived via simulation show that the proposed spectrum overlap, traffic grooming and FIPP p-cycle algorithm can keep the quality of transmission and yet decrease the blocking of connections.

Fog computing brings the cloud close to the users, reducing latency and allowing the deployment of new delay sensitive applications. Fogs and clouds can work cooperatively to improve service delivery to the end users. An essential aspect of a fog-cloud system is the decision-making process on where to allocate resources to run the tasks of an application. This paper introduces a novel mechanism named Gaussian Process Regression for Fog-Cloud Allocation (GPRFCA) for resource allocation in infrastructure composed of cooperative fogs and clouds. The GPRFCA mechanism employs a Gaussian Process Regression to predict future demands in order to avoid blocking of requests, especially delay-sensitive ones. Results show that the GPRFCA mechanism reduces energy consumption, blocking as well as latency.

This paper introduces a mechanism for the support of multi-ONU service level agreements (SLAs) in dynamic bandwidth allocation (DBA) algorithms for Ethernet passive optical networks (EPON). The employment of SLAs for multiple optical network units (ONUs) instead of individual ONUs allows better utilization of the bandwidth reserved for these ONUs. The proposed DBA mechanism allows customers owning multiple ONUs to redistribute the aggregated bandwidth of the group of ONUs to better balance the bandwidth utilization. The proposed DBA can be employed in different use cases such as mobile backhauling/fronthauling, PON virtualization, and multi-site enterprise networking. Simulation results show that the proposed DBA improves the network performance.

Energy Efficiency is one of the main concerns in the design of wireless communication protocols, especially for battery-enabled devices, such as smartphones, tablets and laptops. In this paper, we focus on the impact of transmission fragmentation and resource fragmentation on the energy efficiency of SC-FDMA systems. To deal with these two problems, we introduce the Best Edge Set (BESt) algorithm for adoption in packet schedulers for Single-Carrier Frequency Division Multiple Access (SC-FDMA) LTE/LTE-Advanced systems. The BESt algorithm employs a novel Physical Resource Block (PRB) allocation strategy to avoid resource fragmentation as well as a new way to prioritize User Equipment (UE) transmissions to reduce the transmission fragmentation and the energy consumed in transmissions. Simulation results show the advantages of using the BESt algorithm and the strong correlation between transmission fragmentation and energy efficiency.

The popularization of the Internet of Things (IoT) encouraged a rapid growth in the number of wireless devices. Wireless networks experience serious coexistence problems due to interference caused by devices using the same frequency (mainly, 2.4 GHz). This problem is more serious when the environment has many wireless devices close to each other, such as smart homes. In a smart home, the wireless devices communicate through a Wireless Home Network (WHN). Usually, no suitable strategy is applied to prevent the wireless devices to use the same channel, and, consequently, to reduce the interference in the WHN. Within this context, this paper presents a channel assigner using a Mixed Integer Linear Program (MILP) model, that has the objective to minimize the interference suffered by devices in the WHN. Thus, the proposal aims to mitigate the coexistence problem in a smart home environment. Experiments performed suggested that the proposed channel assigner is capable of reducing the interference in WHN by 50% when compared with the existing approaches.

This paper investigates the problem of locating edge devices in ultra-dense 5G network function virtualization-based small cell networks for the provisioning of reliable broadcasting services. The problem is formulated as a capacitated reliable facility location problem (CRFLP) with failure probability. The solution aims at placing the VNFs of broadcast transmissions optimally on selected edge devices in order to ensure high reliability and minimize the cost of providing broadcast services as well as the probability of loss of service requests. The CRFLP is a non-linear NP-hard problem and it is evaluated by using a multi-objective evolutionary algorithm. Two multi-objective metaheuristics are compared: the multi-objective particle swarm optimization and the nondominated sorting genetic algorithm. Results demonstrate that the proposed solution achieves high levels of reliability as well as low latency.

The introduction of space division multiplexing (SDM) is a promising solution to cope with the ever increasing Internet traffic. The introduction of SDM brings new challenges for protecting the network since a lightpath can span multiple cores. In this paper, we propose a novel routing, modulation level and spectrum assignment (RMLSA) algorithm to dynamically generate primary and backup paths using a shared backup scheme and adaptive modulation in elastic optical networks employing multi-core fibers and space division multiplexing. The proposed algorithm is evaluated and its performance compared to the performance of other algorithms in the literature. Results indicate that 100% protection for single failures is achieved by our algorithm and yet it produces better performance when compared to the performance of existing algorithms.

In this paper, we introduce the Preamble Priority-Aware (PPA) Packet Downlink Control Channel (PDCCH) resources allocation algorithm to provide Quality of Service (QoS) differentiation in the Random Access (RA) procedure of the LTE-Advanced technology. The PPA algorithm uses the preamble priority defined by the RA procedure and Radio Access Network (RAN) overload control schemes to make scheduling decisions. Results derived via simulation show that the proposed PDCCH algorithm significantly increases the chance of accessing the network as well as reducing random-access delays for user equipment employing prioritized preamble sequences. Thus, the proposed algorithm provides enhanced QoS support to prioritized users during intense RA attempts.

Mobile Operators have experienced a growth of demand of new services with strict requirements and features which imposes challenges to operate the mobile wireless network. To tackle these challenges, Telcos must provide flexible, dynamic network architecture, furnishing resiliency to ensure end-to-end (E2E) service continuity in case of resource failures. Virtualization of the core network elements of cellular Long-Term Evolution (LTE) and LTE evolved Multimedia Broadcast Multicast Service (eMBMS) technology has been proposed as a key solution to cope with these new demands. By employing point-to-multipoint services to any wireless device, the LTE eMBMS, allows Mobile Operators (MOs) to send a single stream of data to all mobile users in a specific area. The LTE eMBMS is a potential E2E service technology to leverage costumer experience as well as to optimize use of network resources. We propose to improve the reliability of LTE eMBMS E2E services via redundancy, virtualized network functions (VNF), and autonomic service placement. In this paper, we introduce a redundancy seriesparallel model to improve reliability of LTE eMBMS services. The model is formulated as a VNF redundancy allocation problem (RAP). We employed the particle swarm optimization (PSO) technique to solve the RAP problem to evaluate the performance of the proposed model.

Several reports on Internet traffic have shown that HTTP adaptive streaming is fundamental for multimedia content transport and delivery. Despite the large body of work in this area, running streaming applications on overload channels demands effective delivery strategies. In this work, a video bitrate adaptation strategy, deployed in overloaded channel of an access network, is proposed and evaluated. This strategy takes decisions about bitrate switching based on QoE related parameters to minimize playback stalls. In the experiments conducted to evaluate the effectiveness of the proposed strategy, the average video bitrate, instability and fairness are measured over all of the played video sessions.

This paper proposes a Routing, Core and Spectrum Assignment (RCSA) algorithm based on the image processing Inscribed rectangle algorithm. The solution aims at discovering portions of spectrum capable of accommodating requests with low computational complexity. Advanced fitting policies are proposed to chose which portion of the spectrum to choose in order to reduce blocking and crosstalk. Results show that the proposed algorithm can reduce the blocking ratio under low loads and crosstalk under all loads, when compared to other RCSA algorithms in the literature.

Although shared path protection has been employed for protecting traffic flows against network failures, to our knowledge, it has not been considered for path protection in elastic optical networks with space division multiplexing (SDM). In this paper, we propose an algorithm to dynamically generate primary and backup paths using a shared backup scheme. The proposed algorithm is compared to the Failure-Independent Path Protecting for MultiCore network (FIPPMC) algorithm and to the Shared path with Spectrum and Core Assignment (SSCA) algorithm. Results indicate that 100% protection for single failures can be provided by the proposed algorithm with low overhead when compared to the other two algorithms.

Urban mobility has become one of the most challenging issue in urban centers. As a consequence, traffic congestion has become a daily problem. Several Advanced Traffic Management Systems (ATMS) have been proposed to improve overall traffic efficiency. However, these systems inefficiently exchange traffic information, which can lead to network overload. In order to overcome the mobility problem and improve the efficiency in dealing with vehicle traffic, this paper introduces a fully-distributed advanced traffic management system based on opportunistic content sharing, named PANDORA. Simulation results indicate that PANDORA outperforms the assessed solutions in various scenarios, considering different key requirements of ATMS.

The concept of preamble-priority awareness in downlink control signaling scheduling was recently proposed to provide Quality of Service (QoS) differentiation in the Random Access (RA) procedure of the LTE/LTE-Advanced technology. This approach employs the information about preamble-priority levels used in the the initial phase of the RA procedure to schedule random access response messages. In this paper, we extend the application of this concept to the scheduling of other control messages and analyze its impact when the RACH Resource Separation (RRS) scheme and the traditional RA scheme with both the contention-free and the contention-based modes are used under heavily-loaded, highly-synchronized Machine-Type Communications (MTC) scenarios. Our results derived via extensive simulations show that the preamble-priority-aware concept provides QoS differentiation to users utilizing contention-free preambles. Furthermore, this concept helps to achieve the goal of isolation between traditional LTE users and MTC devices when the RRS scheme is used.

In recent years, elastic optical networks have emerged as a solution for dealing with the diversity of the bandwidth demands of network applications. The use of only two multiplexing dimensions has limited the network capacity. To ameliorate this problem, a third dimension has been added in space division multiplexing(SDM). As transmission rates increase so does the need for protection against network failures. Among the protection schemes,those protecting paths are of great interest due to their end-to-end solutions. This paper introduces a novel algorithm based on p-cycle to provide failure-independent path protection in elastic optical networks with SDM.

This paper provides an analysis of energy efficiency of the Transmission Opportunity Power Save Mode (TXOP PSM) in IEEE 802.11ac Wireless Local Area Networks (WLANs). This mechanism allows a device to sleep during transmissions in the channel that are addressed to other devices. This operation is also referred to as microsleep and can significantly reduce the energy consumption of devices during overhearing periods. A key contribution of the analysis presented in this paper is the awareness of the non-negligible time and energy consumption that a device incurs when it switches between awake and sleep states. If the duration of such state transitions is longer than the transmission time, microsleep operation is not possible. This becomes a critical issue as transmission rates increase, thus reducing the transmission times. In this paper, we show that the performance dependence of TXOP PSM on the awake/sleep state transitions can be overcome by using burst transmission inherent to the TXOP operation. Results obtained through theoretical analysis and computer-based simulation show gains of up to 424% in energy efficiency when compared to legacy mechanisms.

This paper proposes a new Reverse Direction (RD) Medium Access Control (MAC) protocol to improve the throughput and energy efficiency of IEEE 802.11 Wireless Local Area Networks (WLANs). The proposed protocol allows a source device to transmit a burst of data frames to the intended destination device in a single channel access opportunity. After the successful reception of each data frame, the destination device may opportunistically respond with a data frame, thus being able to perform multiple RD transmissions. This operation can reduce the overall channel access overhead, hence increasing the efficiency of data transmission between two sender-receiver devices. The results obtained by means of theoretical analysis and computer-based simulation show that the novel RD protocol can outperform existing IEEE 802.11 protocols by yielding gains close to 60%.

This paper proposes the Topology-aware Virtual Machine Selection (TAVMS) algorithm to choose sets of communicating groups of virtual machines (VMs) to be migrated to other data centers, aiming at global energy savings. It considers the migration of groups of VMs as well as the data center network topology, selecting VM groups with network proximity in order to increase the potential number of equipments to be switched off. Results obtained show that relevant energy savings can be achieved by using the proposed algorithm in the allocation of servers to the migration of virtual machines in a distributed data center scenario.

This paper introduces a novel Routing, Core and Spectrum Assignment (RCSA) algorithm based on the Connected Component Labelling (CCL) algorithm. The RCSA algorithm represents the spectrum of multicore fibers as matrices and the CCL algorithm discovers with low computational complexity the available spectrum to allocate to a connection request. Spectrum fitting policies are also proposed to be jointly employed with the CCL algorithm. Results show the feasibility of utilizing image processing algorithms such as the CCL in RCSA algorithms, given that they demand low computational complexity and yet produce low blocking ratio.

It has been shown in the literature that Network Coding (NC) can boost the performance of wireless networks. However, to really obtain the potential gain of NC, efficient Medium Access Control (MAC) protocols that operate with awareness of the NC functions are necessary. In this paper, we propose a novel NC-aware MAC protocol for IEEE 802.11 wireless networks that combines k-batch transmissions and multiple receiver-initiated reverse direction exchanges involving NC data to boost the overall network performance. The proposed protocol allows any node to transmit a burst of data packets in a single channel access invocation. Then, an intermediate node can transmit an NC data packet when receiving a valid data packet from a source node, without contending for channel access. Both analytical and simulation results presented in this paper show the high throughput and energy efficiency of the proposed protocol with gains ranging from 33% to 298% when compared to existing mechanisms based on the IEEE 802.11 Standard.

The Internet of Things (IoT) paradigm stands for virtually interconnected objects that are identifiable and equipped with sensing, computing, and communication capabilities. Services and applications over the IoT architecture can take benefit of the long-term evolution (LTE)/LTE-Advanced (LTE-A), cellular networks to support machine-type communication (MTC). Moreover, it is paramount that MTC do not affect the services provided for traditional human-type communication (HTC). Although previous studies have evaluated the impact of the number of MTC devices on the quality of service (QoS) provided to HTC users, none have considered the joint effect of allocation of control resources and the LTE random-access (RA) procedure. In this paper, a novel scheme for resource allocation on the packet downlink (DL) control channel (PDCCH) is introduced. This scheme allows PDCCH scheduling algorithms to consider the resources consumed by the random-access procedure on both control and data channels when prioritizing control messages. Three PDCCH scheduling algorithms considering RA-related control messages are proposed. Moreover, the impact of MTC devices on QoS provisioning to HTC traffic is evaluated. Results derived via simulation show that the proposed PDCCH scheduling algorithms can improve the QoS provisioning and that MTC can strongly impact on QoS provisioning for real-time traffic.

In multilayer networks, protection can be accomplished in any of the layers. However, which layer to protect most remains an important problem. In this paper, we consider a three-layer with IP/MPLS-over-OTN-over-DWDM in which we consider an optimization modeling framework incorporating modularization of its capacity for protection in any layer. Our resulting study, conducted on two topologies, shows that the cost ratio of different layers is an important factor in answering this question, as well as the actual modular values of the capacity used. Furthermore, we found that the cost providing protection in the OTN layer is highly influenced by the network connectivity.

In this paper, we propose an energy-efficient solution for implementing Network Coding (NC) in wireless networks based on the IEEE 802.11 Standard. The proposed mechanism, called GreenCode, allows nodes to duty cycle by switching to a low-power (sleep) state when they overhear coded packet transmissions that will not provide any new information for them. To facilitate the sleep operation, bidirectional transmissions involving both coded and non-coded packets between pairs of sender-receiver nodes are integrated into the operation of GreenCode. Both analytical and simulation results presented in this paper show the high energy efficiency of GreenCode with gains of up to 360% when compared to the existing mechanisms based on the IEEE 802.11 Standard.

The Long Term Evolution (LTE) and LTE-Advanced technologies aim at providing improved users' experience by increasing data rate, enhancing coverage and supporting Quality of Service (QoS) to different service classes. However, a large number of User Equipment (UE) devices trying to access the network in a short period can overload the Radio Access Network (RAN). In this situation, more access attempts to the system are made than it can handle, resulting in low access probabilities and poor network performance. In this paper, we introduce the QoS-Aware Self-Adaptive RAN Overload Control (QoS-Dracon) mechanism to reduce the RAN overload problem, taking into account users' QoS requirements. This is achieved by employing a QoS Class Identifier-dependent backoff scheme and an Access Class Barring-based RAN overload control mechanism. QoS-Dracon prioritizes delay-sensitive UE devices over delay-tolerant ones when performing Random Access (RA) procedure. Results derived via simulation show that the proposed mechanism yields satisfactory access delays for delay-sensitive users regardless of the UE devices type attempting to access the channel.

Information and Communication Technology activities consumed 4% of the world energy in 2009, and such consumption will continue to increase due to the traffic growth of the Internet predicted for the next years. Techniques to make the core of the network more energy efficient has been proposed, among them, green routing has been considered a promising technique. This paper proposes a novel Routing, Modulation Level and Spectrum Assignment (RMLSA) algorithm for elastic optical networks that considers the energy consumption of potential routes. Results indicate that this algorithm can save up to 34% energy and produce bandwidth blocking ratio two orders of magnitude lower than existing energy aware RMLSA algorithms.

This paper presents the Topology-aware Virtual Machine Placement algorithm, which places groups of communicating virtual machines in data centers. It aims to use small regions of the data center network in order to consolidate the network flows produced by the virtual machines. We employ extensive simulation and show that the proposed algorithm avoids network bottlenecks, therefore accepting more requests of virtual machines. Moreover, such advantages are obtained without compromising the energy efficiency when compared to other algorithms. The energy consumption of servers and switches are taken into account and they are switched off whenever idle.

Made available in DSpace on 2016-06-07T13:36:10Z (GMT). No. of bitstreams: 1 wos_000367123300001.pdf: 410004 bytes, checksum: 6de6b0e120e3cfc1bb14dcf5e725aa36 (MD5) Previous issue date: 2015

In hybrid clouds, the available bandwidth in inter-cloud links is quite variable. Overestimating the available bandwidth on theses channels at scheduling time can enlarge the makespan and cause deadline misses. In this paper, we propose a procedure for deflating the estimated available bandwidth used as input to cloud schedulers since schedulers are not usually designed to cope with inaccurate information on available bandwidth. The procedure is based on a multiple linear regression procedure which utilizes historical information of previous executions of workflows. Results showed that the proposed procedure can increase the number of valid schedules without increasing the makespan and cost estimations, regardless the variability in the available bandwidth during the execution of an application workflow.

This paper introduces a novel traffic grooming algorithm for the connection establishment of deadline-driven requests in elastic optical networks, named Elastic Batch Grooming Algorithm. The algorithm grooms batches of requests to establish lightpaths with diverse bandwidth demands with deadline requirements. Results show that the algorithm significantly reduces the blocking ratio and the number of demanded transponder when compared to traditional non-batch algorithms.

In optical networks, faults in links and nodes cause massive loss of data even if for short periods. Therefore, protection techniques have been developed to cope with failures. Among these techniques, p-cycle is very attractive since it provides ring-like speed of restoration in mesh topologies. In recent years, the technology of flexgrid networks has emerged as a solution for dealing with the diversity of bandwidth demands of network applications. However, very few investigations have been proposed for path protection in flexgrid networks. This paper introduces a novel algorithm to provide Failure-independent path protecting p-cycle for path protection in flexgrid networks. The proposed algorithm is compared to two other algorithms in the literature. Results indicate that the 100% protection for single failures can be provided by the proposed algorithm with low overhead to networks with high node connectivity.

This paper proposes a heuristic to de-allocate light-paths in Wavelength Division Multiplexing (WDM) networks for reducing the network energy consumption. The idea is to avoid the overhead involved in the establishment of future lightpaths by rerouting connections to a lightpath to be de-allocated. Numerical results show that the proposed strategy saves energy while maintains blocking ratio at levels compatible to those of algorithms which do not employ rerouting of connections.

In flex-grid (elastic) networks, the spectrum can be allocated at a much finer granularity than it can be allocated in WDM networks. However, the dynamic establishment and tear down of lightpaths yields to the fragmentation of the spectrum with consequent increase in blocking of requests for connection establishment. Therefore, it is of paramount importance that allocation decisions try to mitigate the fragmentation problem. In line with that, this paper introduces the Multigraph Shortest Path Algorithm for novel Routing and Spectrum Allocation (RSA) in elastic networks. Results indicate that the joint use of the new algorithm with proposed cost functions can produce bandwidth blocking ratio four orders of magnitude lower than existing RSA algorithms.

In optical flexgrid networks, the optical spectrum can be allocated at a much finer granularity than it can be in fixed-grid WDM networks and variable spectrum widths can be assigned to the lightpaths according to the transmission rates, leading to more efficient spectrum usage. However, the dynamic establishment and tear down of lightpaths yields to the fragmentation of the spectrum with increase in blocking of connections, mainly connections demanding large spectrum widths. This paper proposes a novel algorithm that introduces a zone-based assignment policy together with an alternative path routing mechanism based on the maximum capacity available. Results derived via simulation using different topologies and considering connections requests from 40Gbps to 1000Gbps, show that the proposed algorithm leads to blocking ratio consistently lower than those given by traditional approaches. It also reduces the blocking ratio of high rates connections, in some cases, by a factor of six.

Vehicular Ad-Hoc Networks (VANETs) are a specific type of moving networks in which the nodes are vehicles with processing, storage and wireless communication capacity. VANETs face a number of challenges in terms of data dissemination due to the volatile density of vehicles and frequent changes in the network topology induced by the high mobility of the vehicles and of short-range communications. The envisaged applications, as well as some inherent characteristics of the VANETs render the data dissemination an essential service and a challenging task in these networks. Many data dissemination protocols have been proposed in the literature, nevertheless, most of such protocols do not deal simultaneously with the problems of broadcast storm and network partition. To face such problems, we propose a new data dissemination protocol in vehicular networks named DRIFT, which operates in highway environments. The DRIFT eliminates the broadcast storm problem and maximizes the data dissemination in partitioned networks with little delay and low overhead. When compared with four known solutions, we show that our proposal for data dissemination executes it with higher efficiency than other protocols, exceeding them in different scenarios in all the undertaken evaluations.

This paper introduces a novel LTE uplink scheduler called Hybrid Z-Based QoS Scheduler (HZBQoS), a fully standard-compliant LTE scheduler designed to operate in ONU-eNB devices of integrated LTE/TDM-EPON networks. The HZBQoS scheduler provides delay bound and guaranteed rate even when the backhaul and mobile network are heavily loaded. We evaluated the proposed scheduler under heterogeneous traffic and compared its performance to that of another LTE uplink scheduler, called Z-Based QoS Scheduler (ZBQoS), which does not take into account the variability of the backhaul link capacity. Simulation results show that HZBQoS is able to provide QoS requirements in the integrated network and outperforms the ZBQoS scheduler.

This paper proposes an architecture for mobile wireless networks based on Radio-over-Fiber (RoF) technology. The architecture organizes cells in a multi-tier fashion, with different tiers covering areas with different radii lengths. Proposed optimization algorithm splits cells to improve network capacity in congested areas and merges cells when the demand is low. The evaluation of the effectiveness of the proposed model considered three distinct objectives: minimization of the number of base stations used, maximization of the number of users served, and minimization of network energy consumption. The combination of the first two objectives was also evaluated. Three algorithms based on linear relaxation techniques are introduced for rapid computation of the near-optimum solutions. The proposed architecture is shown to lead to network infrastructures that save costs and energy and yet provide service to a large number of users.

This paper introduces admission control policies for WiMAX networks, which aim to reach three main goals: restrict the number of simultaneous connections in the system so that the resources available for the uplink scheduler are sufficient to guarantee the quality-of-service requirements for each connection, support the service provider expectations by maximizing the revenue, and maximize user satisfaction by granting additional resources. The optimal solution to meet these goals is non-deterministic polynomial-time hard and therefore cannot be solved in acceptable polynomial time. For this reason, both optimal and polynomial time heuristic solutions are introduced. Simulation experiments are used to evaluate and compare the proposed policies. Copyright © 2012 John Wiley & Sons, Ltd.

This paper introduces a novel time-domain (TD) LTE uplink scheduler called Z-Based QoS Scheduler (ZBQoS) which is fully standard-compliant. The ZBQoS scheduler provides Quality of Service (QoS) requirements, supporting delay bound and guaranteed rate even when the network is heavily loaded. We evaluate the proposed scheduler under heterogeneous traffic and compare its performance to that of another TD scheduler, called Bandwidth and QoS Aware (BQA), recently proposed. Simulation results show that ZBQoS scheduler reduces significantly delay of real-time traffic, while it is able to maintain lower packet loss ratio (PLR), when compared with the performance of the BQA scheduler which greatly surpasses the recommended PLR value under heavily loaded scenarios.

This paper investigates the use of multipath grooming to save energy in Wavelength Division Multiplexing (WDM) networks by splitting the bandwidth demand of requests among several paths and aggregating them with already established lightpaths. For that, two algorithms are proposed which employ an auxiliary graph which edge weights represent the energy consumed by all the operations related to the optical transmission in a lightpath to provide the bandwidth requested. Both algorithms select a subset of different sets of k lightpaths in which residual bandwidth surpasses minimally the demanded bandwidth with minimum energy consumption. These two algorithms represent the choice of criteria between energy consumption only or both energy and bandwidth. It is shown that the algorithm which considers both energy and bandwidth employs a lower number of lightpaths while reducing the energy consumption and blocking rate.

This paper introduces a task scheduler for clouds which considers that estimations of the available network bandwidth are not precise. The efficacy of the scheduler was evaluated with different type of applications and degree of uncertainty of available bandwidth estimations. Results show that the proposed scheduler is robust to imprecise input information.

In spite of the increasing deployment of IPTV services, various functionalities still need to be improved. One of the main challenges is a reduction in startup delays, especially in channel switchings, a problem which is quite relevant in P2P IPTV systems. This paper evaluates the iPeer TV, a P2P IPTV architecture with fast channel switching. Our contribution is threefold. Firstly, we propose how our P2P IPTV architecture can be integrated with a previously evaluated channel switching scheme. Secondly, we propose a simple yet effective optimization for such scheme which is capable of improving the system performance. Thirdly, we provide an analysis of the minimum bandwidth requirements for the infrastructure layer of the architecture to ensure the best system performance.

This paper assesses the effectiveness of playlists for improving the content availability in CDN-P2P networks that distributes YouTube-like videos. Real data collected from YouTube was used and the popularity patterns of playlists and first page videos were characterized. Moreover, the impact of playlist viewers on content availability was evaluated. Results show that the improvement in content availability is about 40% for highly connected playlist viewers. For systems with less connected playlist viewers, the improvement exceeds 20% for different scenarios.

Network virtualization is a promising technology for the Internet of the Future. An open issue in virtualization is the management of network resources in a way that energy savings are achieved without compromising the Quality of Service (QoS) requirements of the virtual networks. The dynamic allocation and deallocation of virtual networks can lead the state of the substrate to a less than optimum energy consumption. This paper introduces two algorithms for the migration of virtual routers and/or links which aims to allocate resources so that energy consumption is minimized. The efficacy of the migration of virtual routers and/or links and its impact on energy consumption are analyzed based on results derived via simulations.

This paper introduces a novel traffic grooming algorithm for the connection establishment of deadline-driven requests. The algorithm grooms batches of requests rather than individual requests. Results indicate that the algorithm is able to significantly reduce the blocking ratio and promote a fair distribution of blocking among source destination pairs of nodes.

In spite of the increasing deployment of IPTV services, various functionalities still need to be improved. One of the main challenges is a reduction in startup delays, especially in channel switchings, a problem which is quite relevant in P2P IPTV systems due to bandwidth limitations, as well as the employment of buffers and overlay structures. This paper presents and compares four novel schemes for providing fast channel switching that reduce the occurrence of latency. The results suggest that, in general, the proposed schemes are all capable of performing 68% of all channel switchings instantaneously on average. Moreover, the Fast 2 scheme, which presented the best performance, reduces the overall stream quality received less than 19%, on average.

The so-called hybrid cloud is the composition of an infrastructure that comprises private resources as well as public resources leased from public clouds. Hybrid clouds can be utilized for the execution of applications composed of dependent jobs, usually modeled as workflows. In this scenario, a scheduler must distribute the components of the workflow onto available resources considering the communication demands and the available bandwidth in network links. However, such information can be imprecise, and consequently decisions on resource allocation can be ineffective. In this paper, we evaluate scheduling algorithms in the face of imprecise information on the availability of communication channels. Results showed that schedules are negatively affected by the unforeseen variations in bandwidth during the execution of the application.

The integration of WiMAX networks with EPON networks capitalizes on the large availability of bandwidth in optical access networks with the mobility provided by wireless technologies. In this integration, a WiMAX scheduler needs to take into account the variability of the channel capacity provided by the EPON scheduler. This paper evaluates the performance of the Deficit Based QoS Uplink Scheduler (DBQUS) mechanism, a standard-compliant WiMAX uplink scheduler designed to operate in ONU-BS, under different EPON service cycle durations. The evaluation is conducted using integrated simulators for the WiMAX and for the EPON components. Results show that the proposed scheduler is able to provide QoS to the subscriber stations under different EPON service cycles. As the traffic load increases, the bandwidth received by the BE service flow is reduced due to the service provided to classes of service with higher priority.

Despite the research advances in intra-domain light-path provisioning in WDM networks, efficient and practical schemes for path computation and resource advertisement in multi-domain mesh networks still need to be developed. Most of the proposed solutions in the literature lacks the ability to convey optical network-specific Traffic Engineering information and are based on periodic message flooding technique. The solution presented in [1] achieved better performance than those based on periodic flooding while performing domain chain computation. However, it relies on potentially outdated routing information which can increase blocking of requests for lightpath establishment. The solution proposed in this paper considers the effective wavelength availability during path computation and adopts a destination-driven wavelength assignment scheme.

Network virtualization is a promising technique for building the Internet of the future since it enables the introduction of new features into network elements at low cost. An open issue in virtualization is how to search for an efficient mapping of virtual network elements onto those of the existing physical network. Mapping is an NP-hard problem and existing solutions take long time to find a solution. This paper presents four new approximated algorithms based on two integer linear programming formulations that runs fast and, also, consider various real network characteristics, which is neglected by other proposals in the literature.

In this paper, two Medium Access Control (MAC) protocols exclusively tailored to WSNs over RoF (RWSNs) namely SPP-MAC (Scheduled Priority Polling Medium Access Control) (polling-based) and HMARS (Hybrid Medium Access Control for Hybrid Radio-over-Fiber Wireless Sensor Network Architecture) (hybrid-based) are proposed. They deal with the main problems in RWSNs i.e. the delay imposed by optical fiber and the existence of two collision domains: the wireless and the fiber optical links. The performance of these two protocols evince their effectiveness for the connection of WSNs by RoF links.

Due to the fact that grid networks are non-proprietary systems, resource allocation mechanisms must cope with fluctuations in resource availability to guarantee the QoS requirements of the applications. Mechanisms are classified either as reactive mechanisms, which react to the fluctuations in run time, or as proactive mechanisms, which try to infer the occurrence of fluctuations in resource availability. This paper presents a study that evaluates the performance of these two different mechanisms in order to compare their advantages. Besides, a new mechanism, integrating the main characteristics of these mechanisms, is proposed. It produces makespan lower than those given by the other two mechanisms.

In this paper, we study the effectiveness of object management policies based on users' personal signals, available on YouTube-like content distribution systems, for improving content availability in P2P-CDN networks. Three policies are introduced and evaluated using real data collected from YouTube video collection, the most accessed multimedia distribution system in the Internet. We found those policies can improve content availability, over 60%, compared to the LFU policy, and over 25%, compare to the GDSP policy, in hybrid P2P-CDN networks.

Despite the research advances in intra-domain light-path provisioning in WDM networks, efficient and practical schemes for path computation and resource advertisement in multi-domain mesh networks still need to be developed. Most of the proposed solutions in the literature lacks the ability to convey optical network-specific Traffic Engineering information and are based on periodic message flooding technique. The proposed solution provides a novel and economical way to disseminate information while performing the domain chain computation. It also provides a policy-based wavelength selection scheme that allows a load balanced provisioning of end-to-end lightpaths.

The Future Internet demands energy efficient communication to cope with the ever increasing power consumption. Virtualization techniques have proved to be effective in reducing power consumption of network devices. An open issue in virtualization for green networking is the search for an energy-efficient mapping of virtual networks onto physical networks. This paper introduces a new model for the mapping of virtual networks which aims at reducing the energy consumption. This model is based on an integer linear programming formulation and several parameters, corresponding to characteristic of real networks, are considered. Simulation results attest the efficacy of the proposal.

Optical networks can benefit from multipath routing by routing traffic over diverse fiber links to fulfill bandwidth requirements, balance network load and improve resource utilization. This paper focuses on the effectiveness of multipath routing on aggregating residual bandwidth of the established lightpaths using dynamic traffic grooming. An optimization model based on Integer Linear Programing (ILP) is formulated to leverage multipath routing and grooming to serve connection requests with known duration, in a scenario where the dynamic traffic can demand bandwidth either larger or smaller than a single wavelength capacity. The impact of a balancing policy, referred to as Holding Time Balancing (HTBalancing), on multipath routing with traffic grooming in optical networks is also investigated. Numerical results show that the proposed optimization model can achieve a lower bandwidth blocking and a better load balancing with HTBalancing policy, when compared with single path routing. The proposed relaxation algorithm can effectively find near optimal solutions, and be applied in realistic scenarios.

The problem of lightpath provisioning in WDM optical networks has been extensively studied to reduce cost and blocking, but there is still a need of investigating this problem from a power consumption perspective. In this paper, we introduce a novel algorithm for IP/MPLS over WDM networks based on a reduced auxiliary graph that limits the solution space and captures the power consumption of lightpath provisioning. Results derived via simulation demonstrate that our strategy is energy efficient and that it is able to produce acceptable blocking ratio which are close to values produced by algorithms oriented to the reduction of blocking.

Network virtualization is a promising technique for building the Internet of the future since it enables the low cost introduction of new features into network elements. An open issue in virtualization is how to search for an efficient mapping of virtual network elements onto those of the existing physical network, also called the substrate network. Mapping is an NP-hard problem and existing solutions ignore various real network characteristics in order to solve problem in a reasonable time frame. This paper introduces two new algorithms for the solution of the mapping problem, both based on 0--1 integer programming, for the solution of the mapping problem which consider a whole new set of network parameters not taken into account by previous proposals. Simulation experiments confirm the efficiency of the proposed algorithms.

Both grid and cloud applications may require specific softwares for their execution. Introducing such requirements into the DAG describing the dependencies among the tasks of an application leads to a combinatorial problem with numerous possibilities of modified DAGs. This paper introduces an algorithm to obtain a single DAG with the minimum possible makespan by reducing the need for data transfer over the network.

Rate adaptation represents a relevant issue in optimization of wireless local area network performance. The paper proposes to employ a cognitive approach to perform rate adaptation, which is able to learn cause-effect relationships without any a priori knowledge. Results demonstrate the potential of the proposed scheme.

This paper introduces a batch scheduling algorithm for OBS networks which has linear computational complexity. A transformation of the problem formulation is applied to allow the modeling of the problem as a job scheduling with identical machine type of problem. The proposed algorithm was compared to several other heuristic. Results show that it produces a lower bound to the blocking probability of those given by heuristics and it is only 3% slower than the fastest one.

This article presents a radio resource optimization model for Radio-over-Fiber (RoF) access networks. The proposed model arranges cells in a multi-tier fashion with increasing coverage radius. Considering the available structure of antennas the optimizer performs dynamic cell merging and cell splitting according to mobile users' demands for efficiently utilizing radio resources. It is proposed an integer programming model with a bi-criteria objective function that tries to minimize the use of network resources as well as to maximize network revenue. The computational demand for obtaining integer solutions increases proportionally to the number of mobile users and also to the number of tiers of antennas. In addition to the integer solutions, an algorithm based on linear relaxation technique is presented, which implies on significant computational time reduction when solving large instances of the problem. Moreover, results are very close to those given by the integer programming formulation.

Scheduling is an essential mechanism in IEEE 802.16 networks for distributing the available bandwidth among the active connections so that their quality of service requirements can be furnished. Scheduling mechanisms adopted in wired networks, when used in wireless networks lead to inefficient use of the bandwidth since the location dependent and time varying characteristics of the wireless link usually are ignored by the wired networks. This paper introduces a standard compliant cross-layer scheduling mechanism which considers the modulation and coding of each mobile station to increase the efficiency of channel utilization while furnishing the QoS requirements of the connections.

One of the main challenges in IPTV systems is the reduction of startup delays, especially in channel switchings. While this problem does not exist in traditional television, in IPTV systems it is relevant, due to bandwidth limitation as well as to buffering. This paper proposes three novel schemes for fast channel switching that reduces the occurrences of latencies caused by buffers and overlay structures.

Grid scheduling is essential to Quality of Service provisioning as well as to efficient management of grid resources. Grid scheduling usually considers the state of the grid resources as well application demands. However, such demands are generally unknown for highly demanding applications, since these often generate data which will be transferred during their execution. Without appropriate assessment of these demands, scheduling decisions can lead to poor performance. Thus, it is of paramount importance to consider uncertainties in the formulation of a grid scheduling problem. This paper introduces the IPDT-FUZZY scheduler, a scheduler which considers the demands of grid applications with such uncertainties. The scheduler uses fuzzy optimization, and both computational and communication demands are expressed as fuzzy numbers. Its performance was evaluated, and it was shown to be attractive when communication requirements are uncertain. Its efficacy is compared, via simulation, to that of a deterministic counterpart scheduler and the results reinforce its adequacy for dealing with the lack of accuracy in the estimation of communication demands.

This paper introduces admission control policies for the IEEE 802.16 standard which aim to reach three main goals: restrict the number of simultaneous connections in the system so that the resources available to the scheduler are sufficient to guarantee the QoS requirements of each connection, support the service provider expectations by maximizing the revenue, and maximize the users satisfaction by granting them additional resources. The proposed policies are evaluated through simulation experiments.

Grid computing emerged as a computing paradigm to take advantage of the enormous availability of computing and communication resources in the Internet. Cloud computing succeeded grid computing as a new computer paradigm, offering resource transparency to the computation of user demands. In cloud computing, virtualization techniques are central to the provisioning of resources in clouds. This paper introduces a scheduler for grid applications in clouds which takes into account not only resource demands, but also software requirements of the applications. Moreover, it accounts for network link availability that has been widely neglected in the literature of grid scheduling.Experiments show the efficacy of the scheduler in different scenarios.

Cognitive networks were recently proposed to cope with the complexity and the dynamics of network managements, exploiting reasoning to adapt the behavior of protocols. Among the reasoning formalisms that can be employed, Fuzzy Cognitive Maps seem to be very promising, as they potentially allow the cognitive process to consider cross-layer interactions in the characterization of the performance of a network node. However, when considering a high number of cross-layer interactions, reasoning schemes can be too time consuming and may not provide a suitable solution as environmental conditions change. In order to decrease the demand of reasoning time it is of utmost importance to discover which cross-layer relationships carry relevant information to the cognitive process. This paper discusses how to make such differentiation. Moreover, it proposes a metric to evaluate the influence a cross-layer interaction has on the cognitive process.

In this paper, we introduce a radio resource optimization model for Radio-over-Fiber (RoF) access networks. We propose a mixed integer programming model to minimize the network cost while providing service to all mobile users. The proposed architecture arranges cells in a multi-layer fashion, with cells in each layer providing different coverage radius. The optimization algorithm performs dynamic cell splitting to improve network capacity in congested areas and cell merging in areas with low demand to save resources. The computational demand of the proposed model increases proportionally to the number of layers of RAUs in the infrastructure. Results indicate that two layers of RAUs give the best trade-off between network cost reduction and computational demand.

The IEEE 802.16 standard for broadband wireless access is a low cost solution for Internetaccess in metropolitan and rural areas. Although it defines five service levels to support real-time and bandwidth demanding applications, scheduling mechanisms are not specified in the standard. Due to the wireless channel variability, scheduling mechanisms widely studied for wired networks are not suitable for IEEE 802.16 networks. This paper proposes an uplink cross-layer scheduler which makes bandwidth allocation decisions based on information about the channel quality and on the Quality of Service requirements of each connection. Simulation results show that the proposed scheduler improves the network performance when compared with a scheduler which does not take into account the channel quality.

The evolution of network technologies brought increasing management complexity of networking infrastructure and protocols. Cognitive networking was introduced to deal with such complexity. This work presents a cognitive algorithm for cross-layer performance management which is the core of a decentralized framework for self-configuration of communication protocols. We illustrate the proposed solution for the joint reconfiguration of protocol parameters at different layers. The cognitive joint adaptation of TCP congestion window and MAC layer data rate is carried out as a proof of concept. Simulation results show performance improvement given by the proposed approach under changing network conditions.

One of the main challenges in IPTV systems is the reduction of startup delays, especially in channel switchings. While this problem does not exist in traditional television, in IPTV systems it is relevant, due to bandwidth limitation as well as the employment of buffers and overlay structures. Since the possibility of switching channels quickly is appreciated by users, the reduction of startup delays is an important issue to be addressed in IPTV systems. This paper proposes a novel scheme for fast channel switching that reduces the occurrences of latencies caused by buffers and overlay structures.

In this paper, a new algorithm for dynamic traffic grooming is introduced. It considers the holding-time of the connections and it aims at balancing the load among existing lightpaths to avoid the formation of bottlenecks and, consequently, high blocking probability values. Results indicate that it produces significantly lower blocking probabilities when compared to other holding-time-aware algorithm. Moreover, it promotes a fair distribution of blocking among source-destination pairs.

Dynamic grooming deals with requests for wavelength allocation based on a dynamic pattern of arrivals in contrast to the situation of static grooming in which the pattern of arrivals must be previously known. Solutions for dynamic grooming typically involve the construction of an auxiliary graph for deciding on the routing and wavelength assignment. An auxiliary graph can represent the network either entirely or partially. The complexity of grooming algorithms is significantly reduced when a partial representation of the network is employed. Algorithms that employ reduced auxiliary graph have a step for the expansion of such graphs in case paths are note found for lightpath establishment. Results reveal that the expansion mechanism can be reduced or even eliminated for reducing the complexity of the algorithms without compromising significantly the performance of the algorithms, especially under high load.

Traditional protection schemes guarantees 100% reliability in case of single link failure which demands resources while differentiated reliability provides a granular protection scheme. Moreover, if the signal quality in a path is below acceptable values, a path cannot be used by incoming requests for lightpath establishment. Therefore, the signal quality needs to be checked by the routing and wavelength assignment algorithm (RWA). This paper investigates shared path protection with differentiated reliability taking into account the PMD and the ASE impairments in path selection. The efficacy of the algorithm proposed is compared to that of its impairment unaware counterpart.

In this paper, we propose to apply multipath routing in optical networks for the emerging high-performance applications with extremely high bandwidth requirements, typically larger than the capacity of one wavelength. To this end, we present a novel Multipath lightpath Provisioning mechanism and derive an optimal solution by an ILP (Integer Linear Programming) approach, with differential delay and bandwidth as constraints to multipath finding. Our mechanism can set up multiple lightpaths over multiple fiber-level paths not only to satisfy the extremely high bandwidth requirements, but also to reduce the minimum bandwidth required for backup paths as it reduces the amount of traffic affected by single fiber breaks. For comparison, we also present an ILP-based Single Path Lightpath Provisioning mechanism and show that its multipath counterpart performs better independently of the mesh topology under study. The performance results demonstrate that the proposed multipath lightpath provisioning mechanism outperforms the traditional single path routing by decreased bandwidth request blocking ratio, while reducing the amount of traffic that may be affected by single link failures.

Traffic grooming in wavelength division multiplexing networks merges low-speed flows into large capacity pipes so that the bandwidth discrepancy between them will not lead to underutilization of resources. Dynamic grooming deals with requests for wavelength allocation based on a dynamic pattern of arrivals in contrast to the situation of static grooming in which the pattern of arrivals must be previously known. Solutions for dynamic grooming typically involve the construction of an auxiliary graph for deciding on the routing and wavelength assignment. An auxiliary graph can represent the network partially leading to scalable solutions, although blocking is not fairly distributed among calls in such solutions. A novel algorithm is thus proposed for achieving fairness in blocking among the calls. In an off-line step, it defines an appropriate set of OXCs for achieving fairness and efficient use of resources. Results reveal a higher degree of fairness obtained by the use of the novel algorithm than for previously proposed algorithms.

This paper introduces an optimal batch scheduling algorithm for the scheduling of batches of bursts in optical burst switching networks. The algorithm, called BATCHOPT, considers both the requests being processed in the current batch and the requests previously scheduled in the search for an optimal solution. Moreover, an extended version of the JET reservation protocol is proposed for efficiently handling batches of bursts. Results obtained via simulation show that the BATCHOPT algorithm produces good performance when compared to other proposed existing algorithms.

Cognitive networks are becoming extremely popular in the network domain. This paper proposes a novel concept in cognitive network management and protocol configuration, where any protocol of the TCP/IP protocol reference model can be extended to dynamically tune its configuration parameters based on "immediate past" performance. The approach is focused on inter-node cognitive adaptation which is fostered by the proposed Cognitive Information Service (CIS). Performance evaluation results are obtained for cognitive adaptation of main TCP flow control parameters and show good agreement with design objectives.

In this paper, we introduce a novel queue management technique for the buffer space at the base station of infrastructure 802.11 networks that considers mobile user's receiving characteristics. The maximum amount of the base station buffer that can be used by a given flow is updated proportionally to RTT, measured at the mobile nodes and sent to the base station my the mean of link layer acknowledgements. In this way, the proposed scheme remains transparent to high-level protocols. The proposed approach makes possible the implementation of algorithms able to provide RTT-fairness in wired-cum-wireless networks. Results show the advantage of the proposed queue management scheme when compared to that of traditional drop-tail queue management.

Traffic grooming in wavelength division multiplexing networks merges low-speed flows into large capacity pipes so that the bandwidth discrepancy between them will not lead to underutilization of resources. On-line solutions for dynamic grooming typically involve the construction of an auxiliary graph for deciding on the routing and wavelength assignment. An auxiliary graph can represent the network partially leading to scalable solutions. Previous algorithms based on such type of auxiliary graph produce unfair distribution of resources. This paper introduces a novel algorithm and two of its variants, which are scalable and produce low blocking and fair distribution of resources.

In wavelength division multiplexing (WDM) networks, failures can imply in great loss of data due to high transmission rates, leading to the need of employment of protection mechanisms. Transparency and switching in all-optical networks causes physical impairments, which can significantly degrade the signal quality. If the signal quality in a path is below acceptable values, this path cannot be used by incoming requests for lightpath establishment. Therefore, quality needs to be checked by the routing and wavelength assignment algorithm. This paper introduces two novel algorithms for shared path protection in WDM networks that take into account the PMD, ASE and homowavelength crosstalk physical impairments in path selection. The efficacy of these algorithms are compared to those of their impairment unaware counterpart.

This paper presents a novel channel scheduling discipline for optical burst switching networks called Least Reusable Channel (LRC). LRC decides on which void to allocate an incoming burst based on the potentiality of reusing the voids created. These decisions consider the routes as well as the network load. It is shown via numerical examples that the LRC produces lower blocking probability and distributes more uniformly the losses among routes than existing scheduling disciplines.

Multiscaling traffic in optical burst switching networks yields to considerably higher loss rates than monoscale traffic. The assembly policy at the edge of an OBS network can change the multiscaling characteristic of ingress traffic to monoscaling. The difficulty, however, is the identification of the cut-off scale of multiscaling traffic so that ingress traffic can be aggregated on scales larger than the cut-off one. This paper introduces a method for identifying the cut-off scales as well as proposes and evaluates different assembling policies.

The assignment of wavelengths to lightpaths in WDM networks is a crucial problem that needs to be solved efficiently. However, the coloring of the graph representing the lightpaths and their interference is an NP-hard problem. The parameterized Complexity Theory offers an attractive theoretical framework for the derivation of exact solutions with lower complexity than those derived using the Classical Complexity Theory since it transfers the exponentiality dependence from the input parameters describing the network to a parameter called modulator which can be bounded. This paper presents an algorithm for wavelength assignment in transparent WDM networks. Numerical examples illustrate the benefits of the employment of this new theory for the solution of the wavelength assignment problem.

This paper introduces the HSTCP-H2 AQM controller, an optimal AQM controller for networks which employ the HSTCP protocol as their transport protocol. The synthesis of the controller uses a non-rational approach, in which stability and performance objectives are completely expressed as Linear Matrix Inequalities (LMIs). Results, derived via simulation, show the advantages of adopting HSTCP-H2 rather than RED in high capacity networks.

The assured forwarding per hop behavior of the differentiated services architecture (DiffServ) was proposed to provide throughput differentiation in the Internet. In this paper, we use a non-rational approach to develop an optimal AQM controller for this PHB. The design considers both adaptative and non-adaptative traffic. Simulations show that the proposed controller produces goodput per connection higher than those produced by existing proposals.

In order to support real-time and bandwidth demanding applications the IEEE 802.16 standard is expected to provide quality of service (QoS). Although the standard defines a QoS signaling framework and four service levels, scheduling mechanisms for this network are unspecified. In this paper, we propose a scheduling discipline for uplink traffic. Simulation results show that our scheme is capable to provide QoS. Moreover it shares fairly the resources among connections of the same service type.

We propose a novel policy called proportional sharing with load reservation (PSLR) for scheduling upstream flows in Ethernet passive optical networks. This policy provides bandwidth guarantees on a per flow basis and redistributes the unused bandwidth among active flows in proportion to their priority level.

This paper introduces a procedure called traffic engineering for grids for enabling grid networks to self-adjust to resource availability. The proposal is based on monitoring the state of resources and on task migration. It involves several layers of the Internet architecture. Experiments executed in NS-2 are used to illustrate the efficacy of the procedure proposed.

This paper introduces a traffic model for UDP streams. The model was derived after characterization of the marginal distributions existing in traces of UDP flows. The model has four states and it reproduces the multiscaling characteristics of UDP streams. The efficacy of the proposed model is verified comparing it to the ones of existing models.

This paper presents the design and validation of an WiMAX module based on the IEEE 802.16 standard. The module, which was implemented, includes mechanisms for bandwidth request and allocation, as well as for QoS provision. Moreover, the implementation is standard-compliant.

Although peer-to-peer networks are more scalable than client-server ones, they face efficiency challenges. One of them is the selfish behavior of non-cooperative peers. Another challenge is the short time peers stay connected to the system, which causes disruptions of the delivery of time-constrained content. This paper introduces an incentive mechanism to address both problems in peer-to-peer networks with live streaming.

Access fairness protocols for optical packet- switched ring networks can jeopardize the fairness promoted by the transmission control protocol (TCP), the transport protocol currently responsible for carrying most of Internet traffic. This paper presents the ring virtual queue (RVQ) protocol, a simple and adaptive access fairness protocol for optical packet-switched rings that is capable of providing TCP connections with high goodput and degree of fairness without requiring any information about the state of the TCP connections.

Periodic broadcast has been considered for the deployment of video on demand services due to its scalability. However, most of the protocols proposed so far do not take into consideration the existing bandwidth limitation at the client. In this paper, a technique for designing protocols for limited- bandwidth clients is presented. Moreover, a novel protocol based on the greedy equal-bandwidth broadcasting protocol for users with bandwidth constrains is introduced.

The IEEE 802.11e standard is intended to support applications with QoS requirements. However, such provisioning cannot be achieved when the network load is high. This paper introduces a new control mechanism which dynamically tunes the parameters of the 802.11e contention-based access method. The proposed mechanism aims at providing QoS as well as ameliorating the problem of delay asymmetry.

The ability to cope with dynamic bandwidth demands will be a particularly important asset for Quality of Service provisioning in networks carrying bandwidth hungry applications. This paper introduces a novel approach based on multi-objective optimization with fuzzy constraints for dynamic bandwidth allocation. This new approach deals with uncertain bandwidth demands more efficiently than an approach based on Classical Optimization Theory and yet supports Quality of Service commitments.

Ingress nodes of Optical Burst Switching (OBS) networks are responsible for assembling burst out of incoming packets and to forward these bursts into the OBS network. The most common criteria for burst assembly are based either on time or on traffic volume. The change of the statistical characteristics of a traffic stream at an ingress switch can affect the quality of service provisioning. Therefore, the statistical characteristics of the output flow of an ingress node need to be known for appropriate network dimensioning and service provisioning. This paper evaluates the impact of burst assembly mechanisms on the scaling properties of multifractal traffic flows. It is showed that the most relevant factor that determines the nature of the output traffic flow is the relationship between the cut-off time scale of the input traffic and the time scale of assembly threshold.

Admission control is a fundamental mechanism for the provisioning of quality of services in multiservice networks. The control of multi-scaling traffic demands specially designed mechanism given its highly bursty nature, especially at small time scales. In this paper, a greedy policy for the admission control of multi-scaling traffic is introduced. This policy accepts flows into the network according to a decreasing order of revenue. It is shown that results produced by this new policy are close to the one produced by an optimum policy.

Packet-switched ring networks usually employ destination removal to exploit spatial reuse and, hence, to achieve high performance. By promoting spatial reuse, destination removal may lead to unfair access to the medium and, consequently, to unbalanced use of resources and even to node starvation. This paper introduces LCR-SD, a novel access fairness protocol for high-performance packet ring networks. LCR-SD promotes throughput fairness among flows, and it is simple and adaptive to dynamic changes in traffic patterns. This paper also analyzes the performance of LCR-SD and its impact on TCP fairness.

The paper presents integrated mechanisms for differentiated service (DiffServ) architecture consisting of active rate management (ARM) at the edges of the network and two-color active queue management (AQM) controllers at the core of the network. The AQM controller is a robust linear quadratic regulator based proportional-integral-derivative controller for two-color marking at the core. The proposed mechanism is for DiffServ assured forwarding per hop behavior for guaranteeing minimum rates for exact and over-provisioned systems. The performance of the proposed scheme is evaluated and compared with other approaches using the NS-2 simulator.

This paper proposes an access fairness protocol for optical packet-switched wavelength division multiplexing ring networks that employ destination removal for high-performance. The protocol aims at throughput fairness, and it combines cyclic reservations with transmission credit allocations to meet the demands of the nodes and adapt to changes in traffic characteristics dynamically and efficiently.

The need to reduce the huge bandwidth demand of video-on-demand (VoD) services has led to the conception of both multicast and broadcast based techniques for the deployment of such services on a large scale. Interactivity, a desirable feature for video services, includes the capacity to perform VCR operations. However, whenever a viewer requests the performance of a VCR operation, his/her video stream becomes unsynchronized with that of his/her multicast group, and a new channel must be allocated for the performance of this operation. The present paper introduces a novel approach for determining the number of video channels needed to support such interactivity. Moreover, it investigates the performance of interactive systems with a pool of channels reserved for the support of VCR operations. Systems with both batching and piggybacking are analyzed. Results indicate that for a medium to high number of users performing VCR operations the number of channels required to achieve target levels of quality-of-service is lower for systems with no pool of reserved channels than it is for systems with such a pool.

This paper investigates the impact of design goals of optimal active queue management controllers on the performance of AQM queues. Simulation results indicate that the fast reach of the ideal throughput and bandwidth guarantee both in conjunction with jitter minimization are the most appropriate design goals for Web traffic and for FTP traffic, respectively.

Minimum interference routing is instrumental to MPLS traffic engineering under realistic assumptions of unknown traffic demand. This work presents a new algorithm for minimum interference routing, called light minimum interference routing (LMIR). This algorithm introduces a new approach for critical link identification that reduces the computational complexity. Results, derived via simulation, show that LMIR is precise and has indeed a low computational complexity.

This work evaluates the use of Limited Transmit in conjunction with TCP Reno, TCP NewReno and TCP SACK under an optimal AQM controller for both FTP and Web traffic. Moreover, a novel optimal AQM-controller is presented.

This paper introduces a novel AQM optimal controller. The synthesis of the controller uses a non-rational approach, in which stability and performance objectives of the system are completely expressed as linear matrix inequalities (LMIs). The controller stabilizes the system under diverse network conditions. Simulation experiments using the NS network simulator were conducted. Results indicate a clear advantage of the proposed controller when compared to existing ones.

This paper introduces the computation of an expression for the time at which the length of a queue fed by several multifractal flows reaches its maximum. Expressions for the equivalent bandwidth of an aggregate of multifractal flows are also presented. Moreover, it is shown that modelling based on monofractal process rather than based on multifractal processes leads to overprovisioning of resources.

In this paper, a novel envelope process for multifractal traffic modeling is introduced. The envelope process is an upper bound for the amount of work arrived in a multifractal Brownian motion process. The time scale of interest of a queueing system fed by a multifractal stream is computed. Simulation experiments using both real and synthetic data show that the proposed model is accurate.

This paper introduces a novel policing mechanism, called packet leaky bucket, which marks all cells of a frame with the same level of priority. Moreover, it discusses the need for having frame discard mechanisms in ATM networks when frame-oriented policing mechanisms are used.

This paper compares TCP loss recovery mechanisms that were proposed by the IETF to overcome TCP Reno lack of ability to recover efficiently from multiple losses in a single transmission window. The TCP extensions: NewReno, SACK and limited transmit, are compared under different traffic scenarios.

In this paper, an envelope process called fractional bounded arrival process (FBAP) is proposed fro self-similar traffic representation. The queuing analysis for FBAP traffic is developed, and upper bounds for the backlog and for the delay are obtained. Finally, the use of the leaky bucket algorithm for policing FBAP traffic is investigated.

A procedure for resource allocation method in switchlet networks is introduced. The procedure is based on restricting the search space for the solution of a multicommodity flow problem. The proposed approach is accurate, and amenable to real time implementation.

It has been proved that it is possible to guarantee delay bounds in a generalized processor sharing (GPS) server when traffic is regulated by the leaky bucket algorithm. However, the leaky bucket is not an appropriate regulator for long-range dependent (LRD) traffic. This paper introduces the computation of backlog and delay bounds for a GPS server under LRD traffic. Traffic is assumed to be regulated by the fractal leaky bucket, which is proved to be an effective policing mechanism for LRD traffic.

This paper investigates the joint use of push-out mechanisms with random early detection (RED)-like discarding policies to support service differentiation in the Internet. The efficiency and the degree of differentiation of a complete sharing with push-out, a RIO (RED with in/out) and a RIO with push-out queues are assessed. Results indicate that push-out used jointly with RED-like policies does not improve the performance.

This paper introduces the computation of end-to-end delay and backlog bounds in a network of generalized processor sharing (GPS) servers with long-range dependent traffic. The traffic is supposed to be regulated by the fractal leaky bucket, which is an appropriate regulator for such traffic. The network of GPS servers has arbitrary topology and the stability of these networks is analysed.

This paper introduces a new batching policy, called look-ahead-maximize-batch (LAMB), for reducing the bandwidth demand of video servers. LAMB maximizes the number of users admitted in a window, which includes the reneging time of all pending requests at that scheduling time. LAMB admits a greater number of users than other existing batching policies. Furthermore, the benefits of integrating batching and piggybacking is analyzed.

To ameliorate the problem of long download times experienced by World Wide Web users, as well as to reduce the ever-increasing bandwidth demand of WWW services, Web caches tend to be placed close to the users. The management policies of these caches are intimately related to the perceived quality of service (QoS). This paper investigates the relevance of download time as a key in Web cache management policies, as well as analyses QoS-oriented Web cache removal and admission control policies. The tradeoff between furnishing QoS and optimizing Web cache performance is studied.

To reduce the huge bandwidth demand of video-on-demand, techniques based on multicast have been considered for the deployment of such services on a large scale. Interactiveness, a desirable feature of video services, encompasses the capability of performing VCR operations. Whenever a viewer issues a VCR operation, his/her video stream unsynchronizes with the stream of his/her multicast group. This paper introduces an approach to determine the number of video channels needed to support interactiveness. Moreover, the performance of interactive systems with reserved pool of channels for the support of VCR operations, as well systems with batching and piggybacking are analysed.

The integration of batching and piggybacking in video servers subject to high loads is investigated. The look-ahead-maximize-batch batching policy and the odd-even and simple merge piggybacking policies are used in this investigation. It is shown that a video server with both batching and piggybacking may accept up to 20% more users than a server with batching only.

A simple way to derive the equivalent bandwidth of an aggregate of heterogeneous self-similar sources is introduced. We show an envelope process for the fractal Brownian motion (fBm) process, and we investigate the time scale of interest of queuing systems fed by an fBm process. Based on the time scale, performance metrics can be computed with little computational effort and with the same accuracy of results predicted by the large deviation theory.

In this paper, we study distributed home theatre, a video service which allows distributed users to debate a film. We investigate the interplay between bandwidth reduction and program replication techniques. We evaluate the impact of user distribution, network topology and number of users per session on this interplay. Moreover, we state a bandwidth minimization principle which can be used in admission control policies.

In this paper, we introduce a procedure for modelling the output process of a finite discrete time queue with selective discard mechanism loaded with a prioritized discrete-time batch Markovian arrival process in which the priority level of a cell depends on the priority level of other cells in the flow. We show through numerical examples that this procedure is reasonably accurate. Moreover, we introduce a framework for the analysis of queueing networks with D-BMAP/sup [H,L]/ flows.