The complexity of modern networks, combined with business requirements and human oversight, presents significant management challenges. This thesis focuses on developing a holistic management system, Emergence, which integrates intent-based networking, large language models (LLMs), and policy-driven automation through closed control loops. Our contributions are: 1) Formalizing intents into a hierarchy of policies at various abstraction levels; 2) Intelligent and automated intent-to-policy decomposition using generic pre-trained LLMs, resulting in a Policy Tree—an ordered set of Monitor-Analyze-Plan-Execute (MAPE-K) policies; 3) Automated and scalable intent deployment through control loops and Finite State Machines for policy execution; 4) Monitoring and mitigating intent drift using LLMs and additional tools to assure intents in response to changing conditions. Our solution provides a robust, scalable, and intelligent system for modern network management, fulfilling and assuring intents 1-3x faster on average compared to manual procedures. Moreover, the policy-based approach enhances explainability and control over management decisions and actions. Lastly, we share future directions towards trustworthiness.

Intent-Based Management provides a shift in network management by automating the alignment of network operations with business objectives. However, primary challenges include: 1) intent processing (translate, decompose and identify the logic to fulfill the intent), and 2) ensuring intent conformance (ongoing adaptation of the logic to ensure the intent is met, considering dynamic conditions). We use a 3-tier Large Language Model (LLM) pipeline to convert intents into Policy Trees, that are then executed using closed control loop automation. In this paper, we focus on assurance that is tasked with continuous monitoring, verification, and validation of the operational state, and corrective actions to ensure conformance with the target objectives. To do so, we use a generic LLM (OpenAI's GPT) with in-context learning and well-established decision-making algorithms (feedback controllers) to determine assurance actions and remediate intent deviation. We show that AI-driven policies can support intent fulfillment and assurance, and we discuss current limitations, benefits, and future directions to address critical challenges in using AI for network management, towards improved generalizability, scalability, and overall trustworthiness.

The proliferation of Virtual and Augmented Reality (VR/AR) and the Internet of Things (IoT) applications is driving the demand for efficient Deep Neural Network (DNN) inference at the edge. These applications often impose stringent Service Level Objectives (SLOs), such as latency or accuracy, that must be met under the constraints of limited resources and dynamic network conditions. In this study, we explore a novel approach to DNN inference across multiple edge devices, incorporating both model customization and partitioning dynamically, to better align with these constraints and SLOs. Unlike conventional methods that employ a single fixed DNN network, our system, termed Murmuration, combines one-shot Neural Architecture Search (NAS) and Reinforcement Learning (RL) to dynamically customize and partition DNN models. This approach adapts in real-time to the capabilities of the edge devices, network conditions, and varying SLO requirements. The design of Murmuration allows it to effectively navigate the large search space defined by DNN models, network delays, and bandwidth, offering a significant improvement in managing trade-offs between accuracy and latency.

Intent-Based Networking (IBN) presents a paradigm shift for network management, by promising to align intents and business objectives with network operations–in an automated manner. However, its practical realization is challenging: 1) processing intents, i.e., translate, decompose and identify the logic to fulfill the intent, and 2) intent conformance, that is, considering dynamic networks, the logic should be adequately adapted to assure intents. To address the latter, intent assurance is tasked with continuous verification and validation, including taking the necessary actions to align the operational and target states. In this paper, we define an assurance framework that allows us to detect and act when intent drift occurs. To do so, we leverage AI-driven policies, generated by Large Language Models (LLMs) which can quickly learn the necessary in-context requirements, and assist with the fulfillment and assurance of intents.

In today’s scientific landscape, Directed Acyclic Graphs (DAGs) are pivotal for representing task dependencies in data-intensive applications. Traditionally, two dominant bottom-up DAG scheduling approaches exist: one overlooks communication contention and the other fails to exploit parallelization for improving latency. This study distinguishes itself by advocating a top-down approach prioritizing latency or cost optimization in multi-tier environments to fulfill QoS and SLA requirements. Our strategy effectively mitigates bandwidth contention and facilitates parallel executions, leading to substantial completion time reductions. Our findings suggest that myopic knowledge-based scheduling, emphasizing latency or cost minimization, can yield benefits comparable to its look-ahead counterparts. Through latency-efficient and cost-efficient topological sorting, ourwDAGSplitstrategy introduces a two-stage partitioning and scheduling approach. Its simplicity and adaptability extend its usability to DAGs of any scale. Evaluated on over 100,000 real-world DAG applications,wDAGSplitdemonstrates latency enhancements of up to 80x compared to Edge-only scenarios, 15x to Near-Edge-only, and 6x to Cloud-only. In terms of cost, our approach achieves enhancements of up to 60x compared to Edge-only scenarios, 250x to NE-only, and 70x to Cloud-only. Moreover, for DAGs with 50 tasks, we achieve 5x reduced latency compared to previous approaches, along with a complexity reduction of up to 24 times.

There is an ever-urgent need for accessing real-time crowdedness and airflow information for indoor study spaces in universities, for example, to control COVID-19 transmission risk. Even before the pandemic, many students spent valuable time finding suitable study areas with proper lighting, low noise, and ample seating. This paper presents a pilot system, CampusX, which aims to provide students with useful real-time information about study spaces on campus. Our system collects and analyzes environmental data before presenting them to students as useful information. This helps them to select the most suitable study spaces. The main components of this system include a sensor platform, data collection and processing pipelines, networking, and an interactive web-application.

Automated management requires decomposing high-level user requests, such as intents, to an abstraction that the system can understand and execute. This is challenging because even a simple intent requires performing a number of ordered steps. And the task of identifying and adapting these steps (as conditions change) requires a decomposition approach that cannot be exactly pre-defined beforehand. To tackle these challenges and support automated intent decomposition and execution, we explore the few-shot capability of Large Language Models (LLMs). We propose a pipeline that progressively decomposes intents by generating the required actions using a policy-based abstraction. This allows us to automate the policy execution by creating a closed control loop for the intent deployment. To do so, we generate and map the policies to APIs and form application management loops that perform the necessary monitoring, analysis, planning and execution. We evaluate our proposal with a use-case to fulfill and assure an application service chain of virtual network functions. Using our approach, we can generalize and generate the necessary steps to realize intents, thereby enabling intent automation for application management.

Data exchange in information systems that span multiple policy domains typically rely on network middleware that can abstract the management of underlying heterogeneous communication protocols. This also involves issues in managing interoperability, scalability, and privacy that arise in the movement of data from one domain to another information domain. The Data Fabric is an emerging approach to systematically build and design such middleware systems to support multi-domain exchange at scale. In this paper, we discuss and compare two key data-centric approaches: 1) application layer topic-based messaging and name-based networking in a multi-cloud environment. We implement and deploy these two approaches (using Kafka and NDN) and we compare the performance in terms of object transfer latency and CPU and memory utilization. We find that NDN networking has superior latency performance and lower resource usage. We believe that this advantage derives from the fact that named-based messaging operates at the network level, while topic-based messaging operates at the application level.

Managing complex infrastructures in multi-domain settings is time-consuming and error-prone. Intent-based infrastructure management is a means to simplify management by allowing users to specify intents, i.e., high-level statements in natural language, that are automatically realized by the system. However, providing intent-based multi-domain infrastructure management poses a number of challenges: 1) intent translation; 2) plan execution and parallelization; 3) incompatible cross-domain abstractions. To tackle these challenges, we propose AppleSeed, an intent-based infrastructure management system that enables an end-to-end intent-to-deployment pipeline. AppleSeed uses few-shot learning for training a Large Language Model (LLM) to translate intents into intermediate programs, which are processed by a just-in-time compiler and a materialization module to automatically generate parallelizable, domain-specific executable programs. We evaluate the system in two use cases: Deep Packet Inspection (DPI); and machine learning training and inferencing. Our system achieves efficient intent translation into an execution plan with an average 22.3x lines of code to intent word ratio. It also speeds up the execution of the management plan by 1.7-2.6 times with our JIT compilation for parallelized execution compared to sequential execution.

Information-Centric Networking (ICN) is a class of Future Internet protocols that can empower and protect networks by using names rather than addresses to identify data and move packets. This capability allows ICN architectures to build networks that are secure by design and that can better handle the addressing, mobility, and multicasting challenges of managing network flows in dynamic computing environments in contrast to IP. For these reasons, ICN can benefit communications in Software-Defined Infrastructures (i.e., SDIs) by increasing the potential and flexibility to meet emerging and dynamic applications requirements. SDIs provide a unified view towards the management of hardware, storage, and networking resources in a distributed computing environment that are becoming typical of the infrastructures that serve applications at Internet scale. SDIs intrinsically are able to handle the networking challenges to extend to more application areas, to lower operational costs, and to enable enhanced user experience. In this paper, we introduce a proposal to create an ICN-enabled SDI environment using the SAVI testbed. We evaluate the benefits of ICN in our SDI environment by measuring key performance indicators in a use case scenario. Our analyses show promise for ICN to improve latency and the handling of multicasting in SDI networks.

End-to-end delay is a critical attribute of quality of service (QoS) in application domains such as cloud computing and computer networks. This metric is particularly important in tandem service systems, where the end-to-end service is provided through a chain of services. Service-rate control is a common mechanism for providing QoS guarantees in service systems. In this paper, we introduce a reinforcement learning-based (RL-based) service-rate controller that provides probabilistic upper-bounds on the end-to-end delay of the system, while preventing the overuse of service resources. In order to have a general framework, we use queueing theory to model the service systems. However, we adopt an RL-based approach to avoid the limitations of queueing-theoretic methods. In particular, we use Deep Deterministic Policy Gradient (DDPG) to learn the service rates (action) as a function of the queue lengths (state) in tandem service systems. In contrast to existing RL-based methods that quantify their performance by the achieved overall reward, which could be hard to interpret or even misleading, our proposed controller provides explicit probabilistic guarantees on the end-to-end delay of the system. The evaluations are presented for a tandem queueing system with non-exponential inter-arrival and service times, the results of which validate our controller's capability in meeting QoS constraints.

Web-based management dashboards provide intuitive interfaces to support various infrastructure management tasks. However, the lack of programmability in these dashboards makes it difficult to automate management tasks. To address this limitation, we propose a system call MAIL (Management Automation through Imitation Learning) that learns from an operator's demonstrations using imitation learning to automate management tasks on web-based dashboards. A novel Contextual Imitation Learning algorithm is proposed in MAIL to overcome the learning challenges brought by the requirements of infrastructure management automation. The effectiveness of the MAIL system has been demonstrated using both synthetic environments and production environments. It outperforms existing methods and is able to achieve an 86%-100% success rate for most tasks.

Summary form only given. In the world of telecommunications, there is greater focus on using Virtual Network Functions (VNFs) managed by Software Defined Networking (SDN). VNFs are tradition-ally implemented as software functions, but as technology evolves and application demands dramatically increase, the high performance and low latency of FPGAs make them more suited for use in VNF implementations. We propose FFIVE, a framework for the creation of FPGA-based VNF containers that can be deployed and man-aged in the same way as software-based VNF containers, but with improved bandwidth, efficiency, and latency. Our framework offers an approach for the virtualization of FPGA devices, the deployment of FPGA-based Virtual Network Functions (VNFs), and configuring the VNFs.

Software defined networking (SDN) is a promising technology in fifth generation wireless networks (5G) where due to the adoption of a centralized SDN-controller, resources such as processing and storage, can be utilized in an optimal manner. Although SDN was first considered with a logically centralized controller, due to delay, reliability, and scalability challenges, moving towards multiple distributed controllers is inevitable. In distributed control schemes, an assignment that associates a controller with each switch leads to three challenges of (1) Computational complexity, since the assignment is an NP-hard problem, (2) Resource and energy efficiency, to obtain an assignment with the lowest number of controllers in order to reduce resource and energy consumption, and (3) Dynamicity, where a dynamic approach of assignment is required to adapt to the network’s traffic changes. In this paper, we investigate the controller-switch assignment problem given the aforementioned challenges, and propose efficient algorithms for static and dynamic scenarios, that even achieve quantitative optimality guarantees in special cases. As shown through simulations, the proposed lower complexity algorithms not only outperform earlier works but also approach the performance of exhaustive search schemes, in some scenarios.

Ensuring quality of service (QoS) guarantees in service systems is a challenging task, particularly when the system is composed of more fine-grained services, such as service function chains. An important QoS metric in service systems is the end-to-end delay, which becomes even more important in delay-sensitive applications, where the jobs must be completed within a time deadline. Admission control is one way of providing end-to-end delay guarantee, where the controller accepts a job only if it has a high probability of meeting the deadline. In this paper, we propose a reinforcement learning-based admission controller that guarantees a probabilistic upper-bound on the end-to-end delay of the service system, while minimizes the probability of unnecessary rejections. Our controller only uses the queue length information of the network and requires no knowledge about the network topology or system parameters. Since long-term performance metrics are of great importance in service systems, we take an average-reward reinforcement learning approach, which is well suited to infinite horizon problems. Our evaluations verify that the proposed RL-based admission controller is capable of providing probabilistic bounds on the end-to-end delay of the network, without using system model information.

End-to-end network slicing is a promising concept based on softwarization and virtualization, leading the way towards efficiently achieving the network and operational key performance indicators (KPIs) for future wireless systems that comprise softwarized network functions. It leverages the underlying physical infrastructure to create and orchestrate agile and programmable network functions which satisfy the end-to-end user demands. These features are crucial during situations in which sudden demand surges stress the wireless system. Proper network orchestration can provide the necessary and timely adaptability to offer sustained communication between end-users. This paper addresses the design and implementation of an end-to-end network slicing framework specifically designed to provide orchestration tools for softwarized network functions, in order to fulfill the system requirements for surge events such as flash crowds. The conducted performance evaluations demonstrate the applicability of this approach and validate the proof-of-concept implementation.

Many modern day cloud services are composites of multiple smaller services working correctly together. This design has become increasingly prevalent due to the rise of the microservices application architecture, as well as service chaining in Network Function Virtualization (NFV). Future composite applications and services will be deployed on multi-tier clouds where their constituent microservices may be geographically spread over different regions. To optimize the delivery of such composites, the constituent microservices must be placed in locations where their clients, which may be other microservices, are able to meet certain QoS constraints. We propose an architecture and present a prototype system for incorporating network metrics into the auto-scaling and scheduling decisions of cloud management systems. Given a service with QoS constraints, our system monitors the network metrics (e.g. latency and bandwidth) of their clients. If a particular client is unable to receive the required latency or bandwidth of the service, our system auto-scales the service and strategically places the new instance(s) in a location capable of meeting the service quality, and re-directs traffic to the new instance.

Ensuring the conformance of a service system's end-to-end delay to service level agreement (SLA) constraints is a challenging task that requires statistical measures beyond the average delay. In this paper, we study the real-time prediction of the end-to-end delay distribution in systems with composite services such as service function chains. In order to have a general framework, we use queueing theory to model service systems, while also adopting a statistical learning approach to avoid the limitations of queueing-theoretic methods such as stationarity assumptions or other approximations that are often used to make the analysis mathematically tractable. Specifically, we use deep mixture density networks (MDN) to predict the end-to-end distribution of the delay given the network's state. As a result, our method is sufficiently general to be applied in different contexts and applications. Our evaluations show a good match between the learned distributions and the simulations, which suggest that the proposed method is a good candidate for providing probabilistic bounds on the end-to-end delay of more complex systems where simulations or theoretical methods are not applicable.

Missing data is a challenge in many applications, including intelligent transportation systems (ITS). In this paper, we study traffic speed and travel time estimations in ITS, where portions of collected data are missing due to sensor instability and communication errors at collection points. These practical issues can be remediated by missing data analysis, which are mainly categorized as either statistical or machine learning (ML)-based approaches. Statistical methods require the priori probability distribution of the data which is unknown in our application. Therefore, we focus on an ML-based approach, Multi-Directional Recurrent Neural Network (M-RNN). M-RNN utilizes both temporal and spatial characteristics of the data. We evaluate the effectiveness of this approach on a TomTom dataset containing spatio-temporal measurements of average vehicle speed and travel time in the Greater Toronto Area (GTA). We evaluate the method under various conditions, where the results demonstrate that M-RNN outperforms existing solutions, e.g., spline interpolation and matrix completion, by up to 58% decreases in Root Mean Square Error (RMSE).

In this paper, we study a general transactive energy (TE) retailing problem in smart grids: a TE retailer (e.g., a utility company) publishes the energy price, which may vary over time. TE customers arrive in an arbitrary manner and may choose to either purchase a certain amount of energy based on the posted price, or leave without buying. Typical examples of such a setup include a transactive electric vehicle charging platform, or a general market-based demand-side management program, etc. We consider the setting where the customer arrival information is unknown (i.e., without prediction), and focus on maximizing the social welfare of the TE system through a posted-price mechanism (PPM) that runs in an online fashion with causal information only. We quantify the performance of the proposed PPM in the competitive analysis framework, and show that our proposed PPM is optimal in the sense that no other online mechanisms can achieve a better competitive ratio. We evaluate our theoretic results for the case of transactive electric vehicle charging. Our extensive experimental results show that the proposed PPM is competitive and robust against system uncertainties, and outperforms several existing benchmarks.

We study a general online combinatorial auction problem in algorithmic mechanism design. A provider allocates multiple types of capacity-limited resources to customers that arrive in a sequential and arbitrary manner. Each customer has a private valuation function on bundles of resources that she can purchase (e.g., a combination of different resources such as CPU and RAM in cloud computing). The provider charges payment from customers who purchase a bundle of resources and incurs an increasing supply cost with respect to the totality of resources allocated. The goal is to maximize the social welfare, namely, the total valuation of customers for their purchased bundles, minus the total supply cost of the provider for all the resources that have been allocated. We adopt the competitive analysis framework and provide posted-price mechanisms with optimal competitive ratios. Our pricing mechanism is optimal in the sense that no other online algorithms can achieve a better competitive ratio. We validate the theoretic results via empirical studies of online resource allocation in cloud computing. Our numerical results demonstrate that the proposed pricing mechanism is competitive and robust against system uncertainties and outperforms existing benchmarks.

Motivated by interest in providing more efficient services in customer service systems, we use statistical learning methods and delay history information to predict the conditional distribution of the customers' waiting times in queueing systems. From the predicted distributions, descriptive statistics of the system such as mean, variance and percentiles of the waiting times can be obtained, which can be used for delay announcements, SLA conformance and better system management. We model the distributions by mixtures of Gaussians, parameters of which can be estimated using Mixture Density Networks. We use the extensions of the Lindley's equation for multi-server queues to generate our datasets. The evaluations show that exploiting more delay history information can result in much more accurate predictions under realistic time-varying arrival assumptions.

In smart grid, some attackers manage to get their false price data and malicious disconnect commands to pass authentications on smart meters by stealing legal credentials. Against those threats, we propose the detection mechanisms based on context analyses. Specifically, we analyze the communication scenarios of true price data and normal disconnect command and investigate the attack scenarios. We also formalize the contexts for that true data and command as well as the attack contexts. We further design the detection unit with specific requirements and propose the detection algorithms respectively against false price data and malicious disconnect command, of which both are with legal credentials. We evaluate the detection mechanisms by selecting evaluation parameters through simulation procedures. Simulation results demonstrate how the parameters affect the detection accuracy and we suggest improvement measures to increase the detection accuracy.

The SAVI testbed is a multi-tier SDN-enabled heterogeneous cloud created as an application enablement platform for academic research. It was developed to investigate the hypothesis that the entire infrastructure can be virtualized and abstracted as a service. Key to this investigation was the creation of a resource management system based on the concept of Software-Defined Infrastructure (SDI), which enables integrated control and management over heterogeneous resources and exposes a programmable interface for users. In this paper, we present our experiences in designing and deploying the Canadian national SAVI testbed, and discuss the various lessons learned along the way. In addition, we describe our ongoing work to enhance the testbed management system to meet the demands and challenges of the IoT era.

Internet of Energy (IoE) is a subset of the Internet of Things which covers all aspects of electrical energy systems and provides secure connectivity and interoperability between power grid and Internet. In this paper, we present a fog-based IoE architecture for transactive energy (TE) management systems. The proposed design consists of three different layers. In the first tier, home gateways are employed which collect customers energy consumption data and provide necessary interface between customers and power grid. In the second layer, there are some local fog nodes located at the network edge and provide services with low latency. From the TE system point of view, the fog node act as retail energy market server which provides energy services to the end users. In the third layer, cloud servers are utilized to provide permanent and reliable data storage and high computing power. The proposed architecture supports different communication protocols such as hypertext transfer protocol, constrained application protocol, and OpenADR. We calculate the required bandwidth and delay performance of both fog- and cloud-based models. We present an optimal day ahead energy consumption schedule and an intercustomer energy trading mechanism for exchanging energy between end users. The performance of the proposed architecture is evaluated in terms of different power grid and communication network metrics. Results confirm the superiority of the proposed architecture.

The advanced metering infrastructure (AMI) is one of the main services of smart grid (SG), which collects data from smart meters (SMs) and sends them to utility company meter data management systems (MDMSs) via a communication network. In the next generation AMI, both the number of SMs and the meter sampling frequency will dramatically increase, thus creating a huge traffic load which should be efficiently routed and balanced across the communication network and MDMSs. This paper initially formulates the global load-balanced routing problem in the AMI communication network as an integer linear programming model, which is NP-hard. Then, to overcome this drawback, it is decomposed into two subproblems and a novel software defined network-based AMI communication network is proposed called OpenAMI. This paper also extends the OpenAMI for the cloud computing environment in which some virtual MDMSs are available. OpenAMI is implemented on a real test bed, which includes Open vSwitch, Floodlight controller, and OpenStack, and its performance is evaluated by extensive experiments and scenarios. Based on the results, OpenAMI achieves low end-to-end delay and a high delivery ratio by balancing the load on the entire AMI network.

The nineteen articles in this special section focus on energy informatics, a new and emerging nterdisciplinary research field. The main goal is to tackle the future global warming, energy crisis, and climate change challenges by exploiting advanced information and communication (ICT) theories and tools to address energy-related problems. The scope of energy informatics includes the next-generation communications, networking, computing, sensing, and control technologies (e.g., big data, machine learning, 5G, cloud computing, and fog computing); and their applications in the energy sectors (e.g., smart cities, smart grid, electric vehicles, and PV systems).

VoIP is becoming a low-priced and efficient replacement for PSTN in communication industries. With a widely growing adoption rate, session initiation protocol (SIP) is an application layer signaling protocol, standardized by the IETF, for creating, modifying, and terminating VoIP sessions. Generally speaking, SIP routes a call request to its destination by using SIP proxies. With the increasing use of SIP, traditional configurations pose certain drawbacks, such as ineffective routing, un-optimized management of proxy resources (including CPU and memory), and overload conditions. This paper presents OpenSIP to upgrade the SIP network framework with emerging technologies, such as software-defined networking (SDN) and network function virtualization (NFV). SDN provides for management that decouples the data and control planes along with a software-based centralized control that results in effective routing and resource management. Moreover, NFV assists SDN by virtualizing various network devices and functions. However, current SDN elements limit the inspected fields to layer 2-4 headers, whereas SIP routing information resides in the layer-7 header. A benefit of OpenSIP is that it enforces policies on SIP networking that are agnostic to higher layers with the aid of a deep packet inspection engine. Among the benefits of OpenSIP is programmability, cost reduction, unified management, routing, as well as efficient load balancing. This paper implements OpenSIP on a real testbed which includes Open vSwitch and the Floodlight controller. The results show that the proposed architecture has a low overhead and satisfactory performance and, in addition, can take advantage of a flexible scale-out design during application deployment.

The economies of scale afforded by cloud computing has been a driving force behind the rapid development and deployment of new cloud-based network applications and services. With the massive growth of IoT devices, we expect a sharp rise in the volume of traffic seen going to and coming from cloud datacenters, which will continue to grow over the next several years. Network Function Virtualization (NFV) is a recent concept which promises to grant network operators the required flexibility to quickly develop and provision new network functions and services in the cloud. As NFV is agnostic to the computing resource, we foresee scenarios where unconventional resources such as FPGAs and GPUs will be of benefit. To this end, we present an architecture based on Software-Defined Infrastructure (SDI) which offers an abstracted control and management interface over virtualized heterogeneous resources in the cloud. Through a unified set of APIs, this architecture enables both application developers and network operators to dynamically deploy and manage new services in the cloud alongside the underlying network that interconnects them, all in a fully software-defined manner. We demonstrate and evaluate an implementation of our NFV-enablement architecture using the SAVI testbed, a multi-tier and SDN-enabled cloud containing virtualized heterogeneous compute resources.

Intent-Driven Networking is recently gaining interest, with all major SDN control platforms now providing an intent Northbound Interface (NBI) as a high-level abstraction for network management. With these frameworks network operators can conveniently define “what needs to be done”, rather than “how it should be done”. Current IDN frameworks pose two main limitations that affect deployment in production grade and multi-domain networks. They are mainly concerned with a single network domain, and thus enabling end-to-end network intents over a multi-domain and large-scale setup is still a challenge. Furthermore, these frameworks do not consider any differentiation between user intents and provider intents, and a limited set of intent classes are available for both. In this paper we present MD-IDN, which provides an intent framework for the users of multi-domain cloud infrastructures. We first propose a graph-based abstraction model for user-defined intents and a generic intent compilation process. Then, we propose compilation algorithms to achieve scalability in multi-domain networks: First, user-defined intents get processed over an abstracted multi-graph of network domains and their interconnections, and a set of local intents will be generated for each of the involved domains. Afterwards, the local intents will be compiled and installed in local regions in parallel. MD-IDN is deployed as a public service in the SAVI Testbed over more than ten data centers spanning across Canada. In multi-domain environments, our experiments show that MD-IDN outperforms current practices that compile intents over a flat network topology.

We present a framework for creating heterogeneous virtualized network function (VNF) service chains from cloud data center resources. Traditionally, these functions are packaged in software images within a catalog of networking applications that can be loaded onto a virtual machine CPU, and can be offered to users as a service. Our framework combines the best of both software and hardware by allowing users to chain traditional software-based VNFs with hardware-based VNFs that the user provides as an IP to generate a bitstream or a pre-generated VNF as part of a library. To accomplish this, our framework first creates the hardware bitstreams and programs the FPGA VNFs, loads any software VNFs requested, and programs the network to daisy chain the VNFs together. Furthermore, this enables an incremental design flow where the user can start by implementing a chain of VNFs in software and incrementally substitute software VNFs for their hardware counterparts. Our paper investigates two case studies to show the ability to switch between hardware and software VNFs in our framework and to demonstrate the benefit of using hardware VNFs. The first study is signature matching at fixed offsets, similar to matching packet headers. In this case study, the CPU can keep up at line-rate using specialized networking drivers. The second case study involves string matching within a packet, which requires scanning through the entire frame. In this case, the CPU performance drops to approximately 20 percent of the input rate, whereas the FPGA can continue to keep up at line-rate.

With the growing pervasiveness of virtualization technologies, carrier networks are shifting from simple packet delivery platforms to multi-tenant integrated clouds offering fine-grained resource management. The need for interoperability among these autonomous cloud-based service providers has created demand for versatile and extensible exchange points to interconnect the future Internet. A novel SDX (Software Defined Exchange) can address this challenge and help redefine the Internet exchange by leveraging SDN. Current implementations of SDXs have focused on traffic exchange between conventional IP networks and have not been specifically intended for exchange between multi-tenant environments and virtual networks; and they have mostly relied on OpenFlow for network forwarding and functionality. While OpenFlow is the de-facto solution for fine-grained forwarding, it nevertheless provides limited network functionality. In this paper we present HyperExchange, a protocol-agnostic exchange fabric for peering of virtual networks. HyperExchange is designed to provide exchange services between autonomous Infrastructure Providers and their hosted Virtual Networks. As a result, it specifically offers solutions for inter-domain tenant authentication and authorization for network control. By leveraging SDI as the core building architecture, HyperExchange uses SDN to forward and steer traffic in a fine-grained manner and yet relies on NFV to push all network functionalities to standard servers as software-based functions. This solution meets both scalability and extensibility requirements for long-term use. We have deployed a prototype of the HyperExchange between SAVI and GENI testbeds to serve real world exchange experiments.

We demonstrate the peering of virtual networks between the SAVI and GENI testbeds using HyperExchange1, a software-defined exchange fabric. The exchange is deployed between the physical networks of the two testbeds. Specifically, a layer-two WAN including nodes in SAVI testbed is peered with a VLAN in GENI testbed without using encapsulation and overlays. Each of these testbeds has a different logic to create and manage layer-two networks, so this demonstration shows how the HyperExchange is protocol-agnostic and allows tenants to create networks across dissimilar networks.

With the advent of SDN, efforts on network virtualization have accelerated. Many concepts have been developed to enable the coexistence of multiple logical network domains on a shared networking infrastructure while also ensuring isolation between them. In this context, we envision a multi-tenant cloud environment that grants users the ability to dynamically alter the behaviour of the underlying network, thus achieving a truer sense of Infrastructure as a service. In this paper, we propose a method for providing users in multi-tenant cloud environments open APIs for installing custom flows into the network at layer 2 (L2). Our proposed system ensures tenant isolation while detecting possible flow-level conflicts that can lead to tenancy violations and to problems in end-to-end reachability. We prototyped our system on a nationwide testbed environment, which showed that our proposed method reduces flow-level conflict detection time over existing proposals from ms to μs scale.

Auto-scaling is a key challenge and benefit in cloud computing infrastructures where applications are deployed on one or more virtual machines (VMs) to balance efficiency in use against delivered performance. In different scenarios, there may be a need for either horizontal or vertical scaling. Therefore, scaling is an important operation of cloud management systems. One way to enable scaling as an automated service is to use a model to predict the VM's future state as a function of time. However, this method is not completely feasible, because the performance of a VM is so dynamic and depends on many parameters. A simpler approach to enable auto-scaling is to use real-time utilization data of VM's and a set of fixed thresholds to execute scaling when thresholds are crossed. However, this method is prone to false positive decisions. Uses this paper, we propose an adaptive method that uses threshold-based mechanisms to control the auto-scaling process and leverages the accuracy and precision given by threshold-based methods to reduce the number of false positives. We present performance results, comparing the fixed threshold methods with our proposed method. We show that our method frequently correctly triggers scaling process in situations where fixed threshold based measurement methods fail.

Cloudification, softwarization and edge processing are been heavily adopted to design, implement and deploy IoT applications at scale. Building upon our previous initiatives and incorporating the above-mentioned paradigm, we propose and demonstrate a hierarchical, programmable and autonomic IoT platform that deploys highly distributed, manageable and efficient IoT applications in a softwaredefined manner. The platform leverages both cloud microservices and macroservices to support big data, local/edge data processing, high level of programmability and runtime autonomic management.

This paper introduces research that addresses the subjective assessment of Quality of Experience (QoE) during the entire life cycle of a video session. We define a video session life cycle as the time from when a user attempts to initiate playback, until such time that the video ends either from normal video conclusion or through a network-induced failure. We provide a detailed description of our assessment methodology designed to discern whether a user's QoE would be impacted by the presence of failures. To accomphsh this, we carefully select various test conditions to take into consideration the rating scale used, the types of impairments and failures seen by the user, and whether impaired videos are seen together with failed videos in multi-video sessions. The selection and creation of source video sequences are also discussed, as well as the use of between-subjects and within-subjects approaches for running our experiments in a controlled laboratory setting. Statistical analysis was carried out to interpret our experimental results. We compared the results of the between-subjects measures and the results of the within-subjects measures, and concluded that the introduction of a scale with an extended lower bound enabled subjects to more clearly express their dissatisfaction of videos with failures when compared to the traditional ITU 5-point rating scale. In addition, we observed that videos that were simply impaired but concluded normally did not have a statistically significant difference when an extended scale was used.

Demand side management (DSM) is an important application of the future smart grid. DSM programs allow consumers to participate in the operation of the electric grid by reducing or shifting their electricity usage during peak periods. Therefore, in this paper, we propose a two-tier cloud-based DSM to control the residential load of customers equipped with local power generation and storage facilities as auxiliary sources of energy. We consider a power system consisting of multiple regions and equipped with a number of microgrids. In each region, an edge cloud is utilized to find the optimal power consumption schedule for customer appliances in that region. We propose a two-level optimization algorithm with a linear multilevel cost function. At the edge cloud, the power consumption level of local storage and the amount of power being demanded from both local storage facilities and power grid are scheduled by using a bi-level optimization approach. The core cloud then gathers information of the total demand from consumers in different Regions and finds the optimal power consumption schedule for each microgrid in the power system. Simulation results show that the proposed model reduces consumption cost for the customers and improves the power grid in terms of peak load and peak-to-average load ratio.

Quality of Experience (QoE) is a crucial guiding factor for network management of an end-to-end service session. The network provider can control the resources allocated to sessions and in doing so, influence the Technical Quality (TQ), which covers the technical aspects of signal quality during the session. On the other hand, the network provider has no control over the Content Quality (CQ), which pertains to the user's level of interest in a particular video. Together TQ and CQ influence the Overall eXperience (OX) in a session. In this paper, we present results from a user subjective study in which the impact of TQ and CQ on OX was investigated for Over-The-Top (OTT) video sessions from the perspective of a network provider. This perspective places a focus on those elements of QoE that can be controlled by the provider. Various studies have shown that very high interest in a content can strongly influence QoE independent of other factors, so our study uses videos that are neutral with respect to content. We assess the TQ, CQ and OX for video sessions that contain Integrity impairments (in the form of image freezing) and failures in terms of session Accessibility and Retainability. Our findings indicate that TQ and CQ have a strong impact on OX in the presence of impairments, but no failures. On the other hand, TQ is the main determinant of OX when failures are present.

In this demonstration we use a prototype of a Wireless Sensor Node along with a Software Defined Infrastructure to monitor the quality of the air in different classrooms at a University. Specifically, a number of wireless nodes are deployed in different classrooms. Each node has a number of sensors to monitor the air quality in the room. A number of relay nodes forward the data to a vCPE, which delivers the data to a Smart Edge. In the vCPE and the Smart Edge, a monitoring and analytic system, called MonArch, is used for collection, storage and analytic purposes of the monitoring data.

Performing system diagnosis is a critical task in modern datacenters. Investigating individual resource behavior may not be efficient in detecting abnormal behavior in large and complex datacenters. In this paper, we propose a scalable graph based diagnosis framework to detect system anomalies in Software-Defined Infrastructure running in SAVI testbed. We have leveraged Graph Mining and Machine Learning techniques in our approach in order to detect different kinds of anomalies. We have experimentally tested our framework on several use cases: Webserver-Database workload pattern, bandwidth throttling between a pair of VMs, denial-of-service (DoS) attack on a webserver and Spark Job failure. Our framework was able to detect the aforementioned anomalies accurately.

Real-time content delivery (RTCD) systems have become a prominent aspect of telecommunications as evidence by popularity of news-casting, real-time event subscription / publication and live media streaming. Unlike conventional content delivery systems, RTCDs need to deliver processed information to users in real time. This may require the network to handle some of the processing closer to the users to efficiently use the bandwidth consumed by the applications. The combination of Network Function Virtualization (NFV) and service chaining is a promising solution to address this challenge. Our work applies a service chaining algorithm to place NFV modules of an RTCD application in a Software Defined Infrastructure (SDI), where virtualized Customer Premise Edges (vCPEs), possessing scarce resources, are employed. We suggest containers to efficiently pack VNFs into vCPEs. Our objective is to maximize the total number of chains that can be serviced in the RTCD application. To optimally chain the NFV modules, a heuristic algorithm is proposed and evaluated. Using simulations, we show that our algorithm with the help of vCPEs can support higher number of users while providing high-level service quality.

Customer satisfaction is an important factor governing adoption and retention of multimedia products and services, such as Over-The-Top(OTT) video transmission. Quality of Experience involves user-centric evaluation of various services. However, users differ in terms of their ratings of service quality. Some rating differences are due to unreliability (outlier users who are not motivated, or are not sensitive to differences in quality), but others are systematic differences in rating that may reflect different perspectives on quality. In this paper, we explore the use of outlier analysis and clustering as tools for interpreting QoE data. We report on experimental results demonstrating the use of outlier analysis and clustering. In interpreting the clusters, we examine users' opinions on different types of video disruption, and their ability to distinguish the different levels of impairments/failures.

Wireless virtualization is a promising approach to foster innovation and prevent the ossification of wireless networks. Within a virtualized wireless network, multiple network slices, or virtual operators (VO), are co- hosted on the same physical infrastructure. A fundamental question in this environment is which multiplexing technique, TDMA, FDMA or SDMA, should be used to slice the network among the VOs. Another related question is how should the stochastic arrival process affect the slicing and QoS criteria. To answer these two questions, we study the problem of QoS-aware joint admission control and network slicing. Due to the NP- hardness of the problem, we approach it using a heuristic algorithm composed of three steps: spectrum allocation, admission control and spatial multiplexing. The proposed algorithm incorporates the effects of QoS and stochastic traffic. We study through simulations the benefits of joint spatial- frequency multiplexing over the static frequency slicing approach. Finally, our simulation results help shed some light on the trade-offs between frequency and spatial multiplexing as well as between QoS and utilization.

In this paper, we study the relationships between Quality of Service (QoS) and Quality of Experience (QoE) in a session-based Over-The-Top (OTT) video service. A number of Performance Metrics (PMs) with and without the existence of failures during a video are examined. As QoE factors, Technical Quality (TQ) and Acceptability are used. We analyze the correlation between QoS performance metrics and QoE factors, and find new PMs should be employed because failures are included in QoE evaluation. We also summarize the relationships between QoS metrics and QoE factors through machine learning approaches. Using decision tree, we have a general idea about the relationships between PMs and QoE factors. We also understand the impact caused by failures and the value of rating scales.

The software-defined approach of cloud radio access networks (C-RANs) enables supporting multiple virtual operators (VOs) on the same physical infrastructure. In this shared environment, a coordinator is needed to manage the sharing of resources between the VOs. Designing a coordinator is about striking a good balance between the flexibility given to the VOs, and the efficiency of the resource utilization. In this paper, we study the problem of coordinated scheduling in the multi-operator cloud-RAN environment. We formulate the problem as a distributed scheduling performed by the VOs, after which they submit their resource requests to a centralized coordinator. The coordinator selects a subset of non-conflicting requests for transmission. We show that the problem in the general case is NP-hard. We then discuss two special cases and relate them to the existing communication protocols. By gaining insights from these two special cases, we propose a general heuristic, which works on any formulation of the problem, and is still able to provide close-to-optimum performance in the special cases we considered. The heuristic is shown to have some similarities to the neuro-computation techniques such as Hopfield-network. Finally, simulation results are provided to show the efficiency of the proposed algorithms.

Cloud data centers today use visualization technologies to facilitate allocation of physical resources to multiple applications. As cloud data centers continue to grow in scale and complexity, effectively monitoring and identifying system anomalies is becoming a critical problem. Furthermore, due to complex dependencies between system components in a virtualized data center, a single cause of anomaly can typically trigger multiple alarms. Therefore there is also a need to efficiently analyze and identify the causes of the anomalies in a scalable and effective manner, in order to reduce the overhead of diagnosis and troubleshooting performed by the cloud operator. Motivated by these observations, we present a mechanism for automatic anomaly detection and root cause analysis in virtualized cloud data centers. We first use unsupervised learning techniques to identify abnormal system behaviors, and then propose a technique for root cause analysis with consideration to anomaly propagation among system components. Using a real virtualized cloud testbed, we show that our mechanism efficiently identifies system anomalies and accurately determines their causes.

Network function visualization (NFV) has emerged as a promising paradigm in networking, where the hardware-based middleboxes are replaced with software-based virtualized entities typically running on the cloud to provide specific functionalities. By deploying NFV, network services become more adaptive and cost-effective. Many multicast services such as real-time multimedia streaming and intrusion detection require appropriate services chaining; however, NFVs placement in the network as well as traffic routing strategy to guarantee that the multicast flows traverse through the services chain before reaching the end user is still an open problem. In this paper, we present an algorithm to solve this problem.

Cloud Radio Access Networks (C-RAN) promise to leverage cloud computing capabilities for enhancing the quality and coverage of next generation 5G networks. 5G networks shall witness an increasing density of users and access points, very small latencies, more bandwidth resources, and the use of virtualized hardware for baseband processing. Within such an environment, the problem of scheduling the network users across the radio resources might become a bottleneck of the system. In this paper, we study the problem of fully distributed scheduling in C-RAN systems. The idea is that each user's base band processing unit (BBU) tries to guess whether its user should be scheduled or not. First, we focus on the case of maximum throughput scheduling and Rayleigh channels, and provide closed-form expression for the expected effective channel and signal-to-noise ratio (SNR) in the distributed scenario. In order to deal with general channels and schedulers, we adopt the classification techniques from machine learning. We discover an interesting relationship between the fairness of the scheduler, and its ability to be distributed. In particular, schedulers which are more fair are also more prune to prediction errors in the distributed scenario. Finally, we provide simulation results that show that distributed scheduling can provide up to 90% of the performance of the centralized case.

Cloud Radio Access Networks (Cloud-RAN) promise to leverage cloud computing capabilities to enhance the quality and coverage of wireless networks. A dense network of remote radio heads (RRHs) ensures less attenuation at the receiver side. However, two drawbacks are associated with such dense network: the first is the high energy consumption associated with such a large number of RRHs; the second is the interference experienced by the receiver due to close proximity of the transmitters. To address these challenges, we study the problem of joint activation and clustering of RRHs. Since the problem is NP-hard, we provide a two-step algorithm that can find an efficient solution. The first step uses linear-programming relaxation to find a feasible solution. The second step is a greedy approach to improve the utility function through gradual activation-clustering of RRHs. Our simulation results demonstrate the benefit in the joint design of activation and clustering over existing activation only approaches.

Network functions virtualization provides opportunities to design, deploy, and manage networking services. It utilizes cloud computing virtualization services that run on high-volume servers, switches, and storage hardware to virtualize network functions. Virtualization techniques can be used in IP multimedia subsystem (IMS) cloud computing to develop different networking functions (e.g., load balancing and call admission control). IMS network signaling happens through session initiation protocol (SIP). An open issue is the control of overload that occurs when an SIP server lacks sufficient CPU and memory resources to process all messages. This paper proposes a virtual load balanced call admission controller (VLB-CAC) for the cloud-hosted SIP servers. VLB-CAC determines the optimal “call admission rates” and “signaling paths” for admitted calls along with the optimal allocation of CPU and memory resources of the SIP servers. This optimal solution is derived through a new linear programming model. This model requires some critical information of SIP servers as input. Further, VLB-CAC is equipped with an autoscaler to overcome resource limitations. The proposed scheme is implemented in smart applications on virtual infrastructure (SAVI) which serves as a virtual testbed. An assessment of the numerical and experimental results demonstrates the efficiency of the proposed work.

We present a novel method of using cloud-based virtualized reconfigurable hardware to enhance the functionality of OpenFlow Software-Defined Networks. OpenFlow is a capable and popular SDN implementation, but when users require new or unsupported packet-processing, software processing in the OpenFlow controller cannot provide multi-gigabit rates. Our method sees packet flows redirected through virtualized hardware with custom-designed packet-processing engines that can add new capabilities to an OpenFlow network, while retaining line-rate processing. A case study shows this can be achieved with virtually no loss in throughput and minimal latency overheads.

We consider the minimization of electricity cost of a core network where each node has access to solar renewable energy and energy storage in a time-of-use pricing environment. Using an optimization based approach we demonstrate that expenditure on electricity can be reduced by 60% through an effective energy management policy. We also present a distributed, greedy energy management algorithm, which makes hourly electricity purchase and energy storage decisions at each of the nodes in the network and performs close to the optimal case. Finally, we measure the impact of parameters including solar panel size, energy storage capacity and storage charging rate as well as seasonal variations of solar energy on the service provider's expenditure on electricity.

Many multicast services such as live multimedia distribution and real-time event monitoring require constructing a multicast mechanism that involves network functions (e.g. firewall, video transcoding). Network Function Virtualization (NFV) is a concept that proposes using virtualization to implement network functions on infrastructure building block (such as high volume servers, virtual machines), where software provides the functionality of existing purpose-built network equipment. We present an approach for building the multicast mechanism whereby multicast flows are processed by NFV before reaching their end users. We propose a routing algorithm and a method for building an appropriate multicast topology.

Distributed file systems such as Google File System and Hadoop Distributed File System have been used to store large volumes of data in Cloud data centers. These systems divide data sets in blocks of fixed size and replicate them over multiple machines to achieve both reliability and efficiency. Recent studies have shown that data blocks tend to have a wide disparity in data popularity. In this context, the naive block replication schemes used by these systems often cause an uneven load distribution across machines, which reduces the overall I/O throughput of the system. While many replication algorithms have been proposed, existing solutions have not carefully studied the placement of data blocks that balances the load across machines, while ensuring node and rack-level reliability requirements are satisfied. In this paper, we study the dynamic data replication problem with the goal of balancing machine load while ensuring machine and rack-level reliability requirements are met. We propose several local search algorithms that provide constant approximation guarantees, yet simple and practical for implementation. We further present Aurora, a dynamic block placement mechanism that implements these algorithms in the Hadoop Distributed File System with minimal overhead. Through experiments using workload traces from Yahoo! and Facebook, we show Aurora reduces machine load imbalance by up to 26.9% compared to existing solutions, while satisfying node and rack-level reliability requirements.

Virtual machine (VM) migration occurs very frequently in cloud computing. VM Migration enables a running OS, including memory and storage to move from one physical host to another physical host. A particular case of interest is live migration where the process of migrating the full state from one OS to the other should happen continuously and without any connection disruption. In order to have a seamless VM migration process the system has to be able to resume network connectivity very quickly. Fast resumption has proved to be a challenging problem. In this paper, we present a scheme to efficiently to migrate VMs networking resources using SDN techniques to achieve fast network flow resumption on SDN. We formulate the problem by an integer programming problem, we prove its NP-completeness and we propose a heuristic algorithm to solve the problem. Software simulation and real testbed implementation are done to demonstrate the performance of the flow migration scheme.

We propose ViNO (Virtual Network Overlay), an orchestration service that can be used to create arbitrary network topologies with OVS (Open vSwitch) switches and VMs. ViNO connects switches and VMs through an overlay network using VXLAN encapsulation. ViNO provisions VMs by making API calls to the underlying platform. Users specify the desired topology using an expressive Domain Specific Language that allows users to easily express commonly used network topologies while hiding the underlying complexity. An important use case for ViNO is enabling the seamless migration of Linux services across VMs in different regions with very little downtime.

Programmability in wireless access networks can provide unprecedented flexibility in meeting the communications needs of a diverse set of wireless devices under changing demand and network conditions. Programmability also holds the promise of enabling multiple simultaneous virtual operators providing a variety of access networks that offer different services using different business models. In this paper we present our work on enabling wireless access network programmability in the SAVI testbed. We introduce an architecture for Software-Defined Infrastructure that offers virtualized heterogeneous resources in support of services and applications. Central to this architecture is the Janus SDI resource manager that can coordinate the actions of a set of controllers, e.g. OpenStack, OpenFlow, and other controllers such as a wireless access controller. We describe a design where Janus is used to integrate the wireless access network into a Smart Edge node. We introduce use cases that exploit the flexibility offered by this design, and we present experimental results from our implementation.

Software-Defined Infrastructure (SDI) presents an approach for integrated management of virtualized heterogeneous resources. Monitoring and measurement is an essential component for effective control and management. This paper presents an architecture of a system, named MonArch, based on SDI that provides integrated monitoring and measurement functionalities. Unlike existing cloud and network monitoring systems, MonArch supports execution of user-generated monitoring tasks, offers monitoring as a service to tenants, administrators as well as management modules, and provides a framework for monitoring data analytics. We have implemented and deployed MonArch in the SAVI Testbed, and our experience shows the system is able to support a wide variety of monitoring tasks while achieving high performance and scalability.

In this paper we introduce an architecture for wireless access on two-tiered heterogeneous clouds. We first discuss the concept of Software Defined Infrastructure (SDI), and role of Software Defined Radio in SDI, and review relevant literature. Next we present the architecture design for a Software Defined Wireless Access module in detail and provide measurements for the implemented solution. While the architecture introduced is capable of handling protocols such as LTE and WiFi, GSM is used for in our implementation.

In this paper we present an approach to implement security as a Virtualized Network Function (VNF) that is implemented within a Software-Defined Infrastructure (SDI). We present a scalable, flexible, and seamless design for a Deep Packet Inspection (DPI) system for network intrusion detection and prevention. We discuss how our design introduces significant reductions in both capital and operational expenses (CAPEX and OPEX). As proof of concept, we describe an implementation for a modular security solution that uses the SAVI SDI testbed to first detect and then block an attack or to re-direct it to a honey-pot for further analysis. We discuss our testing methodology and provide measurement results for the test cases where an application faces various security attacks.

Real-time content delivery services such as live media streaming, news casting and real-time event subscription/publication systems have become popular in recent years. Unlike traditional content delivery applications, real-time content delivery requires live content to be processed and delivered to end users in a timely and efficient manner. Furthermore, as both content producers and consumers may change over-time, it is a challenge to provision resources for these applications to achieve high service quality while minimizing total operational costs. Fortunately, the recent development of Cloud computing and Software Defined Networking (SDN) enables efficient implementation of real-time content delivery systems. Recently, the concept of Software Defined Infrastructure aims at combining Cloud computing and SDN to provide an unified framework for application deployment and management. In this paper, we present Kaleidoscope, an architecture for real-time content delivery in Software Defined Infrastructures. Kaleidoscope leverages network virtualization, SDN-based broadcasting and dynamic cloud resource provisioning to achieve high resource efficiency and service performance. Specifically, we present a resource management scheme that controls Cloud resource allocation and network configuration at run-time in accordance with service demand. Experiments show that Kaleidoscope is able to achieve lower resource cost while providing high service quality.

Many multicast services such as live multimedia distribution and real-time event monitoring require multicast mechanisms that involve network functions (e.g., firewall and video transcoding). Network function virtualization (NFV) is a concept that proposes using virtualization to implement network functions on infrastructure building block (such as high volume servers and virtual machines), where software provides the functionality of existing purpose-built network equipment. We present an approach for building the multicast mechanism whereby multicast flows are processed by NFV before reaching their end users. We propose a routing algorithm and a method for building an appropriate multicast topology.

We present a new approach for integrating virtualized FPGA-based hardware accelerators into commercial-scale cloud computing systems, with minimal virtualization overhead. Partially reconfigurable regions across multiple FPGAs are offered as generic cloud resources through OpenStack (opensource cloud software), thereby allowing users to “boot” custom designed or predefined network-connected hardware accelerators with the same commands they would use to boot a regular Virtual Machine. We propose a hardware and software framework to enable this virtualization. This is a first attempt at closely fitting FPGAs into existing cloud computing models, where resources are virtualized, flexible, and have the illusion of infinite scalability. Our system can set up and tear down virtual accelerators in approximately 2.6 seconds on average, much faster than regular virtual machines. The static virtualization hardware on the physical FPGAs causes only a three cycle latency increase and a one cycle pipeline stall per packet in accelerators when compared to a non-virtualized system. We present a case study analyzing the design and performance of an application-level load balancer using a fully implemented prototype of our system. Our study shows that FPGA cloud compute resources can easily outperform virtual machines, while the system's virtualization and abstraction significantly reduces design iteration time and design complexity.

This paper presents a novel architecture to manage identity and access (IAM) in a Multi-tier cloud infrastructure, in which most services are supported by massive-scale data centres over the Internet. Multi-tier cloud infrastructure uses tier-based model from Software Engineering to provide resources in different tires. In this paper we focus on design and implementation of a centralized identity and access management system for the multi-tier cloud infrastructure. First, we discuss identity and access management requirements in such an environment and propose our solution to address these requirements. Next, we discuss approaches to improve performance of the IAM system and make it scalable to billions of users. Finally, we present experimental results based on the current deployment in the SAVI Testbed. We show that our IAM system outperforms the previously proposed IAM systems for cloud infrastructure by factor 9 in throughput when the number of users is small, it handle about 50 times more requests in peak usage. Because our architecture is a combination of Green-thread and load balanced process, it uses less systems resources, and easily scales up to address high number of requests.

In this paper we discuss how to enable Software-Defined Networking (SDN) applications on Software-Defined Infrastructure (SDI) which is an approach for integrated control and management of converged computing and networking resources. Current separated resource management for computing or networking resources is not sufficient for addressing applications and multimedia services that require guaranteed service and quality levels. In addition, current resource management is not capable of managing heterogeneous resources that include computing and networking resources in combination with other resources such as programmable hardware, GPUs and network processors. We present an SDI that provides pluggable resource management modules for scheduling, networking control, fault management, and so on. This paper focuses on the design and implementation of a networking control module that enables SDN applications using information available from other modules. Currently, we have deployed the network control module in the practical multi-tier cloud infrastructure, SAVI Testbed. We present real measurements that show the functional evaluation results of our network control module.

Accurate Quality of Experience measurement for streaming video has become more crucial with the increase in demand for online video viewing. Quantifying video Quality of Experience is a challenging task. Significant efforts to quantify video Quality of Experience have primarily focused on the measurement of Quality of Experience for videos with network and compression related impairments. These impairments, however, may not always be the only main factors affecting Quality of Experience in an entire video viewing session. In this paper, we evaluate Quality of Experience for entire video viewing sessions, from the beginning to the end. In doing so, we evaluate videos with temporary interruptions as well as those with permanent interruptions or failures. We consider two types of failures, namely Accessibility and Retainability failures, and present the results of two subjective studies. These results indicate: (a) Accessibility and Retainability failures are rated lower compared to temporary interruption impairments; (b) Accessibility failures are rated close to the lowest value on the rating scale; and (c) the traditionally used 5-point scale to measure video Quality of Experience is not sufficient in the presence of Accessibility and Retainability failures.

We examine the packet loss performance of scalable all-optical routers exploiting fiber delay lines, under non-uniform and bursty data center traffic conditions. Our analysis reveals that a load balancing stage, capable of evenly distributing the incoming traffic in both space and time, is indispensable in wavelength-routing data centers with a distributed-buffer architecture.

In this paper, we address the problem of robust network design. Robustness is defined as the minimizing variations in network performance, such as average delay and throughput, due to the perturbations in the network, e.g. topology, demand and community of interest. We pose an optimization problem is cast in the form of minimizing a new robustness metric that is a function of network routing, capacities and external traffic demand distributions. We use the correspondence between packet flows in a network and random walk models. We use Markov chain sensitivity analysis to derive a new measure and prove its robustness property. We show that the node robustness factor, along with the Kemeny constant, plays a critical role in the robustness of a network. We evaluate the proposed robust optimization method by comparing to conventional network design approaches.

Due to the time-varying nature of wireless networks, it is required to find robust optimal methods to control the behavior and performance of such networks; however, this is a challenging task since robustness metrics and QoS-based (Quality of service) constraints in a wireless environment are typically highly non-linear and non-convex. This paper explores the possibility of using graph theoretic metrics to provide robustness in a wireless network at the presence of a set of QoS constraints. In particular, we are interested in robust planning of a wireless network for a given demand matrix while preserving end-to-end delay for input demands below a given threshold set. To this end, we show that the upper bound of end-to-end round trip time between two nodes of a network can be approximated by point-to-point network criticality (or resistance distance) of the network. We construct a convex optimization problem to provide a delay-guaranteed jointly optimal allocation of transmit powers and link flows. We show that the solution provides a robust behavior, i.e. it is insensitive to the environmental changes such as wireless link disruption, this is expected because network criticality is a robustness metric. Our framework can be applied to a wide range of SINR (Signal to Interference plus Noise Ratio) values.

This paper proposes a robust Criticality-based Clustering Algorithm (CCA) for Vehicular Ad Hoc NETworks (VANETs) based on the concept of network criticality. Network criticality is a global metric on an undirected graph, that quantifies the robustness of the graph against environmental changes such as topology. In this paper, we localize the notion of network criticality and apply it to control cluster formation in the vehicular wireless network. We use the localized notion of node criticality together with a universal link measure, Link Expiration Time (LET), to derive a distributed multi-hop clustering algorithm for VANETs. Simulation results show that the proposed CCA forms robust cluster structures.

Congestion in a transportation network is usually the result of either an increase in traffic demand, i.e. the desire of drivers to use the transportation network, or a decrease in traffic supply, i.e. the traffic capacity, which is affected by weather conditions, incidents, etc. In either case, congestion reduces the efficiency of the transportation network and increases the travel time of vehicles in the network. In this paper, we leverage the benefits that Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communications provide in Intelligent Transportation Systems (ITS), to optimize traffic assignment in transportation networks. In particular, we formulate a convex optimization problem for a transportation network and minimize network criticality, a new graph metric that measures centrality. The robustness of this solution is studied and compared to that of the System Optimal Equilibrium (SOE) Optimization. The results show that using network criticality provides robustness (lack of sensitivity) to both increases in traffic demand and decreases in traffic supply, thus reducing traffic congestion.

All-optical switching has been proposed to overcome the limitations of electronic switches in terms of scalability, speed, footprint, and power consumption. A key passive optical component to bypass electronic processing limitations is the arrayed waveguide grating (AWG). Switch architectures combining wavelength converters and fiber delay lines provide tunable routing and contention resolution when used with AWGs. An AWG passively routes either single or multiple input port wavelengths to its output ports. A single wavelength per port strategy reduces crosstalk within the AWG, but drastically increases the dimensionality of the device. Physical constraints on AWG design limit the port number for the foreseeable future to under 100. To scale optical switches to emerging network requirements, we can use multiple wavelengths per port. In this paper we examine one multiple wavelength per port architecture and quantify the physical layer impairments due not only to the AWG crosstalk, but also Q-factor degradation due to multiple wavelength conversions, and as a function of the number of recirculations in the contention resolution delay lines. While previous work has addressed this issue in terms of accumulated loss, we focus on accumulated relative intensity noise and amplified spontaneous emission.

We present an auction-based spectrum market approach to service provider spectrum trading. Service providers buy and sell spectrum amongst one another in a spectrum market and simultaneously compete for customers from a common pool. Multi-agent reinforcement learning solutions are applied in both customer nodes and service providers to dynamically manage participation in the market. We outline four possible regulatory scenarios with varying degrees of flexibility and competition. Simulations demonstrate that the allocation of spectrum is efficient and fair. Customers and service providers of varying size are shown to benefit from this approach while the system spectrum efficiency is also significantly improved.

Intelligent Transportation Systems (ITS) aggregate, analyze and display geographic- and temporal-specific sensor information to reduce congestion while promoting safety. Until now, the coverage and potential of ITS have been restricted by the excessive cost of deploying the required road sensor and communications infrastructure. Our solution to this problem is focused on a novel integrated ITS Network Architecture where vehicles are the main infrastructure in the network. We propose The Connected Vehicle Infrastructure (CVI) for Intelligent Transportation Systems (ITS), where vehicles adapt to mobility changes to form stable vehicular clusters using a Network Criticality-based algorithm we have developed. Further, they build on their clusters to form more stable Mobile Networks, as part of the ITS network. Simulation results using NS-2 show that CVI clustering provides more stable clusters, lower handoffs, higher resilience to errors and better connectivity than popular density-based vehicle clustering methods. In addition, the overhead analysis of CVI shows that it achieves reasonable overhead compared to common clustering algorithms.

We present a Distributed Ethernet Traffic Shaping (DETS) system for regulating the flow of data when multiple virtual machines run on one host and share a single Ethernet link to send and receive traffic in a cluster or a data center. In such settings, virtual machines can undermine each other's ability to receive traffic on the shared link. In DETS, sending machines monitor and regulate their transmission rates to conform to target rates. The DETS system is implemented in the host system, and there is no need to change or modify any processing or networking hardware. We describe an implementation on a Linux-based cluster, and through experimental performance evaluations, we show that DETS can guarantee the access rate of virtual machines. We also describe modifications to the Ethernet control plane so that DETS can be natively supported in Ethernet networks.

We present an auction-based approach to spectrum management in a multi-operator context. Service providers compete for customers in real-time through live auctions. To automate the bidding process we implement a multi-agent reinforcement learning solution. We study the effect of real-time competition between service providers by considering the cases where there is a single provider and multiple providers. Furthermore, we demonstrate how users of varying types, based on application-type and willingness to pay, can be accommodated. We utilize a low-complexity bid-proportional allocation mechanism which ensures fairness. Our simulation results show that when there is a single provider, revenue can be maximized by artificially limiting supply and creating contention. However, when there are multiple providers from which the customers can dynamically choose, there is no longer an incentive to restrict supply due to the direct competition between service providers.

The continuously increasing complexity of communication networks and the increasing diversity and unpredictability of traffic demand has led to a consensus view that the automation of the management process is inevitable. Currently, network and service management techniques are mostly manual, requiring human intervention, and leading to slow response times, high costs, and customer dissatisfaction. In this paper we present AutoNet, a self-organizing management system for core networks where robustness to environmental changes, namely traffic shifts, topology changes, and community of interest is viewed as critical. A framework to design robust control strategies for autonomic networks is proposed. The requirements of the network are translated to graph-theoretic metrics and the management system attempts to automatically evolve to a stable and robust control point by optimizing these metrics. The management approach is inspired by ideas from evolutionary science where a metric, network criticality, measures the survival value or robustness of a particular network configuration. In our system, network criticality is a measure of the robustness of the network to environmental changes. The control system is designed to direct the evolution of the system state in the direction of increasing robustness. As an application of our framework, we propose a traffic engineering method in which different paths are ranked based on their robustness measure, and the best path is selected to route the flow. The choice of the path is in the direction of preserving the robustness of the network to the unforeseen changes in topology and traffic demands. Furthermore, we develop a method for capacity assignment to optimize the robustness of the network.

Application creation through service composition is a cornerstone for several architectures including Service-Oriented Architecture. As the number and diversity of applications created based on this paradigm increase, the need for guaranteeing quality of service becomes more important. In this paper, we present a distributed algorithm for guaranteeing a specified level of application completion probability. The algorithm is designed to control service commitments in both queue-less and queue-enabled service-oriented systems. The algorithm does not assume a specific distribution type for service execution times and application request inter-arrival times, and hence is suitable for systems with stationary or non-stationary request arrivals. We show that the proposed distributed algorithm achieves its performance objectives for both queue-less and queue-enabled service oriented systems.

We consider the problem of maximizing network revenue from the perspective of bandwidth allocation and route selection. The objective is to perform offline maximization of revenue from served demands in the context of self-similar (long range dependent) traffic. We use an alpha-stable distribution for the aggregate demand volume to capture the appropriate level of traffic burstiness. We take a centralized view of the network topology, link capacity and demand. We use a new mean-risk modeling approach to that considers both the mean and the risk of bandwidth allocation. We also propose a risk measure appropriate for infinite variance alpha-stable distribution.

Node churn can have a severe impact on the performance of P2P applications. In this paper, we consider the design of reliable P2P networks that can provide predictable performance. We exploit the experimental finding that the age of a node can be a reliable predictor of longer residual lifetime to develop mechanisms that organize the network around these more reliable nodes. We propose two protocols, TrebleCast and TrebleCast?, to implement reliable overlay networks. These protocols dynamically create reliable layers of peers by moving nodes with higher expected lifetime to the center of the overlay. These more reliable layers can then be called upon to deliver predictable performance in the presence of churn.

Summary form only given. Together, the proliferation of sensors and communicating devices and the emergence of cloud computing represents a major opportunity to develop applications for connected environments in general, and especially management systems that address urgent challenges facing society. These challenges include the deployment of large-scale cloud computing, smart power grids, intelligent transportation systems, and next-generation communications and collaborations that will provide the foundation for a post-carbon society. In this talk we discuss the socio-economic context that gives these challenges urgency as well as the technical challenges that need to be addressed by the ICT community.

In a service oriented environment an application is created through the composition of different service components. In this paper, we investigate the problem of application admission control in a service oriented environment. We propose an admission control system that makes admission decisions using an online optimization approach. The core part of the proposed system is an online optimization algorithm that solves a binary integer programming problem which we formulate in this paper. An online optimizer maximizes the system revenue given the system's available resources as well as the system's previous commitments. Another part of the proposed system carries out a feasibility evaluation that is intended to guarantee an agreed level of probability of success for each admitted application instance. We use simulations and performance comparisons to show that the proposed application admission control system can improve the system revenue while guaranteeing the required level of quality of service.

This paper reports on a probabilistic method for traffic engineering (specifically routing and resource allocation) in backbone networks, where the transport is the main service and robustness to the unexpected changes in network parameters is required. We analyze the network using the probabilistic betweenness of the network nodes (or links). The theoretical results lead to the definition of "criticality" for nodes and links. Link criticality is used as the main metric to model the risk of taking a specific path from a source to a destination node. Different paths will be ranked based on their criticality measure, and the best path will be selected to route the flow along the core network. The choice of the path is in the direction of preserving the robustness of the network to the unforeseen changes in topology and traffic demands. The proposed method is useful in situations like MPLS and Ethernet networks where path assignment is required.

In this paper, we extend our previous work on committing service instances to the applications in a service-oriented environment, and we propose a distributed heuristic algorithm which is able to estimate the number of future service instances needed by each application instance in a future time. Also, this algorithm does not assume any specific type of distribution function for services execution time and applications interarrival time. In this paper, after presenting the mathematical basis for the proposed distributed algorithm, we explain how this algorithm can be implemented in a distributed environment, and through the simulations and performance comparisons, we show that the proposed algorithm improves the performance of the system significantly, compared to a No commitment policy system and a full commitment policy system.

With the growth in wireless network technologies and the emergence of cognitive radios, the need arises for mechanisms to effectively manage the resources involved in such environments. In this paper, we propose a market-based resource management approach for cognitive radios using machine learning, consisting of a negotiation phase where nodes are allocated resources in order to meet their requested bit rate, and a learning phase where nodes adjust their pricing of the resources in order to steer the cognitive radio environment towards the greater network good. We are interested in improving the utilization of the resources through price adjustments as compared to the case where the prices are kept fixed. We perform extensive simulations to study the performance of the proposed resource management mechanism in the cognitive radio environment.

In this paper, we propose a Peer-to-Peer naming architecture for integrated wireline/wireless networks that takes into account the expected changes in the next generation all-IP networks, and harnesses the emerging trends that are expected to shape such networks. This paper mainly focuses on the potential of Peer-to-Peer concepts in designing a scalable, flexible, and robust naming architecture, allowing efficient name resolution, resource discovery, and mobility support. The goal of this paper is to present the architecture suggested for naming, rather than to study its performance. This new use of the Peer-to-Peer paradigm is analyzed through some sample simulations.

The packet-pair dispersion techniques are the most common probing-based approach to measuring the bottleneck capacity of a path. In practice, the dispersion measurement, and therefore the bandwidth estimation, could be seriously distorted by the cross traffic queuing between or in front of the probe packet pair. Almost all the existing packet-pair techniques depend on heuristic filtering methods to find a final capacity estimate. In this paper, we take a different perspective to exploit the cross- traffic effect. We develop a queueing model to describe the output packet-pair dispersions interfered by the cross traffic, based on which a new measurement technique to estimate the available bandwidth is derived. Another important contribution is that we for the first time reveal that the statistics of the cross traffic, e.g. the marginal distribution and the autocovariance function of the arrival process, can also be inferred from the stochastic behavior of the output packet dispersions. Efficiency of the proposed available bandwidth estimation and traffic characterization techniques are demonstrated by computer simulations.

With the increasing number of wireless devices, the importance of mobility management in future mobile networks is growing. In addition, the number of access technologies available to those wireless devices is more diversified, leading to further heterogeneity and the need for convergence of mobility management solutions. Furthermore, traditional mobility management solutions, which are based on client/server paradigms, suffer from the shortcoming of such centralized solutions (single point of failure, congestion, bottlenecks). With the initial success of peer-to-peer for file sharing applications, and based on our previous attempt to exploit its benefits by proposing novel horizontal mobility management schemes, we examine in this paper the potential of peer-to-peer for vertical mobility management. We also perform extensive simulations to quantify the performance of our proposed peer-to-peer vertical mobility management scheme.

This paper reports on a promising approach for solving problems found when multi protocol label switching (MPLS), soon to be a dominant protocol, is used in core network systems. Difficulty is found largely in LSP routing and traffic engineering approaches. While there are a number of online and offline proposals to establish the LSPs but no one is a complete solution considering all the aspects of routing plan from traffic engineering point of view. Our research takes a viewpoint inspired by the concept of "between-ness" from graph theory, from which we introduce notions of link and path criticality indexes. The basis of the work is finding the most critical paths which are mathematically defined based on the algebra of routing. We try to avoid running aggregated flows or commodities on the most critical paths for the short term, and plan increasing the bandwidth of the critical paths for future if possible. This approach shows promise in simulations have run on benchmark networks available from research literature.

This paper presents an edge-based Internet traffic characterization approach. Our objective is to estimate the marginal distribution and the correlation structure of the packet arrival process at a queue, by sending probe packet pairs with a specific dispersion to sample the traffic. The aggregate work load process inferred from the output dispersions is a compound process of the packet arrival process and the packet size distribution. We show that the packet arrival marginal distribution and the packet size distribution can be decoupled by using the probability generating function; given one of the distributions, the other can then be estimated. We use the fact that the Internet packet size follows a known multi-modal distribution. Moreover, multiple series of packet pairs with different input dispersions can be used to estimate the packet arrival process at different time scales, and therefore to estimate the Hurst parameter, which characterizes the long-range dependence, by generating the variance-time plot. While the traffic characterization techniques are developed and validated in a single-queue context, we indicate how the techniques can be applied to a black box system for end-to-end quality of service provisioning along a multi-hop path.

Keywords: NCCR-MICS ; NCCR-MICS/CL3 Reference LCA-ARTICLE-2007-012 Record created on 2007-06-06, modified on 2017-05-12

We address the problem of allocating transmission rates to a set of network sessions with end-to-end bandwidth and delay requirements. We give a unified convex programming formulation that captures both average and probabilistic delay requirements. Moreover, we present a distributed algorithm and establish its convergence to the global optimum of the overall rate allocation problem. In our algorithm, session sources selfishly update their rates as to maximize their individual benefit (utility minus bandwidth cost), the network partitions end-to-end delay requirements into local per-link delays, and the links adjust their prices to coordinate the sources' and network's decisions, respectively. This algorithm relies on a network utility maximization (NUM) approach, and can be viewed as a generalization of TCP and active queue management (AQM) algorithms to handle end-to-end QoS. We extend our results to deterministic delay requirements when nodes employ Packet-level Generalized Processor Sharing (PGPS) schedulers.

This paper presents an analytical model for evaluating the capability of wireless LANs (WLANs) to provision quantitative quality of service (QoS) guarantees. We consider a distributed medium access control (MAC) with class differentiation, where mobile nodes belonging to different classes may have heterogeneous traffic arrival processes or different contention windows. With on/off inputs, our analysis shows that the WLAN admission region under the QoS constraint can be significantly improved, when the statistical multiplexing effect is taken into account. Moreover, the statistical multiplexing gain can be further improved by aggregating the downlink flows at the access point (AP). We also demonstrate that the proper selection of contention windows plays an important role in improving the WLAN QoS capability, while the optimal contention window for each class and the maximum admission region can be jointly solved in our analytical model.

We address the problem of allocating transmission rates to a set of network sessions with end-to-end bandwidth and delay requirements. We give a unified convex programming formulation that captures both average and probabilistic delay requirements. Moreover, we present a distributed algorithm and establish its convergence to the global optimum of the overall rate allocation problem. In our algorithm, session sources update their rates as to maximize their individual benefit (utility minus bandwidth cost), the network partitions end-to-end delay requirements into local per-link delays, and the links adjust their prices to coordinate the sources' and network's decisions, respectively. This algorithm relies on a network utility maximization approach, and can be viewed as a generalization of TCP and queue management algorithms to handle end-to-end QoS. We also extend our results to deterministic delay requirements when nodes employ packet- level generalized processor sharing (PGPS) schedulers.

With the increasing number of wireless devices, the importance of mobility management in future mobile networks is growing. Traditional mobility management approaches are based on client/server paradigms, and suffer from their well-known shortcomings (single point of failure, congestion, bottlenecks). With the success of P2P for file sharing applications, we believe that its benefits can be brought into new mobility management schemes to improve their scalability, robustness, availability, and performance. To the best of our knowledge, this paper is a first attempt to examine the potential of P2P concepts for mobility management. We perform experiments to quantify the performance of the proposed scheme, and compare it to traditional approaches such as Mobile IP.

Content Delivery over Internet is optimized for low user perceived latency by designing specialized Content Delivery Networks (CDN). Request Routing systems in CDNs generally achieve low user latency by balancing the server load and selecting the nearest server. Although Traffic engineering is another factor that impacts the client latency, which is not generally integrated with the Request Routing. In this paper we proposed a CDN architecture that employs a TE-Friendly Request Routing (TFRR) system, which not only distributes the server load but also achieves network efficiency by balancing the path loads. We also presented a detailed TFRR system design and an algorithm to perform the TFRR function. Our simulation results show that the proposed CDN with our TFRR algorithm achieves both server and traffic load balancing.

Peer-to-Peer (P2P) systems have witnessed an explosive growth in popularity due to their desirable characteristics (robustness, scalability, availability). In this paper, we present an approach to bring these characteristics into the control plane of IP networks, which mainly relies on signaling protocols such as SIP to setup multimedia and instant messaging sessions. We present a structured P2P control plane based on modifications to the original Chord P2P topology, resulting in a hierarchical overlay of SIP peers that replaces traditional client-server paradigms in control plane signaling protocols. Implementations were used to study the performance of the proposed structured P2P control plane, and its suitability for use in IP networks.

Data and telephone service providers have started considering migration to an IP based environment. This paper presents an unstructured peer-to-peer approach to initiating and maintaining sessions over IP using session initiation protocol (SIP). The offered solution is completely modular and is compatible with traditional server-client based approaches using SIP. The peer-to-peer nature of our design allows it to be highly scalable and self managing with low maintenance costs, making it an attractive solution for service providers

This paper presents an analytical model for evaluating the statistical multiplexing effect, admission region, and contention window design in multiclass wireless LANs (WLANs). We consider a distributed medium access control (MAC) which provisions service differentiation via contention window differentiation, where mobile nodes belonging to different service classes have different quality of service (QoS) requirements. With bursty input traffic, we show that the WLAN admission region under the QoS constraint can be significantly improved by exploiting the statistical multiplexing gain. Moreover, the statistical multiplexing gain can be further improved by aggregating the downlink flows at the access point (AP). We also demonstrate that the selection of contention windows plays an important role in improving the WLAN's QoS capability, while the optimal contention window for each class and the maximum admission region can be jointly solved from our analytical model. The analysis accuracy and the resource utilization improvement are demonstrated by extensive numerical results.

This paper proposes efficient resource allocation techniques for a domain-based wireless/wireline interworking architecture. Resource allocation is driven by the service level agreement (SLA). Each wireless domain can freely choose its internal resource management schemes to guarantee the customer access SLA (CASLA), while the border-crossing traffic is served by a DiffServ/MPLS core network according to the transit domain SLA (TRSLA). Specifically, we propose an engineered priority scheme for a cellular wireless domain, where the CASLA for each service class is met with efficient resource utilization and the interdomain TRSLA bandwidth requirement can be obtained conveniently. In the transit domain, the traffic load fluctuation from upstream access domains is tackled with an inter-TRSLA resource sharing technique, where the spare capacity from underloaded TRSLAs can be exploited by the overloaded TRSLAs to improve resource utilization.

This paper presents an efficient resource sharing scheme for a network supporting multiple service level agreements (SLAs). Specifically, an overloaded SLA can borrow bandwidth from those underloaded SLAs based on a call level service differentiation concept. While flows admitted with the SLA nominal capacity are considered as in profile flows, flows admitted with borrowed bandwidth are tagged as out profile flows and may be preempted later when the original bandwidth owner needs to claim back the resources. Such preemption is considered as the quality of service (QoS) differentiation between the in profile and out profile flows. Through the implementation design and computer simulations, we show that high resource utilization and SLA compliance can be simultaneously achieved by bandwidth borrowing and call level differentiation.

Traditional telecommunications service providers are undergoing a transition to a shared infrastructure in which multiple services will be delivered by peer and server computers interconnected by IP networks. IP transport networks that can transfer packets according to differentiated levels of QoS, availability and price are a key element to generating revenue through a rich offering of services. Automated service and network management are essential to creating and maintaining a flexible and agile service delivery infrastructure that also has much lower operations expense than existing systems. In this paper we focus on the SLA-based IP packet transport service on a core network infrastructure and we argue that the above requirements can be met by a self-management system based on autonomic computing and virtual network concepts. We present a control and management system based on this approach.

This paper discusses and compares different approaches to handle mobility in all-IP networks, at both the application and network layers. First, three key parameters of mobility schemes are quantified: handoff delay, registration/binding cost, and packet delivery cost. Next, these schemes are compared based on criteria such as the need for encapsulation, changes in endsystems and/or infrastructure, scalability, and reliability. Finally, a mobility model is used to perform extensive simulations in order to compare the different all-IP mobility approaches.

We propose a hierarchical packet scheduling technique to closely approximate a hierarchical extension of the generalized processor sharing model, hierarchical generalized processor sharing (H-GPS). Our approach is to undertake the tasks of service guarantee and hierarchical link sharing in an independent manner so that each task best serves its own objective. For tight and harmonized integration of the two independent service functions into a single packet scheduling algorithm, we introduce two novel concepts of distributed virtual time and service credit, and develop a packet version of H-GPS called hierarchical fair queuing (HFQ). We demonstrate the layer-independent performance of the HFQ algorithm through simulation results.

In all-optical wavelength-switched WDM networks, 3R regeneration does not need to be performed at every node in a path. Thus, a significant cost savings can be realized by efficiently provisioning a limited amount of 3R regeneration resources in each node in the network and utilizing these resources efficiently. In order to aid in these two tasks, we present an analytical model to predict the location and relative frequency of 3R regeneration requests in the network. Because the model is based solely on the topological information of the network, the predictions provided are very general and are independent of specific network operating parameters, such as the routing protocol employed. Simulation results are also presented to verify the accuracy of the model.

This paper addresses the transport of real-time multimedia traffic generated by MPEG-2 applications over ATM networks using an enhanced UBR best effort service (UBR+). Based on the factors affecting the picture quality during transmission, we propose an efficient and cost-effective ATM best effort delivery service. The proposed service integrates three components: a dynamic frame level priority assignation mechanism based on the MPEG data structure and feedback from the network (DexPAS), a novel audiovisual AAL5 SSCS with FEC, and an intelligent packet video discard scheme named SA-PSD, which adaptively and selectively adjusts the cell drop level to switch buffer occupancy, video cell payload type and forward error correction ability of the destination. The overall best effort video delivery framework is evaluated using ATM network simulation and MPEG-2 video traces. The ultimate aim of this framework is twofold. First, minimizing loss for critical video data with bounded end-to-end delay for arriving cells. Second, reducing the bad throughput crossing the network during congestion. Compared to previous approaches, performance evaluation shows a good protection of predictive coded and bidirectional predictive coded frames at the video slice layer.

This paper introduces the MIBlet concept as a means for effectively designing and managing virtual networks (VN). MIBlets are logical structures providing abstract and selective views of the physical network resources allocated to VN customers. They result from the partitioning of the network resources (their MIB representations) and restrict customers' access only to those resources allocated to them. Different partitioning schemes are supported to provide virtual network services with different quality of service requirements. Customer control/management functions are implemented through MIBlet controllers located at every network node involved in the customer network. MIBlet controllers enforce customers' access control and resource usage policing strategies and are invoked to set up, monitor and control the customer connections. In this paper the partitioning of network resources into MIBlets is mainly addressed within the scope of the ATM testbed as a part of the network resources management (NRM) project of the Network Architecture Laboratory at the University of Toronto.

This paper proposes an approach to support integrated services Internet with RSVP over ATM shortcuts (ISAC). While similar to other LP switching approaches, our work is different in three major aspects. First, it focuses on supporting the integrated services model whereas other approaches currently support only best effort traffic. Second, our architecture adopts RSVP as the major signaling protocol and eliminates duplication of functionality in the ATM domain. Finally, while heterogeneous multicast has not yet been supported in any other approaches, it is considered in our proposal. Our design strives to achieve three fundamental objectives: (1) ensuring compatibility with existing networking standards, applications and system software, (2) maintaining data path efficiency, and (3) assuring portability for different operating system and switch control protocol. Our proposed architecture has been proven by a prototype implementation. Its operation has been verified by demonstrating a videoconferencing application. Our prototype has also been evaluated by measuring its signaling and control latency as well as the transfer delay of the data path.

Future wireless ATM networks are expected to support a variety of services with different bit-rates and quality-of-service (QoS) requirements. A major challenge for these networks is the design of the multiple access scheme. In our previous works, we proposed the hybrid CDMA/TDMA technique as an appropriate multiple access control (MAC) scheme for wireless ATM networks. We also investigated the problem of power control in such hybrid systems. In this paper, we continue our study and address the time scheduling issue of hybrid CDMA/TDMA. Using the generalized processor sharing technique, typically employed in TDMA systems, we develop a time scheduling scheme suitable for the class of hybrid CDMA/TDMA systems. We also study the implementation of this scheme in a specific hybrid system we proposed earlier and address its integration with our power control technique.

A new multicasting mechanism for RAM-based shared-buffer ATM switches is introduced. Multiple logical output queues, including a new queue for multicast and broadcast cells, are all interleaved into a single physical buffer as in the single-queue switch architecture. Queues are hardware-independent and full buffer-sharing is achieved. Cells are scheduled in the multicast queue based on their priority level and service type as in the unicast queues. A single copy of a multicast cell is kept in the queue. The cell is sent to all of its destinations upon its service time. A unicast cell in a given output queue can still be sent if it has higher priority than a multicast cell. In this case a unicast copy of the multicast cell for that output port is placed in the output queue. This copying scheme requires neither extra hardware nor extra memory space for duplicated cells. A new grouping algorithm is presented which supports the incorporation of the multicast queue and the unicast queues into a single overall queue.

Groups of cells, such as cells belonging to different priority levels, that are all placed in one queue, can be identified by using labels or tags to distinguish them from each other. We describe a buffering device called a sequencer, which can distinguish logical queues within the same physical queue, and at the same time can successfully schedule the service among these logical queues. Scheduling the service among cells, VCs, or groups of cells in ATM switches is necessary to provide guaranteed QoS for each connection which is a major goal of ATM networks. The proposed sequencer is quite flexible and can realize different scheduling algorithms in different levels, including per VC scheduling. The sequencer can operate in real time and at very high speeds. It has a simple and modular architecture and can be implemented in a single chip. The site of the buffer can be increased simply by cascading several sequencers. The sequencer can be used as a traffic shaper, input buffer, output buffer, or a queue controller of RAM-based switches.

In this paper we introduce a new approach to ATM switching. We propose an ATM switch architecture which: uses only a single shift-register-type buffering element to store and queue the cells; and within the same physical queue switches the cells by organizing them in logical queues destined to different output lines. The buffer is also a sequencer which allows flexible ordering the cells in each logical queue to achieve any appropriate scheduling algorithm. This switch is proposed for use as the building block of large-scale multi-stage ATM switches and as the scheduler/controller for the RAM-based switches. The single queue switch implements output queueing and performs full buffer sharing. The hardware complexity is low. The number of input and output lines can vary independently without affecting the switch core. The size of the buffering space can be increased by simply cascading the buffering elements to each other.

The application of asynchronous transfer mode (ATM) to a wireless local area network (WLAN) environment is a new undertaking and poses many problems not found in either wireline ATM or data-only WLAN networks. The WLAN is designed as a centralized network, where a complex base station polls simpler remote stations. A polling algorithm called distributed fair queueing (DFQ) is developed from the self-clocked fair queueing (SCFQ) service discipline. The DFQ protocol allows SCFQ performance in a wireless LAN environment where queue information is not automatically available to the poller. Bounds for delay for certain services are derived explicitly, and other services are shown to be derivable from fair queueing theory. A reasonable service mix is simulated to show delay performance versus system load.

We introduce a new approach to ATM switching. We propose an ATM switch architecture which uses only a single shift-register-type buffering element to store and queue cells, and within the same (physical) queue, switches the cells by organizing them in logical queues destined for different output lines. The buffer is also a sequencer which allows flexible ordering of the cells in each logical queue to achieve any appropriate scheduling algorithm. This switch is proposed for use as the building block of large-stale multistage ATM switches because of low hardware complexity and flexibility in providing (per-VC) scheduling among the cells. The switch can also be used as scheduler/controller for RAM-based switches. The single-queue switch implements output queueing and performs full buffer sharing. The hardware complexity is low. The number of input and output lines can vary independently without affecting the switch core. The size of the buffering space can be increased simply by cascading the buffering elements.

This paper focuses on designing a large N/spl times/N high-performance broad-band ATM switch. Despite advances in architectural designs, practical switch dimensions continue to be severely limited by both the technological and physical constraints of packaging. Here, we focus on augmentation in a "single-switch" design: we provide ways to construct arbitrarily large switches out of modest-size components and retain overall delay/throughput performance. We propose a growable switch architecture based on several key principles: 1) the knockout principle exploits the statistical behavior of cell arrivals, and thereby reduces the interconnect complexity; 2) output queueing yields the best possible delay/throughput performance; 3) distributed control in routing (multicast) cells through the interconnect fabric without internal path conflicts; and 4) simple basic building blocks facilitate scalability. Other attractive features of the proposed architecture include: 1) intrinsic broadcast and multicast capabilities; 2) built-in priority sorting functionality; and 3) the guarantee of first-in, first-out cell sequence, To achieve 10/sup -14/ cell loss probability, only maximum size 32/spl times/16 basic building modules are required, and no crossover interconnects exist between modules in a three-dimensional configuration.

Credit-based flow control is a promising method to use in ATM networks. We analyze the properties and performance of a credit-based protocol as a function of different system parameters such as propagation delay, source peak rate and network utilization. We have found robust non-probabilistic bounds for the throughput, cell and burst delay of a flow controlled connection as a function of its round-trip delay and buffer allocation. These bounds also serve as a fairness criteria in dealing with local users with small buffers and remote users with large buffers. Extensive simulations have been used to verify our results and to study the buffer occupancy, achievable throughput and cell transfer delay under credit-based flow control.

We present a novel design concept for constructing high-speed output port controllers for ATM switches, and statistical multiplexers. The newly proposed concept provides an external framework in which the internal hardware designs can be modified to achieve a specific quality of service. Two distributed control designs are provided, namely the fully shared buffer and partially shared buffer architectures. The fully shared buffer architecture can provide the push-out mechanism or complete buffer sharing queueing discipline which gives the best loss and delay performance for an incoming cell stream with static priority.

Through comprehensive simulation studies, we have evaluated the ATM layer end-to-end performance of a constant bit rate (CBR) MPEG2 connection. For most practical cases that we have considered, a cell delay variation (CDV) value of 160 /spl mu/sec is obtained (using 155 Mbps OC-3 rate), well below the 1 msec worst case stated in prior studies. The results also indicate that the uniform distribution proposed in the ATM Forum provides a pessimistic model for the cell delay variation. We demonstrate that a gamma distribution adequately models the cell delay and delay variation (CDV). We also study the effect of various network/source parameters (such as the background load, the number of background sources, the number of hops, and the link-speed) on the variances of CDV and the end-to-end delay of the reference connection. Finally, we examine the variation in the cell delay correlation of a reference connection with the above parameters. We show that the correlation is a decreasing non-periodic/periodic function if the reference CBR is multiplexed with the same/other classes of CBR connections.

AAL1 represents a long term solution for the transport of CBR MPEG2 video traffic over ATM networks. This paper describes an integrated implementation model for AAL1 carrying CBR MPEG2 traffic with particular focus on the receiver convergence sublayer functions and the issues affecting the end-to-end performance of the AAL1 connection. Through a comprehensive simulation of the AAL and the ATM layers, we verify that the implementation model is capable of delivering the desired QoS for video applications under a wide range of cell losses and cell delay variations. In addition, we show the effects of using FEC with byte interleaving on the end-to-end performance parameters. We conclude that cell loss statistics constitute the key factors in determining the overall performance of the AAL1 connection.

Future wireless ATM networks are expected to support a variety of services with different bit-rates and quality-of-service (QoS) requirements. A major challenge for these networks is the design of the multiple access scheme. We introduce a new MAC protocol called scheduled CDMA (SCDMA). This scheme is a hybrid CDMA/TDMA scheme in which the base station schedules transmission of CDMA-based mobile terminals. At any time, a group of services are scheduled to transmit simultaneously. Interference control is done with power control. Several QoS issues of this scheme are addressed including power control, application of FEC coding, and high bit-rate service support.

In the original paper by Sharifi and Leon-Garcia (see ibid., vol.5, p. 52-56, Feb. 1995) the authors propose a method to estimate the shape parameter for a generalized Gaussian probability density function to be fitted to the subbands of a video signal. Their method, which uses certain moments of the subband histogram, has in fact already been presented some years ago by Mallat (1989). The authors reply that they thank Murching and Woods for bringing to their attention a previously published work, which has developed the method reported in their paper. They regret that their search of the previous related literature did not reveal the paper by Mallat. They note, however, that the effectiveness of the method in comparison to statistical goodness-of-fit tests, was shown in their work and not in Mallat's.

A subband decomposition scheme for video signals, in which the original or difference frames are each decomposed into 16 equal-size frequency subbands, is considered. Westerink et al. (1991) have shown that the distribution of the sample values in each subband can be modeled with a "generalized Gaussian" probability density function (PDF) where three parameters, mean, variance, and shape are required to uniquely determine the PDF. To estimate the shape parameter, a series of statistical goodness-of-fit tests such as Kolmogorov-Smirnov or chi-squared tests have been used. A simple alternative method to estimate the shape parameter for the generalized Gaussian PDF is proposed that significantly reduces the number of computations by eliminating the need for any statistical goodness-of-fit test.>

A new technique to recover the information loss in a block-based image coding system is developed in this paper. The proposed scheme is based on fuzzy logic reasoning and can be divided into three main steps: (1) hierarchical compass interpolation/extrapolation (HCIE) in the spatial domain for initial recovery of lost blocks that mainly contain low-frequency information such as smooth background (2) coarse spectra interpretation by fuzzy logic reasoning for recovery of lost blocks that contain high-frequency information such as complex textures and fine features (3) sliding window iteration (SWI), which is performed in both spatial and spectral domains to efficiently integrate the results obtained in steps (1) and (2) such that the optimal result can be achieved in terms of surface continuity on block boundaries and a set of fuzzy inference rules. The proposed method, which is suitable for recovering both isolated and contiguous block losses, provides a new approach for error concealment of block-based image coding systems such as the JPEG coding standard and vector quantization-based coding algorithms. The principle of the proposed scheme can also be applied to block-based video compression schemes such as the H.261, MPEG, and HDTV standards. Simulation results are presented to illustrate the effectiveness of the proposed method.

Most work in video traffic modelling has concentrated on the frame level and little work has been done to model the cell level traffic. The authors give the cell inter-arrival statistics for several sequences and used them in a multiplexer simulation to obtain cell loss results. Many models have assumed that the cell level traffic is Poisson. They show that the cell inter-arrival is not i.i.d., but is correlated. This is due to the fact that in image coding the compression scheme is only applied locally. Thus, some correlation still remains in the cell stream produced. The cell loss obtained were larger than those from the uniform cell spacing and Poisson assumptions, and the cell burst loss length distribution was found to be approximated by a geometric distribution.>

The authors investigate burst-level bandwidth reservation schemes in ATM LANs and compare the performance of REQ/ACK and on-the-fly reservation schemes for a client-server model with a single ATM switch. To compare performance, they derive an analytical model for the mean burst transfer delay, blocking probability and throughput. They discuss the dependence of these performance parameters on the propagation delay-to-burst duration ratio and peak rate-to-link speed ratio. They show that, for moderate propagation delay-to-burst duration ratio, the on-the-fly scheme is more desirable since the REQ/ACK scheme has limited achievable throughput for fast reservation traffic due to unused bandwidth during the REQ-ACK cycle. Also, for a given burst length (in bits), the delay performance of REQ/ACK scheme is more sensitive to increase in the peak rate than the on-the-fly scheme.>

The paper presents a new cell switching architecture for ATM-based networks. The proposed helical switch is a multistage interconnection network which implements the self-routing technique with efficient buffer sharing. Although the switch may route cells along multiple paths, the connection-oriented mode required by the ATM-based network is supported. Cell sequence integrity is guaranteed by introducing a virtual helix which forces cells routed along different paths to proceed in order and fill the internal buffers uniformly. The performance of the helical switch is investigated under uniform and nonuniform traffic patterns. Unlike single-path multistage networks such as buffered banyan networks which can degrade significantly under nonuniform traffic, the helical switch is shown to be quite robust with respect to nonuniform traffic conditions.>

In order to efficiently utilize network resources while still providing satisfactory QoS to both real-time and nonreal-time applications, prioritizing these two types of traffic according to their service requirement becomes necessary. Several slot-oriented transmission priority schemes applicable to the output queue of ATM switches have been proposed. We studied the slot-oriented queueing disciplines that further involve the buffer management of the output queue of ATM switches. A fundamental principle called the separation principle is presented, which asserts that (1) the QoS (measured by the time-cumulative cell loss for each traffic class) region of the efficient disciplines (provide the best QoS tradeoff between the two types of traffic) can be divided into two mutually exclusive ones by the QoS of a special efficient discipline called R*; and (2) the efficient disciplines may involve either dynamic transmission priority or dynamic enqueueing priority but not both depending on which of the two mutually exclusive QoS regions is desired. The QoS region of less time-cumulative nonreal-time cell loss than R* is shown to be approximately linear in the space of time-cumulative cell loss vector when the real-time traffic is well regulated. The suboptimal but simple disciplines which are functions of only a small set of system parameters are also investigated to achieve less time-cumulative nonreal-time cell loss than R*.>

In BISDN, the asynchronous transfer mode (ATM) requires all information to be represented as a sequence of standard data units called cells. Cell los is inherent in ATM networks due to the cell header corruption and buffer overflow in the network. Several studies have shown that cell losses are bursty for an ATM network. In this work, we encoded real video sequences with a variable bit-rate (VBR) version of the H.261 video encoder in order for us to determine the relationship between blocks in a video frame and the number of ATM cells generated. We then considered the impact of bursty cell losses on image block loss probability. Block loss distributions are given at different codec and channel parameters. We also obtained block loss results using a cell loss correction scheme. Three sequences were analyzed to obtain the cumulative block loss probability distribution. Similar maximum and minimum block loss probability values were obtained for each sequence. The block loss probability distribution varies according to the amount and type of motion present in each sequence. We show that the block loss is confined to one group of blocks (GOB). The maximum block loss probability can be two orders of magnitude larger than the channel cell loss probability. By using the cell loss correction scheme, block loss was reduced to a level equivalent to reducing cell loss probability by five orders of magnitude.

A new technique to recover the information loss in a block-based image coding system is developed in this paper. The proposed scheme is based on the fuzzy logic reasoning and can be divided into three main steps: (1) hierarchical compass interpolation/extrapolation in the spatial domain for initial recovery of lost blocks that mainly contain low-frequency information such as smooth background; (2) coarse spectra interpretation by fuzzy logic reasoning for recovery of lost blocks that contain high-frequency information such as complex textures and fine features; (3) sliding window iteration in both spatial and spectral domains to efficiently integrate the results obtained in step (1) and (2) such that optimal results can be achieved in terms of surface continuities on block boundaries and the established inference rules. The proposed method, suitable for recovering both isolated and contiguous block losses, provides a new approach for error concealment of block-based image coding systems such as the JPEG coding standard and vector quantization based coding algorithms. The principle of the proposed scheme can also be applied to block-based video compression schemes such as the H.261, MPEG, and HDTV standards. Simulation results are presented to illustrate the effectiveness of the proposed method.

In this paper a new algorithm for digital video coding is presented that is suitable for digital storage and video transmission applications in the range of 5 to 10 Mbps. The scheme is based on frame differencing and, unlike recent proposals, does not employ motion estimation and compensation. A novel adaptive grouping structure is used to segment the video sequence into groups of frames of variable sizes. Within each group, the frame difference is taken in a closed loop Differential Pulse Code Modulation (DPCM) structure and then decomposed into different frequency subbands. The important subbands are transformed using the Discrete Cosine Transform (DCT) and the resulting coefficients are adaptively quantized and runlength coded. The adaptation is based on the variance of sample values in each subband. To reduce the computation load, a very simple and efficient way has been used to estimate the variance of the subbands. It is shown that for many types of sequences, the performance of the proposed coder is comparable to that of coding methods which use motion parameters.

This paper presents an application of Markov random field theory to image coding. First we use Markov random fields to model the correlation in the image intensity fields. We then propose a noncausal predictive image coding scheme in which the estimation of present pixel is based on both past and future neighboring pixels. A sequential iterative decoding algorithm is extended from 1D to 2D to perfectly reconstruct the image from estimation residuals at the decoder. We also develop a fast whirlpool algorithm to speed up the decoding. Open-loop and closed-loop quantizer structures are implemented for noncausal prediction and performances are compared with conventional DPCM predictive coding.

An approach to the delay analysis of various service disciplines in symmetric token passing networks is presented. It is shown that exact or approximate accurate expressions for the average packet delay of different service disciplines can be directly derived by the delay expression of the exhaustive service system. This can be accomplished by inflating, by an appropriate factor, the packet size of the discipline whose performance is analyzed and then using the inflated packet in the delay expression of the exhaustive service system. The method is applied to the analysis of the limited service and TTS disciplines, and its accuracy is verified by simulation results. The advantages of the analytic method presented are its generality, higher accuracy over previous analytic methods, and insensitivity to network latency and other system parameters.>

The authors proposed a method for decoding interpolatively encoded data. This class of coding scheme achieves higher estimation gain and are symmetric with respect to time which makes them a good candidate for storage application. They showed that different trade-off parameters are involved and investigated their relationships. These parameters are estimation gain, delay experienced by the encoder and the decoder and end-to-end signal-to-noise ratio. They also showed the implementation and the effect of incorporating quantizers in the circuits. Specifically, they investigated two extreme open and closed loop architectures and compared their performances. Generalization of the above algorithm to noise feedback coding can be achieved easily.>

A novel cell switching architecture for asynchronous transfer mode (ATM)-based networks is presented. The proposed helical switch is a multistage interconnection network which implements the self-routing technique with efficient buffer sharing. Although the switch may route cells along multiple paths, the connection-oriented mode required by the ATM-based network is supported. Cell sequence integrity is guaranteed by introducing a virtual helix which forces cells routed along different paths to proceed in order and fill the internal buffers uniformly. Under a uniform traffic pattern, it is shown that the minimum achievable throughput is 5/6 per output line.>

A throughput and delay analysis of FDDI and FDDI-II is presented under mixed traffic. The case of voice/data transmission is considered, and the throughput and delay behavior of FDDI, under packetized voice transmission, and FDDI-II, under isochronous voice transmission, is examined. The performance of the two networks is then investigated under the transmission of voice, data, and video. Two transmission alternatives are considered. In the first, all three types of information are transmitted in packets over an FDDI network. In the second, the isochronous slots of FDDI-II carry the voice and video. The effect of various system parameters on the performance of both networks is examined, and their voice, video, and data performance are compared.>

An error-correction scheme for a helical-scan magnetic recording system is presented. The system consists of a commercial VHS video cassette recorder with the front-end electronics adapted for high-speed digital recording. Error statistics have been collected and show a bursty error recording channel both within each track and from track-to-track. The proposed error-correction scheme uses interleaved Reed-Solomon codes. The interleaving function consists of a two-level interleaver performing track interleaving and byte interleaving. An efficient interleaving implementation is presented.>

The authors present a new nonblocking property of the reverse banyan network under a particular input packet pattern at the input ports. The reverse banyan network is the mirror image of the banyan network. If the input packets of the N*N reverse banyan network have consecutive output address as modulo N, then the reverse banyan network is nonblocking. The routing of packets in the reverse banyan network is described, and the nonblocking property of the reverse banyan network is proved. A possible application of this property in the switching network is discussed.>

A multilink access subsystem based on the Batcher-banyan network architecture is proposed. With this subsystem, multiple physical output links connecting a pair of switching nodes can be shared in an effective way. The subsystem is also configurational so that there is no restriction on any particular partition of physical output links. This is accomplished by executing the proposed multilink access algorithm on a modified Batcher sorter. It is shown that the required hardware can be integrated into the Batcher sorter, and the multilink access algorithm can be integrated with the contention resolution three-phase algorithm. The overhead incurred due to the running of the multilink access algorithm is calculated and the asymptotic performance analyses of the resulting single queue multilink access switch are presented. Results show that the proposed architecture has higher capacity than the unilink access counterpart, has low delay, and has low packet loss probability with small buffer size.>

A novel approach to the delay analysis of various service disciplines in symmetric token ring networks is presented. It is shown that exact or approximate expressions for the average packet delay of different service disciplines can be directly derived by the delay expression of the exhaustive service system. This is accomplished by: (a) inflating, by an appropriate factor, the packet size of the discipline whose performance is analyzed; and (b) using the inflated packet in the delay expression of the exhaustive service system. The proposed method is applied to the limited service and time token systems, and its accuracy is verified by simulation results. Advantages of the method are its higher accuracy over previous analytic methods and its robustness to ring latency and other system parameters.>

A report is presented on a queueing analysis and a simulation study of a switch fabric based on a buffered banyan structure whereby buffers are placed at the output links of each switching element. When buffers are located at the input links, it is well known that maximum throughput is limited to approximately 0.45 under a uniform input traffic pattern. This bottleneck is due to the head of the line (HOL) contention at each switching element and is intrinsic to input queueing. The authors propose a buffered banyan switch built from smaller knockout switches which are output-buffered switches. With small knockout switches as the basic switching elements, the complexity of the overall switch fabric is manageable and no internal clock speedup is required. Furthermore, it is shown that with the proposed output-buffered banyan switch, a maximum throughput of 1 can be achieved.>

A new approach for video traffic characterization (VTC) is proposed. In this approach, it is assumed that every video sequence is characterized by a set of fundamental indexes or parameters and that the bit rate process can be generated by a parametric model of the corresponding indices. Among the implications of this approach are: the encoding process is no longer necessary to simulate the bit rate process for a particular video sequence: a video sequence needs to be processed only once to obtain its fundamental parameters: and, in general, the computation of the index processes requires much less processing than the actual encoding. If parametric models are identified for all encoding algorithms of interest, then the problem of developing models for various combinations of encoders and classes of video sequences reduces to the problem of developing a single model for the index processes of various classes of video sequences.>

An asynchronous transfer model (ATM) switch which has lower hardware complexity than that of the output queuing switch is presented. The reduction in the hardware complexity is obtained without either losing the self-routing property or suffering from performance degradation under nonuniform traffic patterns. The switch consists of shift networks that are interconnected with distributors in two stages. Introducing the distributor between the stages of shift networks allows of packets to be distributed evenly to all the input ports of shift networks in the following stage. Although the switch becomes blocking, it retains the self-routing property and achieves the maximum throughput of 100% with only a small additional delay.>

A switching network that approaches a maximum throughput of 100% as buffering is increased is proposed. This self-routing switching network consists of simple 2*2 switching elements, distributors, and buffers located between stages and in the output ports. The proposed switching requires a speedup factor of two. The structure and the operation of the switching network are described, and its performance is analyzed. The switch has log/sub 2/N stages that move packets in a store-and-forward fashion, incurring a latency of log/sub 2/N time periods. The performance analysis of the switch under uniform traffic pattern shows that the additional delay is small, and a maximum throughput of 100% is achieved as buffering is increased.>

An analytical method of evaluating the performance of the buffered banyan packet-switching network under nonuniform traffic patterns is presented. It is shown that nonuniform traffic can have a detrimental effect on the performance of the network. The analytical model is extended to evaluate the performance of multibuffer and parallel banyan networks. These modified networks are shown to have better throughput capacity and delay performance than the single-buffer banyan network.>

A queuing model for an integrated voice and data node using burst switching is presented. The integrated node is assumed to have finite capacity for holding the data units waiting for transmission. An exact analytical technique is presented for estimating the mean number of data units in the system. The computational complexity of the analytic approach developed does not depend on the buffer size. The mean number of data units in the system obtained using a quasistatic analysis is compared to that obtained using the exact approach. It is shown that the accuracy of the quasistatic analysis depends on how valid the assumption that each mode reaches the steady state is.>

The authors present an analytical method to evaluate the performance of the buffered Banyan packet-switching network under nonuniform traffic patterns. It is shown that the nonuniform traffic can have a detrimental effect on the performance of the network. The analytical model is extended to evaluate the performance of multibuffer and parallel Banyan networks. These modified networks are shown to have better throughput capacity and delay performance than the single-buffer Banyan network.>

The authors present performance results for medium access control protocols which are appropriate for voice/data integration in high-bandwidth token-passing networks. They consider two classes of protocols: (1) multiple priority cycle protocols and (2) timed-token protocols. To provide bounded delays for voice packets, both types of protocols use timers to control the data-packet transmissions on to the channel. The effect of the number of active voice sources on the timers' values is discussed. Simulation results are presented indicating that for both protocols the most important performance parameter is the maximum data information that can be carried by the channel, when the number of active voice sources is specified. Analytic formulae are derived which accurately predict the data capacities for both protocols. The derived formulae are used to present the effect of several system parameters on performance as well as to compare the performance of the two types of protocols.>

This paper presents performance results that indicate that packetized voice service can be provided on a token-passing ring without adversely affecting the performance of data traffic. This is accomplished by introducing a relatively mild priority structure: stations are limited to a single packet transmission per medium access, and voice packets are given access priority over data packets at the same station. In addition, voice traffic is allowed longer packet lengths than data traffic. Several versions of this basic scheme are considered: 1) the number of active stations is constrained so that voice packets are guaranteed access within one packetization period, 2) no guarantee on access time is provided and voice packets are discarded when the waiting time exceeds one packetization period, and 3) no guarantee on access time is provided and voice packets are buffered until they can be transmitted.

A new simple algorithm for unique ranking ofq-ary sequences is presented, using a general triangle (a triangular array of integers) that includes the well-known Pascal triangle as a special case. Applying the algorithm gives a new multilevel source coding scheme for which the prefix is the Lee weight and the suffix is the ranking number. A detailed analysis of the asymptotic performance shows that the new scheme is weighted universal. The inverse enumeration algorithm for decoding is also presented, and the complexity of the algorithm increases linearly in proportion to the length of source sequences.

Numerical techniques for the solution of a class of twodimensional Markov processes are presented. These techniques are used to analyze the performance of several versions of hybrid switching including the movable boundary scheme with finite or infinite buffers, with flow control, and with or without TASI. Also included are results for TASI in which the number of off-hook calls is not fixed. Finally, the accuracy of the quasi-static approximation is evaluated for several problems.

The performance of several simple noiseless coding schemes for binary finite-order Markov sources is considered. Bounds are derived on the maximum difference between the performance achievable by the schemes and the entropy of the sources. The schemes can be modified for the case where the source statistics are unknown.

A simple model for the intersymbol interference due to a low-frequency cutoff channel is presented. The model is used to develop a computationally efficient and accurate method for computing symbol error probability for alphabetically line-encoded sequences transmitted over this channel. The model is also used to design alphabetic line codes that minimize the symbol error probability. A method is presented for comparing codes of different efficiencies (and, hence, for a given information rate, different transmission bandwidths). Sample calculations are then presented for two commercial high-capacity baseband digital transmission systems.

This paper presents an approximation method for estimating the average number of data packets in a SENET-concept integrated voice and data system. The method is simple to use and its estimates are found to be in good agreement with simulation results. In general, the method applies to any system that integrates packet traffic with a more slowly varying traffic class that can preempt a portion of the packet transmission capacity.

A method for the noiseless coding of binary memoryless sources when the symbol probabilities are unknown is investigated. Codes of long block length are constructed from truncated run-length codes. Though not universal, the codes are shown to achieve high efficiencies over a wide range of symbol probabilities. Several generalizations of the basic scheme are also presented. The schemes presented in this paper are particularly well-suited for facsimile coding.

A source matching approach is presented to the problem of finding minimax cedes for classes of memoryless sources. The approach leads to a channel capacity problem so that Blahut's algorithm can be used to find approximations to the minimax code. Closed form solutions are presented for the class of monotonic sources and for a class of Bernoulli-like sources. For extensions of finite alphabet memoryless sources, a modified Lynch-Davisson code has performance close to that of the minimax code. The exact solution to the source matching problem and the resulting codes are presented for the extensions of binary codes up to blocklength 31.

Two results on the coding of stationary nonergodic sources are presented. The first is a source coding theorem stating that there exist variable-rate codes with performance arbitrarily close to the rate-distortion function of the stationary nonergodic source. The second is a converse information transmission theorem. It is shown that the distortion which results when the source is transmitted across a channel with capacityCis no less than the least distortion achievable by fixed-rate codes with rateC.