Unmanned Aerial Vehicles (UAVs) play an increasingly critical role in Intelligence, Surveillance, and Reconnaissance (ISR) missions such as border patrolling and criminal detection due to their ability to access remote areas and transmit real-time imagery to servers. However, UAVs face limitations in payload, power, and communication bandwidth, necessitating selective data transmission strategies. While traditional methods strive to preserve maximal information in transferred video frames, missing the fact that only certain parts of images/video frames are relevant for Object Detection and Tracking (OD/OT) in ISR missions. This paper adopts a different perspective and offers an alternative AI-driven scheduling policy that prioritizes selecting regions of the image that significantly contribute to the mission objective. The key idea is tiling the image into small patches and developing a Deep Reinforcement Learning (DRL) framework that assigns higher transmission probabilities to patches that present higher overlaps with the detected object of interest while penalizing sharp transitions over consecutive frames to promote smooth scheduling shifts. Although we used YOLOv8 object detection and UDP transmission protocols as a benchmark testing scenario, the idea is general and applicable to different transmission protocols and OD/OT methods. To further boost the system's performance and avoid OD errors for cluttered image patches, we integrate it with inter-frame interpolations. With this method, we achieved about 45% improvement in terms of OD accuracy for the proposed method (F1 score:98%) compared to random selection (F1 score: 53%) when the transmission budget is 50% (we afford sending half of the image patches). Under an extremely constrained transmission budget (5%), this gain can be as high as 87%. The only cost for such improvement is a feedback channel from the ground server to drones.

Emergent Cyber-Physical Systems (CPSs) like VANETs and UAV swarms are expected to fulfill essential roles in critical infrastructure domains. This increasing utility and the present nurturing economic conditions that enable their cost-effective deployment herald a period of significant growth and adoption. In addition, these systems are increasingly required to support complex data-intensive and QoS-sensitive applications in challenging operating conditions. However, the growth of these systems is limited by current Internet protocols that do not comprehensively meet the communication requirements of these systems. In this work, we present the design and evaluation of Software-Defined NAmed-data enabled Publish-subscribe (SNAP) communication framework that can effectively meet the communication requirements of demanding applications in emergent CPSs.

We live in a world where social and economic disparity has led to many 'disconnects' that collectively provide unfair bias towards the top 1 % of of the wealthiest individuals and elite industry behemoths. This bias can be seen in the technical world leading to ‘disconnects' including limited access to broadband access and advanced technology. In this paper we identify hidden 'disconnects' that we believe are stifling innovation. We introduce an abstraction called 'application systems' (APPSYS) which, with more development, could move our Nation's disparate forms of large scale technology use (Facebook, Tik- Tok, and ‘the Internet’) to a technology fabric that includes current Internet applications but supplemented with an overlay of APPSYSs forming a ‘tech-fabric’ that can benefit all citizens, and that promotes citizens to contribute to the evolution of the concept. The ‘fabric’ is potentially a merging of our Nation's Critical Infrastructure with commercial innovation. These two worlds historically have been isolated however there are clearly overlaps and synergies that can no longer go unchecked. As the Nation enters the ‘Age of Machines‘, this fabric would provide the unique architectural model required to facilitate more secure, dependable Critical Infrastructure in a manner that reflects Internet-like attributes such as transparency, and policies/protocols for joining individual Autonomous Systems to form a unified system. Critical to the concept is an APPSYS which will have incentives to ‘contribute to the greater good’. In this paper, we summarize the APPSYS concept and identify necessary incremental mandates by the FCC to broaden access to advanced technology for all citizens primarily by shifting the FCC's bias away from current policies that promote the disconnect between economic success centered on the allocation of wealth that has seen the allocation move from 80- 20 (80 % of the wealth is owned by 20 % of the population to the current 90–10 allocation split.

As the adoption rate of connected vehicle technology and the complexity of associated vehicular applications grows, the load on the supporting connected vehicular network will also grow accordingly. Sustaining future application requirements will necessitate network optimization. To that end, a comprehensive understanding of network behavior under different operational conditions is essential. This paper studies vehicular network performance in a DSRC/IP network in terms of a set of network indicator metrics that are controllable through adjustments to lower layer parameters within the DSRC stack. We present and analyze results using DSRC enabled hardware modules that are substantiated and validated through our integrated simulator.

HTTP-based Adaptive Streaming (HAS) is the dominant Internet video streaming application. One specific HAS approach, Dynamic Adaptive Streaming over HTTP (DASH), is of particular interest, as it is a widely deployed, standardized implementation. Prior academic research has focused on networking and protocol issues, and has contributed an accepted understanding of the performance and possible performance issues in large deployment scenarios. Our work extends the current understanding of HAS by focusing directly on the impacts of choice of the video quality adaptation algorithm on end-user perceived quality. In congested network scenarios, the details of the adaptation algorithm determine the amount of bandwidth consumed by the application as well as the quality of the rendered video stream. HAS will lead to user-perceived changes in video quality due to intentional changes in quality video segments, or unintentional perceived quality impairments caused by video decoder artifacts such as pixelation, stutters, or short or long stalls in the rendered video when the playback buffer becomes empty. The HAS adaptation algorithm attempts to find the optimal solution to mitigate the conflict between avoiding buffer stalls and maximizing video quality. In this article, we present results from a user study that was designed to provide insights into “best practice guidelines” for a HAS adaptation algorithm. Our findings suggest that a buffer-based strategy might provide a better experience under higher network impairment conditions. For the two network scenarios considered, the buffer-based strategy is effective in avoiding stalls but does so at the cost of reduced video quality. However, the buffer-based strategy does yield a lower number of quality switches as a result of infrequent bitrate adaptations. Participants in buffer-based strategy do notice the drop in video quality causing a decrease in perceived QoE, but the perceived levels of video quality, viewer frustration, and opinions of video clarity and distortion are significantly worse due to artifacts such as stalls in capacity-based strategy. The capacity-based strategy tries to provide the highest video quality possible but produces many more artifacts during playback. The results suggest that player video quality has more of an impact on perceived quality when stalls are infrequent. The study methodology also contributes a unique method for gathering continuous quantitative subjective measure of user perceived quality using a Wii remote.

Resource allocation optimization is critical to the overall performance of wireless heterogeneous networks (HetNet). Endpoint flow association optimization tries to reach a target resource allocation outcome by only controlling the associations of data flows to abstract/concrete network interfaces at the two ends of communication sessions. An instance of this problem in a single cellular heterogeneous network is the user association optimization problem, which plans the usage of macrocells and picocells. In this paper, we focus on this problem in a multi-provider HetNet, where the component wireless networks belong to different organizations. We identify and abstract the problem, comparing with the similar systems that are under the control of a single provider. After analyzing the changes in the new context and their implications, we provide a general centralized over-the-top network service design, which does not assume controls to the underlying network infrastructure. With the problem and design in mind, we then explore the performance problem when extending the existing user association schemes in a single-provider context to the new design. Though various association schemes are proposed in the prior research under different contexts, few of them provide an in-depth evaluation to several fundamental problems that are required by the problem in single/multi-provider context, i.e. 1) the distances of the association schemes to the optimal solution under various scenarios; 2) the sources and impacts of the potential throughput estimation errors. By using relatively small scale and more controlled scenarios, this paper is the first to provide answers to the above questions, which are valuable for guiding further studies and real system designs.

This paper reports on aspects of the performance of three operational deployments of Dedicated Short Range Communication (DSRC) equipment. Performance metrics considered include throughput, latency, and the characteristics of the packet loss process. A laboratory deployment is used to establish a performance baseline for operation under ideal network conditions. Vehicle to infrastructure and vehicle to vehicle deployments are then used to evaluate the effects of real world deployments. The impact of degraded performance upon a Cooperative Adaptive Cruise Control (CACC) application is evaluated.

Due to the explosive growth of data demand from mobile devices, cellular operators have been exploring the use of WiFi to offload traffic from the LTE network. Such an integration opens the door for exploiting the network usage diversity for further overall network performance improvement, by intelligently and dynamically scheduling flows over the most appropriate network. However, how such a function can be efficiently and systematically realize, is missing from the current standard specifications, especially on the network infrastructure side. In this paper, we aim to solve such a challenge by proposing a Software-Defined Networking (SDN) based flow scheduling system that is compatible to the 3GPP LTE-WiFi integration framework. The global view provided by SDN makes it easy to collect necessary flow information, and the flexible control of SDN enables efficient flow scheduling. We view the flow scheduling problem as an overall network utility maximization problem. We prove its hardness and propose an approximation algorithm for solving the problem. The proposed system can be incrementally deployed over existing wireless network infrastructure. With extensive simulations in NS3 and demo implementation, we prove the feasibility and effectiveness of both the framework and the scheduling algorithm.

The emergence of multipath TCP (MPTCP) has made it much easier for mobile devices to use multiple wireless network access paths simultaneously. However, we find that a large amount of multipath users could negatively impact the performance of wireless networks in terms of throughput and fairness due to increased amount of wireless connections. Therefore, in this paper, we aim to mitigate such a problem while retaining the benefits of multipath access in wireless networks from the perspective of network owner. We solve the challenge by 1) identifying a solution principle that can effectively balance the two goals and 2) implementing the principle through an SDN based bandwidth usage management system on the network side. When there is congestion on an AP, our method enforces necessary suppressions on non-primary subflows from multipath users to protect the network performance, while keeping the multipath benefits as much as possible. When an AP owns idled capacity, no intervention is imposed, thus offering the maximal benefits to multipath users without substantially affecting the network performance. Thus, the multipath access is dynamically scaled to achieve a balance of the two goals. Extensive NS3 experiment with Linux Kernel MPTCP implementation demonstrates our findings as well as the effectiveness of the proposed system.

This paper presents ThinGs In a Fog (TGIF)- a system designed to support interdisciplinary research that fall under the broad context of the Internet of Things. The framework is based on an Edge Computing system design that distributes application processing to system compute nodes leveraging geographic compute location diversity of a Cloud-to-the-edge to support machine-to- machine interactions that potentially have real- time constraints. To provide further insight, we focus on Connected Vehicle as an exemplar application domain. This paper provides a summary of work-to-date, including results from a small prototype of the system deployed at Clemson University. We illustrate the system be presenting work-to-date on the design, implementation and evaluation of a Queue Warning which is an application that has been studied thoroughly by the transportation community. This particular application is nicely suited for illustrating the additional benefits and complexities associated with implementing well understood applications in emerging distributed computing environments expected to be supported by the IoT.

In this paper we implemented a switched digital video broadcast simulator to simulate a deployment by a service provider that offers a list of content channels to a pool of users. Content channels have different popularity ranking, and therefore, unpopular channels have low probability of being watched. Service providers can exploit this to use limited bandwidth to provide the same number of content channels to users. Our solution investigates the effect of using limited bandwidth allocation on the percieved quality from users' perspective. We ran experiments in which the video quality is adjusted according to bandwidth load. Our results show that it is possible to achieve a reasonable quality of service even when allocating lower bandwidth than would be needed in a traditional broadcast deployment.

As an alternate form in the road transportationsystem, electric vehicle (EV) can help reduce the fossil-fuelconsumption. However, the usage of EVs is constrained by thelimited capacity of battery. Wireless Power Transfer (WPT) can increase the driving range of EVs by charging EVs inmotionwhen they drive through a wireless charging laneembedded in a road. The amount of power that can be suppliedby a charging lane at a time is limited. A problem here iswhen a large number of EVs pass a charging lane, how toefficiently distribute the power among different penetrationslevels of EVs? However, there has been no previous researchdevoted to tackling this challenge. To handle this challenge, wepropose a system to balance the State of Charge (called BSoC) among the EVs. It consists of three components: i) fog-basedpower distribution architecture, ii) power scheduling model, and iii) efficient vehicle-to-fog communication protocol. The fogcomputing center collects information from EVs and schedulesthe power distribution. We use fog closer to vehicles ratherthan cloud in order to reduce the communication latency. Thepower scheduling model schedules the power allocated to eachEV. In order to avoid network congestion between EVs and thefog, we let vehicles choose their own communication channelto communicate with local controllers. Finally, we evaluateour system using extensive simulation studies in NetworkSimulator-3, MatLab, and Simulation for Urban MObilitytools, and the experimental results confirm the efficiency ofour system.

Mobile devices nowadays can find multiple wireless networks, such as WiFi, 4G/LTE and relay through devices. These networks have different characteristics in terms of coverage, data rate, and price. Meanwhile, mobile applications (and even different TCP/UDP connections) often have diverse and time-variant network needs. Thus, to better use all wireless network resources, it would be ideal to enable a TCP/UDP connection to 1) select the most appropriate network dynamically and 2) migrate between networks transparently. However, existing methods fail to provide both functions in a systematic and efficient way at the TCP/UDP connection level. In this paper, we adopt Software-Defined Networking (SDN) to realize such a feature. We use the features of SDN to realize intelligent network selection that is adaptive to time-variant application needs, network availability, and scheduling commands. To support transparent migration, an intelligent home agent (HA) is designed with the SDN to anchor packets from the mobile device. It can intelligently determine which wireless network a TCP/UDP connection is running over. Finally, our implementation demonstrates the effectiveness and efficiency of the proposed system.

Multipath TCP (MPTCP) was designed to increase the throughput and reliability of TCP, with specific motivation coming from scenarios including data center and cloud computing. The use of MPTCP has been recently explored to support heterogeneous wireless networks (HetNets) involving hosts that have multiple network interfaces. However, current solutions generally involve many simplifying assumptions. In this paper, we propose a new framework to collect scheduling information from various scheduling network entities and conduct optimization from a global view. The framework uses the existing or readily accessible MPTCP parameters. Under this framework, we introduce a centralized optimization algorithm to realize general proportional fairness of user throughput. Based on results from NS3 simulations, we provide evidence that the approach provides a low cost solution for improved performance from the perspectives of both applications and network operators.

We study the resource allocation and management issues related to heterogeneous wireless systems made up of several radio access technologies (RATs) that collectively provide a unified wireless network to a diverse set of users through co-ordination managed by a centralized global resource controller (GRC). We assume that the user devices are multimodal, which makes it possible for each device to use any available access point (AP)/base station (BS) of a RAT at any given time. Through detailed protocol level simulations performed in ns-2, we show an increase in spectral efficiency of up to 99 percent and an increase in short-term fairness of up to 28.5 percent for two greedy sort-based user device-to-AP/BS association algorithms implemented at the GRC compared to a distributed solution used in practice today where each user makes his/her own association decision. While the increase in overhead due to re-associations for a centralized solution grows only slightly (by up to 4.1 percent) compared to a distributed solution, we find the performance increase in spectral efficiency and short-term fairness attributes come at the cost of an order of magnitude increase (of up to 794 percent) in energy consumption.

Energy management for multimode software defined radio systems remains a daunting challenge. This brief develops a high level framework that generates a multiprocessor systems on chip architecture from a library of heterogeneous processing resources that can be reconfigured to support various modes of operation. The framework proposes joint task and core mapping with system level floorplanning. With the objective of minimizing energy, we develop an analytical probabilistic model that considers static, dynamic, configuration, and communication energy components for multiple applications characterized by probabilities of execution. Finally, a fast energy aware joint task and core mapping heuristic is proposed and performance is demonstrated on realistic benchmarks.

We study the resource allocation and management issues related to heterogeneous wireless systems made up of several Radio Access Technologies (RATs) that collectively provide a unified wireless network to a diverse set of users through co-ordination managed by a centralized Global Resource Controller (GRC). We assume that the user devices are multi-modal, which makes it possible for each device to use the Access Point (AP)/Base Station (BS) of any available RAT at any given time. Through detailed protocol level simulations performed in ns-2, we show an increase in spectral efficiency of up to 99.2% and an increase in instantaneous fairness of up to 28.5% for two greedy sort-based user device-to-AP/BS association algorithms implemented at the GRC compared to a distributed solution where each user makes his/her own association decision.

The widespread deployment and adoption of the Dynamic Adaptive Streaming over HTTP (DASH) standard is making Internet video-on-demand a ‘standard’ Internet application similar in impact as email and web browsing. While video streaming has been widely deployed and studied for decades, DASH-based streaming is very different as it involves adaptation both by the application and by TCP. The dynamics and implications of multiple levels of end-to-end congestion control are not well understood. The contribution of the research presented in this paper is twofold: first, we characterize the bandwidth consumption of a widely deployed DASH application (i.e., Netflix); second, we provide insight in how different implementations and different access networks can impact bandwidth consumption. Our results suggest that Netflix adaptation defaults to underlying TCP mechanisms during periods of heavy, sustained network congestion. However, the application algorithm is clearly intertwined with the underlying TCP mechanisms during periods of volatile network conditions. In one network scenario, we observed that a backlogged TCP flow achieved a throughput of 6 Mbps while a Netflix session (under similar path conditions) consumed less than 3 Mbps of bandwidth.

The genome sequencing problem with short reads is an emerging field with seemingly limitless possibilities for advances in numerous scientific research and application domains. It has been the hot topic during the past few years. Growing with the data population and the ease to access for personal users, how to shorten the response interval for short read mapping at a large scale computing domain is extremely important. In this paper we propose a novel FPGA-based acceleration solution with Map-Reduce framework on multiple hardware acceleration engines. The combination of hardware accelerators and Map-Reduce execution flow could greatly expedite the task of aligning short length reads to a known reference genome. Our approach is based on preprocessing the reference genomes and iterative jobs for aligning the continuous incoming reads. The read-mapping algorithm is modeled after the creditable RMAP software approach. Furthermore, theoretical speedup analysis on a MapReduce programming platform is presented, which demonstrates that our proposed architecture has efficient potential to reduce the average waiting time for large scale short reads applications.

In this paper, we present an approach to managing resources in a large-scale heterogeneous wireless network that supports reconfigurable devices. The system under study embodies internetworking concepts requiring independent wireless networks to cooperate in order to provide a unified network to users. We propose a multi-attribute scheduling algorithm implemented by a central Global Resource Controller (GRC) that manages the resources of several different autonomous wireless systems. The attributes considered by the multi-attribute optimization function consist of system spectral efficiency, battery lifetime of each user (or overall energy consumption), and instantaneous and long-term fairness for each user in the system. To compute the relative importance of each attribute, we use the Analytical Hierarchy Process (AHP) that takes interview responses from wireless network providers as input and generates weight assignments for each attribute in our optimization problem. Through Matlab/CPLEX based simulations, we show an increase in a multi-attribute system utility measure of up to 57% for our algorithm compared to other widely studied resource allocation algorithms including Max-Sum Rate, Proportional Fair, Max-Min Fair and Min Power.

We describe an efficient scheduling technique for providing weighted sharing of aggregate capacity in networks having parallel bonded channels in which a single channel may simultaneously be a member of multiple bonding groups. Our work is motivated by the introduction of this capability into version 3 of the Data Over Cable Service Interface Specification (DOCSIS). Our technique extends Golestani's self-clocked fair queuing algorithm (SCFQ). We illustrate its weighted fair-sharing properties via simulation and provide some analytic results that establish fairness under certain conditions. We also demonstrate that round robin based techniques such as weighted deficit round robin do not extend equally easily and effectively to this environment.

The proliferation of wireless broadband usage over the last decade has led to the development and deployment of multiple broadband wireless radio access technologies (RATs) such as EVDO, WiMAX, HSPA and LTE. To support the ever-increasing wireless traffic demand, researchers have worked on the concept of an integrated heterogeneous wireless environment that encompasses several of these RATs which makes the resource allocation process more efficient by assigning each user in the system to the best RAT/RATs. In this paper, for such an integrated heterogeneous wireless system, we show the possible gains in spectral efficiency at the cost of increased energy consumption for an unbalanced heterogeneous wireless network deployment scenario. In prior work, based on the assumption that all cellular operators under study were equally well-provisioned, we showed an increase in spectral efficiency of up to 75%. In the research presented in this paper, we assume the coverage of each operator might differ significantly in a given area. With this `unbalanced' scenario, we show that an ideal, centralized allocation strategy provides an almost linear tradeoff between gain in spectral efficiency (554%) and worst-case increase in energy consumption (615%) for users supporting elastic traffic.

As broadband data further blends with cellular voice, mobile devices will become the dominant portals to the connected world. However current design practices still involve building independent networks that each make their own resource decisions. In spite of the tremendous amount of related research in this area, there are still several elemental questions that must be addressed. First, is it better to treat wireless systems as independent access networks requiring the user to handle aspects of roaming between disparate wireless networks or is an internet model better where independent autonomous wireless systems (AWS) cooperate to form a single, unified cloud to users, with network level resource allocation? Second, is it better to have dedicated, low power circuitry that supports a limited set of independent wireless Radio Access technologies (RATs) or is it better to build agile handsets that adapt (reconfigure) in real-time to operate over a large range of RAT technologies and operating modes? The results in this paper shed light on these questions. We present preliminary results from a MATLAB-based simulation study that highlights the increase in spectral efficiency as the modality of devices increase. Our analysis takes into account the cost of radio reconfiguration in terms of the temporary communications downtime and the surge of power that occurs with each reconfiguration operation. Our main result suggests that nomadic users benefit the most primarily due to their ability to route traffic over 'hotspot' type of RATs that tend to have high data rates at reduced coverage, and that this in turn helps increase the 3G or 4G bandwidth available to mobile users. All nodes in the system experience an increase in spectral efficiency ranging from 14% to 75% when compared to a similar scenario that assumes no network cooperation and static radios.

Energy Management for multi-mode Software Defined Radio (SDR) systems remains a daunting challenge. In this paper, we focus on the issue of task allocation for multi-processor based systems with hybrid processing resources that can be reconfigured. With the objective of minimizing energy, we propose a fast, energy aware static task mapping heuristic to minimize the average overall energy consumption. Simulation results show that the proposed heuristic is capable of achieving results that are within 20% of the optimal solution while providing orders of magnitude speedup in processing time.

The term WiMAX is used to refer to a collection of standards, products, and service offerings derived from the IEEE 802.16 family of standards for wireless networks. These standards define physical and MAC layer elements that ensure interoperability of compatible equipment. However, the standards leave both the details of the packet scheduling algorithms and the values of performance related configuration parameters to the discretion of the equipment vendor or network operator. These algorithms and parameters ultimately determine fundamental performance characteristics such as round-trip latency and sustainable throughput on the network. In this paper, we examine performance characteristics of an operational WiMAX testbed upon which we were able to conduct controlled experiments in the absence of competing traffic. We characterize latency, throughput, protocol overhead, and the impact of WiMAX on TCP dynamics. We show that scheduling policies and parameter values impact actual performance in ways that are not possible to characterize in generic studies of WiMAX.

The paper presents results from a link capacity measurement study conducted over an IEEE 802.11b/g network with highly stressed radio propagation conditions in a football stadium. Existing capacity studies for IEEE 802.11 networks have considered either stationary or statistical multipath fading channel conditions. In an environment with a high density of people and movement such as in a football stadium or a subway station, the radio characteristics vary much more vibrantly, and their impact on network capacity is not well understood. As a first step to better understand such network characteristics, the study examines the throughput of a mobile terminal over the stadium network in the presence of varying radio conditions due to movement of people and concurrent transmissions by other IEEE 802.11 devices. The study uses a novel approach to quantify network utilization by the experiment terminal as well as other contending terminals, using a recorded packet trace. From the measured utilization, throughput, and signal strengths, key observations made include the fast variations in signal strength due to crowd movement, through put's dependency on signal strength and chosen link rate, and contention with other terminals. Based on the findings, the paper discusses useful insights for performance assessment, protocol enhancements, and improvements in measurement methodology for such networks.

Switched Digital Broadcast (SDB) is a new method of distributing video programming. Compared with traditional broadcast methods, it reduces spectrum requirements by taking advantage of the fact that not all program channels are being viewed by subscribers at the same time. The actual spectrum savings depends on human TV watching behavior, the popularity of delivered TV programs, streaming bit-rate composition and subscriber group size. We have developed a simulation model of an SDB system that allows us to explore the impact of these factors, in particular subscriber’s channel flipping behavior, on the capacity requirement. Our subscriber viewing model ranges from intense, correlated channel flipping behavior to minimal flipping behavior representing DVR usage. Our results suggest that frequent channel flipping has little effect on the spectrum requirements under normal viewing assumptions.

BitTorrent is a widely deployed peer-to-peer protocol that provides scalable file sharing capabilities. While BitTorrent applications contribute to the demand for high speed broadband access, they also contribute to the undesirable 80/20 effect wherein 80% of the bandwidth is consumed by 20% of the users. In this study we explore the impact that BitTorrent users can have on a DOCSIS cable network. We began the study by capturing packet traces of BitTorrent applications operating on two commercial DOCSIS cable networks. Next we developed for the ns-2 simulation tool a configurable mix of BitTorrent, Web browsing, and VoIP workloads and verified that the behavior of the simulated BitTorrent workloads to be consistent with the behavior observed on the commercial network. In this simulated environment, we show that as few as 15 BitTorrent users can significantly reduce the service quality experienced by other subscribers.

In this paper we evaluate the performance of a hybrid WLAN network which consists of a mixture of 802.11e nodes and 802.11b nodes. Using simulation, we show that the choice of the con- tention parameters severely affects the trade-off between the perfor- mance improvement at the 802.11e nodes and the performance degra- dation at the 802.11b nodes. An imperfect choice of contention param- eters could lead to throughput starvation at the 802.11b nodes or to a severe degradation in the ability of the 802.11e nodes to meet QoS guarantees. We demonstrate that the best choice of contention param- eters varies with the actual mix of 802.11e and 802.11b nodes and we propose an adaptive algorithm that addresses the issue. I. INTRODUCTION

The number of broadband cable access subscribers in the United States is rapidly approaching 30 million. However there is very little research that has evaluated TCP/IP in modern cable environments. We have developed a model of the data over cable system interface specification (DOCSIS) 1.1/2.0 MAC and physical layers using the 'ns' simulation package. In this paper we show that the interaction of the MAC layer on downstream TCP Web traffic leads to poor network performance as the number of active users grow. We provide an intuitive explanation of this result and explore several possible improvements.

Although virtual machine performance has been widely studied in the context of CPU utilization, the effects of virtual machines on network traffic dynamics has received far less attention. In this study, using VMware's GSX server on a Linux host, we evaluate the impact of VM overhead on TCP performance in both a LAN and emulated WAN environment. It is shown that when multiple VM hosted TCP senders compete on a LAN, sustained aggregate throughput decreases significantly and that ack arrival distributions are strongly affected. In the emulated WAN environment, TCP is shown to exhibit increasingly bursty behavior with associated increases in loss rate as the number of virtual Web servers increases.

Using the ns simulator, we perform a detailed study of the fairness and the smoothness properties of SimdNR, an enhanced version of SIMD. Our study includes TFRC and TCP congestion control protocols in both steady-state and highly dynamic network conditions through RED and DropTail routers. Our results show that SimdNR is fair to TCP through RED routers in steady-state scenario. But, SimdNR is not fair to TCP over drop tail routers. Also our results show that SimdNR demonstrates less smoothness than TFRC in steady-state scenario and superior smoothness than TFRC in dynamic network conditions

A model of the data over cable (DOCSIS) version 1.1/2.0 MAC and physical layers using the ns simulation package is developed. In this paper we present the results of a performance analysis that we have conducted using the model. The main objective of our study is to examine the performance impact of several key MAC layer system parameters as traffic loads are varied. We focus on the DOCSIS best effort service. We measure the level of ACK compression experienced by a downstream TCP connection and show that even under moderate load levels DOCSIS can cause TCP acknowledgement packets to compress in the upstream direction leading to bursty (and lossy) downstream dynamics. We explore the use of downstream rate control on network performance and find that it does reduce the level of ACK compression for moderate load levels compared to an equivalent network scenario without rate control. However, as the number of active subscribers on a given channel increase, the level of ACK compression grows implying that other mechanisms should be looked at to improve performance during periods of high usage.

The set of TCP congestion control algorithms associated with TCP-Reno (e.g., slow-start and congestion avoidance) have been crucial to ensuring the stability of the Internet. Algorithms such as TCP-NewReno (which has been deployed) and TCP-Vegas (which has not been deployed) represent incrementally deployable enhancements to TCP as they have been shown to improve a TCP connection's throughput without degrading performance to competing flows. Our research focuses on delay-based congestion avoidance algorithms (DCA), like TCP-Vegas, which attempt to utilize the congestion information contained in packet round-trip time (RTT) samples. Through measurement and simulation, we show evidence suggesting that a single deployment of DCA (i.e., a TCP connection enhanced with a DCA algorithm) is not a viable enhancement to TCP over high-speed paths. We define several performance metrics that quantify the level of correlation between packet loss and RTT. Based on our measurement analysis, we find that, although there is useful congestion information contained within RTT samples, the level of correlation between an increase in RTT and packet loss is not strong enough to allow a TCP-sender to improve throughput reliably. While DCA is able to reduce the packet loss rate experienced by a connection, in its attempts to avoid packet loss, the algorithm reacts unnecessarily to RTT variation that is not associated with packet loss. The result is degraded throughput as compared to a similar flow that does not support DCA.

Many corporate WAN architects are considering migrating from costly leased line circuits to 'private IP' services. In order to do so IP service providers must provide service level agreements (SLA) that offer robust assurances that cover service availability and performance. The industry direction is to model IP SLA after those offered by frame relay networks. The reality however is that the SLA surrounding today's private IP services only loosely mirror frame relay SLA. In this paper, we examine the intent and limitations of current IP SLA. We explore the feasibility of two significant enhancements. First we study the feasibility of reducing the time scales associated with the performance assessment to something that is meaningful to the corporate end user. Second we explore the potential benefits of extending current performance assessment methods with application level performance metrics. We present preliminary results suggesting that it is possible to offer performance assurances based on carefully chosen latency objectives as long as the average utilization of the access link is less than 50% over time scales identical to those used by the performance metrics. We introduce a Web-oriented performance metric (the Web Response Time metric) and show promising benefits over traditional ping based metrics. However, for either ping or Web-based performance metrics, due to the inherent nature of a best-effort IP service, IP performance assurances are only practical when applied over long time scales.

Our research focuses on end-to-end congestion avoidance algorithms that use round trip time (RTT) fluctuations as an indicator of the level of network congestion. The algorithms are referred to as delay-based congestion avoidance or DCA. Due to the economics associated with deploying change within an existing network, we are interested in an incrementally deployable enhancement to the TCP/Reno protocol. For instance, TCP/Vegas, a DCA algorithm, has been proposed as an incremental enhancement. Requiring relatively minor modifications to a TCP sender, TCP/Vegas has been shown to increase end-to-end TCP throughput primarily by avoiding packet loss. We study DCA in today's best effort Internet where IP switches are subject to thousands of TCP flows resulting in congestion with time scales that span orders of magnitude. Our results suggest that RTT-based congestion avoidance may not be reliably incrementally deployed in this environment. Through extensive measurement and simulation, we find that when TCP/DCA (i.e., a TCP/Reno sender that is extended with DCA) is deployed over a high speed Internet path, the flow generally experiences degraded throughput compared to an unmodified TCP/Reno flow. We show (1) that the congestion information contained in RTT samples is not sufficient to predict packet loss reliably and (2) that the congestion avoidance in response to delay increase has minimal impact on the congestion level over the path when the total DCA traffic at the bottleneck consumes less than 10% of the bottleneck bandwidth.