Energy consumption in buildings accounts for a significant portion of the global energy use. Consequently, understanding building energy use is important. Data over the past decade show that the energy intensity (Joules/sqft) of commercial buildings has decreased. While some of the improvements (decrease in energy use) are easily measurable such as the use of more energy efficient lighting, impact of other modifications such as changes to the operation of the HVAC system or changes in the usage pattern of the building potentially due to external events are difficult to quantify. Simply comparing energy consumption prior and post change is not accurate as energy use is impacted by many factors including external weather conditions. In this paper, we present a case study to quantify the impact of external events on the energy consumption of a medium-sized office building. We adopt an approach based on counterfactual analysis. Towards this end, we first build two models based on Linear Regression and k-Nearest Neighbors to predict the daily energy use given different input features related to the weather. We determine the statistical features of the weather that are most predictive of energy use. We then use the models to determine a counterfactual baseline and thereby to accurately estimate the impact of the events. The results of the counterfactual analysis provide new insights on the impact of the events on energy consumption. The update to the building cooling system resulted in more energy savings than direct yearly comparison reveals. On the other hand, the tests of a MPC-based controller for the HVAC system saved less energy than determined by the direct yearly comparison. Finally, the results show that there no gains in terms of energy savings due to remote work during the COVID-19 pandemic. An increase in airflow setting in the HVAC system corroborates this finding and further validates the underlying model and the counterfactual analyses.

For a Chinook salmon restoration project in the lower Yuba River in California, we designed and deployed a wireless sensor network to monitor river temperatures at micro-habitat scales. The study required that temperatures be measured along a 3 km study reach, across the channel, and into off-channel areas. To capture diel and seasonal fluctuations, sensors were sampled quarter-hourly for the full duration of the six-month juvenile salmon winter residency. This sampling duration required that nodes minimize power-use. We adopted event-based software on MSP430 micro-controllers with 433 MHz radio and minimized the networking duty-cycle. To address link failures, we included network storage. As the network lacked real-time clocks, data were timestamped at the destination. This, coupled with the storage, yielded timestamp inaccuracies, which we re-aligned using a novel algorithm. We collected over six months of temperature data from 35 sensors across seven nodes. Of the packets collected, we identified 21% as being incorrectly timestamped and were able to re-align 41% of these incorrectly timestamped packets. We collected temperature data through major floods, and the network uploaded data until the flood destroyed the sensors. The network met an important need in ecological sampling with ultra-low power (multi-year battery life) and low-throughput.

The choice of feedback mechanism between delay and packet loss has long been a point of contention in TCP congestion control. This has partly been resolved, as it has become increasingly evident that delay based methods are needed to facilitate modern interactive web applications. However, what has not been resolved is what control should be used, with the two candidates being the congestion window and the pacing rate. BBR is a new delay based congestion control algorithm that uses a pacing rate as its primary control and the congestion window as a secondary control. We propose that a congestion window first algorithm might give more desirable performance characteristics in situations where latency must be minimized even at the expense of some loss in throughput. To evaluate this hypothesis we introduce a new congestion control algorithm called TCP Davis, which is a congestion window first algorithm that adopts BBR's approach of maximizing delivery rate while minimizing latency. In this paper, we discuss the key features of this algorithm, discuss the differences and similarity to BBR, and present results based on a real implementation.

There is an increasing trend in the use of wireless communication along with new traffic signal control (TSC) algorithms to leverage and accommodate connected and autonomous vehicles. However, this development has increased the potential for cyber-attacks on TSC that can undermine the benefits of these new algorithms. An advanced persistent adversary can learn the behavior of TSC algorithms and launch attacks to preferentially get green time and/or to create traffic congestion in one intersection which can spread to the entire network. In this paper, we consider backpressure-based (BP-based) TSC algorithms and compare their performance under two misinformation attacks - 1) time spoofing attack in which vehicles alter their arrival times at the intersection and 2) ghost vehicle attack in which vehicles disconnect the wireless communication and thereby hide from the TSC. We show that these misinformation can influence the signal phases determined by BP-based TSC algorithms. We consider an adversary that determines a set of arriving vehicles to be attack vehicles from many candidate sets (attack strategies) in order to maximize the number of disrupted signal phases. We show that by formulating the problem as a 0/1 Knapsack problem, the adversary can explore the space of attack strategies and determine the optimal strategy that maximally compromises the performance in terms of average delay and fairness. We propose two protection algorithms, namely, auction-based (APA) and hybrid-based (HPA) algorithms and show that they are able to mitigate the impacts of the misinformation attacks.

One major source of air pollution is automobile emissions in urban areas. Although hybrid and fully electric vehicles are started to gain popularity, the majority of vehicles are still fuel-based. With the rapid advancement of artificial intelligence (AI) and automation based controllers, there have been numerous studies applying such learning-based techniques to Intelligent Transportation Systems (ITS). Combining deep neural networks with reinforcement learning (RL) models called DRL has shown promising results when applied to urban Traffic Signal Control (TSC) for adaptive adjustment of traffic light schedules. Centralized and decentralized DRL-based controller models are proposed in literature to optimize the total system travel time. However, the associated impact of such learning-based TSCs to the air quality remains unexplored. In this paper, we examine the impact of DRL-based TSCs on the environment in terms of fuel consumption and CO2 emission. We studied a major DRL approach called advantage actor-critic (A2C) using multi-agent settings on a synthetic multi-intersection network and on a real traffic network of San Francisco downtown with 24 hours traffic dataset. Our initial results indicate that learning based DRL methods achieved the lowest air pollution level on synthetic networks even with a simple delay-based reward function. However, DRL-based TSC performs slightly worse than rule-based adaptive TSCs (max-pressure control) in the San Francisco network.

In 5G networks, wide-band mmWave can be used to provide extreme data rates to user equipments (UEs). However, since mmWave is coverage limited, it necessitates dense placement of base stations, which in turn can significantly increase the fiber deployment cost. One solution being considered is to replace fibers with Integrated Access and Backhaul (IAB) network, where a part of the wireless spectrum is used for connecting base stations. In an asymmetric IAB network, standard proportional fair scheduling algorithm (PF) fails to distribute resources among UEs fairly. We propose a new weighted proportional fair (WPF) scheduling algorithm to improve the fairness of UE's achieved throughput in an IAB network. Also to mitigate congestion in IAB nodes and improve system throughput, we propose an IABaware end-to-end flow control (I-EEFC) algorithm. Through detailed analyses for both symmetric and asymmetric network topologies, we show that our proposed combined scheduling and flow control algorithm (WPF+I-EEFC) improves both fairness and system throughput.

We consider a science network that runs applications requiring data transfers to be completed within a given deadline. The underlying network is a software defined network (SDN) that supports fine grain real-time network telemetry. Deadline-aware data transfer requests are made to a centralized network controller that schedules the flows by setting pacing rates of the deadline flows and metering the background traffic at the ingress routers. The goal of the scheduling algorithm is to maximize the number of flows that meet the deadline while maximizing the network utilization. In this paper, we develop a Reinforcement Learning (RL) agent based network controller and compare its performance with well-known heuristics. For a network consisting of a single bottleneck link, we show that the RL-agent based network controller performs as well as Earliest Deadline First (EDF), which is known to be optimal. We also show that the RL-agent performs significantly better than an idealized TCP protocol in which the bottleneck link capacity is equally shared among the competing flows. We also study the sensitivity of the RL-agent controller for different parameter settings and reward functions.

The recently-proposed centralized cloud radio access network (C-RAN) promises to deal with the ever-increasing traffic volume and reduce network cost by centralizing the baseband operation and simplifying radio access points. However, compared with traditional radio access network, whether it always has performance gain, and how large the gain will be are still open questions. This paper presents and analyzes a simple stochastic model for C-RAN wherein dynamic resource sharing is allowed in the centralized pool. Based on this, a cost-constrained delay minimization framework for C-RAN is proposed to optimize its capacity configuration. With the same network cost and traffic load, the multiplexing gain of C-RAN over traditional access network is analyzed under this framework. Bounds of the multiplexing gain are obtained, and the conditions under which C-RAN performs better are derived. Besides showing the optimal delay and multiplexing gain performance under homogeneous traffic scenario, numerical results also extend to heterogeneous arrivals, where the impact of traffic heterogeneity on the multiplexing gain is explored.

In a model-based covert timing channel (CTC), the (covert) sender modulates the inter-packet delays (IPDs) of the packet stream generated by the overt application (source) by following a well-known statistical model of the application traffic. Implementing a CTC system that operates on real application traffic such as Skype requires addressing several challenges. First, packets generated by Skype must meet a maximum end-to-end delay requirement, which imposes limits on how long a packet can be buffered by the sender. Second, buffer overrun and underrun may occur because of transient mismatches between the rate at which packets are generated by the source and the rate at which the sender can service the covert buffer. As a single IPD of Skype traffic is small and has a small delay spread, we propose to use delay of multiple IPDs to modulate the encoded symbols. To minimize buffer overruns and underruns, we partition the delay of multiple IPDs so that each encoded symbol can be mapped to multiple partitions of the delay distribution. We then provide a mathematical model to choose the appropriate partition for a given encoded symbol based on the state of the buffer. We evaluate the performance of a users-space implementation of the CTC system in real network settings for Skype traffic. We show that the covert channel based on the proposed design can be established even when the source is connected to a public WiFi network and it is largely non-detectable under well-known statistical tests including the entropy test, the Kolmogorov–Smirnov test, and the Kullback–Leibler divergence test. Copyright © 2015 John Wiley & Sons, Ltd.

In existing model-based timing channels, the requirement for the target model to be shared between the sender and the receiver limits the sender's ability to adapt to changes in the inter-packet delay (IPD) distribution of the application traffic. In this paper, using analog fountain codes (AFCs) with a general model-fitting coding framework, we design timing channel schemes that allow the sender to change the target model without synchronizing with the receiver. We first propose analog fountain timing channels based on symbol transition when the application packet streams have IPD distribution that is shape similar to the distribution of AFC code symbol values. For more general packet streams, we then propose analog fountain timing channels based on symbol split in which the linearly mapped symbols are split using a symbol probability split matrix to mimic the IPD distribution of the application traffic. We use real VoIP and SSH traffic to compare the proposed schemes with model-based timing channels using LT codes and AFC. Experimental results show that both the proposed schemes are model-secure. The robustness of the two schemes is higher than the model-based timing channels using LT codes whereas not as good as those using AFC when the sender and receiver sides are synchronized with respect to the target model. Moreover, when the sender and the receiver are not synchronized with respect to the model, the robustness of the proposed schemes is significantly higher than model-based timing channels.

Network throughput is scaling "up" to higher data transfer rates while processors are scaling "out" to multiple cores. As a result, network adapter "offloads" and performance "tuning" have received a good deal of attention lately. However, much of this attention is focused on the "how" and not the "why" of performance efficiency. There are two types of efficiencies that we have found particularly intriguing: First, processor core "affinity," or "binding" is fundamentally the choice of which processor core or cores handle certain tasks in a network- or I/O-heavy application running on a MIMD machine. Second, Ethernet "pause frames" slightly violate the "end-to-end" nature of TCP/IP in order to perform link-to-link flow control. The goal of our research is to delve deeper into why these tuning suggestions and this offload exist, and how they affect the end-to-end performance and efficiency of a single, large TCP flow.

For a given TCP or UDP flow, protocol processing of incoming packets is performed on the core that receives the interrupt, while the user-space application which consumes the data may run on the same or a different core. If the cores are not the same, additional costs due to context switches, cache misses, and the movement of data between the caches of the cores may occur. The magnitude of this cost depends upon the processor affinity of the user-space process relative to the network stack. In this paper we present a prototype implementation of a tool which enables the application processing and protocol processing to occur on cores which share the lowest cache level. The Cache-Aware Affinity Deamon (CAAD) analyzes the topology of the die and the NIC characteristics and conveys information to the sender which allows the entire end-to-end path for each new flow to be be managed and controlled. This is done in a light-weight manner for both uni and bi-directional flows. Measurements show that for bulk data transfers using commodity multicore machines, the use of CAAD improves the overall TCP throughput by as much as 31%, and reduces the cache miss rate as much as 37.5%. GridFTP combined with CAAD improves the download time for big file transfers by up to 18%.

Data centers are being deployed in a wide variety of environments (cloud computing, scientific, financial, defense, etc.). When geographically distributed, these data centers must transmit and receive growing volumes of data. In order to avoid congestion in the public internet, most use high speed dedicated optical networks, which can be thought of as private highways for carrying data. In this work, we examined the impact of such high speed network traffic on a commodity multicore machine, and identified a number of scenarios that cause packet loss and degraded throughput due to an end-system inability to consume incoming data fast enough. We show that high speed single flow traffic nullifies the benefits of multicore systems and multiqueue NICs, and we propose an end-system aware flow bifurcation technique to optimize the data transfer time using rate based protocols. Using introspective end-system modeling, we determine the optimal number of parallel flows required to utilize the available bandwidth, and the optimal rate for each of the flows. We compare our approach with GridFTP, which is a widely used data transfer protocol in computational grids, and show that our approach performs better (particularly when the end-system losses are in the receive ring buffer.).

A model-based Covert Timing Channel (CTC) embeds a covert message into the inter-packet delays (IPDs) of the network traffic generated by a legitimate overt application. The modulated IPDs are generated to follow a well known statistical model of the overt application's network traffic. This provides non-detectability of the covert channel using certain statistical tests and hence the modulation is referred to as model-secure. However, jitter, introduced by the network or an adversary, can disrupt the timing channel. In this work, we improve the CTC's robustness without prior knowledge of the channel error characteristics. We encode the covert message using Fountain codes, continuously generating encoded symbols until transmission is successful. Additionally, we reduce bit error with an IPD guard band between the intervals that represent the binary alphabet. While the guard band reduces bit error, it also alters the IPD distribution, resulting in degraded model-security. We measure the loss in model-security using the Kolmogorov-Smirnov (KS) test and the Kullback-Leibler (KL) divergence measure and study the trade-off between security, robustness, and throughput. We describe the implementation of the Fountain code based covert communication system, which we refer to as the Covert Fountain, and extensively study the performance under multiple network settings.

The transmission capacity of today's high-speed networks is often greater than the capacity of an end-system (such as a server or a remote client) to consume the incoming data. The mismatch between the network and the end-system, which can be exacerbated by high end-system workloads, will result in incoming packets being dropped at different points in the packet receiving process. In particular, a packet may be dropped in the NIC, in the kernel ring buffer, and (for rate based protocols) in the socket buffer. To provide reliable data transfers, these losses require retransmissions, and if the loss rate is high enough result in longer download times. In this paper, we focus on UDP-like rate based transport protocols, and address the question of how best to estimate the rate at which the end-system can consume data which minimizes the overall transfer time of a file.

Traffic density in wireless networks is time- and space-varying as users move from one area to another. For example, the majority of traffic stays in residential areas in the early morning and late evening; but moves to business or commercial areas in daytime. Therefore, it is challenging to efficiently locate base stations during network planning stage, due to the time-varying traffic distribution. Base stations vary from highly congested to seldom utilized depending on time. However, measurement studies show that the movement of the traffic density is highly predictable, and the traffic always travel along similar routes among different parts in a city or town during one day or over a week. Therefore, we introduce the traffic-tracing gateway (TTG), which acts as the base station that tracks the movement of the traffic. Given the traffic distribution of a period, we design an algorithm to determine the optimal trajectories of TTGs that can cover the maximum traffic. Our solution framework can optimally deploy TTGs in the congested areas to provide better coverage and relieve congestion. Our simulation studies based on realistic user mobility show that TTGs can result in significant improvement over fixed infrastructure based network across multiple metrics in multiple scenarios.

One of the key challenges facing network administrators in securing an enterprise network is the anonymity of the traffic on the network. Although current research has taken steps forward addressing the issue of identifying the application layer protocols (e.g., SSH, HTTP, or FTP) a more fine-grained identification is required for a variety of applications that run over these established application layer protocols. We are specifically interested in disambiguating traffic that is carried by the HTTP application layer protocol. In this paper, we investigate representatives of classes of applications, namely social networking (Facebook), web-mail (Gmail), and streaming video applications (YouTube), all of which communicate via the HTTP protocol. We use specific features derived from network traffic (i.e., the TCP/IP packet headers) that can be used to classify the flows as belonging to each application. An important aspect of our work is to classify the applications based on any segment of the traffic flow. We consider different signals that can be derived from the network flow such as the packet sizes and inter-arrival times and apply simple statistical and spectral analysis to identify distinguishing features of the applications. Our classification system yields a classification rate of 93% or better using only packet size statistics. We evaluate our system on network flows collected from the backbone of the UC Davis campus network. Furthermore, we consider two types of noise an adversary may inject to evade detection: packet padding and altering the inter-packet delays. Despite these two types of noise, using our classification method we are still able to achieve a reasonable classification rate.

Excessive Green House Gas emission and high fuel consumption from vehicles has become not only an environmental but also an economic issue. This work demonstrates CarbonRecorder, a mobile-social application suite that is designed to enable individuals to track their daily vehicular carbon emission, and share them on social networks. It is intended to not only raise social awareness of vehicular carbon emission and encourage more efficient driving behavior, but also serve as a platform for data collection for research in vehicular traffic management, carbon emission, and user behavior analysis in social network based applications.

Wireless networking enabled vehicles can form vehicular ad hoc mesh networks (VMeshs). Using cooperative communication among VMeshs, a local transient information could be "retained" within a given geographic region for a certain period of time, without any infrastructure help. In this paper, we study this "storage capability" of VMeshs. We analyze the scenarios of highway traffic (both one-way and two-way highway free flow traffic) and vehicular traffic in a city environment. For highway traffic, we study different properties of the "VMesh storage", using a simulation tool that accurately models the freeway vehicular mobility. For city traffic, we first perform simulations based on real traffic trace of San Francisco Yellow Cabs. Then we compare the results with the scenario where a general Random Way Point (RWP) mobility model is used. Our results show that transmission range has high impact on the storage lifetime for one-way highway traffic, and the size of the region in which we want the information stored has high impact for two-way highway traffic. For city-wide traffic, the storage's lifetime generated using San Francisco Yellow Cab trace is shorter than that obtained using the RWP mobility model. This is due to the regular movement of the cabs as compared to the random vehicle movement in the RWP mobility model.

Network security applications such as to detect malware, security breaches, and covert channels require packet inspection and processing. Performing these functions at very high network line rates and low power is critical to safe guarding enterprise networks from various cyber-security threats. Solutions based on FPGA and single or multi-core CPUs has several limitations with regards to power and the ability to match the ever increasing line rates. This paper describes a MPPA (Massively Parallelized Processing Architecture) framework based on the Ambric parallel processing device that can speed up computation of network packet processing and analysis tasks. This is accomplished with a programmable processor interconnection that enables parallelizing the application and replication of data through channels. In this paper, we consider three network security applications - detecting malware, detecting covert timing channels, and a symmetric encryption engine. Experimental analyses of parallel implementations of the detection algorithms show that MPAA can easily achieve throughput greater than 1 Gbps with low power usage.

Wireless communication provides network access free of the limitations of wired networks. However, some emerging applications with high bandwidth requirements and delay constraints, such as real-time video-on-demand and IPTV, suffer poor performance due to the high compression rate of video frames and/or high packet loss rate in the wireless access networks. In this paper, we propose a novel optimization algorithm referred to as the network state dependent video compression rate (NSDVCR) algorithm, which determines the compression rates depending on the video characteristics and the network condition. The proposed NSDVCR algorithm is able to achieve optimal video transmission rate for a given network state characterized by packet loss rate. The simulation results of the proposed mechanism show that significant improvement of the video quality measured in terms of peak-signal-to-noise ratio (PSNR), is achieved compared with standard compression mechanisms.

Many large-scale scientific applications need to aggregate large amounts of data from multiple distributed sites to a centralized facility. We call such a request as a data-aggregation request (DAR). In this study, we investigate the novel problem of on-demand DAR provisioning over a wavelength-division multiplexing (WDM) backbone network. We provide a mathematical formulation for our problem as a mixed integer linear program (MILP). To solve large versions of our problem, we propose a DAR provisioning heuristic (called DARP). We use the MILP with various objectives as a benchmark for studying the performance of DARP.

Network and service providers are rapidly deploying IPTV networks to deliver a wide variety of video content to subscribers. Some video content may be protected by copyright and/or may be subject to distribution restrictions. Encryption technologies may not always be effective to manage protected video content, particularly when video content is legally decrypted upon receipt by a subscriber. This paper presents a new approach to detect if specific (or protected) downloaded video is being redistributed by a subscriber using the broadband Internet connection. The approach employs a traffic-based signature of the protected video clip. The signature which is shown to be unique is stored in a signature store. We adopt a wavelet-based analysis to match video streams captured from the network to the signatures in the store. The performance of the detection algorithm is evaluated using a large video database populated with a variety of movies and TV shows. The experiment results show that our algorithm achieves high detection rates and low false alarm rates using video clips of only a few seconds.

We study the performance of TCP (transmission control protocol) over a wireless fading link using MIMO (multiple input multiple output) technology. MIMO technology using multiple transmit and receive antennas can potentially mitigate the effect of fading by providing diversity gain and/or increase the throughput by providing multiplexing gain. Given the number of transmit and receive antennas, there exists a tradeoff between the diversity and multiplexing gains. We study the effect of the so-called diversity-multiplexing tradeoff on the throughput of TCP. We demonstrate by cross-layer simulations involving the physical and transport layers that diversity gain is more useful to enhance TCP throughput when the signal-to-noise ratio (SNR) is low, and multiplexing gain is more useful when SNR is high. Our results indicate that there exist SNR levels at which switching from diversity-providing schemes to multiplexing schemes would provide enhanced TCP throughput. We propose a cross-layer rate-switching scheme to enhance TCP throughput over a wide range of SNR values.

Noting that the optical part of a hybrid wireless- optical broadband access network (WOBAN) has high capacity, we need to enhance the capacity for wireless access using a low-cost solution. Our prior work developed a solution where each wireless node was equipped with a single radio. Deploying multiple radios, say two, at each node will improve the performance of wireless access, but this will also increase the cost of the solution. However, deploying multiple radios at only a few nodes, especially those that are overloaded with traffic, can lead to a less-costly solution, possibly without sacrificing performance. Hence, we study how to optimally place a limited number of additional radios at the wireless nodes to save the overall network cost. We formulate this problem as an Integer Linear Program (ILP) and solve it using a standard solver such as CPLEX. As expected, by deploying multiple radios at bottleneck wireless nodes, we can obtain almost the same performance as a WOBAN with multi-radios at all nodes.

Hybrid wireless-optical broadband access network (WOBAN) is a combination of wireless and optical networks to optimize the cost and performance of an access network. Wireless nodes collect traffic from end users and carry them to the optical part of a WOBAN using multiple hops, accumulating delay at each wireless node. Moreover, the radio capacity on each wireless link limits the capacity on each outgoing link from the node in a single-radio wireless mesh network (WMN) of a WOBAN. Thus, delay and capacity limitation in the WMN of a WOBAN is a major bottleneck. We design a capacity and delay aware routing scheme, CaDAR, to minimize the delay and increase network support in the WMN of a WOBAN. Our analysis shows that CaDAR is an efficient routing scheme for a single-radio WMN for a WOBAN that can support much higher load and has lower system delay than other approaches because of better load balanced routing.

In many e-science applications, there exists an important need to aggregate information from data repositories distributed around the world. In an effort to better link these resources in a unified manner, many lambda-grid networks, which provide end-to-end dedicated optical-circuit-switched connections, have been investigated. In this context, we consider the problem of aggregating files from distributed databases at a (grid) computing node over a lambda grid. The challenge is (1) to identify routes (that is, circuits) in the lambda-grid network, along which files should be transmitted, and (2) to schedule the transfers of these files over their respective circuits. To address this challenge, we propose a hybrid approach that combines offline and online scheduling. We define the Time-Path Scheduling Problem (TPSP) for offline scheduling. We prove that TPSP is NP-complete, develop a Mixed Integer Linear Program (MILP) formulation for TPSP, and then propose a greedy approach to solve TPSP because the MILP does not scale well. We compare the performance of the greedy approach on a few representative lambda-grid network topologies. One key input to the offline schedule is the file transfer time. Due to dynamics at the receiving end host, which is hard to model precisely, the actual file transfer time may vary. We first propose a model for estimating the file transfer time. Then, we propose online reconfiguration algorithms so that as files are transferred, the offline schedule may be modified online, depending on the amount of time that it actually took to transfer the file. This helps in reducing the total time to transfer all the files, which is an important metric. To demonstrate the effectiveness of our approach, we present results on an emulated lambda-grid network testbed.

With the availability of cheap and robust wireless devices there is demand for new applications in vehicular ad-hoc networks (VANET). The challenge in implementing applications is in understanding of the complex dynamics of highly mobile multi-hop ad hoc networks which is a characteristics of VANET. Studies have been reported that attempt to quantify transport protocol (TCP and UDP) performance in mobile ad-hoc network in general and VANet in particular. However, very little work has been done in looking at the effect of tuning transmission power and its effect on the performance of the transport layer protocols. Our work specifically looks at the result of tuning transmission power and its effect on UDP throughput in VANet. To facilitate this study we first developed a comprehensive integrated simulation tool which accurately simulates both vehicular mobility patterns and wireless network environment and the communication protocols; the former is based on a cellular automata model while the later is developed using JIST/SWANS network simulator. Results show that the major mitigating factor in VANETs multi-hop environment is the number of hops between the source and the destination. Increasing the transmission range results in decreasing the number of hops between source and destination effectively increasing throughput. However, increasing the transmission range beyond a certain point saturates the throughput due to increased interference. We also found that the effect of vehicle densities is only important at lower transmission ranges to provide the required connectivity.

A control-plane architecture for supporting advance reservation of dedicated bandwidth channels on a switched network infrastructure is described including the front-end web interface, user and token management scheme, bandwidth scheduler, and signaling daemon. A path computation algorithm for bandwidth scheduling is proposed based on an extension of Bellman-Ford algorithm to an algebraic structure on sequences of disjoint non-negative real intervals. An implementation of this architecture for UltraScience Net is briefly described.

Next-generation e-science applications will require the ability to transfer information at high data rates between distributed computing centers and data repositories. To support such applications, lambda grid networks have been built to provide large, on-demand bandwidth between end-points that are interconnected via optical circuit-switched lambdas. It is extremely important to develop an efficient transport protocol over such high-capacity, dedicated circuits. Because lambdas provide dedicated bandwidth between endpoints, they obviate the need for network congestion control. Consequently, past research has demonstrated that rate-based transport protocols, such as RBUDP, are more effective than TCP in transferring data over lambdas. However, while lambdas eliminate congestion in the network, they ultimately push the congestion to the endpoints - congestion that current rate-based transport protocols are ill-suited to handle. In this paper we introduce a "rate-adaptive protocol for intelligent delivery (RAPID)" of data that is lightweight and end-system performance-aware, so as to maximize end-to-end throughput while minimizing packet loss. Based on self monitoring of the dynamic task-priority at the receiving end-system, our protocol enables the receiver to proactively deliver feedback to the sender, so that the sender may adapt its sending rate to avoid congestion at the receiving end-system. This avoids large bursts of packet losses typically observed in current rate-based transport protocols. Over a 10-Gigabit link emulation of an optical circuit, RAPID reduces file-transfer time, and hence improves end-to-end throughput by as much as 25%.

Target tracking in wireless sensor networks requires efficient coordination among sensor nodes. Existing methods have focused on tree-based collaboration, selective activation, and group clustering. This paper presents a prediction-based adaptive algorithm for tracking mobile targets. We use adaptive Kalman filtering to predict the future location and velocity of the target. This location prediction is used to determine the active tracking region which corresponds to the set of sensors that needs to be "lighted". The velocity prediction is used to adaptively determine the size of the active tracking region, and to modulate the sampling rate as well. In this paper, we quantify the benefits of our approach in terms of energy consumed and accuracy of tracking for different mobility patterns. Our simulation results show that advance resource reservation coupled with adaptively changing the size of the active tracking region and the sampling rate reduces the overall energy consumed for tracking without affecting the accuracy in tracking.

With multipath routing in mobile ad hoc networks (MANETs), a source can establish multiple routes to a destination for routing data. In MANETs, multipath routing can be used to provide route resilience, smaller end-to-end delay, and better load balancing. However, when the multiple paths are close together, transmissions of different paths may interfere with each other, causing degradation in performance. Besides interference, the physical diversity of paths also improves fault tolerance. We present a purely distributed multipath protocol based on the AODV-multipath (AODVM) protocol called AODVM with path diversity (AODVM/PD) that finds multiple paths with a desired degree of correlation between paths specified as an input parameter to the algorithm. We demonstrate through detailed simulation analysis that multiple paths with low degree of correlation determined by AODVM/PD provides both smaller end-to-end delay than AODVM in networks with low mobility and better route resilience in the presence of correlated node failures.

The problem of aggregating large data files from distributed databases and address the corresponding challenges involved from a network architecture perspective is considered. We model this problem as one of identifying a time-path schedule (TPS) in a graph representation of the network. We prove that the TPS problem (TPSP) is NP-complete. We then propose a mixed integer linear programming (MILP)-based approach and three heuristics longest-file-first (LFF), disjoint-paths (DP), and most-distant-file-first (MDFF) - to solve TPSP.

Localization and clustering of sensor nodes are important services in a sensor network since the nodes are typically deployed in an ad-hoc manner into an infrastructure-less terrain. When beacons are used for localization, there are two critical design issues: 1) to maximize the lifetime of the beacons and 2) to maximize the coverage area. With clustering, the goal is to minimize the energy dissipation of the sensor network. In this paper, we consider the placement of beacons and data loggers (that act as cluster heads) in the Cosumnes River Preserve, which is a joint collaborative restoration project between the Cosumnes Research Consortium at University of California at Davis (UCD) and The Nature Conservancy. Currently, there are many types of sensors deployed in the preserve which are wired to data loggers. Our objective is to determine the minimum number and placement of beacons and data loggers for wireless sensors deployed in the preserve. We formulated an optimization problem which is solved by integer linear program (ILP).

In this paper we present an analytical model to study the performance of channel sharing schemes to support both circuit switched voice and packet data services in a GSM/GPRS network. We study three channel sharing schemes: 1) fixed sharing in which cell channels are statically partitioned into two sets one for voice calls and the other for data traffic; 2) partial sharing in which n/sub data/ channels are reserved for data while the remaining N $n/sub data/ channels are shared by voice and data with preemptive priority for voice calls; and 3) complete sharing in which all the channels shared by voice and data with preemptive priority to voice calls. We investigate several key issues such as call blocking rate and mean packet delay for different cell loads with the data source modeled by Markov modulated Poisson process (MMPP). We validate the mathematical model through simulations and quantify the impact of the data source model and the call load on the mean packet delay for different channel sharing schemes.

In order to support new personal communication services (PCS) in 2.5G and 3G networks, the underlying signaling network must support scalable and fault-tolerant mobility management. A mobility management architecture based on multiple home location registers (HLRs) and multiple gateway GPRS support nodes (GGSN) can meet both of these requirements. We consider an enhanced network architecture in which the mobility management databases, in particular, the HLRs, are interconnected by a TCP/IP network. The primary function of this additional network interface will be to support synchronization of the replicated and/or distributed HLRs. We outline the architecture of the converged signaling network and discuss the integration with the GPRS network. We then present analytical models to quantify the benefit of distributed HLR and replicated GGSN architectures. Our results show that a distributed HLR architecture can reduce the update and query delay. Finally, by appropriately load balancing the multiple GGSNs, the mean packet delay can be significantly reduced.

This paper we present a comparative study of a few simple but representative usage-based pricing strategies. For the current best-effort Internet, we introduce a QoS sensitive pricing mechanism which takes into account the fact that the quality of received audio degrades as the number of hops traversed by the audio packets increases. We compare the QoS sensitive pricing with flat pricing, congestion sensitive pricing, and a hybrid scheme that combines QoS sensitive and congestion sensitive pricing schemes. Our study is based on a two class user model; type 1 users pay any price for the best QoS and type 2 users request the best QoS at a cost that is less than some maximum price they are willing to pay. Experimental results show the following: i) The QoS sensitive pricing has the lowest blocking probability and also the lowest service distance (the average distance between the client and the servicing gateway) for type 1 calls of any of the schemes. However, it does so by forcing type 2 calls away from the home gateway and hence gives a lower QoS to these calls. ii) The congestion sensitive pricing scheme adapts to the current load at a gateway and hence is good at providing a low service distance to type 2 calls. Unfortunately, it does this by increasing the blocking probability of a type 2 call. iii) The combination of congestion sensitive and QoS sensitive pricing is quite effective and incorporates the best elements of both schemes: it has a very low blocking probability (close to that of QoS sensitive pricing) while retaining a low service distance of type 2 calls. However, at very high loads, the correlation between price and distance breaks down resulting in an increase in the service distance of type 1 calls.

In multi-tier cellular networks a set of contiguous microcells are overlayed with a macrocell. Such architectures provide a higher system capacity because of the small frequency reuse distance of the microcell layer. However, handoff control is a key issue in such architectures; decrease in the cell dwelling time causes higher number of handoffs and hence higher handoff blocking probability. Queueing handoff calls when there are no idle channels, in the target cell, can improve handoff blocking probability without significantly increasing the new call blocking probability. We first present an analytical model to study the performance of a single-tier cellular network with two types of users, namely, high-speed users and low-speed users. We then use this model to analyze a multi-tier network with a queue in only one tier. Finally, we use a simulation model to examine the multi-tier network with different queue strategies. Our results show that by using a priority queue in the multi-tier network, the blocking probability of handoff calls can be significantly improved at the same time supporting a large system load.

Layered video is a video compression technique to encode video data in multiple layers. It typically consists of a base layer and additional layers that provide enhanced video quality. The multicasting operation of a layered video may need to satisfy: (i) bounded end-to-end delay from a source to each receiver, (ii) minimum total cost, and (iii) minimum delay jitter between the various video streams received by the receivers. Because different nodes may request different video quality and because of limited bandwidth on the network's links, different layers of video data may reach their destinations over different distribution trees, and not all receivers may receive all of their requested layers. The problem of computing such data distribution paths is NP-complete, which means that no optimal solution method is available. This paper presents a new heuristic algorithm called LVMSR. With O(Rn/sup 2/) time complexity and O(R/sup 2/) message complexity, where n is the number of nodes in the network and R is the receiver group size. Our simulation results show that the multicast data paths computed by our algorithm can always satisfy the delay constraint with reasonably small total cost.

In this paper, we consider an enhancement to the existing signaling system number 7 (SS7) network architecture in which the mobility management databases, in particular, the home location registers (HLRs), are interconnected by a TCP/IP network. The primary function of this additional network will be to support concurrency control of replicated HLR databases. Since additional bandwidth can be added to the TCP/IP network as required, a higher degree of replication can be supported than in the legacy narrow-band SS7 network. The enhanced signaling network also provides other advantages: 1) since the HLR databases can now be accessed through the Internet, they can be used to support mobility management for mobile-IP services; 2) the enhanced network will enable new types of mobile applications in which the location information of mobile terminals can be queried over the Internet; and 3) the additional network interface will allow more effective management and control of the HLR databases. In this paper, we outline the key aspects of the enhanced network architecture and describe a prototype implementation. Our preliminary results based on experiments on a local area network (LAN) show that when the network is not the bottleneck, a moderate degree of replication can be supported even with nodes with low processing capacities.

Fair allocation of available bandwidth to competing flows is a simple form of quality of service (QoS) that can be provided to customers in packet-switched networks. A number of packet-scheduling and buffer-management techniques have been proposed in the literature to achieve this goal efficiently. However, the complexity of the existing algorithms prevents a high-speed implementation with the current state of router technology. We propose a computationally simple mechanism based on token bucket policing to achieve almost equal bandwidth allocation for a set of competing flows. The proposed method adjusts the token bucket threshold dynamically and measures the instantaneous arrival rate of flows. It uses this information to decide whether or not to admit a packet arriving at the network edge. With minor modifications, our framework can be used in the Internet and frame relay based virtual private networks (VPNs). We present a detailed simulation study that evaluates the performance of our algorithm. The simulation results indicate that DTB is fair, efficient, and robust.

Server-side congestion arises when a large number of users wish to retrieve files from a server over a short period of time. Under such conditions, users are in a unique position to benefit enormously by sharing retrieved files. Pseudoserving, a new paradigm for Internet access, provides incentives for users to contribute to the speedy dissemination of server files through a contract set by a "superserver". Under this contract, the superserver grants a user a referral to where a copy of the requested file may be retrieved in exchange for the user's assurance to serve other users for a specified period of time. Simulations that consider only network congestion occurring near the server show that: (1) pseudoserving is effective because it self-scales to handle very high request rates; (2) pseudoserving is feasible because a user who participates as a pseudoserver benefits enormously in return for a relatively small contribution of the user's resources; (3) pseudoserving is robust under realistic user behavior because it can tolerate a large percentage of contract breaches; and (4) pseudoserving can exploit locality to reduce usage of network resources. Experiments performed on a local area network that account for the processing of additional layers of protocols and the finite processing and storage capacities of the server and the clients, corroborate the simulation results. They also demonstrate the benefits of exploiting network locality in reducing download times and network traffic while making referrals to a pseudoserver. Limitations of pseudoserving and potential solutions to them are also discussed.

Mobility support in IP networks requires the use of servers to forward packets to mobile hosts and to maintain information pertaining to a mobile host's location in the network. In one proposed protocol, the mobile IP protocol, location and packet forwarding functions are provided by servers referred to as home agents. These home agents may become the bottleneck when there are a large number of mobile hosts in the network. In this paper, we consider the design and analysis of load balancing mechanisms for multiple home agents in the mobile IP protocol. We propose a load balancing scheme in which a home agent may periodically transfer the control of a mobile host to another home agent in the same network through the use of functions supported in mobile IP. The periodicity with which this transfer is performed affects the load balancing gain as well as the associated overhead. We analyze our load balancing mechanism under bursty traffic arrival conditions using a Markov modulated Poisson process. The results show that the proposed load balancing scheme can yield modest gains over alternative load balancing strategies.

This paper presents a simulation analysis of the impact of mobility on TCP/IP augmented with features to support host mobility in wide area networks. Our results show that the existing version of TCP can yield low throughput in highly mobile environments due to the fact that TCP cannot discriminate packets dropped due to hand-offs with those dropped due to congestion in one or more network resources. As a result, TCP invokes a congestion recovery process when packets are lost during internetwork hand-offs of the mobile host. We investigate a proposal in which the transport layer explicitly receives information from the network layer of any ongoing mobility. We show that by effectively capitalizing this information, TCP can appropriately extend the slow-start phase in the recovery process and achieve higher throughput. Based on the simulation analysis we also show the robustness of this scheme in the presence of both host mobility and network congestion.>

We study the effectiveness of different parallel architectures for achieving the high throughputs and low latencies needed in processing signaling protocols for high speed networks. A key performance issue is the trade off between the load balancing gains and the call record management overhead. Arranging processors in large groups potentially yields higher load balancing gains but also incurs higher overhead in maintaining consistency among the replicated copies of the call records. We study this tradeoff and its impact on the design of protocol processing systems for two generic classes of parallel architectures, namely, shared memory and distributed memory architectures. In shared memory architectures, maintaining a common message queue in the shared memory can provide the maximal load balancing gains. We show, however, in order to optimize performance it is necessary to organize the processors in small groups since large groups result in higher call record management overhead. In distributed memory architectures with each processor maintaining its own message queue there is no inherent provision for load balancing. Based on a detailed simulation analysis we show that organizing the processors into small groups and using a simple distributed load balancing scheme yields modest performance gains even after call record management overheads are taken into account. We find that the common message queue architecture outperforms the distributed architecture in terms of lower response time due to its improved load balancing capability. Finally, we do a fault-tolerance analysis with respect to the call-record data structure. Using a simple failure recovery model of the processors and the local memory, we show that in the case of shared memory architecture, the availability is also optimized when processors are organized in small groups. This is because when comparing architectures the higher call record management overhead incurred for larger group sizes must be accounted for as system unavailability.

This paper presents a simulation analysis of the impact of mobility on data transport protocols. We consider the TCP/IP protocol augmented with features to support host mobility in wide area networks. Our results show that the existing version of TCP can yield low throughput in highly mobile environments due to the fact that TCP cannot discriminate packets dropped due to hand-offs with those dropped due to congestion in one or more network resources. We investigate a proposal in which the transport layer explicitly receives information from the network layer of any ongoing mobility. We show that by effectively capitalizing this information, TCP can appropriately extend the slow-start phase in the recovery process and achieve higher throughput. Based on the simulation analysis we also show the robustness of this scheme in the presence of both host mobility and network congestion.>

The authors study the effectiveness of different parallel architectures for achieving high throughputs necessary for processing signaling traffic in high speed networks. They consider shared memory and distributed memory parallel architectures for processing signaling messages. A key performance issue is the trade-off between load balancing gains and call record management overhead; arranging processors in large groups potentially yields higher load balancing gains but also incurs higher overhead in maintaining consistency amongst the replicated copies of the call records. They study this tradeoff and its impact on the choice of optimal parallel architectures for protocol processing. The results show that for shared memory architectures, which provide the maximal load balancing gains, organizing the processors in small groups optimizes the performance for a wide range of traffic loads. For distributed memory architectures, which do not inherently provide any load balancing, organizing the processors into small groups and using a simple distributed load balancing scheme yields modest performance gains even after call record management overheads are taken into account. A good architecture is a hybrid one using a distributed architecture in which each node is a small processing group with shared memory.>

The viability of distributed control restoration using digital cross-connect systems (DCS) depends on its capability for restoring services within specified time requirements, and its economics for providing restoration compared to other alternatives. The authors report a Bellcore study for the impact of the DCS architecture on distributed restoration. This study concludes that currently proposed distributed control DCS self-healing schemes may not meet the 2 second restoration objective for large metropolitan local exchange carrier's networks, regardless of the distributed algorithm used, if the present DCS system architecture which uses serial message processing and serial path cross-connection remains unchanged. They also discuss several DCS architecture enhancement options, including a parallel processing/cross-connect DCS architecture, which may improve the service restoration time.>

A well-known algorithm for updating multiple copies is the Thomas majority consensus algorithm. This algorithm, before performing an update, needs to obtain permission from a majority of the nodes in the system. We study the response-time behavior of a symmetric (each node seeks permission from the same number of other nodes and each node receives requests for update permission from the same number of other nodes) distributed update-synchronization algorithm where nodes need to obtain permission from only O(/spl radic/N) (N being the number of database copies) other nodes before performing an update. The algorithm we use is an adaptation of Maekawa's O(/spl radic/N) distributed mutual exclusion algorithm to multiple-copy update-synchronization. This increase in the efficiency of the update-synchronization algorithm enhances performance in two ways. First, the reduction in transaction service time reduces the response time. Second, for a given arrival rate of transactions, the decrease in response time reduces the number of waiting transactions in the system. This reduces the probability of conflict between transactions. To capture the interaction between the probability of conflict and the transaction response time, we define a new measure called the conflict response-time product. Based on the solution of a queueing model we show that optimizing this measure yields a different and more appropriate choice of system parameters than simply minimizing the mean transaction response time.>

A protocol for a slotted-ring local area network to handle two classes of jobs in which one class has preemptive priority over the other is presented. The detailed response time distribution analysis for different classes of jobs is given. It is shown that the modeling and analysis can be extended to multiclass jobs.>

Article Optimal dynamic scheduling of task tree on constant-dimensional architectures Share on Authors: Xiangdong Yu View Profile , Dipak Ghosal View Profile Authors Info & Claims SPAA '92: Proceedings of the fourth annual ACM symposium on Parallel algorithms and architecturesJune 1992 Pages 138–146https://doi.org/10.1145/140901.140916Online:01 June 1992Publication History 1citation209DownloadsMetricsTotal Citations1Total Downloads209Last 12 Months0Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

The concept of a processor working set (PWS) as a single value parameter for characterizing the parallel program behavior is introduced. Through detailed experimental studies of different algorithms on a transputer-based multiprocessor machine, it is shown that the PWS is a robust measure for characterizing the workload of a multiprocessor system. It is shown that processor allocation strategies based on the PWS provide significantly better throughput-delay characteristics. The robustness of PWS is further demonstrated by showing that allocation policies that allocate processors more than the PWS are inferior in performance to those that never allocate more than the PWS-even at a moderately low load. Based on the results, a simple static allocation policy that allocates the PWS at low load and adaptively fragments at high load to one processor per job is proposed.>

The formulation and validation of an analytical approach for the performance evaluation of the Manchester dataflow computer is discussed. The analytical approach is based on closed queuing network models. The average parallelism of the dataflow graph being executed on the dataflow architecture is shown to be related to the population of the closed network. The model of the dataflow computer is validated by comparing the analytical results to those obtained from the prototype Manchester dataflow computer and from simulation. The bottleneck centers in the prototype machine have been identified through the model, and various architectural modifications have been investigated from performance considerations.>

Since each of the levels in a hierarchical system could have various characteristics, different fault-tolerant schemes could be appropriate at different levels. A stochastic Petri net (SPN) is used to investigate various fault-tolerant schemes in this context. The basic SPN is augmented by parameterized subnet primitives to model the fault-tolerant schemes. Both centralized and distributed fault-tolerant schemes are considered. The two schemes are investigated by considering the individual levels in a hierarchical system independently. In the case of distributed fault tolerance, two different checkpointing strategies are considered. The first scheme is called the arbitrary checkpointing strategy. Each process in this scheme does its checkpointing independently; thus, the domino effect may occur. The second scheme is called the planned strategy. Here, process checkpointing is constrained to ensure no domino effect. The results show that, under certain conditions, an arbitrary checkpointing strategy can perform better than a planned strategy. The effect of integration on the fault-tolerant strategies of the various levels of a hierarchy are studied.>

Analytical models are presented that use Petri nets for fault-tolerant schemes used in distributed systems. These models are used in the quantitative evaluation and selection of good fault-tolerant schemes for specific system configurations. Several different fault-tolerant schemes that can be modeled using Petri nets are discussed in detail. These schemes include rollback recovery with checkpointing, recovery blocks, N-version programming, and conversations. After a brief review of Petri net models, extension of the Petri net models to incorporate fault-tolerant schemes is considered. A methodology for evaluating a fault-tolerant scheme for a specific system configuration and the steps involved in building a Petri net model of a fault-tolerant system are described. The subnet primitives involved in building these models are identified and an algorithm for building the models automatically is described. Examples illustrating this extended Petri net model are discussed and numerical results are presented to show the applicability of the models.>

This paper presents analytical results of computation-communication issues in dynamic dataflow architectures. The study is based on a generalized architecture which encompasses all the features of the proposed dynamic dataflow architectures. Based on the idea of characterizing dataflow graphs by their average parallelism, a queueing network model of the architecture is developed. Since the queueing network violates properties required for product from solution, a few approximations have been used. These approximations yield a multi-chain closed queueing network in which the population of each chain is related to the average parallelism of the dataflow graph executed in the architecture. Based on the model, we are able to study the effect on the performance of the system due to factors such as scalability, coarse grain vs. fine grain parallelism, degree of decentralized scheduling of dataflow instructions, and locality.

Asynchronous packet-switched interconnection networks with decentralized control are very appropriate for multiprocessing and data-flow architectures. The authors present performance models of single- and multiple-ring networks based on token-ring, slotted-ring, and register-insertion-ring protocols. The multiple ring networks have the advantage of being reliable, expandable, and cost effective. An approximate and uniform analysis, based on the gate M/G/1 queuing model, has been developed to evaluate the performance of both existing single-ring networks and the proposed multiple-ring networks. Approximations are good for low and medium load. The analyses are based on symmetric ring structure with nonexhaustive service policy and infinite queue length at each station. They essentially involve modeling of queues with single- and multiple-walking servers. The results obtained from the analytical models are compared to those obtained from simulation.>

Dataflow computers are an alternative to the von Neumann architectures and are capable of exploiting large amount of parallelism inherent in many computer applications. This paper deals with the performance analysis of the Manchester dataflow computer based on queueing network models. The model of the dataflow computer has been validated by comparing the analytical results with those obtained from the prototype Manchester dataflow computer. The bottleneck centers in the prototype machine have been identified through the model and various architectural modifications have been investigated both from performance and reliability viewpoints.