Probing Overhead Research Articles

Discovering and Mapping Subnet Level Topology

<p>The research of Internet measurement has promoted the development of router-level topology discovery, while the subnet of the network layer can provide a more detailed intermediate complementary view. To improve the current level of router-level topology discovery, some researchers have proposed subnet discovery methods. However, the existing methods do not perform well in terms of efficiency and accuracy, which leads to the failure of the final resulting topology map. In this paper, we propose a new approach to discover subnets, which consists of a network pre-processing stage and a subnet inference stage. Given a set of target IP prefixes, the network pre-processing stage introduces a minimal probing overhead to improve probing efficiency. Based on the IP address allocation principle, the subnet inference stage utilizes a set of complementary inference rules to infer subnets. The experimental results show that our method can achieve a higher accuracy in discovering subnets while keeping lower probing overhead compared with existing methods. Finally, we utilize the proposed approach to discover the subnets of six geographically dispersed public Autonomous System (AS) networks and analyze their various subnet characteristics, including degree distribution.</p> <p> </p>

Sleeping Contextual/Non-Contextual Thompson Sampling MAB for mmWave D2D Two-Hop Relay Probing

Millimeter wave (mmWave) band, i.e., 30 to 300 GHz, is characterized by short range transmissions and vulnerability to path blockage necessitating the use of relaying. Probing more relays finds out the best relay having the highest spectral efficiency but at the expense of increasing the probing overhead due to excessive beamforming training (BT) causing a decrease in the overall throughput. In this paper, mmWave two-hop relaying will be formulated as a single player multi-armed bandit (MAB) problem enabling one relay probing while maximizing the achievable spectral efficiency. Moreover, the relays could not establish the mmWave link due to blockage for instance will be identified as sleeping relays and eliminated from the rest of the MAB game. Thus, sleeping non contextual MAB (S-MAB) algorithm, namely sleeping Thompson sampling (S-TS) will be proposed to handle the problem. Furthermore, by utilizing the multiband capability of standardized WiGig devices containing both 2.4/5 GHz WiFi and 60 GHz mmWave bands, WiFi information will be used as contexts of the MAB game. Therefore, sleeping contextual MAB (S-CMAB) algorithm, namely S-CTS, will be proposed as well. Numerical and regret analysis ensure the superior performance of the S-CMAB algorithm over the S-MAB counterpart and the existing mmWave relay probing solutions accompanied with high convergence rates.

Achieving Zero Asymptotic Queueing Delay for Parallel Jobs

Zero queueing delay is highly desirable in large-scale computing systems. Existing work has shown that it can be asymptotically achieved by using the celebrated Power-of-d-choices (Pod) policy with a probe overhead d = Ω(log N/1-λ), and it is impossible when d = O(1/1-λ), where N is the number of servers and λ is the load of the system. However, these results are based on the model where each job is an indivisible unit, which does not capture the parallel structure of jobs in today's predominant parallel computing paradigm. This paper considers a model where each job consists of a batch of parallel tasks. Under this model, we propose a new notion of zero (asymptotic) queueing delay that requires the job delay under a policy to approach the job delay given by the max of its tasks' service times, i.e., the job delay assuming its tasks entered service right upon arrival. This notion quantifies the effect of queueing on a job level for jobs consisting of multiple tasks, and thus deviates from the conventional zero queueing delay for single-task jobs in the literature. We show that zero queueing delay for parallel jobs can be achieved using the batch-filling policy (a variant of the celebrated Pod policy) with a probe overhead d = Ω(1/(1-λ)log k) in the sub-Halfin-Whitt heavy-traffic regime, where k is the number of tasks in each job and k properly scales with N (the number of servers). This result demonstrates that for parallel jobs, zero queueing delay can be achieved with a smaller probe overhead. We also establish an impossibility result: we show that zero queueing delay cannot be achieved if d = (o(log N/log k)). Simulation results are provided to demonstrate the consistency between numerical results and theoretical results under reasonable settings, and to investigate gaps in the theoretical analysis.

CoHop

Cross-Technology Interference (CTI) badly harms the transmission reliability for low-power networks such as ZigBee at 2.4-GHz band. Though promising, channel hopping still faces challenges because the increasingly dense deployment of CTI leaves very few available channels. Selecting a good channel with the least overhead is crucial but challenging. Most of the existing works are heuristic methods that choose a channel far from the current one to avoid adjacent channels that may be correlatively interfered by CTI with a wider bandwidth such as WiFi. However, we observe that the correlated channels influenced by the same CTI source do not necessarily have the same channel qualities and even the opposite state, due to the uneven spectrum power density of CTI. Such channel opportunities are unexplored and wasted. In this article, we propose CoHop, a quantitative correlation-based channel hopping method for low-power wireless networks. We establish a quantitative model that describes the correlation of channel qualities to capture channel opportunities and calculate channel quality without probing, to reduce probing overhead. The probing sequence is optimized based on the Pearson Correlation Coefficient and the prediction-based probing algorithm. We implement CoHop on TinyOS and evaluate its performance in various environments. The experimental results show that CoHop can increase the Packet Reception Ratio by 80%, compared with existing methods.

Achieving Zero Asymptotic Queueing Delay for Parallel Jobs

Zero queueing delay is highly desirable in large-scale computing systems. Existing work has shown that it can be asymptotically achieved by using the celebrated Power-of-d-choices (pod) policy with a probe overhead $d = ømegałeft(\fracłog N 1-łambda \right)$, and it is impossible when $d = Ołeft(\frac1 1-łambda \right)$, where N is the number of servers and $łambda$ is the load of the system. However, these results are based on the model where each job is an indivisible unit, which does not capture the parallel structure of jobs in today's predominant parallel computing paradigm. This paper thus considers a model where each job consists of a batch of parallel tasks. Under this model, we propose a new notion of zero (asymptotic) queueing delay that requires the job delay under a policy to approach the job delay given by the max of its tasks' service times, i.e., the job delay assuming its tasks entered service right upon arrival. This notion quantifies the effect of queueing on a job level for jobs consisting of multiple tasks, and thus deviates from the conventional zero queueing delay for single-task jobs in the literature. We show that zero queueing delay for parallel jobs can be achieved using the batch-filling policy (a variant of the celebrated \pod\ policy) with a probe overhead $d = ømegałeft(\frac1 (1-łambda)łog k \right)$ in the sub-Halfin-Whitt heavy-traffic regime, where k is the number of tasks in each job and k properly scales with N (the number of servers). This result demonstrates that for parallel jobs, zero queueing delay can be achieved with a smaller probe overhead. We also establish an impossibility result: we show that zero queueing delay cannot be achieved if $d = \expłeft(ołeft(\fracłog N łog k \right) \right)$. Simulation results are provided to demonstrate the consistency between numerical results and theoretical results under reasonable settings, and to investigate gaps in the theoretical analysis.

High-Throughput and Robust Rate Adaptation for Backscatter Networks

Recently backscatter networks have received booming interest because, they offer a battery-free communication paradigm using propagation radio waves as opposed to active radios in traditional sensor networks while providing comparable sensing functionalities, ranging from light and temperature sensors to recent microphones and cameras. While sensing data on backscatter nodes has been seen on a clear path to increasing in both volume and variety, backscatter communication is not well prepared and optimized for transferring such continuous and high-volume data. To bridge this gap, we propose a high-throughput rate adaptation scheme for backscatter networks by exploring the unique characteristics of backscatter links and the design space of the ISO 18000-6C (C1G2) protocol. Our key insight is that while prior work has left the downlink unattended, we observe that the quality of downlink is affected significantly by multipath fading and thus can degrade the uplink and overall throughput considerably. Therefore, we introduce a novel rate mapping algorithm that chooses the best rate for both the downlink and uplink. Also, we design an efficient channel estimation method fully compatible with the C1G2 protocol and a reliable probing trigger, substantially saving probing overhead. To combat interference, we further design an interference detector using clusters and lightweight countermeasures to make rate adaptation more robust. Our scheme is prototyped using commercial RFID readers and tags. The results show that we can achieve up to $2.6\times $ throughput gain over state-of-the-art approaches across various mobility, channel, network-size, and interference conditions.

A Time-efficient Multi-Protocol Probe Scheme for Fine-grain IoT Device Identification.

Internet of Things (IoT) devices connected to the Internet are exploding, which poses a significant threat for their management and security protection. IoT device identification is a prerequisite for discovering, monitoring, and protecting these devices. Although we can identify the device type easily through grabbing protocol banner information, both brand and model of different types of device are various and diverse. We should therefore utilize multi-protocol probes to improve the fineness of device identification and obtain the corresponding brand and model. However, it is still a challenge to balance between the multi-protocol probe overhead and the identification fineness. To solve this problem, we proposed a time-efficient multi-protocol probe scheme for fine-grain devices identification. We first adopted the concept of reinforcement learning to model the banner-based device identification process into a Markov decision process (MDP). Through the value iteration algorithm, an optimal multi-protocol probe sequence is generated for a type-known IoT device, and then the optimal multi-protocol probes sequence segment is extracted based on the gain threshold of identification accuracy. We took 132,835 webcams as the sample data to experiment. The experimental results showed that our optimal multi-protocol probes sequence segment could reduce the identification time of webcams’ brand and model by 50.76% and achieve the identification accuracy of 90.5% and 92.3% respectively. In addition, we demonstrated that our time-efficient optimal multi-protocol probe scheme could also significantly improve the identification efficiency of other IoT devices, such as routers and printers.

Design of an Efficient OFDMA-Based Multi-User Key Generation Protocol

Secret key generation exploits the unique random features of wireless channels, hence, it is eminently suitable for the resource constrained Internet of Things applications. However, it has only been involved for single links between a pair of users, whilst there is a paucity of the literature on group and multi-user key generation. This paper proposes an orthogonal frequency-division multiple access (OFDMA) based multi-user key generation protocol to efficiently establish keys in a star topology. The uplink and downlink multi-user access facilitated by OFDMA allows the central node to simultaneously communicate with multiple users, which can significantly reduce the channel probing overhead. In particular, we provide a compelling case study of multi-user secret key generation by designing a prototype based on IEEE 802.11ax, a new Wi-Fi standard to be released. Our simulation results have demonstrated that the OFDMA-based multi-user key generation protocol incurs low interference amongst the users, whilst benefiting from channel reciprocity and generating unique random keys.

Optimization of Probe Train Size for Available Bandwidth Estimation in High-speed Networks

Available bandwidth parameter is a crucial characteristic in terms of networking and data transmission. The beforehand knowledge of its value and use of this parameter in various traffic engineering algorithms and QoS calculations is a key for high-efficient multigigabit data transport in nowadays networks. The challenge in available bandwidth estimations is not only in its accuracy and processing speed but also in the reduction of the amount of probe traffic injected into the network by keeping an adequate level of estimation accuracy. In this paper we extend existing active probing measurement algorithms for end-to-end available bandwidth estimation along with methods to reduce estimation times and amount of injected traffic while keeping measurement accuracy constant and even reducing the uncertainty of estimations. The main goal of this research was to detect a sufficient ratio of MTU, packet train size with the link capacity and available bandwidth (AvB) in up to 10 Gbps networks. In order to explore measurement accuracy under different conditions, a new tool for the AvB estimation named Kite2 has been developed and is presented in the paper. Comparative performance of AvB estimations using Kite2, Kite and Yaz is presented. Finally we calculate with statistical means dependency between the estimation error probability, measurement probing overhead and the measurement time.

Improving Access Point Association Protocols Through Channel Utilization and Adaptive Probing

We propose a distributed access point selection scheme by which nodes select an appropriate access point to associate with based upon each individual device's channel utilization. In this paper, we define channel utilization as the ratio of required bandwidth to estimated available bandwidth. By incorporating channel utilization into the access point selection protocol, we can effectively reduce unnecessary reassociations and improve upper layer performance such as throughput and packet delivery delay. We have further enhanced our association protocol by using reinforcement learning to dynamically schedule the probing of neighboring access points (APs), ultimately bringing down the probing overhead by learning from past experience. When channel utilization is combined with adaptive probing, we observe a significant performance improvement compared to traditional association approaches.

On Spatial Capacity of Wireless Ad Hoc Networks with Threshold Based Scheduling

This paper studies spatial capacity in a stochastic wireless ad hoc network, where multi-stage probing and data transmission are sequentially performed. We propose a novel signal-to-interference-ratio (SIR) threshold based scheduling scheme, where by starting with the first probing, each transmitter iteratively decides to further probe or stay idle, depending on whether the estimated SIR in the proceeding probing is larger or smaller than a predefined threshold. Although one can assume that the transmitters are initially deployed according to a homogeneous Poisson point process (PPP), the SIR based scheduling makes the PPP no longer applicable to model the locations of retained transmitters in the subsequent probing and data transmission phases, due to the interference induced coupling in their decisions. We first focus on single-stage probing and find that when the SIR threshold is set sufficiently small to assure an acceptable interference level in the network, the proposed scheme can greatly outperform the non-scheduling reference scheme in terms of spatial capacity. We clearly characterize the spatial capacity and obtain exact/approximate closed-form expressions, by proposing a new approximate approach to deal with the correlated SIR distributions over non-Poisson point processes. Then we successfully extend to multi-stage probing by properly designing the multiple SIR thresholds to assure gradual improvement of the spatial capacity. Furthermore, we analyze the impact of multi-stage probing overhead and present a probing-capacity tradeoff in scheduling design. Finally, extensive numerical results are presented to demonstrate the performance of the proposed scheduling as compared to existing schemes.

Probe scheduling for efficient detection of silent failures

Most discovery systems for silent failures work in two phases: a continuous monitoring phase that detects presence of failures through probe packets and a localization phase that pinpoints the faulty element(s). We focus on the monitoring phase, where the goal is to balance the probing overhead with the cost associated with longer failure detection times.We formulate a general model for the underlying fundamental subset-test scheduling problem. We unify the treatment of schedulers and cost objectives and make several contributions: We propose Memoryless schedules—a natural subclass of stochastic schedules which is simple and suitable for distributed deployment. We show that the optimal memoryless schedulers can be efficiently computed by convex programs (for SUM objectives, which minimize average detection time) or linear programs (for MAX objectives, which minimize worst-case detection time), and surprisingly perhaps, are guaranteed to have expected detection times that are not too far off the (NP hard) stochastic optima. We study Deterministic schedules, which provide a guaranteed bound on the maximum (rather than expected) cost of undetected faults, but like general stochastic schedules, are NP hard to optimize. We develop novel efficient deterministic schedulers with provable approximation ratios.Finally, we conduct an experimental study, simulating our schedulers on real networks topologies, demonstrates a significant performance gains of the new memoryless and deterministic schedulers over previous approaches.

An end-to-end measurement and monitoring technique for the bottleneck link capacity and its available bandwidth

An efficient and accurate measurement technique for the network bandwidths information can be utilized for various areas including the application layer services improvement, congestion control and for the network administration support. For these purposes, we propose an end-to-end measurement and monitoring technique for the bottleneck link capacity and its available bandwidth. This novel technique based on a new packet-pairs scheme figures out and utilizes the path signatures and sampling of the cross traffic density, through which both bandwidth metrics can be obtained from the same measurement data. This feature enables us to measure multi-metrics in a single measurement framework, reducing the probe overhead and the measurement time without causing congestions. We used ns-2 simulations and Internet measurements for the bottleneck link capacity and simulation comparisons for the available bandwidth to evaluate the performance of our proposed methodology. The results showed a high level of accuracy and a short probe time with very low intrusiveness, providing the capability of estimating the dual bandwidth metrics.

A DYNAMIC APPROACH FOR RATE ADAPTATION IN MOBILE ADHOC NETWORKS

A Mobile Ad hoc Network (MANET) is a collection of mobile nodes with no fixed infrastructure. The absence of central authorization facility in dynamic and distributed environment affects the optimal utilization of resources like, throughput, power and bandwidth. Rate adaptation is the key technique to optimize the resource throughput. Some recently proposed rate adaptations use Request to Send/Clear to Send (RTS/CTS) to suppress the collision effect by differentiating collisions from channel errors. This study presents a methodology to detect the misbehavior of nodes in MANET and proposed the new dynamic algorithm for rate adaptation which in turn can improve the throughput. The proposed approach is implemented in the distributed stipulating architecture with core and access routers. This method does not require additional probing overhead incurred by RTS/CTS exchanges and may be practically deployed without change in firmware. The collision and channel error occurrence will be detected by core router and intimated to the access router to choose alternate route and retain the current rate for transmission. The extensive simulation results demonstrate the effectiveness of proposed method by comparing with existing approaches.

Probing-Based Link Adaptation for High Data Rate Wireless LANs

We propose a probing-based link adaptation scheme that is incorporated into the aggregation with fragment retransmission (AFR) scheme for high data rate wireless LANs (WLANs). Thanks to the frame structure of multiple fragments in AFR, the proposed scheme can significantly reduce the probing overhead by transmitting a few fragments in a frame at a higher data rate. At the same time, it can easily estimate the fragment error rate in the MAC layer. To maximize the throughput and maintain the average fragment error rate below the target value, the data rate can be switched to a higher data rate based on the probing result or a more robust data rate based on the estimated fragment error rate. The proposed scheme does not need a calibration process, which is a major difficulty in implementing the exponential effective SNR mapping based fast link adaptation (FLA/EESM) scheme. Moreover, it is less affected by imperfect channel matrix estimation compared to the FLA/EESM scheme. In the performance evaluation for several channel models, the proposed scheme provides 3~10% and 5~15% more throughput than the FLA/EESM scheme with perfect and imperfect channel matrix estimations, respectively, while maintaining the average fragment error rate below the target value.

SigProbe: An Efficient End-to-End Bandwidth Measurement Technique Utilizing the Path Signatures and Graphical Analyses

Internet group-based application layer services such as the overlay networks and P2P systems can benefit from end-to-end network status information. An efficient and accurate bandwidth measurement technique plays an important role in acquiring this information. We propose an end-to-end bottleneck link capacity measurement technique that utilizes path signatures combined with graphical analyses. This feature reduces the probe overhead and decreases the convergence time. We used ns-2 simulations and actual Internet measurements, which resulted in a high level of accuracy and a short probe time with low overhead.

Improved AP association management using machine learning

We propose a distributed scheme by which nodes select an appropriate access point to associate with using each individual device's channel utilization. Specifically, we define a new metric, channel utilization, which is defined as the ratio of required bandwidth to available bandwidth estimation. By incorporating channel utilization into the access point selection protocol, we effectively reduce unnecessary reassociations and improve upper layer performance in terms of throughput, packet delivery delay, etc. We further enhance our protocol by using reinforcement learning to adapt the scheduling of probing neighboring access points (APs), ultimately reducing probing overhead by learning from past experience whether the current operational scenario would suffer from undesirable overhead. When channel utilization is combined with adaptive probing, we observed a significant performance improvement compared to traditional association approaches.

Palmtree: An IP alias resolution algorithm with linear probing complexity

Internet topology mapping studies utilize large scale topology maps to analyze various characteristics of the Internet. IP alias resolution, the task of mapping IP addresses to their corresponding routers, is an important task in building such topology maps. In this paper, we present a new probe-based IP alias resolution tool called palmtree. Palmtree can be used to complement the existing schemes in improving the overall success of alias resolution process during topology map construction. In addition, palmtree incurs a linear probing overhead to identify IP aliases. The experimental results obtained over Internet2 and GEANT networks as well as four major Internet Service Providers (ISPs) present quite promising results on the utility of palmtree in obtaining more accurate network topology maps.

Efficient and Dynamic Routing Topology Inference From End-to-End Measurements

Inferring the routing topology and link performance from a node to a set of other nodes is an important component in network monitoring and application design. In this paper, we propose a general framework for designing topology inference algorithms based on additive metrics. The framework can flexibly fuse information from multiple measurements to achieve better estimation accuracy. We develop computationally efficient (polynomial-time) topology inference algorithms based on the framework. We prove that the probability of correct topology inference of our algorithms converges to one exponentially fast in the number of probing packets. In particular, for applications where nodes may join or leave frequently such as overlay network construction, application-layer multicast, and peer-to-peer file sharing/streaming, we propose a novel sequential topology inference algorithm that significantly reduces the probing overhead and can efficiently handle node dynamics. We demonstrate the effectiveness of the proposed inference algorithms via Internet experiments.

Resolving IP Aliases in Building Traceroute-Based Internet Maps

Alias resolution, the task of identifying IP addresses belonging to the same router, is an important step in building traceroute-based Internet topology maps. Inaccuracies in alias resolution affect the representativeness of constructed topology maps. This in turn affects the conclusions derived from studies that use these maps. This paper presents two complementary studies on alias resolution. First, we present an experimental study to demonstrate the impact of alias resolution on topology measurement studies. Then, we introduce an alias resolution approach called analytic and probe-based alias resolver (APAR). APAR consists of an analytical component and a probe-based component. Given a set of path traces, the analytical component utilizes the common IP address assignment scheme to infer IP aliases. The probe-based component introduces a minimal probing overhead to improve the accuracy of APAR. Compared to the existing state-of-the-art tool ally, APAR uses an orthogonal approach to resolve a large number of IP aliases that ally fails to identify. Our extensive verification study on sample data sets shows that our approach is effective in resolving many aliases with good accuracy. Our evaluations also indicate that the two approaches (ally and APAR) should be used together to maximize the success of the alias resolution process.