Network Performance Prediction Research Articles

A comprehensive approach to flow-based seismic risk analysis of water transmission network

Earthquakes are natural disasters that cause serious social disruptions and economic losses. In particular, they have a significant impact on critical lifeline infrastructure such as urban water transmission networks. Therefore, it is important to predict network performance and provide an alternative that minimizes the damage by considering the factors affecting lifeline structures. This paper proposes a probabilistic reliability approach for post-hazard flow analysis of a water transmission network according to earthquake magnitude, pipeline deterioration, and interdependency between pumping plants and 154 kV substations. The model is composed of the following three phases: (1) generation of input ground motion considering spatial correlation, (2) updating the revised nodal demands, and (3) calculation of available nodal demands. Accordingly, a computer code was developed to perform the hydraulic analysis and numerical modelling of water facilities. For numerical simulation, an actual water transmission network was considered and the epicenter was determined from historical earthquake data. To evaluate the network performance, flow-based performance indicators such as system serviceability, nodal serviceability, and mean normal status rate were introduced. The results from the proposed approach quantitatively show that the water network is significantly affected by not only the magnitude of the earthquake but the interdependency and pipeline deterioration.

Dynamic modulation scaling enabled multi-hop topology control for time critical wireless sensor networks

The previous work on connection driven topology control has shown that it has significant potential to reduce energy consumption of Wireless Sensor Networks (WSNs). Dynamic Modulation Scaling (DMS) which is a technique that manages transmission power levels in order to change the number of bits encoded per symbol has a direct impact on connection driven topology control. In this paper we investigate the transmission scheduling of multi-hop real-time WSNs equipped with DMS enabled radio chips while taking the effect of DMS on topology control into account. To our best knowledge, this is the first paper that addresses this issue. The current work on DMS enabled WSN tend to rely on theoretical DMS models to predict network performance metrics. However, there is little, if any, work that is based upon empirically verified network performance outcomes using DMS especially on its effect on connection driven topology control. This paper fills this gap by using GNU Radio and Software Defined Radio hardware to show how to emulate DMS in low power wireless systems and measure the impact of varying Signal-to-Noise levels, distance and elevation on throughput and delivery rates for different DMS control strategies. Next, we present the Mixed Integer Nonlinear Optimization Problem of minimizing energy consumption of DMS enabled connection driven topology control on real-time WSNs. Lastly, we present two polynomial time heuristics and compare their performance against the optimal solution.

Performance optimization of QoS-supported dense WLANs using machine-learning-enabled enhanced distributed channel access (MEDCA) mechanism

Quality of service (QoS) implementation in a wireless local area network (WLAN) enables the prediction of network performance and utilization of effective bandwidth for multimedia applications. In QoS-supported WLAN, enhanced distributed channel access (EDCA) adjusts back-off parameters to implement priority-based channel access at the medium access control (MAC) layer. Although conventional QoS-supported EDCA in WLANs can provide a certain degree of QoS guarantee, the performance of best effort data (low-priority) traffic is sacrificed owing to the blind use of a binary exponential back-off (BEB) mechanism for collision avoidance among WLAN stations (STAs). In EDCA, the BEB mechanism exponentially increases the contention window (CW[AC]) for any specific priority access category (AC) when collision occurs and resets it to its initial size after successful data transmission. This increase and reset of CW[AC] is performed regardless of the network density inference, i.e., a scarce WLAN does not require an unnecessary exponential increase in CW[AC]. Similarly, a dense WLAN causes more collisions if CW[AC] is reset to its initial minimum size. Machine-learning algorithms can scrutinize an STA’s experience for WLAN inference. Therefore, in this study, we propose a machine-learning-enabled EDCA (MEDCA) mechanism for QoS-supported MAC layer channel access in dense WLANs. This mechanism utilizes a Q-learning algorithm, which is one of the prevailing models of machine learning, to infer the network density and adjust its back-off CW[AC] accordingly. Simulation results show that MEDCA performs better as compared to the conventional EDCA mechanism in QoS-supported dense WLANs.

Performance Bounds of Decentralized Search in Expert Networks for Query Answering

Expert networks are formed by a group of expert-professionals with different specialties to collaboratively resolve specific queries posted to the network. In such networks, when a query reaches an expert who does not have sufficient expertise, this query needs to be routed to other experts for further processing until it is completely solved; therefore, query answering efficiency is sensitive to the underlying query routing mechanism being used. Among all possible query routing mechanisms, decentralized search, operating purely on each expert’s local information without any knowledge of network global structure, represents the most basic and scalable routing mechanism, which is applicable to any network scenarios even in dynamic networks. However, there is still a lack of fundamental understanding of the efficiency of decentralized search in expert networks. In this regard, we investigate decentralized search by quantifying its performance under a variety of network settings. Our key findings reveal the existence of network conditions, under which decentralized search can achieve significantly short query routing paths (i.e., between O (log n ) and O (log 2 n ) hops, n : total number of experts in the network). Based on such theoretical foundation, we further study how the unique properties of decentralized search in expert networks are related to the anecdotal small-world phenomenon. In addition, we demonstrate that decentralized search is robust against estimation errors introduced by misinterpreting the required expertise levels. The developed performance bounds, confirmed by real datasets, are able to assist in predicting network performance and designing complex expert networks.

Bounds on GreenTouch GreenMeter Network Energy Efficiency

In this paper, we validate the energy efficiency improvements in core networks obtained through mixed integer linear programming (MILP) optimization models as part of the GreenMeter study carried out by the GreenTouch consortium by developing closed form expressions and bounds for the power consumption of core networks. We consider nonbypass, bypass, mixed line rates, and physical topology optimization energy efficiency schemes. In addition to validating the optimization model results by setting bounds on the power consumption, these bounds can predict network performance at operating conditions highly complex for the MILP models. The derivation of a single bound that includes all the measures proved intractable and therefore each measure is evaluated separately.

Advanced Wireless Sensor Networks for Sustainable Buildings Using Building Ducts

The communication technology ZigBee has been widely adopted in wireless sensor networks (WSNs) for a wide range of industrial applications. However, although ZigBee provides low-power, low-cost mesh networking, it cannot guarantee steady and predictable network performance as channels are time-variant and highly attenuated by man-made obstacles. The networks also suffer from interference, especially in the important 2.4 GHz industrial, scientific, and medical (ISM) band. These degraded channel characteristics increase the number of hops, thus increasing both the packet error rate and transmission delays. In this paper, we report the deployment of a ZigBee-based WSN inside an existing building duct system utilized for intelligent waste collection in an industrial environment. The Received Signal Strength (RSS) and path losses were measured, revealing that the duct communication channel acts as a very effective waveguide, providing a more reliable and consistent network performance than conventional free space channels.

IDaaS: Inter-Datacenter Network as a Service

Increasing number of Internet-scale applications, such as video streaming, incur huge amount of wide area traffic. Such traffic over the unreliable Internet without bandwidth guarantee suffers unpredictable network performance. This result, however, is unappealing to the application providers. Fortunately, Internet giants like Google and Microsoft are increasingly deploying their private wide area networks (WANs) to connect their global datacenters. Such high-speed private WANs are reliable, and can provide predictable network performance. In this paper, we propose a new type of service—inter-datacenter network as a service (iDaaS), where traditional application providers can reserve bandwidth from those Internet giants to guarantee their wide area traffic. Specifically, we design a bandwidth trading market among multiple iDaaS providers and application providers, and concentrate on the essential bandwidth pricing problem. The involved challenging issue is that the bandwidth price of each iDaaS provider is not only influenced by other iDaaS providers, but also affected by the application providers. To address this issue, we characterize the interaction between iDaaS providers and application providers using a Stackelberg game model, and analyze the existence and uniqueness of the equilibrium. We further present an efficient bandwidth pricing algorithm by blending the advantage of a geometrical Nash bargaining solution and the demand segmentation method. For comparison, we present two bandwidth reservation algorithms, where each iDaaS provider's bandwidth is reserved in a weighted fair manner and a max-min fair manner, respectively. Finally, we conduct comprehensive trace-driven experiments. The evaluation results show that our proposed algorithms not only ensure the revenue of iDaaS providers, but also provide bandwidth guarantee for application providers with lower bandwidth price per unit.

Conflict Resolution in Mobile Networks: A Self-Coordination Framework Based on Non-Dominated Solutions and Machine Learning for Data Analytics [Application Notes

Self-organizing network (SON) is a well-known term used to describe an autonomous cellular network. SON functionalities aim at improving network operational tasks through the capability to configure, optimize and heal itself. However, as the deployment of independent SON functions increases, the number of dependencies between them also grows. This work proposes a tool for efficient conflict resolution based on network performance predictions. Unlike other state-of-theart solutions, the proposed self-coordination framework guarantees the right selection of network operation even if conflicting SON functions are running in parallel. This self-coordination is based on the history of network measurements, which helps to optimize conflicting objectives with low computational complexity. To do this, machine learning (ML) is used to build a predictive model, and then we solve the SON conflict by optimizing more than one objective function simultaneously. Without loss of generality, we present an analysis of how the proposed scheme provides a solution to deal with the potential conflicts between two of the most important SON functions in the context of mobility, namely mobility load balancing (MLB) and mobility robustness optimization (MRO), which require the updating of the same set of handover parameters. The proposed scheme allows fast performance evaluations when the optimization is running. This is done by shifting the complexity to the creation of a prediction model that uses historical data and that allows to anticipate the network performance. The simulation results demonstrate the ability of the proposed scheme to find a compromise among conflicting actions, and show it is possible to improve the overall system throughput.

Machine Learning for Performance Prediction in Mobile Cellular Networks

In this paper, we discuss the application of machine learning techniques for performance prediction problems in wireless networks. These problems often involve using existing measurement data to predict network performance where direct measurements are not available. We explore the performance of existing machine learning algorithms for these problems and propose a simple taxonomy of main problem categories. As an example, we use an extensive real-world drive test data set to show that classical machine learning methods such as Gaussian process regression, exponential smoothing of time series, and random forests can yield excellent prediction results. Applying these methods to the management of wireless mobile networks has the potential to significantly reduce operational costs while simultaneously improving user experience. We also discuss key challenges for future work, especially with the focus on practical deployment of machine learning techniques for performance prediction in mobile wireless networks.

Behavioral Model of IEEE 802.15.4 Beacon-Enabled Mode Based on Colored Petri Net

The IEEE 802.15.4 standard is widely employed in power-constrained scenarios, such as Wireless Sensor Networks deployments. Therefore, modeling this standard is useful to predict network performance and fine-tune parameter settings. Previous work rely on determining all reachable network states, usually by a Markov chain, which is often complex and error prone. In contrast, we provide a novel behavioral approach to the IEEE 802.15.4 modeling, which covers the literature gap in assessing all metrics of interest, modeling asymmetric traffic condition and fully comprising the beacon-enabled mode. In addition, it is possible to test different values for the parameters of the standard, such as aMaxFrameRetries, macMaxCSMABackoffs, initialCW, and aUnitBackoffPeriod. The model was validated by NS2 simulations and by a testbed composed of telosB motes.

Achieving minimum bandwidth guarantees and work-conservation in large-scale, SDN-based datacenter networks

Performance interference has been a well-known problem in datacenters and one that remains a constant topic of discussion in the literature. Software-Defined Networking (SDN) may enable the development of a robust solution for interference, as it allows dynamic control over resources through programmable interfaces and flow-based management. However, to date, the scalability of existing SDN-based approaches is limited, because of the number of entries required in flow tables and delays introduced. In this paper, we propose Predictor, a scheme to scalably address performance interference in SDN-based datacenter networks (DCNs), providing minimum bandwidth guarantees for applications and work-conservation for providers. Two novel SDN-based algorithms are proposed to address performance interference. Scalability is improved in Predictor as follows: first, it minimizes flow table size by controlling flows at application-level; second, it reduces flow setup time by proactively installing rules in switches. We conducted an extensive evaluation, in which we verify that Predictor provides (i) guaranteed and predictable network performance for applications and their tenants; (ii) work-conserving sharing for providers; and (iii) significant improvements over DevoFlow (the state-of-the-art SDN-based proposal for DCNs), reducing flow table size (up to 94%) and having similar controller load and flow setup time.

Intelligent vertical handoff decision strategy based on network performance prediction and consumer surplus value for next generation wireless networks

Vertical handoff (VHO) decision services play an essential role in the current wireless networks. Many algorithms designed aim at quality of service while granting seamless roaming amongst a number of heterogeneous access networks. In this study, the authors proposed an intelligent VHO decision strategy targeting to maximise user satisfaction without compromising on quality of service for non-real time mobile based services. The proposed strategy applies consumer surplus value (CSV)-based pricing scheme and also a prediction system to approximate network performances at various intervals. Finally, a fuzzy rule-based behavioral system is proposed to find optimal network by considering both CSV as well as network performance as stimulus parameters. Simulation is carried out using OM Net++ and MATLAB, and the results are acknowledged with discussion and analysis.

Congestion-Aware Embedding of Heterogeneous Bandwidth Virtual Data Centers With Hose Model Abstraction

Predictable network performance is critical for cloud applications and can be achieved by providing tenants a dedicated virtual data center (VDC) with bandwidth guarantee. Recently, the extended Hose model was applied to the VDC abstraction to characterize the tradeoff between cost and network performance. The acceptability determination problem of a VDC with heterogeneous bandwidth demand was proved to be NP-complete, even in the simple tree topology. In this paper, we investigate the embedding problem for heterogeneous bandwidth VDC in substrate networks of general topology. The embedding problem involves two coupled sub-problems: virtual machine (VM) placement and multipath route assignment. First, we formulate the route assignment problem with linear programming to minimize the maximum link utilization, and provide $K$ -widest path load-balanced routing with controllable splitting paths. Next, we propose a polynomial-time heuristic algorithm, referred to as the perturbation algorithm, for the VM placement. The perturbation algorithm is congestion-aware as it detects the bandwidth bottlenecks in the placement process and then selectively relocates some assigned VMs to eliminate congestion. Simulation results show that our algorithm performs better in comparison with the existing well-known algorithms: first-fit, next-fit, and greedy, and very close to the exponential-time complexity backtracking algorithm in typical data center network architectures. For the tree substrate network, the perturbation algorithm performs better than the allocation-range algorithm. For the homogeneous bandwidth VDC requests, the perturbation algorithm produces a higher success rate than the recently proposed HVC-ACE algorithm. Therefore, it provides a compromised solution between time complexity and network performance.

Pricing the spare bandwidth: towards maximizing data center’s profit

To provide tenants with predictable network performance, tenants are allowed to purchase specified amount of data center network (DCN) resources (e.g., bandwidth). Then, data center will reserve the purchased resources for the corresponding tenants. Meanwhile, some DCNs are work conserving, which means that the spare bandwidth will be fairly shared by all active tenants. Even though the amount of the spare bandwidth is stochastic and uncertain, DCN providers are not likely to give away it for free. Thus, data center with work conserving may impose extra payment on tenants for using the spare bandwidth. In this paper, we propose a suitable tariff to charge for the usages of DCN resources, which includes a bill for the usage of the spare bandwidth. Through theoretical analysis and simulation, we demonstrate that our tariff can incentivize tenants to adjust their purchases of bandwidths, which can lead to the improvement of data center’s profit by 27.4% without impairing the social welfare.

PredCloud: Providing predictable network performance in large-scale OpenFlow-enabled cloud platforms through trust-based allocation of resources

Cloud computing allows tenants to run a wide range of applications without any upfront capital investment. However, providers lack mechanisms to provide fair and predictable bandwidth sharing among allocated applications, enabling selfish and malicious tenants to cause performance interference in the network (and denial of service in an extreme case). Such interference results in poor and unpredictable network performance for well-behaved applications. Recent research has proposed techniques that (i) cannot protect tenants against interference; (ii) result in under utilization of resources; or (iii) add substantial management overhead. In this paper, we describe a resource allocation strategy that aims at providing predictable network performance (i.e., minimizing performance interference) with bandwidth guarantees for tenant applications, while maintaining high network utilization and low management overhead. These benefits are achieved by grouping applications from mutually trusting users into logically isolated domains (virtual infrastructures - VIs) with bandwidth guarantees, while also considering the amount of traffic generated by applications. Despite the benefits, grouping may lead to fragmentation (i.e., available resources are dispersed among VIs and some requests may be unnecessarily declined). Therefore, we also study the associated trade-off (grouping to increase isolation versus resource fragmentation). To illustrate the feasibility of grouping applications inside VIs, we develop PredCloud, a system that implements the proposed strategy on SDN/OpenFlow-enabled networks. Through an extensive evaluation, we show that PredCloud significantly reduces performance interference and application exposure to attacks, while maintaining low resource fragmentation. Furthermore, provider revenue can be increased by efficiently managing and charging network resources.

Development of Emulation Network Analyzer Tool for Computer Network Planning

This paper describes the development of Emulation Network Analyzer (ENA) for heterogeneous services in campus environment. The purpose of this paper is to inform this ENA able to plan and predict network performance. For this purpose, our ENA development is differ from others system such as application and hardware network analyzer. This study focuses on the design of emulation network analyzer, user interface design, characteristics, model description, implementation and evaluation. This ENA can provide a useful network architectural solutions and optimization of network resources during preparation, proposal and planning phases. Finally, ENA tool is a good emulation analyzer that can be used in small to medium size networks for campus environment purposes with minimum cost.

A Flow-based Vulnerability Measure for the Resilience of Urban Road Network

Since the beginning of the new millennium, various ideas and methods of measuring road network vulnerability have been proposed in the field of transportation and infrastructure engineering. However, most of the existing measures have been focusing on large road networks like highways between cities, even though urban networks are equally important. Also, the measures require full microscopic simulations for deriving the value of travel time increase, which is used for predicting network performance in case a disaster situation occurs. In order to overcome such issue, this study provides a new evaluation method for vulnerability of urban road network based on the concept of macroscopic fundamental diagram (MFD). We call such measure as MFD-based Vulnerability Index (MVI), which is derived by comparing the MFD behaviours in normal condition and event condition, in which one or more links of a road network are failed by a disaster. For testing the measure, a simulation study based on the road network of Gangnam district, Seoul, South Korea is provided. The results show that the measure can help us investigate the different patterns of network performance loss by different traffic states. This work provides a different perspective of investigating road network vulnerability.

Efficient network isolation and load balancing in multi-tenant HPC clusters

Multi-tenancy promises high utilization of available system resources and helps maintaining cost-effective operations for service providers. However, multi-tenant high-performance computing (HPC) infrastructures, like dynamic HPC clouds, bring unique challenges, both associated with providing performance isolation to the tenants, and achieving efficient load-balancing across the network fabric. Each tenant should experience predictable network performance, unaffected by the workload of other tenants. At the same time, it is equally important that the network links are balanced, avoiding network saturation. The network saturation can lead to unpredictable application performance, and a potential loss of profit for the cloud service providers.In this paper, we present two significant extensions to our previously proposed partition-aware fat-tree routing algorithm, pFTree, for InfiniBand-based HPC systems. First, we extend pFTree to incorporate provider defined partition-wise policies that govern how the nodes in different partitions are allowed to share network resources with each other. Second, we present a weighted version of the pFTree routing algorithm, that besides partitions, also takes node traffic characteristics into account to balance load across the network links more evenly. A comprehensive evaluation comprising both real-world experiments and simulations confirms the correctness and feasibility of the proposed extensions.

DESIGN A MOBILE TELEPHONE SYSTEM IN A CERTAIN CITY

A mobile telephone system is designed to facilitate better communication among 8000 users in the centre of Roma. The network performance prediction tool was used to determine the best location for deployment of the base station. It was based on some parameters or predictions which were obtained by calculating needed data to construct the base station. Theoretically call planning, cell splitting, frequency re-use, offered traffic etc. techniques are used to obtain a good coverage for a certain city. In order to find the best cell cluster, many calculations were also implemented. The objective achieved was designing a network system in city centre of Roma. The 7 cell cluster and 12 cell cluster was selected for its overall efficiency. In addition to this, co-channel interference, best server, maximum received power etc. were examined for deployment of the base station with help of Winprop.

Using the cooperative game for service placement of virtual network functions

To address the issues that middleboxes as a fundamental part of today's networks are facing, Network Function Virtualization (NFV) has been recently proposed, which in essence asserts to migrate hardware-based middleboxes into software-based virtualized function entities. Due to the demands of virtual services placement in NFV network environment, this paper models the service amount placement problem involving with the resources allocation as a cooperative game and proposes the placement policy by Nash Bargaining Solution (NBS). Specifically, we first introduce the system overview and apply the rigorous cooperative game-theoretic guide to build the mathematical model, which can give consideration to both the responding efficiency of service requirements and the allocation fairness. Then a distributed algorithm corresponding to NBS is designed to achieve predictable network performance for virtual instances placement. Finally, with simulations under various scenarios, the results show that our placement approach can achieve high utilization of network through the analysis of evaluation metrics namely the satisfaction degree and fairness index. With the suitable demand amount of services, the average values of two metrics can reach above 90%. And by tuning the base placement, our solution can enable operators to flexibly balance the tradeoff between satisfaction and fairness of resources sharing in service platforms.